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 Electrical Engineering

In this paper, artificial neural network model developed for the prediction of PM2.5 particulate matter is discussed. Along with artificial neural network, multiple linear regression model is developed for the prediction. Both the techniques are compared for the prediction of PM2.5. The data for the training and testing is collected from OpenAq platform. The result shows that observed and predicted values are in close agreement. Artificial neural network is proved to be better than multiple regression model for the proposed application. Proposed method can also be used for data imputation technique for pollutant dataset. © 2021 IEEE

World University root node

School of Computer Engineering & Technology

Engineering and Technology

2021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT)

Artificial Neural Network for the Prediction of Particulate Matter (PM 2.5)

Artificial Neural Network based Fault Detection System for 11 kV Transmission Line

An artificial neural network based three phase real time power quality analysis is proposed in this paper. The scaled conjugate gradient descent algorithm is used as a learning algorithm for neural network. The training and testing data required is generated from the experimental set up of three phase power quality disturbance generator. The exprimental setup is based on the changing voltage range which is controlled by solid state relays. The solid state relays are controlled by the microcontroller. The disturbances generated are sag, swell, interruption, harmonics with and without sag/swell. These disturbances are acquired with the help of NI USB 6361 data acquisition system. The initial training and testing is done in the MATLAB with the dataset collected from disturbance generator. The mathematical model of the trained network is developed and implemented in the LabVIEW for the real time testing. The real time results of the analysis are displayed in the LabVIEW graphic user interface console.

2021 6th International Conference for Convergence in Technology (I2CT)

Three phase power quality disturbance detection and classification by SCGB Neural Network

Simulation modeling tackles real life problems securely and feasibly. It gives an outstanding strategy for assessment which is effectively checked, passed on and acknowledged. In this paper, dynamic model of an electric vehicle is made with the help of MATLAB Simulink. The energy consumption estimation of the electric vehicle is resolved, compared to the drive cycles related. The impact of various drive cycles on the utilization of energy by vehicle and its consequences for other vehicle boundaries are discussed. © 2021 IEEE.

2021 6th International Conference for Convergence in Technology, I2CT 2021

Range Estimation of Electric Vehicle using MATLAB

In this paper, fault detection system for the AC side of the microgrid is proposed. The fault detection system is based on the bayesian regularization neural network. The neural network is trained with the electromagnetic field signals instead of using current signal. In conventional way, current transformer is used for sensing the current signal. In the proposed method, magnetic sensor is used for sensing the magnetic field generated due to the flow of current in the conductor. Various fault conditions are taken into account for the analysis. The magnetic field under normal current condition is different than the magnetic field under fault conditions. Hence, this is the application of the pattern recognition artificial intelligence technique. The dataset for training and testing are generated with the help of simulation model of the microgrid. The microgrid is consisting of solar energy source, full bridge dc-ac converter, LC filters and load. The LC filter is used for getting the smooth ac output as there are harmonics present in the signal prior to it. The line to line and line to ground faults are created at the AC side of microgrid. A mathematical model is created for transforming current signal to magnetic field signal. These magnetic field signals are used to train and test the neural network. The testing results shows that the accuracy of the proposed system is 98.5% which is comparable with the existing methodologies. © 2021 IEEE.

2021 IEEE Mysore Sub Section International Conference, MysuruCon 2021

Artificial intelligence and magnetic field based fault detection system for microgrid

Computer vision has become a highly evolving field in recent years, dealing with methods for obtaining, processing, examining, and understanding digital images. Human face recognition in computer vision has a vital role to play in security and surveillance, and the mechanisms for increasing the security levels are strengthening day by day. The existing human face recognition system has been enhanced by introducing an anti-spoofing mechanism which will help to stop a nefarious person to intentionally get around with the system. This article focuses on an approach to detect a human face using texture analysis which includes computing a Histogram of Gradients (HOG) over a region of the face and then uses Support Vector Machines (SVMs) to recognize a face. A blink detection mechanism used in this article ensures the liveliness of the person, making the system more reliable. A Raspberry Pi module is used in implementing the work involved in this paper and the programming is done in Python using libraries like OpenCV and NumPy. This model can achieve a maximum accuracy of 92.68% and achieves optimal results during the afternoon, taking a total of 9.89 seconds for face recognition and blink detection. © 2021 IEEE.

