Category: In-Depth

We Care4U

India Today       Economic   Times      Times Now      NDTV         Careers360              Newsgram             Outlook            Hindustan Times             Jagran Josh New Delhi Times                  Express Computer                        Sentinel Assam                     Manorama            The Hindu BusinessLine

For a nation with as many as 112 million elderly people, geriatric care is fast emerging as a major worry for India. Apart from a range of health problems, the elderly face loneliness, abuse, or plain neglect. Even if willing, the caregiver at times finds it inordinately difficult to reach out to the aged at the right time.

A solution might be close at hand. An interdisciplinary team of 2nd year B.Tech students of IIT Kharagpur have built two interconnected android smartphone apps under the name ‘CARE4U’ that connects the caregiver to the elderly. One of these apps can be installed on the phone of the elderly, the other on the smartphone of the caregiver.

The neural network-based fall detection algorithm in the app installed on the phone of the elderly can detect whether the elderly has fallen down. If there is a fall, it automatically calls the caregiver and emergency services with the location of the elderly person. Even if there is no internet connection, the fall detection will work.

CARE4U also has a ‘Medicine Reminder’ feature to remind both the elderly as well as the caregiver that it is time for the former to take medicine. To make a list of the medicine, all one has to do is take a photo of the medicine. The image-to-text recognition algorithm of CARE4U automatically detects the name of the medicine and adds it to the list. The user then just needs to set the time at which the medicine has to be consumed.

The android-based CARE4U app recently won the IIT Kharagpur team, Data_X, the first runners-up position at a nationwide hackathon called ‘vesAIthon’19’ sponsered by Capgemini and LeadingIndia.AI. The 24-hour AI coding event, hosted by VESIT (Vivekanand Education Society’s Institute of Technology), proposed to make an impact on the community by building a workable AI solution for the most pressing social challenges faced by senior citizens, the differently-abled and children. The final judging was done by the end users and experts.

As to why the team chose to work on elderly, Aniruddha Chattopadhyay, a 2nd year student of the Department of Industrial and Systems Engineering said, “We strongly feel that AI should impact and improve everyone’s life. Since not much has been done using AI for old people, we decided to give it a try.” Apart from Aniruddha, the team comprised Aadi Swadipto Mondal and Kanishka Halder of Electronics and Electrical Communication Engineering and Partha Sarathi Roy from the Department of Geology and Geophysics.

CARE4U can also detect emotion. Whenever the elderly opens the app, the phone takes his picture and a mood index is calculated. This detects whether the person is sad or not and automatically updates the caregiver with the timestamp. The caregiver can check what mood the senior citizen has been through in the day and perhaps talk about it.

The app also has a cognitive Intelligent chatbot for the elderly person to engage with. Kanishka Haldar says, “We customized it to recognize the current mood of the person and, accordingly, fine tune its conversations with that of the person. For example, the chatbot can recommend a motivational quote or an old song when the person is sad.”

Aadi Swadipto Mondal of the team says, “The best thing about our app is that except for the chatbot, all other Machine Learning models run on the mobile itself, so no cloud service is needed. Even if there is no internet connection, all other features such as fall detection, emotion detection will work.”

Partha Sarathi Roy adds, “CARE4U can also do a plethora of other day-to-day life activities like make a call, send a text, book a cab and so on.” The app also has a record of medical histories, allergies’ account, an SOS button, real time location tracking and so on.

Aniruddha says, “Another feature of our app is that in case we want to upgrade the tensorflow based Neural Net model, we just have to upload a tensorflow lite model in firebase from our end whenever there is a net connection. The app will then automatically sync with firebase. No hefty updates from Google Play are needed.”

Team Data_X won INR 30,000 prize money. Around 30 teams were shortlisted for the finals on June 28-29 for the hackathon finals in Mumbai.

Smart Sensors for Smarter India @SIH2019

India Today    Millennium Post    The Week    Business Standard    Indian Express

From life-saver to asset-tracker to theft-preventer, SIH 2019 Hardware edition at IIT Kharagpur witnessed prototype sensor development for a wide array of industrial challenges. 93 green horns from seven states participated in this week-long national competition where they were posed challenges by Ministry of Coal and Garden Reach Shipbuilding Yard to develop industry-scale hardware solutions ranging from Smart Communication to Smart Vehicles, from Security and Surveillance to Miscellaneous technological ideas related to tertiary sectors.

This is the first time that public and private sector companies have become part of Smart India Hackathon in its 3 years of existence, including 40 industries and 9 Central Govt. ministries and departments. The purpose is to bridge the gap between industry and academia in order to improve the competitiveness of Indian goods and services in the global market and to encourage entrepreneurship among students in line with Startup India program and thus to boost employment.

Prof. Sriman Kumar Bhattacharyya, officiating Director of IIT Kharagpur, said, “What started as an initiative to playfully involve students to think creatively has emerged as a major initiative which has seen youth from all over India think hard and come up with solutions for many problems facing India today.”

