Grant List
- Home
- Research & Development
- Grants
- Grant List
Automated Web Article Extraction based on RSS and Summarization with Pointer-Generated Networks
User Preference recommendation system and Analytics for news articles
Automated Web Article Extraction based on RSS and Summarization with Pointer-Generated Networks
User Preference recommendation system and Analytics for news articles
AI based statistical analysis of pollution due to land and ocean plastic waste in India
Automatic Attendacne Marking for Kindergarten using Half Face Recognition
Climate, Air Pollution and Forest Fires : AI based models for Indian case study
Clinical Note Generation
Coreveillance- Making our world a “SAFER” Place
Cost effective electronic limbs
FireMan Helper
Food to People: A Blockchain Solution
Forecasting of Carbon Emissions due to Meat Industry
Sahara: A stanchion for the blind
Trail-Tracker: Antipoaching Intelligence using AI and IoT
Advanced Wireless Lab
AI based Farmer Empowerment (Compute Grant)
Artificial Intelligence Model for Epidemiology of Tuberculosis
Automatic Attendacne Marking for Kindergarten using Half Face Recognition
Calibration for Nuclear Spectroscopy Application
Clinical Note Generation
Conversion of Handwritten document into Text
Coreveillance- Making our world a “SAFER” Place
Drowsiness detecting Wearable for Heavy Machinery Operators
FireMan Helper (ext)
Food to People: A Blockchain Solution (ext)
Forest Fire Prediction Using LSTM Networks
High Resolution Multichannel Analyzer for nuclear spectroscopy application
IoT based Waste Management System: A Step towards Smart City
Monitoring and Assessing Coral Reefs in Oceans
Sahara: A stanchion for the blind (ext)
Search Engine Ranking Prediction & Improvement. Using Neural Networks
Swadeshi Battery Management Systems
Swechchha स्वेच्छा
Trail-Tracker: Antipoaching Intelligence using AI and IoT (ext)
Adoption of Artificial Intelligence in agriculture (Compute Grant)
Agri Robot
air pollution monitoring system using WSN
Air Quality Monitoring System for Chembur Area( using wireless sensor network)
Assistive Smart Stick for Independent and Safe Travel
Automatic Attendacne Marking for Kindergarten using Half Face Recognition
Automatic Attendance Marking for Kindergarten using Half Face Recognition
Autonomous Luggage carrying Robot using Image Processing
Capacity Planning for Public Toilets for Urban Slums
Clinical Note Generation
Clinical Note Generation
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Coreveillance:Let's make our Society a Safe Place to Live In
Coreveillance:Let's make our Society a Safe Place to Live In
Cost effective electonic limbs
Development of Methodology for Indian Evaluated Nuclear Data Library for applications in S & T
Drone based Warehouse Automation
E-toll
FireMan Helper
FireMan Helper
Food to People: A Blockchain Solution
Food to People: A Blockchain Solution
Fraud Prevention on Crowdfunding Platform
Garuda: The Intelligent Ornithopter
GPS and GSM based small compact Tracking Module
Maximum Power Point Tracking of Photovoltaic Cell
Multi-Functional Detachable Applications For Drones
Parallel Synthesizer with Independent Temparature Control
Predicting floods in coastal regions as a direct consequence of deforestation
Predicting floods in coastal regions as a direct consequence of deforestation
Predictive analysis of carbon footprint in metropolitan cities of India.
Predictive analysis of carbon footprint in metropolitan cities of India.
Preparation and characterisation complexes of Cetyltrimethylammonium bromide and Cetylpyridinium Chloride with butyl benzene sulphonates without salt.
Programmable Computer Controlled Active Analog Filter
Rehabilitation and Protection of Coastal Areas
Rehabilitation and Protection of Coastal Areas
Road pot hole Detection
Sahara: A stanchion for the blind
Smart Box
Smart health assistant
Trail-Tracker: Antipoaching Intelligence using AI and IoT
Trail-Tracker: Antipoaching Intelligence using AI and IoT
Transparent and trackable donations using blockchain
voice controlled wheelchair
Water Monitoring System using IoT
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
" Machine Learning based Flood Prediction model for MumbaiIndia"
Air quality monitoring and control system using WSN
Autonomous Luggage carrying Robot using Image Processing
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Digital India - Smart Subsidy System.
Farm Guide
Heart Disease prediction using AI (Deep Learning).
Infant Incubator intelligent control system
Intelligent Classroom : Students’ behaviour and Emotions Analysis using Face Recognition (Compute Grant)
Machine Learning based Flood Prediction model for Mumbai,India
Optimized rescue system for accidents and emergencies
Prototype Design and controller implementation for a battery- ultra capacitor hybrid electric vehicle
Recommender System to Identify Influential Individuals on Social Media
Rehabilitation and Protection of Coastal Areas
River Cleaning Robot
Smart Box
Smart Locker
Smart vehicle for physically challenged people
Time to Digital Converter for Nuclear Timing Spectroscopy Systems
Transparent and trackable donations using blockchain
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
App for Aromatic and Medicinal crop growers
Electricity Consumption and Home Automation
Electricity Consumption and Home Automation
Mind controlled assistive quadrotor drone
Reinforcement learning on robot
Speed Regulating mechanism for Road Safety
Speed Regulating mechanism for Road Safety
Vehical collision avoidance at junctions blind urns and hairpin bends
Martian Landform Segmentation Based on Structural Similarity
Land Use Classification Using Satellite Images(Compute Grant)
Artificial Intelligence based Smart Driver Assistant for Reduction of Road Fatality.
Description
To design a low cost Smart Driver Assistant (Digital Dashboard unit) using Artificial Intelligence for navigating through unsafe road conditions to reduce fatality.
Automated Web Article Extraction based on RSS and Summarization with Pointer-Generated Networks
Description
The amount of text data available from various sources has exploded in the big data era. This large volume of literature has a wealth of information and knowledge that must be adequately summarized in order to be useful. Because of the growing availability of documents, extensive research in the field of natural language processing (NLP) for automatic text summarization is required. The job of producing a succinct and fluent summary without the assistance of a person while keeping the sense of the original text material is known as automatic text summarization. Observing the summary results, extractive and abstractive techniques are one of the most common. As a state-of-the-art method for abstractive summarization, the pointer-generator network produces more fluent summaries and solves two shortcomings of reproducing factual details inaccurately and phrase repetition.
User Preference recommendation system and Analytics for news articles
Description
With advancements in technology, the content space has changed and the major problem faced by the digital space is providing personalized content to users. This enables users to get more relevant content, increasing the time spent on the application. This is great for business as higher retention leads to more data being stored which in turn can be analyzed. This gives better business insights to enhance targeted marketing. This would solve the poor merchandising problem faced by businesses. The cycle continues and our project comes into the picture to streamline this process using machine learning. With the advent of digitization, there has been a change in traditional media. Through the means of software, we are able to read, share and interact with news articles on our smartphone devices. This has completely changed the game for News supplying houses because of the abundance of information available on the internet. Instead of orthodox print newspapers, people have started to prefer the convenience of mobile articles. The written structure of articles has also changed to comply with the fast and to-the-point inclination of the users. Finding niche arti-cles with copious amounts of information is the problem faced by users and even news supply agencies. It is hence critical to analyze user data
Automated Web Article Extraction based on RSS and Summarization with Pointer-Generated Networks
Description
The amount of text data available from various sources has exploded in the big data era. This large volume of literature has a wealth of information and knowledge that must be adequately summarized in order to be useful. Because of the growing availability of documents, extensive research in the field of natural language processing (NLP) for automatic text summarization is required. The job of producing a succinct and fluent summary without the assistance of a person while keeping the sense of the original text material is known as automatic text summarization. Observing the summary results, extractive and abstractive techniques are one of the most common. As a state-of-the-art method for abstractive summarization, the pointer-generator network produces more fluent summaries and solves two shortcomings of reproducing factual details inaccurately and phrase repetition.