Proceedings of the 6th International Conference on Inventive Computation Technologies, ICICT 2021

Anti-Spoofing Door Lock Using Face Recognition and Blink Detection

Batteries act as one of the primary sources of energy for high power Hybrid Electric Vehicle (HEV). The life of the battery becomes a significant constraint while building an HEV. So researchers found Lithium-ion batteries are more suitable for HEV with a better lifecycle. But the manufacturing cost of Lithium-ion batteries is expensive. Thus, while designing an economic HEV, the cost of batteries also a constraint. In subsequent years, lead-acid batteries are found one of the best alternatives for lithium-ion. Sulfation is the main problem in lead-acid batteries. So de-sulfation is a solution to recover the sulphated lead-acid battery. But de-sulfation was not found as a better solution for preventing sulfation. Hence battery management system for proper charging or discharge is found as a passive solution for the sulfation. In literature, many methods are reviewed related to proper charging and a discharging controller which may trap in sulfation problem. Hence, this paper, an Atom Search Algorithm (ASA) based Hybrid Energy Storage System (HESS) is designed to enable proper charging and discharging controller for increasing the lifecycles of the lead-acid battery by avoiding sulfation. The lead-acid battery is connected with Ultra-Capacitor (UC) through a bidirectional DC-DC converter to enable proper charging and to discharge of controller in a. The lifetime extension of lead-acid battery is attained by maintaining the proper charging and discharging through the conservation of Depth of Charge (DOC) and State of Charge (SOC). The charging and discharging controller of the lead-acid battery are enabled by a rule-based control strategy in the converter. The optimal operation of the converter is to provide essential supply to meet the load drive cycle as well as battery charging progress. To avoid battery's dry conditions, UC is playing the leading role to supply by the converter. The controller action is performed through the consumption of the Fractional-Order Proportional Integral Derivative Controller (FOPID) in the bidirectional DC-DC converter. The optimal switching operations are selected with the utilisation of the ASA algorithm. The proposed method is implemented in MATLAB/ Simulink and contrasted with existing methods. Finally, the proposed method extends the lifecycles of the battery to 7500 cycles by proper charging and discharging controller. © 2020 Elsevier Ltd

Journal of Energy Storage

Mitigation of sulfation in lead acid battery towards life time extension using ultra capacitor in hybrid electric vehicle

Dental radiographs do a great deal of work on theevidence of criminal classification. Science deontology is used incrimes that deal with the evidence of a person's separation relatedto dental exposure. Due to the advances in data design and theneed to evaluate more cases by legal professionals, it is importantto use a human evidence framework. Dental radiographs can beclassified as biometric if there are no alternatives to bodybiometrics, for example, palm, finger, iris, face, leg print, and soon. The human body seen using dental radiographs is best undercertain conditions when there are no biometric alternativesbecause the teeth and bones are treated like skin tissues andtissues found in the human body.

Fulltext

International Journal of Recent Technology and Engineering (IJRTE)

A Machine Learning Access for Person Identification using Dental X-Ray Images

In the past few years, the computational performanceof smartphone devices has seen tremendous growth. Due to whichthe smartphone has become a suitable platform for variouscomputer-vision based applications which earlier was notpossible. In this paper, we study various methods through whichwe can achieve computer vision-based hand gesture recognitionnatively on smartphones. If smartphones can support handgesture recognition it can provide a new way to interact withmobile devices and overcome the hurdles of voice and touch-baseduser interface improving the user experience at the same time alsosupports other gesture-based applications. The techniques westudy are mainly vision-based since camera module is present onmost of the smartphones and it does not require other additionalsensors or other hardware. We have compared the variousmethods available based on algorithms used and correspondingaccuracy.

Vision-Based Hand Gesture Recognition Techniques using Smartphones

Smart glasses are designed for all kinds of applications and can be employed in industrial applications, medical and healthcare, consumer, logistics, security, and government, etc. In practice, blind people identify objects or find out walk able paths using a white cane. In spite of a variety of such canes (long cane, guide cane, support cane) available, it doesn’t recognize what the actual object is. The guiding sticks give an idea about the objects that lie only in a limited area. Having a camera vision with the support of audio messages for the visually impaired ones gives them a better and more precise sense of their surroundings, especially in an outdoor environment. However, because of the high cost of such devices, the dependency of blind people on common people is consistent. This paper provides a new design of Smart glasses, that the user can wear as normal glasses. These devices are optical head-mounted devices that integrate camera and allow hands-free operations. The fundamental objective of smart glasses for people with normal vision is to blend human vision with the virtual world, producing a kind of ubiquitous computing. But, using this design, the camera placed on the device obtains the video equivalent to the point of view which will be processed for assisting the visually impaired user. There is no need for the user to hold the device in his hands or move it in the necessary position and the vision of the user is not occluded. It will provide a field of view up to 120 degrees.