Prof. Shailendra K. Varshney, coordinator of the event at IIT Kharagpur said, “Smart India Hackathon is an innovative platform to ignite young minds to think, to solve problems with the help of technology. It is learning through innovation!”

The Ministry of Coal announced five winners for all of its five problem statements carrying an award of Rs. 1 Lakh each for designing prototypes.

While Team Gravity Plus from Lingaya’s Vidyapeeth, Faridabad, Haryana developed a sensor which could use a combination of the chemical composition of air to locate victims trapped under mining debris or roof fall or gas explosion, Team Wild Crew from Netaji Subhas Institute of Technology, Dwarka, Delhi developed a prototype sensor and software which would work as an automatic alert for Safety Officers and Ambulances for accident victims in vehicles.

Team Magnificent Dreams from PSNA College Of Engineering and Technology, Dindigul, Tamil Nadu developed a prototype control panel to display key parameters of heavy earth moving machinery, Team Enigma 99 from CVR College of Engineering, Ibrahimpatan, Telangana developed a smart sensor based fuel tank guard alarm to give protection against theft and siphoning.

Team Robogyan Dr. Akhilesh Das Gupta Institute of Technology & Management, Delhi, developed an IoT device with GPS which can help CSR project monitoring on a real-time basis and create a databank of all the assets to conduct appropriate analysis. The team’s prototype is market ready confirmed team member Jai Garg.

Garden Reach Shipbuilding Yard adjudged Team Tesseract of Sri Ramakrishna Engineering Colleges, Coimbatore, as the only winner for their new hardware design solution towards insulation issue in Auxiliary and Deck machinery motors in naval ships. They were awarded Rs. 50,000/- as prize money. Mr. Ambudhi Shukla, Deputy Manager in Garden Reach Shipbuilding Yard, said, “Students apply their fresh minds and bring into play new concepts. They have worked well and devised cost effective, simple solutions which can be implemented industrially.”

Where there’s a will…

Careers360

An AI-based intelligent traffic control system could revolutionize traffic management in India. Already, the Delhi Traffic Police are mulling over the matter. At IIT Kharagpur, an undergraduate student team  -Bits n Bytes – presented an exhaustive model of such an AI system based on real time traffic feed and lifted the top prize at the up.AI Challenge recently.

The up.AI Challenge is what can be called the ‘endgame’ of the up.AI summit that was held at the IIT Kharagpur campus last October (http://www.kgpchronicle.iitkgp.ac.in/eat-pray-love-artificial-intelligence/). After a week-long jamboree in 2018 that saw a congregation of close to a thousand students, various faculty members and industry experts to talk and think about the application of Artificial Intelligence in various sectors, the up.AI Challenge was launched. Under the mentorship of IIT Kharagpur professors, students were to work on projects during the winter vacation and then present their conclusions to the judges.

They did this summer. And the result was the winning idea of Bits n Bytes, followed by the projects of team EduFYI and TinTEd-AI which won the 1st runner-up and 2nd runner-up prizes respectively. EduFYI proposed an AI tool to automatically guide its users through a distance learning course, helping them to learn faster and more efficiently. TinT-AI proposed an AI-based Intelligent Automated Software Applications (iASA) to replace the prevalent ASA or Applicant Tracking Systems in the recruitment industry.

The intelligent traffic control system devised by Y. Sai Sanjeet, P. Anusha and P.V.S.L Hari Chandana of the winning team uses a deep reinforcement learning architecture to dynamically adjust traffic signals’ duration using a Deep Q network. The idea is to reduce the waiting time of vehicles at traffic intersections and allow a smooth flow of traffic.

Hari Chandana says, “Compared to the existing approaches that focus on traffic signal optimization for a single intersection, our approach is based on a collaborative control of traffic signal phases of multiple intersections.” As the model uses Independent Q-Learning, it takes all the other intersections as part of the environment and gets to train on a wider sample of data.

The model, the team says, is adaptable and can be used to control traffic in any area, by simulating the road network and training the model on it. The model can then be used to intelligently control the real-time traffic in that particular road network.

Like Bits n Bytes, EduFYI also tackles a relevant problem. In online distance learning courses, it often becomes difficult for instructors to answer individual doubts and questions. With classification of these questions into educational categories, the instructor can hope to better address student queries. At the same time, students can get a better evaluation of their understanding of the study material.

Divyansh, who was guided by Prof. Jiaul Paik, says, “For our task, we decided to classify the questions based on Bloom’s taxonomy.” The project termed “ConvNets with BiLSTMs for Question Category classification using ELMo Embeddings” has led to a model that has showed 80 per cent test accuracy and, it is hoped, will improve personalized learning such as in the online MOOC sector.

TintEd-AI hopes to help job-seekers to get hired and recruiters to hire using AI. The lone member team of Kumar Aniket was mentored by Arindam Chatterjee of HSBC Global Analytics, India, and Poornima Muthuswamy of Innovation Team Wells, Fargo, California.