User Preference recommendation system and Analytics for news articles
Description
With advancements in technology, the content space has changed and the major problem faced by the digital space is providing personalized content to users. This enables users to get more relevant content, increasing the time spent on the application. This is great for business as higher retention leads to more data being stored which in turn can be analyzed. This gives better business insights to enhance targeted marketing. This would solve the poor merchandising problem faced by businesses. The cycle continues and our project comes into the picture to streamline this process using machine learning. With the advent of digitization, there has been a change in traditional media. Through the means of software, we are able to read, share and interact with news articles on our smartphone devices. This has completely changed the game for News supplying houses because of the abundance of information available on the internet. Instead of orthodox print newspapers, people have started to prefer the convenience of mobile articles. The written structure of articles has also changed to comply with the fast and to-the-point inclination of the users. Finding niche arti-cles with copious amounts of information is the problem faced by users and even news supply agencies. It is hence critical to analyze user data
AI based statistical analysis of pollution due to land and ocean plastic waste in India
Description
Plastic debris has been piled up on dumpsites and found its way into the oceans as a result of widespread usage of plastics and inadequate waste management procedures, adding to the global problem of ocean plastic pollution. There has not been a comprehensive assessment of the amount of plastic that enters the ocean through the Indian riverine system. Even if data for a few rivers exists, unit conversion becomes a real hassle. Natural elements such as river flow, rainfall, and a variety of other factors have made quantitative measurements on river plastic generation difficult to obtain. In this paper, we have calculated and provided plastic waste generated by the major rivers of India for the past 10 years. We also created a model to forecast the amount of plastic waste that Indian rivers will contribute to the ocean over the next five years. The project aims to calculate India's plastic waste footprint by gathering data on the amount of land-based plastic waste generated over the last ten years in various Indian states. The proposed system would use AI techniques to forecast and visualize the amount of plastic waste that will be generated in the following 5 years given comparable conditions and limits. The recommended solution is based on a 10-year mapping of plastic waste generated in India, and it offers the best recommendations for minimizing plastic waste. Heatmaps will be created to indicate locations with low, moderate, and high levels of plastic waste, as well as recycling plant details. A final report will be produced and given to government departments and other non-governmental organizations, along with recommendations for minimizing plastic waste.
Automatic Attendacne Marking for Kindergarten using Half Face Recognition
Description
Educational institutions are also concerned with student attendance on a daily basis. This is mostly because his or her attendance at the school influences the overall academic performance of students. There are primarily two traditional marking approaches that name the roll call or take the student sign on paper. Both have become longer and more difficult. There is thus a need for a student attendance program based on computers that helps the faculty automatically to maintain records. This algorithm compares the test image and the training picture and decides the present and absent students. The attendance record is held in an excel sheet that is automatically changed in the program.The Algorithm will be performed on Kindergarten students.
Climate, Air Pollution and Forest Fires : AI based models for Indian case study
Description
A FSI study showed an increase in forest fires in India since 2004-05 i.e 8,654 forest points which went up to 30,892 in 2009-10 and further surged to 35,888 in 2017. As a forest burns, large amounts of smoke are released into the atmosphere. Air pollution from fires has the potential to travel great distances and oftentimes may pose a threat to human health. We will develop a web based system that will predict the forest fire for a given region and the changes in pollutant caused by that forest fire. Our project aims to cover maximum districts from Pan-india covering 13 most vulnerable states.
Clinical Note Generation
Description
The objective of our project is to make a software that helps to generate clinical notes during surgeries/operations by converting voice to text. It would save time of writing down the notes. A systematic clinical note prepared by converting voice to text would include Database backup,, Reports generated with respect to various end users' perspective and it is customizable. Generating clinical notes during operations and surgeries can be used for future reference and for comparing clinical notes to see the patients progress.
Coreveillance- Making our world a “SAFER” Place
Description
Abstract:Security in urban civilization, especially today has always been a big concern. Previous societal methodologies have proved to be working to some extent but always had a scope of improvement with the advent of new technologies in the field of security and surveillance. This application broadens the spectrum of security under technological domains by introducing machine learning and computer vision. A smart society is an empowered society. Most research inevitably focuses on technology. A smart society successfully harnesses the potential of digital technology and connected devices and the use of digital networks to improve people’s lives.A smart society is a set of systems that express a consensually established set of values. Everything flows from those values. It isone in which leaders and citizens make data-based decisions that enable constantly improving outcomes in economic prosperity, social well-being, environmental sustainability, and good governance. A smart society includes a reward or incentive system that engenders socially desirable and environmentally regenerative behaviours without compulsion or punishment.
Cost effective electronic limbs
Description
A bionic limb is an add-on that is provided to the amputees, replacing the missing limb. This project is mainly focused on the person who has been a victim of any fatal accident which has caused loss of human limbs. The electronics limbs that are available are not cost effective & stable. So, to serve as an alternative for this, our method can give a highly cost effective and flexible method of making a bionic limb.
FireMan Helper
Description
In a world where fire accidents are increasingly common and the brave first responders always risk their lives to save the lives of others; unfortunately, history tells us that these brave first responders do not survive most of the time. Hence, to save as many lives as possible and aid the firefighters in the rescue process, it is important to leave dangerous tasks to machines. One such device is drone- It provides great maneuverability, doesn't risk any personnel and can also gather information at greater speed and reliability. The proposed solution tackles all the problems using drone equipped with the required hardware as follows : Ability to detect fires and monitor the risk of fire approaching a building, fence, or spreading through cameras. Generation of a map or 3D model for firefighting personnel to get better information on positions of trapped victims at places ablaze and determine the best course of action. Ability to put out a fire in case of unreachable areas or in situations where using Unmanned Drone is the safest approach. Generation of toxicity reports and identify the level of fire for deciding the safety measures to be undertaken and need to be provided to the victims.
Food to People: A Blockchain Solution
Description
Abstract:Security in urban civilization, especially today has always been a big concern. Previous societal methodologies have proved to be working to some extent but always had a scope of\ improvement with the advent of new technologies in the field of security and surveillance. This application broadens the spectrum of security under technological domains by introducing machine learning and computer vision. A smart society is an empowered society. Most research inevitably focuses on technology. A smart society successfully harnesses the potential of digital technology and connected devices and the use of digital networks to improve people’s lives. A smart society is a set of systems that express a consensually established set of values. Everything flows from those values. It is one in which leaders and citizens make data-based decisions that enable constantly improving outcomes in economic prosperity, social well-being, environmental sustainability, and good governance. A smart society includes a reward or incentive system that engenders socially desirable and environmentally regenerative behaviours without compulsion or punishment.
Forecasting of Carbon Emissions due to Meat Industry
Description
All living and non conscious things are a section of the scheme because of a rise within the range of vehicles, rapid population growth and industrialisation over the years, the carbon content within the atmosphere has risen at an associate degree exponential rate.Transportation, Industrialization and technological growth are beneficial to the modern world but are major concerns generating carbon footprint. Livestock and meat industry is a sector which is always overlooked when talking about carbon footprint. The Meat industry is considered to be generating over 14.50% of global carbon footprint.The objective of our project is to analyze carbon emission due to livestock and meat and develop a prediction model which will give us accurate predictions for the next coming years. These predictions will be visualized in different types of charts and graphs which will help the end user to refer to the predictions efficiently.
Sahara: A stanchion for the blind
Description
Owing to demonetization and the foray of new Indian currencies in the market, it has been observed that the visually impaired persons are having a hard time in identifying and distinguishing the Indian currencies. Another major issue is text reading. Although there are many OCR engines that are available today, it is quite difficult for the visually impaired to operate them. Also, all of these engines require an internet connection. Face recognition is a further add-on which is of a major concern considering certain security aspects. Several other tasks like these, if packaged in a single device can be a breakthrough for the visually impaired and would revolutionize their world. Currently, the devices offering such features are exorbitantly charged and the price of such devices is around INR 3 lakhs. Owing to the client-server architecture which is the base for such devices, they continuously require a strong internet connection. The client-server architecture further adds to its disadvantages, in the sense that the server may get overloaded and the availability of such a system would be challenged under real-world conditions. To combat the availability issue, the devices designed currently offer a constrained time limit say 100 minutes per month. Thus a user after spending an exorbitant amount on the device would also have to pay a price if he reaches this 100 minutes limit for a particular month. The proposed system is a portable, handy, easy-to-use, internet-less device that would aid the visually impaired in his quotidian chores. The highlighting feature of our system is that it doesn't embody client-server architecture. We aim at providing a feasible device that can aid the blind in chores that they really need help for.
Trail-Tracker: Antipoaching Intelligence using AI and IoT
Description
Epidemiology of a disease provides a thorough and exhaustive analysis of the transmission and control of viral infections. The intended outcome aims to exercise the Artificial Intelligence and Machine Learning models in order to understand the substantial effects of Tuberculosis in India. A host of Tuberculosis data segregated in comorbidities (Pediatric, Geriatric, HIV) from the multiple states and districts of India will be correlated with climate data, accustomed to bring optimal precision to the prediction model in order to increase the efficacy of the system. A graphic user interface will be provided to improve the comprehension of the expected solution to assist in geographically visualizing the control of Tuberculosis in India and its effects in the near future.
Advanced Wireless Lab
Description
This research is granted by AICTE under the scheme Modernization and Removal of Obsolescenc (MODROB) for the year 2019-20 payable during the current financial year 2020-21. This fund is being utilized for the development of advanced wireless lab with high end equipment like Software defined radio and MIMO configurations.
