MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Computer Engineering & Technology

Human behaviour and actions are greatly affected by their emotions. Through human computer interactions (HCI) interpreting of emotions has become easier. Modals like Facial Emotion Recognition(FER) that considers the facial features of the human, Speech Emotion Recognition (SER) that concentrates on the texture of human speech, Electroencephalography (EEG) that deals with brain waves and Electroencephalogram(ECG) that focuses on one’s heart rate are few of the widely used unimodels that are in place for recognizing emotions. In this paper we see how multimodal system tends to provide higher accurate results than the unimodels in existence. In order to implement the multimodal system two fusion methods were considered that are Feature Level Fusion and Decision Level Fusion. It was observed that Feature Level Fusion was preferred by most researchers due to its capability of providing more valid results in case of compatible features. Facial-Speech, Speech-ECG and Speech-Facial are few of the well liked multimodals that have been implemented by varied researchers. Out of these Facial-EEG provided most robust and efficient outputs.

World University root node

Engineering and Technology

2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)

Multimodal Techniques for Emotion Recognition

Maritime surveillance is very crucial for every nation even if it is surrounded by land. The surveillance can not only inform about the threats and illegal activities but also manage the traffic and regulate a lot of movement on water. With more and more satellites with Synthetic-Aperture Radar (SAR) and other capabilities to capture high-resolution images being launched, automation of ship detection from these images is now a necessity. The experiments are performed on satellite image datasets where various encoders and loss functions for the Unet model are evaluated based on segmentation results over the test dataset. Our research and analysis of these encoders and loss functions for the Unet model lead us to certain conclusions as to which situation would benefit from which of the loss function and encoder and their combination. The research shows that the modes are robust and can perform well even with difficult backgrounds like clouds, waves etc. Our best model archived 0.823 on F2 score at different IOU thresholds on Airbus ship detection challenge test dataset. © 2021 IEEE

Proceedings of the 2021 1st International Conference on Advances in Electrical, Computing, Communications and Sustainable Technologies, ICAECT 2021

Ship detection and segmentation using Unet

The past few decades have witnessed an increase in dietary ailments, majorly caused due to unhealthy food habits. According to experts, mobile-based diet monitoring and assessment systems can capture real-time images of various food items as well as analyze the nutritional content present in it and can be very convenient to use and assist in improving food habits. This can help people lead a healthier lifestyle. This proposed model provides an innovative system that can automatically estimate various food attributes like the nutrients and ingredients by classifying the food image that is given as input. The approach involves the use of different types of deep learning models for accurate food item identification. Apart from image recognition and analysis, the food ingredients, nutrients and attributes are obtained and estimated by extracting words which are semantically related from a large collection of text, accumulated over the Internet. Experimentation has been performed with the Food-101 dataset. The proposed system assists the user to obtain the nutritional value of the food item in real-time which is effective and simple to use. The proposed system also provides supporting features such as food logging, calorie tracking and healthy recipe recommendations for self-monitoring of the user.

ICT Analysis and Applications

<a href="https://link.springer.com/chapter/10.1007/978-981-15-8354-4_58">A Model for Automated Food Logging Through Food Recognition and Attribute Estimation Using Deep Learning</a>

As the COVID-19 pandemic has captured the country, states, and the entire world, technology is taking a step forward to prevent this danger and resolve the situation. The health authorities are taking some major technological support to trace the movement of the citizens at the most granular level to verify with whom they had contact over the given period. This helps to discover the contact with a Covid-19 positive patient to implement immediate quarantine measures and break the chain of the people exposed to the disease and minimize the count in high-density areas. This paper has proposed a system for effective contact-tracing in real-time using GPS and Bluetooth technology. Also, here is a study of such existing systems with their drawbacks and a proposed solution to overcome those limitations. Hence, the purpose is to provide a solution for combating the spread of Covid-19.&nbsp; &nbsp;

International Journal of Computer Trends and Technology (IJCTT)

An Effective Approach to Contact Tracing Applications for Covid-19

Visual information has become an effective medium of communication forpeople across the globe. Rather, it has become an essential ingredient to conveyinformation. An image as a media of communication is possible only when its perceptionis determined by humans. In the field of photography, aesthetics is perceived as anappreciation of beauty in an image or a photograph. This paper presents an organizedreview of the prevalent literature on image aesthetics. Initially, we discuss the low-level,middle-level, and high-level image attributes with their aesthetic contributions; this isfollowed by ways to bridge the existing semantic gap between them. We further elaborateon the existing computational frameworks, which are used in literature for imageaesthetics evaluation and enhancements. We conclude by providing an extensivediscussion of our interpretation of the literature survey.

GIS SCIENCE JOURNAL

<a href="https://drive.google.com/file/d/16UI08BiehA4bPZHlNPfjUh3YyvWP_WtA/view?usp=sharing">A Review On Digital Image Aesthetics</a>

Special issue in Journal of Information Science and Engineering

Cat Swarm Optimization Based Energy Efficient Reliable Sectoring Scheme in WSN

In today's digital world of information overload, the recommendation system plays an important role in the decision making of an individual as well as the collective societal level at large scale. The recommendation system is useful for leveraging the power of available data to create a better user experience and incremental revenue for the E-commerce companies. As per statistics from McKinsey about recommendation system gives 35 percent incremental revenue for Amazon, around 75 percent video consumption and 1billion $ saving for Netflix due to recommendations and around 60 percent of views on YouTube come from the leverage of powerful recommendations. This research paper shows, how a hybrid approach is useful to improve the prediction accuracy of the recommender system by using various matrix factorization techniques and regression on given sample data. Using all rating information from a large number of users and movies build a recommendation system that recommends/suggest a movie to concern user.

International Journal of Future Generation Communication and Networking 13 {\ldots}

A Hybrid Approach towards Improving Performance of Recommender System Using Matrix Factorization Techniques

A Pandemic engenders unusual challenge to conveyance of provision of medical care of our health. All these challenges are faced by workers which are limited in number. Covid-19 (Corona) becomes pandemic as it spreads throughout the world. With appearance of novel disease that covid-19 pandemic, whole world has facing critical situation from last few months ago. Now days, as every industry looks for an advance technique to observe/monitor and control the spreading of corona virus pandemic. So solution for this is the artificial intelligence supports to easy track with identification of the patient which are on high risk and easily useful in case of real time environment. AI technologies have high potential in improvement in planning, various treatments and reports about the covid-19 patients. Artificial intelligence is one of the important concept helps us to sort out those issues. Here this paper put the concept of how to maintain the safe distance to avoid the spreading of covid -19 ( SARS–CoV) virus using the artificial intelligence. This paper summarized all general concepts related to Artificial intelligence and Covid-19

International Journal of Grid and Distributed Computing

Artificial Intelligence Based Techniques To Prevent The Spread Of The Covid-19 Pandemic

International Journal of Advanced Science and Technology

Optimum analysis of brain activities by using classification and learning techniques

Now a day’s fingerprint-based authentication system is becoming very popular because of its applications. The fingerprint of an individual is a unique and persistent feature that can be used for identification and authentication. There are several different methods that has been implemented by different researchers for the fingerprint recognition. In this paper, we examine writing of various systems and angles utilized for unique finger impression acknowledgment.