Please wait a minute...
, No 3

■ Cover page(PDF 3225 KB) ■  Table of Content, March 2024(PDF 33 KB)

  
  • A Hybrid Lightweight Method of ABE with SHA1 Algorithm for Securing the IoT Data on Cloud
    Neha Kashyap, Sapna Sinha, and Vineet Kansal
    2024, 20(3): 131-138.  doi:10.23940/ijpe.24.03.p1.131138
    Abstract    PDF (425KB)   
    References | Related Articles
    The advancement of the Internet of Things enables devices to make life easy and become vital in the modern lifestyle. of data from numerous smart devices in Internet of Things configuration: The most significant issue of security is leakage of data. This Manuscript, per the authors, proposes a novel algorithm that shows the combination of Attribute-Based Encryption (ABE) and Secure Hash Algorithm 1 (SHA1) called the Secure Hash ABE (SH-ABE) for securing the IoT data on the cloud, which is based on encryption. The authors present the methods of a cipher text-policy attribute based on encryption, and an arbitrary number of attributes will be connected to the user's private key expressed as strings. This paper describes the implementation of updating attributes, Initialization, Key generation, Encryption, and Decryption by using SH-ABE algorithms. This proposed method reduces the computational time of the encryption and decryption process so that this hybrid SH-ABE method can be implemented in the encryption and decryption process and on IoT devices.
    Hybrid Technique of Topic Modelling and Text Summarization: A Case Study on Predicting Trends in Green Computing
    Mansi Pandey, Chetan Sharma, Shamneesh Sharma, and Trapty Aggarwal
    2024, 20(3): 139-148.  doi:10.23940/ijpe.24.03.p2.139148
    Abstract    PDF (488KB)   
    References | Related Articles
    Text mining techniques are used for trend prediction using keyword analysis; however, these processes result in the formation of relevant and irrelevant keywords. Based on the keywords, various clusters are formed, resulting in various topics. Due to the presence of irrelevant keywords, there are chances of the formation of wrong topics. To overcome this problem, this research contributes to developing an algorithm that deals with topic prediction using a noble technique wherein text summarization is inculcated into topic modeling algorithms. This research focuses on implementing text summarizing to generate summaries of published publications by diverse researchers using the Genism library with an extractive text summarization approach and then applying text mining to it to predict trends in various fields. The current approach was compared with existing techniques based on the parameters used in automatic and semi-automatic text mining techniques.
    Reliability Assessment of Distribution System Grid-Connected Multi-Inverter for Solar Photo-Voltaic Systems: A Case Study
    Darius Muyizere, Arcade Nshimiyimana, Theophile Mugerwa, Lawrence K. Letting, and Bernard B. Munyazikwiye
    2024, 20(3): 149-156.  doi:10.23940/ijpe.24.03.p3.149156
    Abstract    PDF (730KB)   
    References | Related Articles
    The contemporary electrical grid aims to deliver safe and reliable energy to consumers. As technology advances and distributed generation (DG) becomes more prevalent, the distribution system grows increasingly complex and decentralized. The swift integration of renewable energy sources, driven by concerns about global warming and carbon emissions, adds to this complexity. Given the direct link between the distribution system and consumer needs, reliability is paramount. However, the current distribution system faces operational issues, necessitating a dependable, resilient power system devoid of interruptions and glitches. Distributed generation (DG), along with its grid integration, holds promise in significantly enhancing the reliability of the existing distribution system. This research studied a case study of distribution system reliability evaluation using solar PV in the system. Various instances were addressed, and we found that after implementing DG, system dependability increased. For the case study and analysis, data were taken from a solar photo-voltaic energy source linked to the Kigali national grid in the Rwanda bus system. The Electrical Transient Analyzer Program (ETAP 19) software is utilized for modeling and reliability analysis.
    Efficient Resource Managing and Job Scheduling in a Heterogeneous Kubernetes Cluster for Big Data
    Jayanthi M and K. Ram Mohan Rao
    2024, 20(3): 157-166.  doi:10.23940/ijpe.24.03.p4.157166
    Abstract    PDF (467KB)   
    References | Related Articles
    Cloud computing is an on-demand model of computing that utilizes virtualization expertise to offer cloud resources such as CPU, memory, storage, and network in virtual machines. As a result, most big data analytics in many modern enterprise applications are run from the cloud. Since resources in these private clouds are limited, getting the most out of resource applications and providing guaranteed user service by efficiently scheduling tasks and resources is the ultimate goal. However, existing big data processing system schedulers need to consider application performance and resource utilization when performing allocations. Therefore, it is difficult to design workflows for low turnaround time and high resource consumption in extensive data systems. In this paper, we propose a resource management system for efficient job scheduling, called RMS, which dynamically schedules big data jobs in Kubernetes cluster nodes for Spark applications and autonomously adjusts scheduling policies in heterogeneous node clusters to enhance application execution and resource consumption. The RMS mechanism will ensure adequate guidance and resources available in its planning objectives and satisfactory resource utilization. The experimental analysis of different RMS and performance preferences using different methods depends on the predicted completion time and the benchmark statistical result of different significant data performance indicators traces. The results show that RMS decreases the cost and scheduling overhead and improves job execution performance.