AI based Farmer Empowerment (Compute Grant)
Description
AI based Farmer Empowerment (Compute Grant)
Artificial Intelligence Model for Epidemiology of Tuberculosis
Description
Epidemiology of a disease provides a thorough and exhaustive analysis of the transmission and control of viral infections. The intended outcome aims to exercise the Artificial Intelligence and Machine Learning models in order to understand the substantial effects of Tuberculosis in India. Our proposal aligns with the vision of National Strategic Plan 2017-2025 and aims towards understanding the challenges for TB prevention. Our aim is to predict the future outline of TB and understand it’s impact through correlation of the factors such as climatic conditions, pollution parameters and population density on most at risk TB diaspora from state to district level. A host of Tuberculosis data segregated in comorbidities (Pediatric, Geriatric, HIV) from the multiple states and districts of India will be correlated with climate data, accustomed to bring optimal precision to the prediction model in order to increase the efficacy of the system. A graphic user interface will be provided to improve the comprehension of the expected solution to assist in geographically visualizing the control of Tuberculosis in India and its effects in the near future.
Automatic Attendacne Marking for Kindergarten using Half Face Recognition
Description
The management of the attendance can be a great burden on the teachers if it is done by hand. To resolve this problem, a smart and auto attendance management system is being utilized. But authentication is an important issue in this system. The smart attendance system is generally executed with the help of biometrics for the kindergarten. Face recognition is one of the biometric methods to improve this system. Trying to find a face within a large database of faces is cumbersome. In this approach, the system returns a possible list of faces from the database. The most useful applications contain crowd surveillance, video content indexing, personal identification, mug shots matching, etc. Here, face recognition is used to identify a person on the spot and grant access to a building or a compound, thus avoiding security hassles.
Calibration for Nuclear Spectroscopy Application
Description
Calibration for Nuclear Spectroscopy Application
Clinical Note Generation
Description
The objective of our project is to make a software that helps to generate clinical notes during surgeries/operations by converting voice to text. It would save time of writing down the notes. A systematic clinical note prepared by converting voice to text would include Database backup,, Reports generated with respect to various end users' perspective and it is customizable. Generating clinical notes during operations and surgeries can be used for future reference and for comparing clinical notes to see the patients progress.
Conversion of Handwritten document into Text
Description
"Day by day paper documents abound and this requires large storage space as well as proper care. To solve this problem and to save all the old documents we come to this solution. We create a neural network and we train it to read the text from the document which helps in the functioning of the institution by digitizing the documents provided to our neural network. This eases the process of taking and managing text from documents at the click of a button. Our pipeline for automatically identifying handwritten text includes: page segmentation line segmentation followed by handwriting recognition.Process - 1.Page segmentation - Here we focus on the segmentation of handwritten texts from the IAM dataset. Documents from the IAM dataset contain a printed portion and handwritten portion. The goal of this algorithm is to fit a bounding box around the handwritten portion of the document. The MSERs algorithm was used to detect ??blobs?? on the image which correspond to text on the images. 2.Line segmentation with Gluon The input to the model is an image that only contains handwritten text. The outputs are bounding boxes that correspond to each line of the text. The problem is similar to the object detection problem in computer vision. In this method we utilized the single shot multibox detector (SSD) architecture to detect the positions of each line of the passage. 3. Handwriting recognition It take??s output of Line segmentation neural network and crop each line from image to neural network. The neural network detect the text from image and combine all text into documented text. "
Coreveillance- Making our world a “SAFER” Place
Description
Abstract:Security in urban civilization, especially today has always been a big concern. Previous societal methodologies have proved to be working to some extent but always had a scope of improvement with the advent of new technologies in the field of security and surveillance. This application broadens the spectrum of security under technological domains by introducing machine learning and computer vision. A smart society is an empowered society. Most research inevitably focuses on technology. A smart society successfully harnesses the potential of digital technology and connected devices and the use of digital networks to improve people’s lives.A smart society is a set of systems that express a consensually established set of values. Everything flows from those values. It isone in which leaders and citizens make data-based decisions that enable constantly improving outcomes in economic prosperity, social well-being, environmental sustainability, and good governance. A smart society includes a reward or incentive system that engenders socially desirable and environmentally regenerative behaviours without compulsion or punishment.
Drowsiness detecting Wearable for Heavy Machinery Operators
Description
Drowsiness detecting Wearable for Heavy Machinery Operators
FireMan Helper (ext)
Description
In a world where fire accidents are increasingly common and the brave first responders always risk their lives to save the lives of others; unfortunately, history tells us that these brave first responders do not survive most of the time. Hence, to save as many lives as possible and aid the firefighters in the rescue process, it is important to leave dangerous tasks to machines. One such device is drone- It provides great maneuverability, doesn't risk any personnel and can also gather information at greater speed and reliability. The proposed solution tackles all the problems using drone equipped with the required hardware as follows : Ability to detect fires and monitor the risk of fire approaching a building, fence, or spreading through cameras. Generation of a map or 3D model for firefighting personnel to get better information on positions of trapped victims at places ablaze and determine the best course of action. Ability to put out a fire in case of unreachable areas or in situations where using Unmanned Drone is the safest approach. Generation of toxicity reports and identify the level of fire for deciding the safety measures to be undertaken and need to be provided to the victims.
Food to People: A Blockchain Solution (ext)
Description
Abstract:Security in urban civilization, especially today has always been a big concern. Previous societal methodologies have proved to be working to some extent but always had a scope of\ improvement with the advent of new technologies in the field of security and surveillance. This application broadens the spectrum of security under technological domains by introducing machine learning and computer vision. A smart society is an empowered society. Most research inevitably focuses on technology. A smart society successfully harnesses the potential of digital technology and connected devices and the use of digital networks to improve people’s lives. A smart society is a set of systems that express a consensually established set of values. Everything flows from those values. It is one in which leaders and citizens make data-based decisions that enable constantly improving outcomes in economic prosperity, social well-being, environmental sustainability, and good governance. A smart society includes a reward or incentive system that engenders socially desirable and environmentally regenerative behaviours without compulsion or punishment
Forest Fire Prediction Using LSTM Networks
Description
Forest Fire Prediction Using LSTM Networks
High Resolution Multichannel Analyzer for nuclear spectroscopy application
Description
High Resolution Multichannel Analyzer for nuclear spectroscopy application
IoT based Waste Management System: A Step towards Smart City
Description
"The purpose of taking up the project is directly related to the cleanliness and hygienic conditions of the society which is directly related to the health of the people. The project is related to Cloud Computing and Internet of Things. The different sensors will provide the readings needed to perform the analysis on the data using the different algorithms of data science. The analyzed pattern will help ensure the fullness of the dustbins to take necessary actions. "
Monitoring and Assessing Coral Reefs in Oceans
Description
"Coral reefs play a significant role in helping marine life survive, acting as a barrier from surge water to reduce waves and buffer the shore, and in many other factors regarding the thriving of marine life. The project will focus on monitoring these coral reefs to keep a check on the extent of the damage being done to these coral reefs at specific intervals of time. Keeping a track of this would allow us to raise awareness and provide necessary information regarding the exact places where better measures need to be taken to avoid the possibility of their extinction. "
Sahara: A stanchion for the blind (ext)
Description
Owing to demonetization and the foray of new Indian currencies in the market it has been observed that the visually impaired persons are having a hard time in identifying and distinguishing the Indian currencies. Another major issue is text reading. Although there are many OCR engines that are available today it is quite difficult for the visually impaired to operate them. Also all of these engines require an internet connection. Face recognition is a further add-on which is of a major concern considering certain security aspects. Several other tasks like these if packaged in a single device can be a breakthrough for the visually impaired and would revolutionize their world. Currently the devices offering such features are exorbitantly charged and the price of such devices is around INR 3 lakhs. Owing to the client-server architecture which is the base for such devices they continuously require a strong internet connection.
The client-server architecture further adds to its disadvantages in the sense that the server may get overloaded and the availability of such a system would be challenged under real-world conditions. To combat the availability issue the devices designed currently offer a constrained time limit say 100 minutes per month. Thus a user after spending an exorbitant amount on the device would also have to pay a price if he reaches this 100 minutes limit for a particular month. The proposed system is a portable handy easy-to-use internet-less device that would aid the visually impaired in his quotidian chores. The highlighting feature of our system is that it doesn't embody client-server architecture. We aim at providing a feasible device that can aid the blind in chores that they really need help for.
Search Engine Ranking Prediction & Improvement. Using Neural Networks
Description
"SEO technique includes two major processes: off-page optimization and on-page optimization. Off-page optimization entails building back links on other well reputed websites and thus boosting domain-level and page-level authority. On-page optimization SEO requires the optimization of web pages using target keywords in the title snippets and in the URL. This research wants to analysis website??s internal parameters that affect determining site rank in search engine. For as much as how to choose and number of HTML tags for a particular website has direct impact on page rank important concepts in this area should be examined. These concepts include Number Proximity Domain Authoity Page Authority External linking internal linking age of domain and Density. Within literature no single research is reported to predict the search engine ranking of a website correctly. "
Swadeshi Battery Management Systems
Description
Swadeshi Battery Management Systems
Swechchha स्वेच्छा
Description
Looking at the acute need of development of the ‘ITeS based Operation and Maintenance Monitoring System’ for the Community Toilet (CT) and Public Toilet (PT) blocks in Mumbai, working with MCGM as a Knowledge Partner and contributing to the Swachh Bharat Mission of the Government of India (GOI), the objective of the project is to bring in accountability and transparency as a component of good governance in sanitation.
