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

Engineering and Technology

In this paper, power quality problems that occur in an AC part of the microgrid system are detected and classified with artificial neural network. The model for generating power quality problems is developed in MATLAB simulink The simulink model consists of a solar energy source, full bridge dc-ac converter, LC filters and load. The full bridge converter is used to convert the DC solar output to single phase AC. The LC filter is used to eliminate the harmonics present in the AC output of the converter. A series RLC load is used in the proposed system. The power quality detection system is based on the pattern recognition neural network. The neural network is trained with samples of sag, swell and interruption. These power quality problems are created with the help of a circuit breaker. The duration of these problems/distortions are changed for producing the datasets for training the neural network. The dataset for training and testing is generated with the help of simulation model converter circuit. © 2021 IEEE.

World University root node

School of Electrical Engineering

Proceedings of the 2021 2nd International Conference on Communication, Computing and Industry 4.0, C2I4 2021

Power Quality Analysis in Microgrid System with Bayesian Regularized Neural Network

Computer vision is a top-tier domain of the technological world that is responsible for automating the visual systems from healthcare to self-driving vehicles. With a reputation for surpassing human intelligence, it can be implemented in various trigger systems like wildfire smoke detection where the emission of smoke as a result of wildfire is fairly unpredictable.Low contrast and brightness have a detrimental effect on computer vision tasks. We present a novel approach to detect forest wildfire smoke, using image translation for converting nighttime images to day time which eliminates the confusion between smoke, cloud, and fog. This translation aids the YOLOv5 object detection algorithm to detect the smoke with the same aptness irrespective of time and lighting conditions. This paper demonstrates that the object detection model performs better on the images translated to day time with a better confidence score as compared to the corresponding nighttime images. © 2021 IEEE.

School of Computer Engineering & Technology

2021 International Conference on Computational Performance Evaluation, ComPE 2021

Impact of Image Translation using Generative Adversarial Networks for Smoke Detection

Object detection has application in numerous sectors. It is very crucial in the areas of security and surveillance. The Personal Protective Equipment (PPE) object detection Software can be used to detect people wearing masks in public places. In this paper we used the MobileNet SSD, a TensorFlow model, and Yolo v5, a Pytorch framework, to achieve PPE object identification. Many studies in the Object Detection domain focus only on accuracy. In our study we have also focused on the deployability of the model. We have obtained the 'COVID-19 Personal Protective Equipment (PPE) Detection Dataset' from Kaggle. Furthermore, we have used performance metrics such as mAP, Loss Function and Learning Rate and a comparison between TensorFlow Object Detection API and Yolo v5. These metrics would give us a deeper insight into the models. The classification loss for the Yolo v5 model is significantly lower than that of a TensorFlow model, as can be seen from the observed data. The minimum classification for the Yolo v5 model is 3.719e-3 at 500 epochs, whereas the lowest classification for TensorFlow is 0.0881 at 20250 steps. This indicates that the Yolo v5 model is more effective at categorising data. © 2021 IEEE.

2021 International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2021

Personal Protective Equipment Kit Detection using Yolo v5 and TensorFlow

In recent times, nanotechnology has emerged as one of the key driving factors in the technological and scientific advancements around the globe. The material property enhancement is the key towards various applications of nanotechnology. The incorporation of nanoparticles into a matrix of standard material can enhance specific mechanical and thermal properties. Graphene oxide is one such compound with excellent dispersibility that is widely used to enhance the mechanical properties of certain ceramics and polymers. The main objective of this study was to determine the variation in the flexural properties of S-2 glass/epoxy nanocomposite laminates with different concentrations ranging from 2% to 8% of graphene oxide (w/w %) using finite element analysis (FEA). The test specimen matrix layup was selected as 0/45/-45/90/90/-45/45/0 (8 layers). The test setup for FEA and specimen dimensions were selected according to the ASTM D790 test standard for three-point bending test. It was observed that the incorporation of graphene oxide into S-2 glass/epoxy matrix enhances the flexural strength up to 6% of graphene oxide concentration. The flexural strengths of 2%, 4% and 6% graphene oxide laminates were increased by up to 10%, 57% and 80% respectively with respect to pure S-2 glass/epoxy laminate. This enhancement in the flexural strength can prove to be extremely beneficial for aerospace and structural applications. © 2021 Elsevier Ltd. All rights reserved.

School of Mechanical Engineering

Materials Today: Proceedings

Flexural analysis of graphene oxide infused S2-glass/epoxy nanocomposite laminates

Wireless networks involve spatially extended independent sensor nodes, and it is associated with each other's to preserve and identify physical and environmental conditions of the particular application. The sensor nodes batteries are equipped with restricted energy for working with an energy source. Consequently, efficient energy consumption is themain important challenge in wireless networks, and it is outfitted witharestricted power storage capacity battery. Therefore, routing protocol with energy efficiency is essential in wireless sensor network (WSN) to offer data transmission and connectivity with less energy consumption. As a result, the routing scheme is the main factor for decreasing energy consumption and the network's lifetime. The energy-aware routing model is mainly devised for WSN with high network performance when transmitting data to a sink node. Hence, in this paper, the effectiveness of energy-aware routing protocols in mobile sink-based WSNs is analyzed and justified. Some energy-aware routing systems in mobile sink-based WSN techniques, such as optimizing low-energy adaptive clustering hierarchy (LEACH) clustering approach, hybrid model using fuzzy logic, and mobile sink. The fuzzy TOPSIS-based cluster head selection (CHS) technique, mobile sink-based energy-efficient CHS model, and hybrid Harris Hawk-Salp Swarm (HH-SS) optimization approach are taken for the simulation process. Additionally, the analytical study is executed using various conditions, like simulation, cluster size, nodes, mobile sink speed, and rounds. Moreover, the performance of existing methods is evaluated using various parameters, namely alive node, residual energy, delay, and packet delivery ratio (PDR). © 2021 Walter de Gruyter GmbH, Berlin/Boston.