    Efficiency and Security in WSN Routing through Hybrid Algorithm Fusion
    Kanchan Bala Jaswal and Pawan Thakur
    2024, 20(3): 167-176.  doi:10.23940/ijpe.24.03.p5.167176
    Abstract    PDF (1071KB)   
    References | Related Articles
    Wireless Sensor Networks (WSNs) are pivotal in data collection and monitoring across various domains. This study introduces a novel approach that combines firefly, Neural Network, AODV, and LEACH algorithms in the route discovery phase and firefly and neural techniques in the ranking phase to optimize route transitions within WSNs. Through a comprehensive analysis, the Proposed algorithm consistently outperforms existing solutions, including Fotohi & Firoozi and Sharma et al., regarding Throughput, Packet Delivery Ratio (PDR), and Energy Consumption. Notably, at Node Range 40, the Proposed algorithm achieves a significantly higher Throughput of 9758.94 compared to 9333.39 and 9368.25 achieved by Fotohi & Firoozi and Sharma et al., respectively. This superior performance extends to larger WSNs, highlighting its scalability. Moreover, the Proposed algorithm exhibits exceptional reliability, consistently delivering higher PDR values. This reliability ensures data integrity and network stability, essential factors in WSNs.
    Optimizing Credit Card Fraud Detection: Classifier Performance and Feature Selection Empowered by Grasshopper Algorithm
    Manu Jyoti Gupta and Parveen Sehgal
    2024, 20(3): 177-185.  doi:10.23940/ijpe.24.03.p6.177185
    Abstract    PDF (586KB)   
    References | Related Articles
    Identifying fraud with credit cards is still a significant obstacle in economic safety, requiring precise and effective classification models to reduce the dangers connected with fraudulent transactions. The evaluation of several classifiers, such as "MLP," "SVM," "Random Forest," and "Logistic Regression," is examined in this paper using extensive evaluation criteria like Precision, Recall, F-measure, and Accuracy. The dataset encompasses average values for these metrics, providing insights into the classifiers' abilities to predict positive and negative instances accurately. Understanding the Grasshopper algorithm's function in enhancing feature selection for credit card fraud detection is essential to this research. The results highlight 'MLP' as a standout performer across multiple metrics, showcasing its precision (0.942), recall (0.891), F-measure (0.915), and accuracy (95.49%). 'Random Forest' and 'Logistic Regression' demonstrate commendable results, reflecting their suitability for this task. However, 'SVM' slightly lags in comparison. The results highlight the complementary roles that good feature selection and suitable classifier selection play in improving the identification of credit card fraud systems. The robustness of 'MLP' and high accuracy position it as a promising option for addressing the complexities of credit card fraud. This study highlights the importance of careful feature selection and classifier optimization in building effective fraud detection systems that can successfully address changing fraudulent actions.
    Layout Detection of Punjabi Newspapers using the YOLOv8 Model
    Atul Kumar and Gurpreet Singh Lehal
    2024, 20(3): 186-193.  doi:10.23940/ijpe.24.03.p7.186193
    Abstract    PDF (1554KB)   
    References | Related Articles
    Layout analysis is an essential task in the Newspaper recognition system. Conventional techniques for layout analysis, such as top-down and bottom-up methodologies, are environment-specific and cannot achieve accurate results. A novel and potentially effective technique is deep learning-based detection, like the YOLO algorithm. This paper presents a layout analysis of a newspaper using the deep learning model YOLOv8. Newspaper images from different sources are collected and annotated to create the dataset. Around 600 images were collected and annotated. Then, we trained YOLOv8 based on a custom dataset of Punjabi newspapers. We have tested the performance of the trained model over various newspaper images giving a very good accuracy. We have also compared the trained model with a Faster RCNN model with a different backbone. We have even tested the model on other newspapers in other languages.
Online ISSN 2993-8341
Print ISSN 0973-1318