Trail-Tracker: Antipoaching Intelligence using AI and IoT (ext)
Description
Epidemiology of a disease provides a thorough and exhaustive analysis of the transmission and control of viral infections. The intended outcome aims to exercise the Artificial Intelligence and Machine Learning models in order to understand the substantial effects of Tuberculosis in India. A host of Tuberculosis data segregated in comorbidities (Pediatric, Geriatric, HIV) from the multiple states and districts of India will be correlated with climate data, accustomed to bring optimal precision to the prediction model in order to increase the efficacy of the system. A graphic user interface will be provided to improve the comprehension of the expected solution to assist in geographically visualizing the control of Tuberculosis in India and its effects in the near future.
Adoption of Artificial Intelligence in agriculture (Compute Grant)
Description
Adoption of Artificial Intelligence in agriculture (Compute Grant)
Agri Robot
Description
In Today??s era is marching towards the rapid growth of all sectors including the agricultural sector. To meet the future food demands the farmers have to implement the new techniques which will not affect the soil texture but will increase the overall crop production. The aim of this project is to design and develop an Automatic seed sowing robot.Seed sowing machine is a key component of agricultural field. The various techniques used in India for seed sowing and fertilizer placement are manual ox and tractor operated. The manual and ox operator techniques are time consuming and productivity is low.
air pollution monitoring system using WSN
Description
air pollution monitoring system using WSN
Air Quality Monitoring System for Chembur Area( using wireless sensor network)
Description
"Rapid urbanization and industrialization has resulted in a sustained degradation of environmental quality parameteIt is important to keep track of various environmental pollution indices so that realistic models can be developed and relevant public policies are created. Traditional methods for air pollution measurements are expensive and have a spatial constraint. With these limitations air pollution monitoring in broader area is not feasible. However the use of modern low cost sensors in conjunction with wireless sensor network (WSN) creates an opportunity to collect real time data from different locations and provide detailed pollution map. The main aim of this project is to develop a low cost multi-sensor mote for air pollution measurement system and to develop WSN protocols for data gathering and data aggregation protocol which will help the society in terms of health."
Assistive Smart Stick for Independent and Safe Travel
Description
Assistive Smart Stick for Independent and Safe Travel
Automatic Attendacne Marking for Kindergarten using Half Face Recognition
Description
The management of the attendance can be a great burden on the teachers if it is done by hand. To resolve this problem a smart and auto attendance management system is being utilized. But authentication is an important issue in this system. The smart attendance system is generally executed with the help of biometrics for the kindergarten. Face recognition is one of the biometric methods to improve this system. Trying to find a face within a large database of faces is cumbersome. In this approach the system returns a possible list of faces from the database. The most useful applications contain crowd surveillance video content indexing personal identification mug shots matching etc. Here face recognition is used to identify a person on the spot and grant access to a building or a compound thus avoiding security hassles.
Automatic Attendance Marking for Kindergarten using Half Face Recognition
Description
The management of the attendance can be a great burden on the teachers if it is done by hand. To resolve this problem, a smart and auto attendance management system is being utilized. But authentication is an important issue in this system. The smart attendance system is generally executed with the help of biometrics for the kindergarten. Face recognition is one of the biometric methods to improve this system. Trying to find a face within a large database of faces is cumbersome. In this approach, the system returns a possible list of faces from the database. The most useful applications contain crowd surveillance, video content indexing, personal identification, mug shots matching, etc. Here, face recognition is used to identify a person on the spot and grant access to a building or a compound, thus avoiding security hassles.
Autonomous Luggage carrying Robot using Image Processing
Description
Automation can not only save the human effort but also increases the efficiency accuracy and productivity of work. Thus Automation can provide optimal solutions where human capabilities face restrictions. Old age and Handicapped people deal with great difficulties while carrying a luggage as it requires considerable human effort. Even for normal people carrying heavy loads becomes a Herculean Job. Automation can be used to tackle such a situation. The proposal aims to create a luggage carrier robot which can save the human efforts by following the user and deliver the luggage at the desired destination with the help of automation. The project emphasizes on creating a robot which follows the user by tracking the unique symbol. The robot will understand the position and will be keeping track of the user by tracking the speed. The robot will also sense the surrounding by the sensors and will try to find the best possible way to keep in pace with the user and also avoid bumping into obstacles.
Capacity Planning for Public Toilets for Urban Slums
Description
Capacity Planning for Public Toilets for Urban Slums
Clinical Note Generation
Description
"The objective of our project is to make a software that helps to generate clinical notes during surgeries/operations by converting voice to text. It would save time of writing down the notes. A systematic clinical note prepared by converting voice to text would include Database backup Reports generated with respect to various end users' perspective and it is customizable. Generating clinical notes during operations and surgeries can be used for future reference and for comparing clinical notes to see the patients progress. "
Clinical Note Generation
Description
The objective of our project is to make a software that helps to generate clinical notes during surgeries/operations by converting voice to text. It would save time of writing down the notes. A systematic clinical note prepared by converting voice to text would include Database backup,, Reports generated with respect to various end users' perspective and it is customizable. Generating clinical notes during operations and surgeries can be used for future reference and for comparing clinical notes to see the patients progress.
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Description
Extension
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Description
"Climate changes such as global warming increased rainfall or increased water scarcity and even more extreme weather conditions such as flooding and storms have measurable effects on the varied climates found across countries like India. The magnitude of these changes impacts the local conditions and the specific ecology and epidemiology of the different diseases. Climatic conditions strongly affect air-borne water-borne and vector-borne diseases. Geographical conditions also add to these effects. Therefore capacities need to be built to assess how climate change might alter the effectiveness of proposed programs or might affect future population health so that the cumulative or catastrophic events with large health impacts could be avoided. We focus on how to improve future global disease containment typically airborne (case study Tuberculosis) by the inferences that can be drawn by mining of environmental data and correlating it with the disease data and climatic and geographical conditions to predict the transmission patterns of communicable diseases. "
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Description
Extension
Coreveillance:Let's make our Society a Safe Place to Live In
Description
The culture in our civic society has undergone an abrupt change due to the extensive use of CCTV Surveillance. Currently our Urban Society is exclusively dependent upon CCTV Footage for divulging any abnormal situation. This scenario has opened up a new arena for the Researchers to judiciously utilize Video Analytics techniques to address many sensitive social issues such as violation of Human Rights (HR). So the objective is to design a Surveillance Platform equipped with Situation Intelligence to aid Government bodies in taking corrective action against unfavourable intruders and destructive mishaps.
Coreveillance:Let's make our Society a Safe Place to Live In
Description
The culture in our civic society has undergone an abrupt change due to the extensive use of CCTV Surveillance. Currently our Urban Society is exclusively dependent upon CCTV Footage for divulging any abnormal situation. This scenario has opened up a new arena for the Researchers to judiciously utilize Video Analytics techniques to address many sensitive social issues such as violation of Human Rights (HR). So, the objective is to design a Surveillance Platform equipped with Situation Intelligence to aid Government bodies in taking corrective action against unfavourable intruders and destructive mishaps.
Cost effective electonic limbs
Description
A bionic limb is an add-on that is provided to the amputees replacing the missing limb. This project is mainly focused on the person who has been a victim of any fatal accident which has caused loss of human limbs. The electronics limbs that are available are not cost effective & stable. So to serve as an alternative for this our method can give a highly cost effective and flexible method of making a bionic limb.
Development of Methodology for Indian Evaluated Nuclear Data Library for applications in S & T
Description
NA
Drone based Warehouse Automation
Description
The proposed idea will be useful for the warehouse automation. Using drones for this purpose will not only save time but also it will be cost effective and it also lowers error probability.
