Real-time facial expression recognition using CNN
Enhancing modern day machines or computers to recognize various facial expressions and to understand human emotions from them in real time is an exigent research subject. Through this paper, I put forward a solution to recognize emotions by understanding different facial expressions by collecting live video through a Flask App created. I deploy a Flask App to video stream live feed captured through the local camera attached to the machine or computer system. The video captured is fed to various image extraction techniques. The facial features are identified by different operations provided by OpenCV and the region consisting of parts of the face are made to surround or enclose by a contour. This region, enclosed by the contour is used as an input to Convolutional Neural Network (CNN). The CNN model created consists of six activation layers, of which four are convolution layers and two are fully controlled layers. Each layer is designed to undergo several training techniques. The main objective of this project is to demonstrate the accuracy of Convolutional Neural Network model designed. The paper is concluded by discussing the outcomes of our project and the ways to improve the efficiency of the model. The scope of this project is also analyzed to enhance technologies developed in the near future.
Published by: Revanth Krishna
Author: Revanth Krishna
Paper ID: V6I3-1492
Paper Status: published
Published: June 11, 2020
Research paper on physical activity and fitness patterns among university students in Mumbai
Due to the increase in the workload and the observable increase in the competition amongst the youth, the health and fitness of oneself are put as a secondary priority amongst them. This research was conducted to test this very reason and to check its validity. As not many studies are carried out on targeting this specific set of the population on this subject, this research was carried out to understand the physical activity patterns among university students and their perception towards the same. Descriptive research was carried out where a cross-sectional data on physical activity levels were collected (Self-reported data). The attitudes, motivations, demotivation, food consumption patterns, and the perception of them regarding their health and fitness were collected from the respondents. A sample of 122 was used where there were 63 women and 59 men. This study gathered quantitative data through structured questionnaires to understand each of the objectives. Descriptive statistics were used to analyze data where the mean, median, mode, and standard deviation was calculated and a number of correlations were made using the same. It was found that respondents aging from 15-26 have low levels of physical activity. Moreover, when a comparison was made between males and females on their levels of physical activity, women were found to do easier levels of physical activity. The BMI was likewise determined, so as to discover the class of weights that individual’s fall into. While the vast majority expressed that practicing was imperative to them, they, despite everything neglected to work out for adequate hours per week. While individuals know and have the correct disposition towards working out, they have recently been unsuccessful when it came to really work out. At the point when it went to the reasons why individuals work out, the most well-known ones were to get fitter or more grounded or accomplish a positive inclination. Be that as it may, when it went to the demotivation of working out the most widely recognized reasons were the lack of time, energy, and inspiration to work out. Some different elements that were a consequence of individuals being overweight were their temptations/cravings to eat fast food. A greater part of the respondents said that they expended cheap food in any event 2-3 times per day. 15-26 years old have busy lifestyles and hence are much harder to reach. A targeted intervention could be carried out in order to educate people about the importance of the physical activity.
Published by: Salonee Jambusaria, Sara Berry, Shivam Bhadra, Shrutika Sanghvi
Author: Salonee Jambusaria
Paper ID: V6I3-1465
Paper Status: published
Published: June 11, 2020
Intelligent surface heating using LSTM networks
Electrically heated blankets have been around the market for a long time. They are extremely handy during winters, as they can be used to warm beds. There have been many advances in the control systems to ensure that the desired temperature of the blanket is maintained. The drawback of such systems is its power consumption. Commercially available heating blankets use about 200 watts of power. On average, an adult’s body occupies only about 60 to 70 percent of the total sleeping area of a bed. Existing technologies heat the full blanket irrespective of the users sleeping position and orientation. This results in wastage of power due to inefficient heating of the blanket. In this paper, we present an intelligent heating system that uses Long Short Term Memory (LSTM) to learn the sleeping patterns of the user to predict the future position and orientation of the user to maximize its overall efficiency.
Published by: Rushad Mehta, Abhay Sahu
Author: Rushad Mehta
Paper ID: V6I3-1410
Paper Status: published
Published: June 11, 2020
Eco-sanitation as a means to treat wastewater from underground metro rail stations
Sanitation trouble exists for people throughout the globe: simple human waste collection and remedy is inaccessible to a whole lot of the world’s populace; and the reputation-quo gray infrastructure system of sanitation is unsustainable and fallacious for extensive software. Ecological sanitation, or ecosan, refers to a range of sanitation technologies in which human excreta is recovered and retained on-web page, and in the end reused. The underlying aim is to shut (nearby) nutrient and water cycles with as little expenditure on fabric and strength as viable to contribute to sustainable development. Human excreta are treated as a resource and are typically processed on-website online and then treated off-site. The nutrients contained in excreta are then recycled via the use of them, e.G., in agriculture. EcoSan is a systemic approach and a mindset; unmarried technology is the most effective method to an end and may vary from near-herbal wastewater treatment techniques to compost toilets, easy family installations to complicated, specifically decentralized structures. These techniques aren't ecological consistent with se however best on the subject of the found surroundings. They are picked from the complete range of available conventional, present-day and conventional technical options, combining them to EcoSan structures. The paper affords an advent to EcoSan standards and Zero waste toilet devices as a way to make certain powerful eco-sanitation.
Published by: Akarshika Chaudhary, Akanksha Maurya, Anant, Abraj Singh
Author: Akarshika Chaudhary
Paper ID: V6I3-1485
Paper Status: published
Published: June 11, 2020
A comparative study on usage of Python and C/C++ for firmware development
The C/C++ programming languages dominate embedded systems programming,though they have a number of disadvantages. Python on the other hand has many strengths that make it a great language for embedded systems. This paper presents a comparative analysis of Python and C Programming languages in the context of firmware development.
Published by: Abhinav Upadhya, B. K. Srinivas
Author: Abhinav Upadhya
Paper ID: V6I3-1484
Paper Status: published
Published: June 11, 2020
HelpApp – A WiFi direct based disaster management application
Communication during a disaster is very crucial and a very challenging domain due to the fact that the traditional communication infrastructure are very prone to go offline which prevents the people stuck in the disaster to communicate with each other and report their status to the rescue authorities which in turn causes delays to rescue operations. To enable communication between devices during a disaster and for effective and productive rescue operations, we propose an Android Application (named HelpApp) to overcome the inoperative traditional communication network where we use WiFi Direct. Android OS is used because it has 70% of the total smartphone users in the world 95.2% of the market share in India. While the primary connection is WiFi Direct, we make use of WiFi Legacy to give it adhoc-like behaviour where the network can be largely scaled up. A prototype of this application has been successfully built and tested in a controlled environment to show the capabilities. This application is published under a FOSS license and source code is available on GitHub.
Published by: Anirudh M. V., Prashant Singh, Rajat Kumar Panda, Yash Dubey
Author: Anirudh M. V.
Paper ID: V6I3-1476
Paper Status: published
Published: June 11, 2020