Energy Harvesting and Systems

Performance study and critical review on energy aware routing protocols in mobile sink based WSNs

Sensor fusion is the process of acquiring and fusing data from two different sensors for environment perception. With the increase in the level of automation needed for almost all the systems, depth perception has become an integral part of environment perception. There are various sensors available for the same, but most of them are expensive and provide insufficient data. This paper describes in detail the sensor fusion of two cameras for depth perception. The use of cameras not only allows the user to calculate depth, it also opens up a new dimension of using machine learning algorithms because of the availability of image frames. The depth of an object is calculated using the triangulation method. The paper focuses on the use of triangulation methods for depth analysis and it is used along with ultrasonic sensors for quantifying the error. A comparative analysis of the results obtained from the cameras, the sensor, and the actual distance has led to quantifying the error. Use of cameras for depth perception helps to eliminate the use of extra sensors, thereby reducing the complexity and cost, and thus increasing the efficiency. © 2021 IEEE.

School of Electronics & Communication Engineering

An Efficient System to Quantify Error in Sensor Fusion for Cameras in ADAS.

Stock price forecasting is a very interesting topic in financial studies. Technical analysis indicators are mathematical models/calculations that help us predict stock price direction. The share market is not an ideal place for prediction as the share market is very volatile and share prices keep on fluctuating based on multiple factors. According to business reports, more than 90-95% of traders lose their money in the share market. The main objective of this work is to apply understanding of technical analysis indicators like RSI, exponential moving averages, Heiken Ashi candlesticks, price-volume analysis, MACD, decision tree, random forest analysis, Naïve Bayes classifier, neural network and KNN. The work in this research paper compares and analyses short-term profit considering 5-year data (2015-2019) for high-traded stocks based on accuracy. © 2021 IEEE.

2021 12th International Conference on Computing Communication and Networking Technologies, ICCCNT 2021

Technical Analysis Indicators in Stock Market Using Machine Learning: A Comparative Analysis

The world today faces the grave crisis of a pandemic that threatens life, health, industries, economies and society as we know it. To tackle the spread of the COVID-19 disease, it is imperative that the individuals affected by it are identified efficiently. The medical workforce is overwhelmed in many countries, and doctors and nurses must be assisted with rapid automated systems that detect COVID-19 confidently without the need for trained personnel or special manufacturing processes. The currently available testing mechanisms are accurate but take up to 5 days to show results. Automated radiological testing is faster and does not require any testing kits. This study aims to simplify, speed up and validate the process of COVID-19 detection and differentiation from other lung diseases using Artificial Intelligence and Machine Learning principles to implement a cost effective and accurate COVID-19 test by detection of inflamed parts of lungs in chest X-Rays. Two approaches for separate target users are built. In the first approach, a customized Convolutional Neural Network model is built to classify chest X-ray images into two classes- 0(COVID-19 negative) and 1 (COVID-19 positive). This model reached an accuracy of 98%. The Inception v3 architecture (GoogLeNet) was trained for the second application, in which people infected by COVID-19 were distinguished from patients of other underlying lung diseases such as Atelectasis and Pneumonia. This approach demonstrates how reliably an automated COVID-19 test can be extended to people with other lung complications and showed a 91% accuracy. © 2021 IEEE.

2021 2nd Global Conference for Advancement in Technology, GCAT 2021

COVID-19 Detection Using Convolutional Neural Networks and InceptionV3

One of the rising stresses of human life is over prosperity and wellbeing. Undeniably, prosperity and sustenance are one of the huge pieces of life. As such, mechanical progressions to help overhaul and even development prosperity care is key. In this Paper, We will look at changed framework dependent on a couple past assessment work done by significant scientists. By the strategies for that, we can orchestrate the right food as demonstrated by our lifestyle. © 2021 IEEE.

Proceedings of the 3rd International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2021

A survey paper on food sensor technologies and their process

Cloud Computing has many facets to it which makes it diverse. Investigation of a cyber-crime that involves the cloud as a subject, object, or as an environment, is cloud forensics. Challenges in cloud forensics exist at every phase of digital forensics. To provide a holistic solution to overcome these challenges we must first understand the cloud forensics landscape (the Cloud). The elements which give the Cloud the diversity that it has, and have an impact on the forensics process of the cloud should be taken into consideration while designing the cloud forensics framework. In this paper, the researchers present a comprehensive survey of the research trend in cloud forensics. The paper also proposes a cloud forensics taxonomy based on the paradigms of cloud computing that have an impact on cloud forensics. Although forensics solution taxonomies have been proposed earlier, this paper aims at a taxonomy solution at a more generic level. The proposed taxonomy provides cloud forensics solution strategies for efficient cloud forensics. © 2021, CIMNE, Barcelona, Spain.