E-toll
Description
"Majority of the unnecessary traffic that exists in India is due to the improper management of toll systems. Manual collection of toll is practiced in over 80% of the existing systems. This has proved to delay and crowding near the toll systems majorly caused due to the manual money exchange and improper lane management. The other problems with current toll systems are that they are slow inefficient and unregulated. In automatic systems vehicles are scanned in a fraction of a minute and the payment is done. In manual systems barriers have to be lifted or needs to be slid or pushed. Manual collection of toll implies that no detail is recorded into a computer and mostly written down in log sheets. Hence its retrieval is difficult. Through the project being proposed a complete automatic e- toll system is proposed using license plate detection and e- wallet linkage for faster and practical implementation of tolls. "
FireMan Helper
Description
"In a world where fire accidents are increasingly common and the brave first responders always risk their lives to save the lives of others; unfortunately history tells us that these brave first responders do not survive most of the time. Hence to save as many lives as possible and aid the firefighters in the rescue process it is important to leave dangerous tasks to machines. One such device is drone- It provides great maneuverability doesn't risk any personnel and can also gather information at greater speed and reliability. The proposed solution tackles all the problems using drone equipped with the required hardware as follows : Ability to detect fires and monitor the risk of fire approaching a building fence or spreading through cameras. Generation of a map or 3D model for firefighting personnel to get better information on positions of trapped victims at places ablaze and determine the best course of action. Ability to put out a fire in case of unreachable areas or in situations where using Unmanned Drone is the safest approach. Generation of toxicity reports and identify the level of fire for deciding the safety measures to be undertaken and need to be provided to the victims. "
FireMan Helper
Description
In a world where fire accidents are increasingly common and the brave first responders always risk their lives to save the lives of others; unfortunately, history tells us that these brave first responders do not survive most of the time. Hence, to save as many lives as possible and aid the firefighters in the rescue process, it is important to leave dangerous tasks to machines. One such device is drone- It provides great maneuverability, doesn't risk any personnel and can also gather information at greater speed and reliability. The proposed solution tackles all the problems using drone equipped with the required hardware as follows : Ability to detect fires and monitor the risk of fire approaching a building, fence, or spreading through cameras. Generation of a map or 3D model for firefighting personnel to get better information on positions of trapped victims at places ablaze and determine the best course of action. Ability to put out a fire in case of unreachable areas or in situations where using Unmanned Drone is the safest approach. Generation of toxicity reports and identify the level of fire for deciding the safety measures to be undertaken and need to be provided to the victims.
Food to People: A Blockchain Solution
Description
The food supply chain is garnishing more attention as consumers are concerned about outbreaks of diseases.As with other industries food retailers and manufacturers have to be more knowledgeable about the suppliers they use and where their product originates. A food supply chain system is maintained from farmers to retailers using Blockchain. The farmer needs to save details of grown-up crops like origination type of crop the procedure used for sowing and storage information.After receiving food items from the farmers refineries or food processing companies can add information about the processing of crops like packing etc.After each process certain information is added to the block. The consumer can now get information about each crop and be assured of the quality. This system brings transparency and traceability in the food chain and consumers can be assured about the safety of the food and it can help in controlling food adulteration to some extent as the whole process from producing to packing to transportation is traced. Any problems encountered can be easily traced back. Using Blockchain everything is maintained in a decentralized manner and no third party is allowed to add data in the system so that the system can work in a reliable and transparent manner.
Food to People: A Blockchain Solution
Description
The food supply chain is garnishing more attention as consumers are concerned about outbreaks of diseases.As with other industries, food retailers and manufacturers have to be more knowledgeable about the suppliers they use and where their product originates. A food supply chain system is maintained from farmers to retailers using Blockchain. The farmer needs to save details of grown-up crops like origination, type of crop, the procedure used for sowing and storage information.After receiving food items from the farmers, refineries or food processing companies can add information about the processing of crops like packing etc.After each process, certain information is added to the block. The consumer can now get information about each crop and be assured of the quality. This system brings transparency and traceability in the food chain and consumers can be assured about the safety of the food and it can help in controlling food adulteration to some extent as the whole process from producing to packing to transportation is traced.Any problems encountered can be easily traced back.Using Blockchain everything is maintained in a decentralized manner and no third party is allowed to add data in the system so that the system can work in a reliable and transparent manner.
Fraud Prevention on Crowdfunding Platform
Description
Fraud Prevention on Crowdfunding Platform
Garuda: The Intelligent Ornithopter
Description
Proposed project aims at developing a bird-like drone(ornithopter) and a deep learning based AI system for video surveillance.The purpose of the system is to provide a powerful surveillance tool to the police force so as to reduce crime and help maintain the peace of our country. The system consists of ornithopter a bird shaped drone surveilling a specific area with a specific radius and an artificial intelligence powered server capable of detecting violent or malicious crimes from the video data input given by the bird. The law enforcement agencies have been motivated to use video surveillance systems to monitor and curb these threats. But this becomes a tedious task prone to human erroThe core module of this system consists of a frontend having ScatterNet Hybrid Neural Network estimating the pose in humans present in the video and a backend Long Short Term Memory(LSTM) network capable of understanding the context as a whole. Many AI powered surveillance systems are good at recognising the violent or malicious activity but fail to understand the context as a whole. We aim to understand the gradual change in human behaviour in the given scenario understand the confidence level of each expression and derive if the given scenario is truly violent or malicious. The bird is allowed to follow the suspect wherein the direction offsets are given by server. The system differs from any state-of-the-art surveillance systems as it provides aerial surveillance covering larger area and since the drone is bird shaped it can easily navigate the area without being easily detected. And as mentioned the recognition of the true violent or malicious activity is context based.
GPS and GSM based small compact Tracking Module
Description
This is GSM and GPS based Tracking system for child can be fitted in watch or shoes
Maximum Power Point Tracking of Photovoltaic Cell
Description
Solar energy offers a clean climate-friendly very abundant and inexhaustible energy resource to mankind. The main hindrance for the penetration and reach of solar Photo-Voltaic (PV) systems is their low efficiency and high capital cost. This project aims at developing a sliding mode control based buck-boost converter for control of photo-voltaic power using Maximum Power Point Tracking (MPPT). The MPPT is responsible for extracting the maximum possible power from the photovoltaic cell and feed it to the load via the buck-boost converter which steps up the voltage to required magnitude. The main aim of this project is to design a system that will track the maximum power point of the photovoltaic module so that the maximum possible power can be extracted from the photovoltaic cell.
Multi-Functional Detachable Applications For Drones
Description
Its is Multi-attachment application drone the planned applications to be implemented on drones are: All Terrain Attachment Pollution and weather monitoring and Mapping LIDAR Based Mapping and Military Surveillance Fire Fighting combined with Solar Panel Cleaning Agricultural Watering with Pesticides Spraying Secured Delivery Attachment
Parallel Synthesizer with Independent Temparature Control
Description
Parallel Synthesizer with Independent Temparature Control
Predicting floods in coastal regions as a direct consequence of deforestation
Description
The degree and scale of flood hazards have increased massively with the changing climate in the last decades and large-scale flash floods bring fast-moving and rapid-rising water with force resulting in tremendous life and property losses as well as social disruption worldwide. Cutting of mangroves and trees in coastal regions and river plains for land development has led to decreasing water retention and increasing surface runoff which in turn increases the probability of flash floods. Thus flood prediction and flood control are important issues for policy makers and designeTo mimic the complex mathematical expressions of physical processes of floods during the past two decades machine learning (ML) methods and Artificial intelligence (AI) contributed highly in the advancement of prediction systems providing better performance and cost-effective solutions. Flooding in coastal areas depends on factors such as rainfall sea tides bank heights man-made structures like embankments and reservoirs and mangroves and forest cover. Our proposed system will make use of Machine Learning Artificial Intelligence and Image Processing to predict floods in prone areas. Satellite Imagery will be processed to determine changes in tree cover in the target area to get an idea of the scale of deforestation which will then be determined as a cause leading to the occurrence of floods in the region.
Predicting floods in coastal regions as a direct consequence of deforestation
Description
The degree and scale of flood hazards have increased massively with the changing climate in the last decades, and large-scale flash floods bring fast-moving and rapid-rising water with force, resulting in tremendous life and property losses as well as social disruption worldwide. Cutting of mangroves and trees in coastal regions and river plains for land development has led to decreasing water retention and increasing surface runoff which in turn increases the probability of flash floods. Thus, flood prediction and flood control are important issues for policy makers and designers. To mimic the complex mathematical expressions of physical processes of floods, during the past two decades, machine learning (ML) methods and Artificial intelligence (AI) contributed highly in the advancement of prediction systems providing better performance and cost-effective solutions. Flooding in coastal areas depends on factors such as rainfall, sea tides, bank heights, man-made structures like embankments and reservoirs and mangroves and forest cover. Our proposed system will make use of Machine Learning, Artificial Intelligence and Image Processing to predict floods in prone areas. Satellite Imagery will be processed to determine changes in tree cover in the target area to get an idea of the scale of deforestation which will then be determined as a cause leading to the occurence of floods in the region.
Predictive analysis of carbon footprint in metropolitan cities of India.
