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

Mobile ad hoc network (MANET) consists of a group of self-operated mobile nodes that form a network without considering predefined infrastructure. In the network, each node poses less energy due to battery-operated sensor nodes. Numerous methods are devised for routing, but each method suffered from the energy constraint. This paper proposes an energy-efficient multipath routing protocol for exploiting different routes between source and destination to mitigate energy constraints. The key idea is to determine the optimal path from a set of paths available between the source and the target node. To improve the security in routing protocol, the factors, like energy, trust, and mobility are considered as major components. Here, the trust is modeled by considering trust factors, like average encounter rate (AER), successful cooperation frequency (SCF), direct trust, integrity factor, and forwarding rate factor. Moreover, secure routing is performed between the nodes using the proposed Adaptive-Atom Whale Optimization algorithm (Adaptive-AWOA). The proposed Adaptive-AWOA) is designed by incorporating the Adaptive concept in the Atom Whale Optimization algorithm (AWOA). The fitness function is newly modeled considering mobility, energy, and trust factors. The proposed Adaptive-AWOA outperformed the other methods with a minimal end-to-end delay of 0.009, maximal throughput of 85.802% and maximal packet delivery ratio (PDR) of 97.391%, respectively. © 2020 World Scientific Publishing Company.

World University root node

Engineering and Technology

International Journal of Modeling, Simulation, and Scientific Computing

Adaptive-atom whale optimization algorithm using autonomous mobile ad hoc network for energy-efficient multipath routing

International Journal of Innovative Technology and Exploring Engineering (IJITEE)

A Machine Learning-Based Method for Predicting unknown Pharmacointeractions

Personality, a typical way of thinking, feeling, and behaviour. Personality embraces moods, attitudes and views and is expressed most obviously in relationships with others. It involves both intrinsic and acquired behavioural features that differentiate one individual from another and can be found in the relationships of people with the surroundings and with the social group. With the development of social networks, a broad variety of techn iques have been developed to identify user personalities based on their social activities and language usage practices. In terms of distinct machine learning algorithms, information sources and function sets, particular methods vary. Personality prediction has been an important research topic for describing user profiles and person not only in psychology but also in computer science. This paper presents a systematic survey of current work done of personality prediction from social networks. We also prepared a Comparison chart of existing techniques for personality prediction on the basis of relevant parameters. Based on this survey, we finally presented a few future research directions related to personality prediction.

Fulltext

International Journal of Recent Technology and Engineering (IJRTE)

Personality Prediction from Social Networks text using Machine Learning

In today’s digital era recommendation system is widely used applications from Netflix to Amazon, from Google to Goodreads, etc. Amazon estimated about 35% incremental revenue from product recommendations every year. Majority of e-commerce companies provides a recommendation system for purchasing product. The most search engine uses text-based search criteria for finding similar products. In this article, a comprehensive study of research contents related to text and image-based recommendation system is mentioned. First, we presented various text pre-processing techniques are used to clean dataset. Second, we described various techniques used for finding textual based similarity. Third, an advanced technique likeConvolution Neural Network(ConvNets) is used for computing image-based similarity of product. Cosine similarity is calculated when word occurrence is important in textual input whereas Euclidean distance is measured when an image or semantic-based text is considered as input. Experimental results depict how recommendations using ConvNets is more exciting than usual classical techniques.

International Journal of Advanced Science and Technology

Visual Similarity Using Convolution Neural Network over Textual Similarity in Content- Based Recommender System

Data gathering is a basic requirement in many applications of Wireless Sensor Networks (WSNs). In tree based data gathering, Data Aggregation Tree (DAT) is constructed by the sink or by the nodes in a distributed manner. In this paper, we study the problem of enhancing Network Lifetime (NL) using hybrid DAT construction methods. In hybrid methods of DAT construction, the sink and the nodes collaboratively construct the DAT. We propose three algorithms for Scheduling DATs using Local Heuristics with Ordering (SDLHO), with Randomization (SDLHR) and with Tree factor (SDLHT) techniques.These techniques avoid disparity in energy levels of the nodes and increase the survivability of the network. In addition, to address imperfect link quality, we propose an algorithm for Scheduling DATs using Local Heuristics with Ordering based on Link Quality (SDLHO-LQ). Rigorous simulation results demonstrate the efficacy of the proposed algorithms; and their ability to scaleup to suit deployment of applications in harsh regions. Further, their performances evaluated to quantify the amount of enhancements of NL with the existing state of art is propitious to suit the distributed environments.