His ‘Tint’ has several components – Resume Job Matcher, Job Recommender System, Automatic Resume Summarizer based on NLP and Automatic Resume Scoring that takes into account not only how the resume scores across different fields of education and professional degrees but also word count per section such as experience, leadership, projects etc. Aniket says, “Strategic use of AI, combined with the personal touch of human recruiters can help companies fill open positions faster and with more qualified candidates.”

Anirban Santra, a PhD student of the Computer Science and Engineering Department, who was the Program Chair of up.AI said, “Several of the ideas presented at the up.AI Challenge may have been visited before. But what is important is that undergraduate students took up the challenge to use AI to come up with solutions and learnt a lot in the process.”

Many of the participants have plans to further develop their ideas. Kumar Aniket, for example, wants to develop a Virtual Interview Analyzer. Prof. Sudeshna Sarkar, Head of the CoE for AI, said, “Up.AI tapped into the massive interest of students in AI. I hope that in the coming days, they will develop their interests and come up with more robust solutions using AI.”

In a happy place

The Bio-Electrochemistry laboratory at IIT Kharagpur has helped IIT Kharagpur gain the fourth position among institutions in the world on the basis of its publication record on microbial fuel cell research for real field applications (according to Scopus database). The laboratory is the workplace and practically the home of Prof. Makarand Madhao Ghangrekar of the Department of Civil Engineering, who also heads the newly-established Aditya Choubey Center of Re-Water Research.

In the last two years, Prof. Ghangrekar’s lab has published more than 50 journal papers in high impact factor journals such as Bioresource Technology, Electrochimica Acta, Bioelectrochemistry, International Journal of Hydrogen Energy and so on. The group’s 150 journal publications in reputed peer reviewed journals have received more than 3500 citations and command an h-index of 31 (Google Scholars). Students from universities in India and abroad (UC, Berkley; University of Bremen, Germany; Newcastle University, UK) have been visiting the laboratory to train in bio-electrochemistry research.

The laboratory is mainly focused on various types of Bio-Electrochemical Systems (BESs) such as microbial fuel cell (MFC), microbial carbon capture, microbial electrosynthesis and so on. Prof. Ghangrekar says, “We mainly aim to fabricate low-cost BES and take this technology from lab-scale setup to successful field scale demonstration which should be both economically and environmentally sustainable.”

BES is multidisciplinary approach for wastewater treatment and CO2 sequestration. These systems use microbes as biocatalyst for the production of value-added products like bioelectricity and organic chemicals during the treatment of waste water, thus eliminating the use of expensive metal based catalysts for these processes.

The Bio-Electrochemistry lab at IIT Kharagpur has been focussing on various aspects of MFC (microbial fuel cell) to improve its performance both in term of power production and wastewater treatability. Various novel and low-cost electrocatalysts like CoZnFe, CuSn, Geothite, V2O5/Graphene oxide, Bi doped TiO2, WO3 etc. have been developed keeping in mind the field scale application of MFC.

A breakthrough has been the innovation of the proton exchange membrane (PEM) that separates the anodic and cathodic chamber in an MFC. Usually, the membrane is made of Nafion, which is extremely expensive, thereby raising the price of the MFC. But the Polyvinyl alcohol-Nafion-Borosilicate membrane invented by the research group is not only 11-fold cheaper but also more efficient in the treatment of distillery waste water. Extensive research has been undertaken to improve the electricity production of MFCs.

Microbial carbon capture (MCC) is another application of BES where microalgae are used in the cathodic chamber for the sequestration of CO2 and production of organic chemicals. The microalgae can also be an excellent feedstock for biodiesel production on harvesting. Prof. Ghangrekar says, “We have tried to enhance and optimize the efficiency and cost associated with MCC.. Further, application of MCC in sediment remediation, desalination, urine treatment and acid alkali recovery was also examined.”

Microbial electrosynthesis (MES) is a novel application of BESs that produces organic compounds by electrosynthesis through external application of electricity and the use of microorganisms as biocatalysts. Many organic compounds like acetate, butyrate, propionate, piperidinone etc. have been successfully synthesized in the lab through MES. “We are also exploring the possibility of synthesizing higher chain organic compounds using MES, which would increase the revenue generation from the process,” says Prof. Ghangrekar.

Many of the technologies, such as the new PEM, are already in use in the 1500 litre MFC-based demonstration plant installed at IIT Kharagpur. This bio-toilet is the largest plant in the world for onsite treatment of sewage, electricity generation for illuminating toilets at night and producing recyclable quality treated water. A 750 litre MFC based demonstration plant has been installed by the team at NTPC, Noida. They are also working on multiple projects and collaborating with various international partners from Germany, Estonia, Belgium, and UK etc.

I meet an upbeat team on my visit to the laboratory in the Civil Engineering Department. Neetu B., a senior member of the research team talks of Prof. Ghangrekar’s contribution to the success story. “Sir is motivating and at the same time very strict about the timely submission of papers.” Gourav Dhar Bhowmick chips in, “But he always encourages his team to get exposure to the renowned scientific community and gain the necessary confidence for innovative work.” A junior member of the team, Chabungbam Niranjit Khuman, talks about the ‘Chai-parties’ to celebrate the publication of each research article.