Description
The primary objective of our project is to identify the relationship between the increase in carbon footprint and deforestation in Indian metropolitan cities. An additional objective is to predict the increase in carbon footprint over the next 25-years and suggest optimal places for tree plantation to the concerned Municipal Corporations. The proposed solution is based on the mapping of carbon emissions with the loss of vegetation in India over the past 50 years and suggests optimal areas for afforestation. SVM and Time-series forecasting models will be used for future carbon footprint estimation based on population growth automobile emissions and industrialization. Forecasting involves taking models to fit historical data and using them to predict future observations. Image change detection methods will be used for analyzing the changes in land-use and vegetation-cover over the yeaImage change detection is a process to analyze multi-temporal images of the same scene for identifying the changes that have occurred. A deep learning neural network will be used to correlate the results of the above models and suggest effective areas for afforestation along with the number of trees required to cop with the current carbon footprint.
Predictive analysis of carbon footprint in metropolitan cities of India.
Description
The primary objective of our project is to identify the relationship between the increase in carbon footprint and deforestation in Indian metropolitan cities. An additional objective is to predict the increase in carbon footprint over the next 25-years and suggest optimal places for tree plantation to the concerned Municipal Corporations. The proposed solution is based on the mapping of carbon emissions with the loss of vegetation in India over the past 50 years and suggests optimal areas for afforestation. SVM and Time-series forecasting models will be used for future carbon footprint estimation based on population growth, automobile emissions, and industrialization. Forecasting involves taking models to fit historical data and using them to predict future observations. Image change detection methods will be used for analyzing the changes in land-use and vegetation-cover over the years. Image change detection is a process to analyze multi-temporal images of the same scene for identifying the changes that have occurred. A deep learning neural network will be used to correlate the results of the above models and suggest effective areas for afforestation along with the number of trees required to cop with the current carbon footprint.
Preparation and characterisation complexes of Cetyltrimethylammonium bromide and Cetylpyridinium Chloride with butyl benzene sulphonates without salt.
Description
Rheological studies of surfactant hydrotrope mixture provide useful information regarding fluidic behaviour of mixtures. Hydrotropes are amphiphilic molecules with shorter hydrophobic chains. Hydrotropes also are being used in combination with other surfactant in several applications. The surfacatnt hydrotrope mixtures show shear induced behaviour. The surfactant and hydrotrope release counterions in their solution. If Surfactant used is cationic and hydrotrope used is anionic then respective oppositely charged counterions combine with each other to form salt. In the present study we are planning to prepare the surfactant hydrotrope complexes without salt. We plan to study the effect of presence and absence of salt on rheological properties of surfactant hydrotrope mixtures. Surfactants chosen are cetyl trimethyl ammonium bromide and cetyl pyridinium chloride.and hydrotrope chosen is n-butyl benzene sulphonate The reason of choosing these compounds are to study steric factors of surfactant head group on rheological properties of their mixtures.
Programmable Computer Controlled Active Analog Filter
Description
Filters are used to improve signal quality. Based upon the application to meet the desired frequency we need to change filter parameter according to the frequency requirement. This results in change of hardware. Such situation can be avoided by controlling the filter parameters through computer. We can achive this by designing a Computer Controlled Active Analog Filters by which we can vary filter parameters without changing components.
Rehabilitation and Protection of Coastal Areas
Description
Extension
Rehabilitation and Protection of Coastal Areas
Description
Extension
Road pot hole Detection
Description
The idea is an initiative to tackle daily road problems in a country like India.The module to be made is also a very small credit card size box which makes it easy to fit on any vehicle.
Sahara: A stanchion for the blind
Description
Owing to demonetization and the foray of new Indian currencies in the market, it has been observed that the visually impaired persons are having a hard time in identifying and distinguishing the Indian currencies. Another major issue is text reading. Although there are many OCR engines that are available today, it is quite difficult for the visually impaired to operate them. Also, all of these engines require an internet connection. Face recognition is a further add-on which is of a major concern considering certain security aspects. Several other tasks like these, if packaged in a single device can be a breakthrough for the visually impaired and would revolutionize their world. Currently, the devices offering such features are exorbitantly charged and the price of such devices is around INR 3 lakhs. Owing to the client-server architecture which is the base for such devices, they continuously require a strong internet connection. The client-server architecture further adds to its disadvantages, in the sense that the server may get overloaded and the availability of such a system would be challenged under real-world conditions. To combat the availability issue, the devices designed currently offer a constrained time limit say 100 minutes per month. Thus a user after spending an exorbitant amount on the device would also have to pay a price if he reaches this 100 minutes limit for a particular month. The proposed system is a portable, handy, easy-to-use, internet-less device that would aid the visually impaired in his quotidian chores. The highlighting feature of our system is that it doesn't embody client-server architecture. We aim at providing a feasible device that can aid the blind in chores that they really need help for.
Smart Box
Description
An application which can collect and depict the power consumption of various home appliances such as fans air conditioners washing machines and plot graphs to analyse the usage and provide solutions to optimise the bill by incorporating the regional billing system. The application will also predict the estimated bill. It will even allow the user to switch on and off a particular appliance from remote places. The application can also be used to schedule the working of selective devices.
Smart health assistant
Description
Smart Health Assistant(SHA) is designed to alleviate the patient from the error-prone and monotonous task of reading the prescription every time before ingesting the medicine. This portable and economical SHA system would help aged patients and patients with related comorbidities.
Trail-Tracker: Antipoaching Intelligence using AI and IoT
Description
Wildlife is a key part of the ecosystem that keeps the balance of nature intact. However a sharp decrease in a variety of species has a direct negative impact on natural ecosystems and local economies. Poaching is one of the most significant threats to wildlife. A poacher??s main objective is to gain large profits by selling or illegally trading valuable products obtained after processing body parts of animals such as an elephant??s tusks which are used to make ivory tiger??s skin which is used to make leather etc. Hunters use different methods to capture animals. Many commercial poachers use military-grade weapons. Arrows and spears are also used to poach wildlife. Poachers also use techniques to chase the animal into large nets known as trap nets. They can also be chased into pitfall traps (a large hole in the ground that is hidden with leaves and plants that an animal falls in when it tries to walk over it). Thus a solution that works in real-time is needed to pursue the cause of wildlife conservation by preventing the poaching of any species of animals - endangered or non-endangered by profit-hungry poacheIn comparison to previous methods in the same domain it presents an alternate approach in the form of a monitoring system that can track poaching activity and predict poachers?? behaviour and alert forest authorities for any suspicious crime
Trail-Tracker: Antipoaching Intelligence using AI and IoT
Description
Wildlife is a key part of the ecosystem that keeps the balance of nature intact. However, a sharp decrease in a variety of species has a direct negative impact on natural ecosystems and local economies. Poaching is one of the most significant threats to wildlife. A poacher’s main objective is to gain large profits by selling or illegally trading valuable products obtained after processing body parts of animals, such as an elephant’s tusks which are used to make ivory, tiger’s skin which is used to make leather, etc. Hunters use different methods to capture animals. Many commercial poachers use military-grade weapons. Arrows and spears are also used to poach wildlife. Poachers also use techniques to chase the animal into large nets, known as trap nets. They can also be chased into pitfall traps (a large hole in the ground that is hidden with leaves and plants that an animal falls in when it tries to walk over it). Thus, a solution that works in real-time is needed to pursue the cause of wildlife conservation by preventing the poaching of any species of animals - endangered or non-endangered by profit-hungry poachers. In comparison to previous methods in the same domain, it presents an alternate approach, in the form of a monitoring system that can track poaching activity and predict poachers’ behaviour and alert forest authorities for any suspicious crime
Transparent and trackable donations using blockchain
Description
Charity-Chain is a decentralised social impact network built on the Ethereum blockchain. It helps social organisations (charities NGOs social enterprises) to run projects transparently using smart contract-based incentives to ensure their impact is independently?? ??verified?? ??and?? ??accessible?? ??to?? ??everyone. This makes it much easier for funders (philanthropic organisations impact investors small donors) to monitor their transactions and hence restore their trust in giving to such social organizations.It can be used to rebuild public trust in charity by creating an innovative blockchain technology that will ensure charity organizations use the donation they receive judiciously. Blockchain donations are easy global quick and come with little or no transfer fees. It gives small NPOs the chance to receive a donation from global donors using blockchain technology.
voice controlled wheelchair
Description
na
Water Monitoring System using IoT
Description
Water is an essential part of our lives. Therefore the quality of water present in our environment has to be checked now & then. An estimated 580 people in India die of water pollution related illness (including waterborne diseases) every day. 40% of China??s water supply is polluted to unsafe drinking levels. Water pollution kills around 3.6 million people around the world every year. So in today??s times with increasing urbanization and pollution it has become very necessary to monitor & evaluate the quality of water. Our project aims at designing a quick and efficient system that will monitor the key parameters of freshwater health in real-time. Not only is our project cost effective but it will also save manual labour required to go to lakes bring back water samples for testing & time consuming testing procedures.