Computer Networks

Scheduling of data aggregation trees using local heuristics to enhance network lifetime in sensor networks

Working stress is becoming very common. Handling working stress at the workplace is really going to be challenging. As a result, most of the time most of the time people start behaving in sarcastic ways through verbal communication, through different gestures, using emoticons, or writing reviews or comments that leads to increasing their anxiety sometimes promotes depression. It is difficult to identify sarcasm in written notes or communication. Feedback analysis is not a direct method since feedback or employer reviews are written in more formal language. This motivates the authors to work on the employee feedback system. The currently developed system helps to detect the sarcastic emotions by applying different methodologies on several types of statements. This will help corporations and other big organizations to identify reasons behind sarcastic behavior or increased anxiety. As a result, they can promote counseling programs, psychological treatment, or yoga-meditation camps.

International Journal of Synthetic Emotions (IJSE) (2019)

Sarcasm Detection for Workplace Stress Management

Severe mental disorder is recognized as Depression. State of low mood and aversion to activity causes abnormal behavior of a person in both professional and daily lives. As per WHO, around 350 million people worldwide are victimized by depression. Importance of automated real time mental health analysis is increasing day by day. In this paper, we proposed a system of automated depression diagnosis. This is a new approach to predict the depression severity corresponding to HAM-D score values obtained from prediction models. The proposed framework is designed keeping in mind a multi-modal approach, aiming at capturing facial characteristics, speech properties and brain waves. Further, a decision fusion technique has been implemented to integrate the obtained information in real-time. Using statistical features extracted from the speech recording, facial video and EEG data, the individual prediction models classify the subject according to severity of depression and the outputs are then fused to increase the performance parameters. The training data was obtained from 50 subjects, who provided all three recordings necessary for analysis. In unimodal systems the EEG data provides 80%, Speech 78% and Facial recording 72% accuracy, which is much inferior to a multimodal framework which provides 92% accuracy. The experimental results show that the proposed multimodal framework significantly improves the depression prediction performance, compared to other techniques. Inferior to a multimodal framework which provides 92% accuracy. The experimental results show that the proposed multimodal framework significantly improves the depression prediction performance, compared to other techniques.

Real Time Multimodal Depression Analysis

Partial face images are produced in an unconstrained environment. A face may be occluded by sunglasses, a hat and a scarf, captured in various poses, positioned partially out of cameras ﬁeld of view. Human face plays an important role in our social interaction, conveying people’s identity but it is a dynamic object and has a high degree of variability in its appearances. The problem of recognizing an arbitrary patch of a face image remains largely unsolved. This study proposes a new partial face recognition approach, called Dynamic Feature Matching, which combines Fully Convolutional Networks and Sparse Representation Classiﬁcation to address partial face recognition problem regardless of various face sizes. DFM does not require prior position information of partial faces against a holistic face.

Journal of Emerging Technologies and Innovative Research

A Survey on Partial Face Recognition using Novel Approach

Now a days due to the massive growth of online available open source codes and easily available help from the search engines tempts software developers to incorporate these codes into their softwares. Most of the times this is the reason for the code rotting, unhealthy dependencies between classes or packages, bad allocation of class responsibilities, over weight methods or classes, duplicated code, and many other varieties of confusion and clutter. Because of this, unwanted time and space complexities arises which eventually makes the software to work in below estimated level. This is actually the serious problem in the software industry and may play a vital role in software malfunctioning and other vulnerabilities. So as a tiny step towards this proposed model put forwards an idea of software code refactoring using graph dependency and Decision making techniques. The proposed model handles the complex coding structure related to Data members and member functions of the Java programming language efficiently.

International Journal for Scientific Research and Development

Refactoring System for Java Source Code

Most important and need of the hour issue is water conservation and water pollution. As the whole world is suffering from its population growth and worst water pollution problem due to its industrial growth. Due to this mankind is suffering a lot and most of the developing countries like India and China are unable to provide clean and healthy drinking water to its most of the citizens living in rural areas. Many methodologies are exist to provide the solution for the water leakage and water contamination level detection process, but most of them are relying on the electronic sensors and other electronic gadgets. So proposed methodology put forwards a simple and effective methodology of detection of water leakage based on the hyper graph formation for water distribution network by measuring the water collected levels at the check points using goal programming technique. And again Fuzzy logic is used to detect the water contamination level using its velocity at different checkpoints of the water distribution network.