Not surprisingly, Prof. Ghangrekar thanks his team in his Facebook post celebrating the lab’s success. “Credit goes to all the Research scholars working with me for their sincere effort and hard work. I know it is all the more challenging for them to manoeuvre this academic ladder with me maintaining the energy, pace, tenacity, at times patience, sustaining my anger, receiving no appreciation even for late night work and that too for 24X7 all the calendar days,” reads the post.

Risk Perceptions Challenging Green Lighting

India Today

Are perceived risks making Indians shy away from eco-friendly LED lighting? – Researchers at IIT Kharagpur’s Vinod Gupta School of Management find concurrence in a study pointing out at consumer psychology and perceived high-cost factor which might be slowing down the growth of the Indian LED lighting market.

The UJALA scheme by Govt. of India had been aiming to make a transition to LED for all lighting needs by 2019. This could have helped the nation save over ₹ 40,000 crore a year. But looking at the sales figures in 2018, the market share of incandescent bulbs, CFLs, and traditional tube lights still exceeded LED lamps and TLEDs by 116 million pieces. Domestic consumers, who account for about 24% of the total electricity demand in the country, are skeptical and perceive a high level of risk when it comes to purchasing and usage of green products.

What is holding them back? Prof. Sangeeta Sahney and research scholar Sujit Kumar Ray from Vinod Gupta School of Management conducted a PAN India study which suggests financial, psychological, physical, and performance risks perceived by consumers as among the potential reasons behind such conservative buying behaviour, the financial and psychological risks being the key among them. (Access Full Paper)

An LED bulb costs almost 4 times of traditional tube light and close to 15 times of incandescent bulbs. Does the extra cost incurred in purchasing an LED light bulb match the benefits of energy efficiency as claimed? This is a question which a consumer often ponders on while making the buying decision at a retail shop and finally settles with traditional lighting systems, opines Prof. Sahney, based on the study. But LED bulbs are proven power savers with energy efficiency as 9 watts for light output requiring 15 watts and 28 watts in case of CFL and traditional tube lights. This leads to a reduction in electricity usage for an estimated period of 6 hours per day for 5 years to ₹ 493/- for LED bulbs as against the cost of ₹821/- and ₹1533/- for CFL and traditional lighting (assuming average unit cost ₹ 5) thus reducing total cost by 52% and the energy cost by 68%.

Another critical factor observed in the study was the Indian consumers’ psychological barrier in this transition to energy efficient lighting system. Since the technology is still new in the minds of the Indian consumers, they may not be fully aware of the effectiveness of the products available in the market.

“Consumers’ faith on green products get compromised when it comes to their purchase behavior due to their perception that green products have lower value, may not deliver performance as per expectation, and in no case are consumers likely to compromise on value, performance, and price,” says researcher Sujit Kumar Ray in his paper “Indian consumers’ risk perception in buying green products: the case of LED light bulbs” published in the Asia Pacific Journal of Marketing and Logistics recently.

Sujit and Prof. Sahney recommend nationwide campaign to increase consumer awareness regarding benefits of LED bulbs such as warranty available for LED bulbs or if rebates on electricity bills and promotional discounts can be offered to first time users.

Author of the paper may be contacted at sujitkumar@iitkgp.ac.in

Smart thinking

Smart cities need smart water management and distribution system. In advanced countries, telecommunications, computing, computer-based modelling, AI, Machine Learning, Data analysis and processing have changed the way water resources are managed. In fact, they have given rise to what is called hydroinformatics systems. A similar change may happen in India as well.

Aditi (extreme left) and Stuti (extreme right) at Da Lat

Two students of  IIT Kharagpur, Stuti Modi and Aditi Kambli recently presented their paper on an intelligent water management and distribution system based on data-driven models at the Third International Conference on Machine Learning and Soft Computing (ICMLSC) in Da Lat, Vietnam. They won the Best Presentation Award at the conference held in January 2019.

Stuti and Aditi proposed the use of two data-driven models – recurrent neural networks (RNN) and fuzzy-logic based models. With the use of these models, they demonstrated how daily average water demand can be predicted, how drought/flood could be predicted and an optimum level can be maintained in the dam reservoir, how the water level in reservoirs in houses and localities can be controlled, how the drinkability of water can be judged and water treatment can be planned.

Previous works in this field have concentrated on any one aspect of the water management process, for example, on either water demand prediction or treatment. “What we offer is a complete one-package solution. Our model is segmented in such a way that in case of any breakdown, we can easily track the root cause for it and get it fixed. All the individual models here come together and form a platform for water management,” said Aditi.

Aditi is from the Department of Ocean and Naval Architecture and Stuti belongs to the Department of Electrical Engineering. They had worked under the guidance of Prof. Sudhir Kumar Barai of the Department of Civil Engineering on a course of Soft Computing that he teaches to all departments.