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
Description
Extension
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
Description
Extension
" Machine Learning based Flood Prediction model for MumbaiIndia"
Description
"Flooding is a chronic natural hazard with potentially devastating consequences giving rise to all losses due to natural events. ??The control from flooding and harnessing is not so easy. The Mumbai in particular is facing a serious challenge with an increasing frequency of flood in recent yeaIt is therefore crucial to utilize the state-of-the-art sensing and communication technologies to monitor and predict flood occurrences. Thus to warn the city of Mumbai about the disaster in advance to avoid devastating consequences by using prediction technology is the subject of our project. "
Air quality monitoring and control system using WSN
Description
"Rapid urbanization and industrialization has resulted in a sustained degradation of environmental quality parameteIt is important to keep track of various environmental pollution indices so that realistic models can be developed and relevant public policies are created. Traditional methods for air pollution measurements are expensive and have a spatial constraint. With these limitations air pollution monitoring in broader area is not feasible. However the use of modern low cost sensors in conjunction with wireless sensor network (WSN) creates an opportunity to collect real time data from different locations and provide detailed pollution map. The main aim of this project is to develop a low cost multi-sensor mote for air pollution measurement system and to develop WSN protocols for data gathering and data aggregation protocol which will help the society in terms of health."
Autonomous Luggage carrying Robot using Image Processing
Description
Automation can not only save the human effort but also increases the efficiency, accuracy and productivity of work. Thus, Automation can provide optimal solutions where human capabilities face restrictions. Old age and Handicapped people deal with great difficulties while carrying a luggage as it requires considerable human effort. Even for normal people carrying heavy loads becomes a Herculean Job. Automation can be used to tackle such a situation. The proposal aims to create a luggage carrier robot which can save the human efforts by following the user and deliver the luggage at the desired destination with the help of automation. The project emphasizes on creating a robot which follows the user by tracking the unique symbol. Robot will understand the position and will be keeping track of the user by tracing the speed. The robot will also sense the surrounding by the sensors and will try to find the best possible way to keep in pace with the user and also avoid bumping into obstacles.
Contagious disease propagation study and containment strategies using Machine Learning : Indian Scenario
Description
Climate changes, such as global warming, increased rainfall, or increased water scarcity and even more extreme weather conditions, such as flooding and storms have measurable effects on the varied climates found across countries like India. The magnitude of these changes impacts the local conditions and the specific ecology and epidemiology of the different diseases. Climatic conditions strongly affect air-borne, water-borne and vector-borne diseases. Geographical conditions also add to these effects. Therefore capacities need to be built to assess how climate change might alter the effectiveness of proposed programs or might affect future population health so that the cumulative or catastrophic events with large health impacts could be avoided. We focus on how to improve future global disease containment typically airborne (case study Tuberculosis) by the inferences that can be drawn by mining of environmental data and correlating it with the disease data and climatic and geographical conditions to predict the transmission patterns of communicable diseases.
Digital India - Smart Subsidy System.
Description
Digital India - Smart Subsidy System.
Farm Guide
Description
Indian agriculture sector accounts for 18% of India's gross domestic product (GDP) and provides employment to 50% of the countries workforce. India is the world's largest producer of pulses rice wheat corn fruits spices and spice products. Indian farmers not only have to struggle for the better yield against the natural disasters but also have to tackle the losses of the net output because of lack of knowledge of current market trends and real time advisory platforms available. Many farmers today generally rely on intuition and experience for growing and producing crops. Considering this scenario proposed systems aims to use technologies such as deep learning cloud computing image processing to assist farmers in different phases of farming and also selling the crops at a proper price.
Heart Disease prediction using AI (Deep Learning).
Description
Heart Disease prediction using AI (Deep Learning).
Infant Incubator intelligent control system
Description
na
Intelligent Classroom : Students’ behaviour and Emotions Analysis using Face Recognition (Compute Grant)
Description
Intelligent Classroom : Students’ behaviour and Emotions Analysis using Face Recognition (Compute Grant)
Machine Learning based Flood Prediction model for Mumbai,India
Description
Flooding is a chronic natural hazard with potentially devastating consequences giving rise to all losses due to natural events. The control from flooding and harnessing is not so easy. The Mumbai, in particular is facing a serious challenge with an increasing frequency of flood in recent years. It is therefore crucial to utilize the state-of-the-art sensing and communication technologies to monitor and predict flood occurrences. Thus, to warn the city of Mumbai about the disaster in advance, to avoid devastating consequences by using prediction technology is the subject of our project.
Optimized rescue system for accidents and emergencies
Description
Optimized rescue system for accidents and emergencies
Prototype Design and controller implementation for a battery- ultra capacitor hybrid electric vehicle
Description
"Hybrid Electric Vehicles (HEVs) utilize electric power as well as a mechanical engine for propulsion; therefore the performance of HEVs can be directly influenced by the characteristics of the Energy Storage System (ESS). The ESS for HEVs generally requires high power performance long cycle life and reliability as well as cost effectiveness. So the Hybrid Energy Storage System (HESS) which combines different kinds of storage devices has been considered to fulfil both performance and cost requirements. To improve operating efficiency cycle life and cold cranking of the HESS an advanced dynamic control regime with which pertinent storage devices in the HESS can be selectively operated based on their status. The main source to generate the energy is through solar wind and hydro energy. The energy generated is stored in a storable battery or ultra-capacitor (electrical energy storage device used for storing large amount of electrical charge) and when required it is used by the vehicle."
Recommender System to Identify Influential Individuals on Social Media
Description
Recommender System to Identify Influential Individuals on Social Media
Rehabilitation and Protection of Coastal Areas
Description
"The proposed solution uses image change detection process. Image change detection is a process toanalyse multi-temporal images of the same scene for identifying the changes that have occurred.We propose a novel difference image analysis approach based on deep neural networks for image change detection problems.The deep neural network learning algorithm for classification includes unsupervised feature learning and supervised fine-tuning.Sine a deep neural network can learn complicated functions that can represent high level abstractionsit can obtain satisfactory results.Theoretical analysis and experiment results on real datasets show that the proposed method outperforms some other methods. "
River Cleaning Robot
Description
River Cleaning Robot
Smart Box
Description
An application which can collect and depict the power consumption of various home appliances such as fans, air conditioners, washing machines and plot graphs to analyse the usage and provide solutions to optimise the bill by incorporating the regional billing system. The application will also predict the estimated bill. It will even allow the user to switch on and off a particular appliance from remote places. The application can also be used to schedule the working of selective devices.
Smart Locker
Description
Smart Locker
Smart vehicle for physically challenged people
Description
"The main purpose of project is to design a smart vehicle to overcome the problems faced by physically challenged people. The project aims to provide the appropriate help needed by the patient. The vehicle performs multiple tasks. A specific task can be chosen for a desired problem faced by the patient. In this projectwe developed the device that performs the following three tasks: 1.Motion based message conveyor for paralytic/disabled people and mute people using hand gestures2.Hand gesture controlled vehicle 3.Obstacle avoidance for blind people . "
Time to Digital Converter for Nuclear Timing Spectroscopy Systems
Description
"Time Interval measurement is required in various applications from different domains e.g. Laser ranging applications the laser pulse is used to detect the distance of the object. Precise measurement is required of time interval when the laser beam is sent and the arrival of the reflected beam from the object. Time of flight measurement experiments are used in timing spectroscopy systems lifetime measurements in atomic and high energy physics nuclear medical instruments etc. The main aim of the Project is to develop Time to Digital Converter (TDC). At the arrival of START pulse positive slope generator starts building ramp at the output using Reference Input 1 (negative voltage). During time interval T1- ramp starts increases in positive direction. Ramp slope and voltage magnitude is decided by the designed components of positive slope generator. When STOP pulse is received Reference Input 2 (positive voltage - having opposite polarity w.r.t. Reference Input 1) is connected to negative slope generator. Ramp starts decreasing in the negative direction during time interval T2. When ramp crosses zero (ground line) it is detected by Comparator. Time interval (when ramp is decreasing) is digitally counted by counter. So higher the input time difference between START and STOP pulse ramp increases in positive direction to large magnitude of voltage hence time required for decreasing ramp is more and so the digital counter output increases in proportion to this time interval. Depending upon the range of the time interval measurement the positive slope generator circuit will generate calibrated slopes and accordingly negative slope generator circuit will also generate corresponding calibrated negative slopes. These slopes will be decided depending upon the range and resolution required for TDC. "
Transparent and trackable donations using blockchain
Description
Charity-Chain is a decentralised social impact network built on the Ethereum blockchain. It helps social organisations (charities, NGOs, social enterprises) to run projects transparently, using smart contract-based incentives to ensure their impact is independently verified and accessible to everyone. This makes it much easier for funders (philanthropic organisations, impact investors, small donors) to monitor their transactions and hence restore their trust in giving to such social organizations.It can be used to rebuild public trust in charity by creating an innovative blockchain technology that will ensure charity organizations use the donation they receive judiciously. Blockchain donations are easy, global, quick and come with little or no transfer fees. It gives small NPOs the chance to receive a donation from global donors using blockchain technology.
