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

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.

World University root node

Engineering and 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

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

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.

Archives of Computational Methods in Engineering

A Comprehensive Study of Cloud Forensics

Demand forecasting is a crucial part of any company or supply chain. It aims at predicting and estimating the future demand of products to help in better decision-making. This paper is a literature review on different demand forecasting methodologies which are used in different industries. The industries which are mainly focused in this literature review are restaurants, retail stores, drug stores, supermarkets and supply chains. It is observed that different organizations employ different forecasting techniques based on their requirement from these methodologies: traditional statistical models, machine learning, deep learning models and hybrid models. Latest research in demand forecasting using these models is briefly described and their advantages and limitations are discussed. Furthermore, models are classified on the basis of characteristics of data and forecasting time periods. It is observed that these individual models do not always work efficiently with all kinds of data and therefore an integrated approach should be employed where all these models are implemented, evaluated and then the model giving the best accuracy is considered for that particular industry dataset. © 2021 IEEE.

Demand Forecasting: Literature Review On Various Methodologies

Age estimation has been paid great attention in the field of intelligent surveillance, face recognition, biometrics, etc. In contrast to other facial variations, aging variation presents several unique characteristics, which make age estimation very challenging. The overall process of age estimation is performed using three important steps. In the first step, the pre-processing is performed from the input image based on Viola-Jones algorithm to detect the face region. In the second step, feature extraction is done based on three important features such as local transform directional pattern (LTDP), active appearance model (AAM), and the new feature, deep appearance model (Deep AM). After feature extraction, the classification is carried out based on the extracted features using deep belief network (DBN), where the DBN classifier is trained optimally using the proposed learning algorithm named as crow-sine cosine algorithm (CS). Copyright © 2021, IGI Global.

International Journal of Ambient Computing and Intelligence

Deep appearance model and crow-sine cosine algorithm-based deep belief network for age estimation

Air pollution is the most crucial environmental problem to be handled as it has adverse effects on human health, agriculture and climate. Considering its devastating effects, this study is to estimate and monitor nitrogen dioxide (NO2) pollutant concentration. A novel deep learning bidirectional gated recurrent units (GRUs) model is proposed. It is evaluated for its performance with other models like timeseries methods, sklearn machine learning regression methods, AUTOML frameworks and all advanced and hybrid deep learning techniques. The model is evaluated and optimised for the number of features, number of neurons, number of look backs and epochs. It is implemented on real-time dataset of Pune city in India. We also propose a system to monitor concentration of pollutants for buildings or houses in smart city environments which could be helpful to residents, the government and central authorities to prevent excessive pollution levels to avoid adverse effects. Copyright © 2021 Inderscience Enterprises Ltd.