Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : Indonesian Journal of Electrical Engineering and Computer Science

Connection status report generator Pratyush Gupta; Somnath Banerjee; Debani Prasad Mishra; Surender Reddy Salkuti
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 2: May 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v22.i2.pp1069-1077

Abstract

This paper presents “Connection Status Report Generator” which is an auto executable application and it generates a detailed textual and pictorial representation of the network connectivity status of a particular computer and sends the generated reports to the concerned party. The features developed in this paper aim to constantly monitor the network connectivity status as well as ease the troubleshooting process of finding the major cause of call-drops which is a popular problem in every industry. This paper is divided into three major sub-categories of real-time connection status tracker, report generator, and the image viewer interface. The proposed executable application is coded in Java and designed to run as a background application with minimal system prerequisites.
Deadlock detection in distributed system Kshirod Kumar Rout; Debani Prasad Mishra; Surender Reddy Salkuti
Indonesian Journal of Electrical Engineering and Computer Science Vol 24, No 3: December 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v24.i3.pp1596-1603

Abstract

In highly automated devices, deadlock is a case that occurs when no system can permit its event which may give irrelevant economic losses. A process can request or release resources that are either available or are on hold by others. If a process requesting a resource is not available at any time, then that process enters into the waiting state. But if a waiting state is not converted into its present state, it enters more than two processes are having an indefinite waiting state. The proposed algorithm gives an efficient way for deadlock detection. For the implementation of this work, C++ and python as the basic programming language are used. It gives an idea about how resources are allocated, and how few processes result in deadlock.
Comparison of DC-DC converters for solar power conversion system Debani Prasad Mishra; Rudranarayan Senapati; Surender Reddy Salkuti
Indonesian Journal of Electrical Engineering and Computer Science Vol 26, No 2: May 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v26.i2.pp648-655

Abstract

This paper covers the comparison between four different DC-DC converters for solar power conversion. The four converters are buck converter, buck-boost converter, boost converter, and noninverting buck-boost converter. An MPPT algorithm is designed to calculate battery voltage, current of PV array, the voltage of PV array, power of PV array, output power. It is observed that the non-inverting buck-boost converter is the finest converter for solar power conversion. The final circuit design has the results of 12.2V battery voltage, 0.31A current of PV array, 34V voltage of PV array, 23mW power of PV panel, and 21.8mW of output power. The efficiency of this system is nearly 95%. All four circuits are simulated in MATLAB/Simulink R2020b.
Electrical load forecasting through long short term memory Debani Prasad Mishra; Sanhita Mishra; Rakesh Kumar Yadav; Rishabh Vishnoi; Surender Reddy Salkuti
Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 1: January 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v25.i1.pp42-50

Abstract

For a power supplier, meeting demand-supply equilibrium is of utmost importance. Electrical energy must be generated according to demand, as a large amount of electrical energy cannot be stored. For the proper functioning of a power supply system, an adequate model for predicting load is a necessity. In the present world, in almost every industry, whether it be healthcare, agriculture, and consulting, growing digitization and automation is a prominent feature. As a result, large sets of data related to these industries are being generated, which when subjected to rigorous analysis, yield out-of-the-box methods to optimize the business and services offered. This paper aims to ascertain the viability of long short term memory (LSTM) neural networks, a recurrent neural network capable of handling both long-term and short-term dependencies of data sets, for predicting load that is to be met by a Dispatch Center located in a major city. The result shows appreciable accuracy in forecasting future demand.
Fraudulent credit card transaction detection using soft computing techniques Aishwarya Priyadarshini; Sanhita Mishra; Debani Prasad Mishra; Surender Reddy Salkuti; Ramakanta Mohanty
Indonesian Journal of Electrical Engineering and Computer Science Vol 23, No 3: September 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v23.i3.pp1634-1642

Abstract

Nowadays, fraudulent or deceitful activities associated with financial transactions, predominantly using credit cards have been increasing at an alarming rate and are one of the most prevalent activities in finance industries, corporate companies, and other government organizations. It is therefore essential to incorporate a fraud detection system that mainly consists of intelligent fraud detection techniques to keep in view the consumer and clients’ welfare alike. Numerous fraud detection procedures, techniques, and systems in literature have been implemented by employing a myriad of intelligent techniques including algorithms and frameworks to detect fraudulent and deceitful transactions. This paper initially analyses the data through exploratory data analysis and then proposes various classification models that are implemented using intelligent soft computing techniques to predictively classify fraudulent credit card transactions. Classification algorithms such as K-Nearest neighbor (K-NN), decision tree, random forest (RF), and logistic regression (LR) have been implemented to critically evaluate their performances. The proposed model is computationally efficient, light-weight and can be used for credit card fraudulent transaction detection with better accuracy.
Distribution networks power loss allocation with various power factors Debani Prasad Mishra; Rudranarayan Senapati; Arun Kumar Sahoo; Jayanta Kumar Sahu; Surender Reddy Salkuti
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 3: September 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v31.i3.pp1234-1241

Abstract

The users of power distribution and transmission networks are generally guided to sustain advanced power factor (PF) of load as it is affecting the power loss of a feeder network where it separately owns major influence on electric charges layout. Therefore, some cautious loss allotment schemes are to be incorporated and an acceptable satisfying/penalizing policy for advanced/less PF users, independently. Keeping this in view, the mentioned article proposed a new scheme, i.e., the active power loss allocation (APLA) procedure which allows power loss to the system distributors by considering the load demands, topographical localities, and PFs. A newly modified procedure assigns inducements hardly to all the involved utilizers against change in load PF continuously, where it is evaluated via proper mathematical and statistical study. The efficiency of the newly modified APLA scheme is explored in two dissimilar frameworks of low PF using 33 bus system radially distributed network (RDN). The interpretation is in favor of examined transmitted, distributed, and allows generated PF to be verified subsequently. Comparatively, the results achieved highlight the originality of the present method compared with different standard schemes/frameworks.
Image classification using machine learning Debani Prasad Mishra; Sanhita Mishra; Smrutisikha Jena; Surender Reddy Salkuti
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 3: September 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v31.i3.pp1551-1558

Abstract

The objective of this paper is to implement different tools available in machine learning/artificial intelligence to classify faces and identify different features, highlights, and correlations or similarities between different celebrity faces which can apply in everyday security purposes to identity virtually if the authorized personnel is using certain access or not. The material present in this paper is a literature review of a machine learning model developed by the students. This is a classical problem of machine learning executed using a support vector machine. Images are separated based on sub-images. Each sub-image has been classified into a responsive class by an artificial neural network. The website then fetches the data from the back end and classifies the image into the corresponding personal.