For the prediction of daily average water demand, the duo work on the presumption that smart water meters are installed in all houses or localities. Data on water use of individual households, collected by the sensors of the smart water meters, are sent to a central medium. This data is used to train an LSTM based RNN, which then predicts the water usage for the upcoming day.

To validate their assumption, they used the time series data of daily water usage for the last four years. Water usage of the past 30 days was provided as an input to the network. The training of the RNN was performed using Keras.

In the case of drought/flood prediction and the optimum dam reservoir level, the fuzzy inference system is implemented using percentile storage, percentage full storage capacity of the reservoir and rainfall to predict the condition of the dam reservoir. Too much water in the dam threatens dam safety and could cause flood and too little could cause drought. The fuzzy inference system predicts what should be the optimum water level in the reservoir and the Fuzzy PI Controller controls the reservoir water level by releasing or not releasing water.

Such fuzzy logic controller could also man how much water needs to be present in individual water tanks of residential houses. It is often seen that the inlet of water into the tanks is not proportional to the outlet rate, causing the water tank to empty out faster than it fills up. To obtain the water level, however, an ultrasonic water level sensor has to be installed on the top of the reservoir to monitor input and output flows. The water reservoir also has to be modelled as a tank in Simulink whose input and output rates can be controlled.

The water quality model is divided into two parts in this research. One, the assessment of water quality, and two the treatment of moderate/non-drinkable water in a water treatment plant.

For water to be drinkable, various parameters – such as pH, dissolved oxygen, alkalinity, coliform etc – have to be within safe limits. Stuti explains, “Suppose the turbidity of the water is poor and the DO (dissolved oxygen) is moderate, but if the pH and coliform component is rated good, the water is drinkable. This means, all the parameters do not necessarily have to be good for water to be drinkable.” Their fuzzy expert system creates a water quality index that is easy to understand, logical and useful for common people.

Once the fuzzy expert system grades a water to be moderate or non-drinkable through the data collected by sensors and assessed by MATLAB program installed on the computers of the water treatment plant, the water ought to be sent for treatment. For treatment again, the fuzzy logic based system sets ideal values, and based on the error, the correction methodology is powered.

Aditi and Stuti know that the ideas proposed can be improved further with actual sensor data and constant updating of standard points. They would also like to create separate models for each region, since the same parameters don’t work for every region.

Prof. Barai says, “Aditi and Stuti need to implement their model on a large scale hardware model to observe the results and fulfil their goal to implement an intelligent system that conserves and uses water efficiently.”

 

 

Stronger Economy, Cleaner Waters

Business Standard    The New Indian Express     NDTV

A study by IIT Kharagpur researchers has connected the dots between the impact of economic growth reducing fecal coliform (FC) pathogens in groundwater which is a key factor causing water-borne diseases in the densely populated Indo-Ganges-Brahmaputra river basin.

About 100,000 children in India are dying every year from waterborne enteric diseases like diarrhea. While the study reported the excess of fecal coliform concentration in potable groundwater in rural regions in the said area, it also made first-time observations on a significant reduction of fecal pathogen concentration in the spatially variable groundwater from 2002 to 2017.

“Looking beyond the country globally, more than 2 billion people, mostly living in economically stressed areas of Africa and South Asia still do not have access to basic sanitation, and more than 1 billion still opt for open defecation. The resulting unsafe disposal of faecal waste to nearby drinking water sources poses an extremely serious environmental crisis and public health concern,” says Prof. Abhijit Mukherjee, faculty at the School of Environmental Science and Engineering and Dept. of Geology and Geophysics at IIT Kharagpur who led the research project.

The researchers studied data for the densely populated Indo-Ganges-Brahmaputra river basin, across 234 districts in Rajasthan, Haryana, Uttar Pradesh, Bihar, Jharkhand, Chhattisgarh, West Bengal, Assam and also Delhi and NCR and a population of ~ 400 million. The study data collected from National Rural Drinking Water Programme, Ministry of Drinking Water and Sanitation, Govt. of India, covered almost last three decades to delineate the long-term improvement trends of groundwater quality across India, as a consequence of the development.

Figures suggesting the a) trends of decrease in faecal coliform in groundwater between 2002-2017 with the study area of Indus Ganges Brahmaputra basin (Rajasthan, NCR, UP, MP, Bihar, Jharkhand, West Bengal and Assam), b and c) comparison trends of anomalies between groundwater quality and economic development (observed as satellite-observed night-time light), d) changes in economic development across study area, as observed from night-time light

Uniqueness in this study to determine economic development trends and correlations was the use of nigh-time light data instead of GDP or other economic growth data. “We have used satellite-based Night-time Light information based on Defence Meteorological Satellite Program of the US Air Force, archived by NOAA/NASA for the period 1992-2013. In most areas economic development, suggested by increasing satellite-based nightlight correlated to the reduction in fecal coliform concentration and alleviation of water quality,” explained Srimanti Duttagupta, a Ph.D. scholar at IIT Kharagpur, first author of the research paper which has come out recently based on this study.