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
Description
"This project is proposed with the idea to analyze the difference between the past and present condition of the water bodies and provide a solution to the water supply problem by detecting areas suitable for catchment. There has been a significant amount of change in the state of water bodies in the past decade. The shrinkage of the water bodies due to urbanization and changes in the climatic conditions has led to the scarcity of water. Hence there is a need of other alternatives to meet the need of water. One of the ways is to increase the water catchment area in a particular region. Our system is based on this approach it will use AI to predict areas which could be used for the catchment purpose and will lead to optimum distribution of water. This project is proposed with the idea to analyze the difference between the past and present condition of the water bodies and provide a solution to the water supply problem by detecting areas suitable for the catchment. There will be a lot of image processing done in this project on Land Sat Images provided by Google Earth of different timelines. These images will help us understand the change in the regions over the yeaThe proposed system will gather all the data from multiple sources in the form of images and text to analyze all the parameters and factors that have resulted into a shortage of water. The proposed system aims at helping people understand the best areas that can be used for catchment and storage of water. "
Water Supply Management and Catchment Control in Drought Prone Regions of Rural India
Description
This project is proposed with the idea to analyze the difference between the past and present condition of the water bodies and provide a solution to the water supply problem by detecting areas suitable for catchment. There has been a significant amount of change in the state of water bodies in the past decade. The shrinkage of the water bodies due to urbanization and changes in the climatic conditions has led to the scarcity of water. Hence there is a need of other alternatives to meet the need of water. One of the ways is to increase the water catchment area in a particular region. Our system is based on this approach, it will use AI to predict areas which could be used for the catchment purpose and will lead to optimum distribution of water. This project is proposed with the idea to analyze the difference between the past and present condition of the water bodies and provide a solution to the water supply problem by detecting areas suitable for catchment. There will be a lot of image processing done in this project on Land Sat Images provided by Google Earth of different timelines. These images will help us understand the change in the regions over the years. The proposed system will gather all the data from multiple sources in the form of images and text to analyze all the parameters and factors that has resulted into shortage of water. The proposed system aims at helping people understand the best areas that can be used for catchment and storage of water.
App for Aromatic and Medicinal crop growers
Description
App for Aromatic and Medicinal crop growers
Electricity Consumption and Home Automation
Description
An application which can collect and depict the power consumption of various home appliances such as fans air conditioners washing machines and plot graphs to analyse the usage and provide solutions to optimise the bill by incorporating the regional billing system. The application will also predict the estimated bill. It will even allow the user to switch on and off a particular appliance from remote places. The application can also be used to schedule the working of selective devices
Electricity Consumption and Home Automation
Description
An application which can collect and depict the power consumption of various home appliances such as fans, air conditioners, washing machines and plot graphs to analyse the usage and provide solutions to optimise the bill by incorporating the regional billing system. The application will also predict the estimated bill. It will even allow the user to switch on and off a particular appliance from remote places. The application can also be used to schedule the working of selective devices
Mind controlled assistive quadrotor drone
Description
na
Reinforcement learning on robot
Description
"Most of the robots today are programmed explicitly for particular task and cannot perform other task until their software is updated manually. Machine learning algorithms are used in these robots for making them more robust and sensitive to changing environment. Machine learning gives computer the ability to learn without being explicitly programmed and reinforcement learning is an area of machine learning which allows software agents and machines to automatically determine the ideal behavior within a specific context to maximize its performance i.e to maximize a numerical reward. In My project a robot will learn to walk in one direction without being explicitly programmed to do so just by predicting its own mathematical model with help of previous actions and observations and then using feedback to maximize its reward. "
Speed Regulating mechanism for Road Safety
Description
Speed limits one of the oldest methods of managing speeds on roads are intended to enhance road safety by provider an upper bound on speed to reduce the probability and severity of clashes. They also have a coordinating function to reduce the dispersion in vehicle speed and thereby reduce the potential for conflicts. Current system of enforcing speed limits is dependent upon the amount of police officers on duty. It has been noticed that drivers are more likely to adhere to the speed limit in areas of high enforcement and go back to their standard behavior once this enforcement is reduced. Thus to ensure a high level of compliance the limits must be set at levels that are largely self enforcing. There is also the issue of the drivers who don??t care about the speed limit and drive well in excess. These drivers pose a threat to their well-being as well as the well-being of otheFaster vehicles are more prone to accident than the slower one and the severity of accident will also be more in case of faster vehicles. Higher the speed greater the risk. At high speed the vehicle needs greater distance to stop i.e. braking distance. A slower vehicle comes to halt immediately while faster one takes long way to stop and also skids a long distance due to law of motion. A vehicle moving on high speed will have greater impact during the crash and hence will cause more injuries. The ability to judge the forthcoming events also gets reduced while driving at faster speed which causes error in judgment and finally a crash. Sometimes it becomes difficult to identify vehicle owner who violates traffic rules and drives too fast or breaks signal. Therefore it is not possible to catch and punish those kinds of people. Our project aims to restrict the driver from exceeding the maximum speed for a road or highway. The speed limit for the particular location you have entered is provided to the vehicle through the database or through the dynamic color stripes on the road. The purpose of this project is to enforce road safety by forcing the vehicle to adhere to the speed limit. The project also focuses on analyzing the cause of the accident and detection of potholes to alert the driver and the government about it.
Speed Regulating mechanism for Road Safety
Description
Speed limits, one of the oldest methods of managing speeds on roads, are intended to enhance road safety by provider an upper bound on speed to reduce the probability and severity of clashes. They also have a coordinating function, to reduce the dispersion in vehicle speed and thereby reduce the potential for conflicts. Current system of enforcing speed limits is dependent upon the amount of police officers on duty. It has been noticed that drivers are more likely to adhere to the speed limit in areas of high enforcement, and go back to their standard behavior once this enforcement is reduced. Thus, to ensure a high level of compliance, the limits must be set at levels that are largely self enforcing. There is also the issue of the drivers who don’t care about the speed limit, and drive well in excess. These drivers pose a threat to their well-being as well as the well-being of others. Faster vehicles are more prone to accident than the slower one and the severity of accident will also be more in case of faster vehicles. Higher the speed, greater the risk. At high speed the vehicle needs greater distance to stop i.e. braking distance. A slower vehicle comes to halt immediately while faster one takes long way to stop and also skids a long distance due to law of motion. A vehicle moving on high speed will have greater impact during the crash and hence will cause more injuries. The ability to judge the forthcoming events also gets reduced while driving at faster speed which causes error in judgment and finally a crash. Sometimes it becomes difficult to identify vehicle owner who violates traffic rules and drives too fast or breaks signal. Therefore, it is not possible to catch and punish those kinds of people. Our project aims to restrict the driver from exceeding the maximum speed for a road or highway. The speed limit for the particular location you have entered is provided to the vehicle through the database or through the dynamic color stripes on the road. The purpose of this project is to enforce road safety by forcing the vehicle to adhere to the speed limit. The project also focuses on analyzing the cause of the accident and detection of potholes to alert the driver and the government about it.
Vehical collision avoidance at junctions blind urns and hairpin bends
Description
"Transportation has great importance in our daily life and it??s development has made many of our chores much easy. But it can cause disaster to us and even can kill us through accidents. In year 2016 deaths at/close to junctions-t junction (23420 ) y junction(13897) four arm junction(11789). Now-days automotive vehicles are increasingly being equipped with collision warning /detection systems for predicting the potential collision with an external object such as another vehicle or a pedestrian. Upon detecting a potential collision such systems typically initiate an action to provide a warning to the vehicle operator or alert of emergency help The following project deal with idea that targets a low cost retrofit scheme which can be used on Indian roads to prevent the worst case scenarios in road crashes. Monitoring of roads with the help of CCTV cameras would see less people flouting speed limits. Not only will it be cost effective it will also save energy manual labour and lead to smoother operations to ensure road safety. At day time junctions are placed with signal. At night after 11 most signal are closed. This project is specifically aimed to avoid accidents at low traffic density junctions in night. When the signals are closed this system will work it will indicate driver coming from other direction at junction about the cars coming from various directions. This will allow the driver to slow the vehicle and avoid accidents."
Martian Landform Segmentation Based on Structural Similarity
Description
First year of research work mainly focuses on identifying and developing image processing techniques those are necessary to determine science outcomes with greater level of confidence. In this concern the work that we have completed is listed below i. Implemented a fusion-based algorithm to enhance weakly illuminated regions /images captured by Mars Color Camera (MCC). ii. Implemented an automated image segmentation algorithm for area measurement & demarcationof different crater features. the use of some spatial domain normalization & similarity measurement techniques.
Land Use Classification Using Satellite Images(Compute Grant)
Description
Land Use Classification Using Satellite Images(Compute Grant)