The other dataset used was high-resolution geographically spatial information of waterborne fecal pathogen concentration in groundwater from the period 2002-2017. Numerical and statistical analyses were performed on aforesaid culled datasets to understand the efficiency of development in alleviating the water quality and public health, and relationship with economic development. The study showed that the spatially variable groundwater faecal pathogen concentration from 2002-2017 has significantly decreased across the basin. From 2002 – 2013, Night-time Light on the surface area as seen from satellites increased by +3.05% per year and faecal coliform pollution decreased -1.39% per year.

The research group observed a significant decrease in groundwater fecal coliform concentration after 2014, in the acquired data. This could be a direct outcome of improved sanitation construction and utilization of sanitation structures, instituted by the Clean India (Swatch Bharat) mission of the Government of India Prof. Mukherjee remarked, however, needs more data to confirm. “Nevertheless, in areas with inferior water quality, improper human practices outweigh economic development in affecting human health,” he added.

It was observed that areas with lower literacy rate and very high population density suffer from poor groundwater quality because of faecal coliform pollution, irrespective of economic development. The problem of overpopulation and slums is an intricate problem which is reflected in all life aspects in countries like India. The study reflects through results that higher faecal coliform concentration in urban, and peri-urban areas, suggesting economic progress may not be the only influencing factor on water quality alleviation.

The researchers opined that social behavior and practices, use and disuse and beliefs are mostly related to lower literacy rate. In turn, these results lack awareness and encourage malpractice on sanitation, eventually leading to increased fecal waste into drinking water sourced to groundwater.

The research was published this year in the Journal of Earth System Science published by Indian Academy of Sciences.

Download Research Paper

The Social Salesperson

Economic Times    Economic Times (Bangalore)    Economic Times (Delhi)    Economic Times (Kolkata)

Researchers at IIT Kharagpur have developed a new marketing model for influencing sales on social media. While customer reviews play a critical factor in online sales through social media, the researchers have developed an advanced model to identify influencers who could have more influence on potential buyers based on opinions and social ties on a popular social networking platform.

Social media is one of the most popular emerging strategies today with a fundamental goal of increasing sales. According to a study, about 91% of retail brands use multiple social media channels with 81% of SMEs using at least one social platform. The global revenue of social media sales is expected to grow to Euro 39 billion in 2019 as per a report by the business analytics firm Statista. However, on social media, people are more likely to adopt a product recommended received from their acquaintances or based on product reviews.

“We already know that comments on social media affect potential buyers. We have considered the personal valuation of the adapters based on their comments. Initially, we have segregated the adopters and the influencers based on their valuation and the threshold value to become an influencer. This helped us to categorize the users and strengthen their influence on adopters. In our second model, the peers’ connections are considered to influence a user. Additionally, we considered all the users who have purchased the product earlier, as the influencers other than just the potential buyers who are considered as users highly connected in the network,” explained Prof. M K Tiwari who led the research.

The study identified the different set of users based on their level of the tendency towards the product. This helps to segregate the adopters by whom they will be getting influenced instead of using all the buyers to influence all the adopters.

Thereafter the research group targeted the influencers by offering the product either for free or at a discounted price depending on their possibility to diffuse the information and influence their neighbours effectively for revenue maximization.

This finding provides the required benefits for marketers regarding the future of advertising and targeting customers in social networks. Marketers know that following traditional methods to motivate consumers in any social network might not always be effective. If marketers motivate any informal member of social networks without their knowledge by offering free or discounted products to initiate and launch any product related information, this can then be an effective strategy for social network advertisements. Also, the study showed that iterations in the product reviews by the influencers show a sudden increase in the number of people getting influenced. Such changes are to be estimated beforehand by the company and required steps to be taken in order to stay away from the lost sales.

“Here, we aim to increase the influence on people by offering the product for free to potential buyers who are capable of influencing more people and then the product is offered at an increasing price, i.e., decreasing discount rates and increasing the revenue as well as the growth of the influence among customers’ acquaintances,” he confirmed.

Computational experiments were conducted on real-world networks representing different scenarios with varying complexities and tested the effectiveness of these algorithms.

The research work was conducted under the research project EBusiness Center of Excellence (ECO) funded by the Ministry of Human Resource and Development (MHRD), Government of India under the scheme of Center for Training and Research in Frontier Areas of Science and Technology (FAST).

This work can be extended by implementing this algorithm on dynamic networks and budget and time constraints can be imposed for influencing. The results of this study shows that mixed influence model can be used to identify the potential users whom a company can target and also can decide the budget that can be spent on each category of such users based on their level of influencing others.

A future extension would be interesting by adding more social media futures such as likes and shares from sources like Twitter, Instagram, Pinterest etc.

Graphic Credit: Suman Sutradhar

Smart Solutions for Smarter India

Times of India     News18    India Today    Business Standard   Ei Samay     Outlook   Zee Business

Students from IIT Kharagpur have devised unique solutions for smarter & safer industrial operations ranging from detecting counterfeit currency through a mobile app, to nuclear radiation tracking through wearable sensors, to VR based human resources training at a thermal power plant.

Fake Currency Indian Notes (FCIN) have plagued the country for decades leading to not only economic losses for the country but also as the source of funds of various illegal activities even leading to breach of national security. The country has witnessed a mega initiative like demonetization in 2016. The government has also been promoting digital financial transaction which would minimize the circulation of FCIN. The banks and retail traders who manage institutional high-volume cash transactions have adopted various measures to detect FCIN. But how would an end consumer detect such a currency note? Though there are set guidelines by the Reserve Bank of India, an untrained eye can easily falter.

A group of six students from the Dept. of Computer Science and Engineering IIT Kharagpur have developed the code for a smartphone application to address this issue. T.Y.S.S.Santosh, Satish Kumar Reddy, Vipul Tomar, Sai Krishna, Drishti Tulsi and D V Sai Surya have developed an image processing application which can detect counterfeit currency. The application which can be installed on smartphones can be used by people at various touch points thus reducing the chances of fraud. Explaining the mechanism, T.Y.S.S.Santosh, the group leader said,

a user can upload a currency note image and the mobile app would verify its authenticity using 25 features extracted from the front and rear side of the currency note. In case of detection of a fake note, the user will also be notified of the failure checkpoints.

In another innovative project,  the Department of Atomic Energy gave the challenge of resolving the occupational hazard of people working in the domain of nuclear-powered device. The students were asked to develop a solution for visualising and localising a 3D radiation source along with its size, shape and orientation, given the data on spatial dosage. The 6-member student team from IIT Kharagpur, comprising of Lakshay Bansal, Ch V Sai Praveen, Aditi Kambli, Rajshekhar Singhania, Ayush Mohanty, Kaustubh Agrawal, proposed a solution based on Boltzmann Transport Equations dealing with the flow of heat in fluids from hotter regions to colder ones. The students solved the reverse Boltzmann Transport Equations using the dataset for a given area to estimate the source location.

This solution is well suited to occupational workers carrying wearable sensors detecting radiation dose data. The sensors can pinpoint the location of radiation leaks in nuclear plants and refineries. The solution can also find application in medical radiation therapy or radiotherapy as part of cancer treatment to control or kill malignant cancer cells

– Lakshay Bansal, the team leader.

Another team from the Institute has developed a virtual reality-based application for the training and skill development of the workers through interactive drill based training. The solution is an interactive virtual reality environment of a thermal powerplant with simulations and guides to help operations, maintenance and performance of complex procedures in an efficient and error-free manner.

Our solution offers an economical, intuitive and gamified version of worker training through level wise learning approach. It provides a full set of interactive drills to perform along with quality assessment metrics that could be used by the supervisors to assign different jobs to workers.

– said Rohit Jain who led the team comprising Suresh Gandhi, Sumeet Aher, Ishan Bangia, Sunil Patidar, Ayushi Shakya from IIT Kharagpur.

The students proposed these solutions in the recently concluded Smart India Hackathon 2019 winning some of the top prizes in the nationwide competition held by the Ministry of Human Resources Development, Govt. of India

IIT Kharagpur also hosted the software edition of the Grand Finale of SIH 2019. The prize winners developed codes targeted on smart education solutions. Team CodeLagom developed a wearable Android IoT device for facilitating the education of differently-abled people with vision and hearing impairment. Books in PDF can be uploaded on the web platform of the device which can thereafter be streamed on the wearable device in voice and visual modes. Team LeetCoders wrote the code for a LAN-enabled smart board for classrooms which can detect handwriting in both Hindi and English languages and broadcast the content to connected boards in other classrooms. It can also solve arithmetic equations and saves notes in PDF. The third team, The Creeping Spiders, developed a smart attendance system through facial recognition by means of random image clicks in a classroom or office environment.

Home furnishing

Feel like going to the nearest city? You can take a flight from the mini airport of IIT Kharagpur.

In a hurry to go to class? You can either hop onto the toy train going around the campus or the driverless cars zipping across.

How would it feel to work in a nuclear power plant? Just go to class, put on the VR headset and find out.

It’s raining cats and dogs and you still need to train for the inter-IIT sports meet? No worries. You have a dome over the Jnan Ghosh stadium.

You could say if wishes were horses, beggars would ride, just as any disparaging parent would tell a child whose mind is careening out of control. But no. These are actual scenarios that can play out in the IIT Kharagpur campus.

A few days ago, second year civil engineering students were asked to give free rein to their imagination and come up with something “wow” for the 2,100 acre campus and its residents. Related to the campus infrastructure, these ideas had to be feasible and workable. They would have to carefully work out the cost estimates but not to regard the cost as a constraining factor for an idea that was really good.  As the professor in charge put it, “I wanted them to give me an idea that could be engineered.” The catch? This was to be a semester project and would carry half the marks of the final exam.

Students learnt in class how IIT KGP managed its affairs independently – whether it came to water supply, civil works, electricity distribution or managing the telecommunications network. Formed into nine teams, the 74 students got to work. They burnt midnight oil for two months at a stretch before they were finally ready with their presentation. They were told that they would be graded on the basis of boldness and impact, sound engineering analysis, plan of execution, budgeting and finance. Each project was also going to be peer reviewed by the whole class.

Some of their ideas presented were truly fantastical – a “Wow” dome over the Jnan Ghosh stadium, an air strip in IIT Kharagpur, deployment of light rail throughout the campus  – but all of them were implementable engineering solutions to many of the problems faced by the residents of IIT Kharagpur.  They had not only worked out the cost of the projects but had thought through the likely problems that could arise, and even found solutions to them.

For example, while detailing their proposed Biogas plant, Group 7 not only set out at the micro-level the amount of cement, sand, PVC pipes, stone chips and nails that would be required, but also clearly stipulated that the metal digesters and gas storage tanks for the biogas plant needed to be properly earthed so as to avoid struck by lightning. Team 9, which suggested a dome over the Jnan Ghosh stadium, had even considered the fact that since the dome would get sun rays from the southern side only, half the solar panels fitted on the dome (that would power the movement of the dome) would not be getting any sun light. As solution, they suggested moveable solar panels and Heliotex technology for their cleaning.

Team 1 dealt with improving classroom infrastructure. They argued that incorporating augmented virtual reality in classroom teaching could revolutionize learning by changing the way students experience subjects. For example, students could actually experience being inside a nuclear power plant. In fact, they argued, the concept of VR lab could be extended to schools. According to the team’s estimate, it could cost a little more than Rs 1 crore to set up a fully functional VR Lab.

There were three ideas on improving the transport network. Team 6 suggested deployment of light rail throughout the campus to serve the purposes of connectivity and amusement. Battery-operated toy trains with two passenger coaches could ply for 10 hours a day on tracks laid in the free space available alongside the roads. Team 8 suggested autonomously controlled carrier shuttles to ply 24×7. The 8 shuttles would be operated by a centralized swarm model and would cost the Institute approximately Rs 56 lakhs. Team 5 suggested an exclusive airstrip for IIT Kharagpur in order to provide easy access and also to provide for air ambulance for residents. They suggested the Institute bought two Cessna aircraft, hired two pilots, two maintenance engineers, and crew on contract basis. According to their calculation, the average cost for a person to travel from KGP to Kolkata airport would be less than than Rs 1,500. The one-time cost for the air strip would Rs 23 crore and the annual cost of running the air service would be Rs 60 lakh.

Two projects talked about betterment of the existent infrastructure. Team 3 suggested revamping the Gymkhana Lakeside and modifying the park in order to promote pisciculture and recreational activities. Team 2 suggested converting the Tech market into a Hi-tech Market by installing a self-sustainable solar power system that would power the Tech market completely. They also suggested the setting up of a cafeteria, a bar, a clothing section and a central canteen with a giant TV screen at a total cost of close to Rs 4 crore.

There were two green projects – Team 4 suggested building a lake that would take care of the run-off and help IIT Kharagpur become self-sufficient in water. The geo-thermal pipes under the water would trigger geo-thermal cooling of the entire campus, bring down the temperature. Team 7 proposed setting up of a Bio-gas plant in order to produce bio-gas from the leftover food from the Halls of Residence. In their calculation, the total food wastage produced by the Halls was about two tons per day, which would produce 345 kg bio-gas worth Rs 11,000 approximately per day.

Team 9 proposed a ‘Wow’ dome over the Jnan Ghosh stadium that will provide an optimum solution to the problem of suspension of sports practices and stadium getting muddy during the monsoon. The retractable multipurpose dome would also use the rainwater for harvesting. The total cost of the dome would come to Rs 135 crore, but the campus could save around 42 million litres of water. Truly ‘wow’ isn’t it?

Despite the wow factor though, most of the students concurred that they ought to immediately have a Bio-gas plant. Somehow, even while letting their imagination soar, the students had kept their feet firmly grounded.

Asked what the project had achieved, the said professor stated, “I wanted them to come up with something imaginative but I also wanted them to connect with the IIT KGP campus…think of it as their home.”

The project had undoubtedly hit home. When asked how they felt about the project, Eknoor Malhotra of Team 9 said, “Initially, it was about marks. But once we started working for it, we realized that if this (idea) gets implemented, then we would have been the first to propose it. In the end, however, the effort became something much more than obtaining the marks. In the end we were so connected to it that we could visualize Jnan Ghosh actually having a dome.”

Now that the project was over and done with, would they keep thinking about IIT KGP? Eknoor declared, “Yes, of course. The domino effect has started. Everywhere I go, I try to see what can be changed.” Raman Shaw of Team 5 agreed, “The mind has started functioning differently… we are oriented differently now.”