Title–A COMPARATIVE ANALYSIS OF LIGHTWEIGHT ENCRYPTION ALGORITHMS FOR RESOURCE-CONSTRAINED IOT DEVICES IN SMART HOME ENVIRONMENTS 

Author– Dr. Suman Kumar,  Sanjeev Prasanna

Abstract

The high rate of the development of Internet of Things (IoT) devices in the smart home settings has also posed a serious security and privacy threat because the embedded devices have limited computing power, memory, energy availability and capacity. Although traditional cryptographic algorithms are secure, they cannot be used in such resource-limited systems due to the high computational and energy costs of these algorithms. In this paper, the comparative analysis has been made on the salient lightweight encryption algorithms that are particular to resource-constrained IoT devices in smart home environments. The paper compares the chosen symmetric lightweight ciphers with such important performance measures as execution time, memory footprint, throughput, energy consumption, and security strength. To simulate actual smart home conditions, e.g. smart lighting, smart surveillance, smart appliances, etc., experimental implementation and benchmarking are performed on representative, low-power IoT hardware platforms. Findings of the results indicate the trade offs between security robustness and computational efficiency, whereby although certain algorithms are better than others in energy efficiency, others are more resistant to cryptanalytic attacks with moderate overhead. The comparative results give viable information on the choice of suitable lightweight encryption systems based on particular applications of smart homes. The study will help in improving the security communication infrastructure in smart homes in IoT-based systems by providing a methodical performance analysis and decision-making template in the deployment of encryption algorithms in limited resources. The results aid in the creation of scalable, energy efficient and secure smart home infrastructures.

Index Term–Lightweight Cryptography, Internet of Things (IoT), Smart Home Security, Resource-Constrained Devices, Encryption Algorithms, Performance Evaluation, Energy Efficiency, Block Ciphers.

Reference to this paper should be made as follows:  Dr. Sanjeev Prasanna, (2026), “A Comparative Analysis of Lightweight Encryption Algorithms for Resource-Constrained IOT Devices in Smart Home Environments” Int. J. Electronics Engineering and Applications, Vol. 13, No. 4, pp. 1-18.

Title–PREDICTING URBAN TRAFFIC CONGESTION LEVELS USING HYBRID RANDOM FOREST AND LSTM MODELS: A CASE STUDY 

Author– Ganesh R. Pathak and Ram Kumar Solanki

Abstract

City traffic jams have become a reality in the fast-developing cities, resulting in the necessity to spend more time on the road, use more fuel, pollute the environment, and lose money. Proper forecasting of the level of traffic congestion is the key to intelligent transportation systems and proper traffic management plans. In this paper, a hybrid predictive model that combines the Random Forest (RF) and Long Short-Term Memory (LSTM) models is suggested to enhance the accuracy of forecasting in traffic congestion in cities. Random Forest model is used to find nonlinear relationships and determine key spatial and contextual features of traffic, whereas LSTM network is effective to model the time dependence and sequential traffic features using the historical data. The hybrid approach proposed is a synthesis of the advantages of machine learning and deep learning methods to work with heterogeneous traffic data, such as vehicle flow, speed, occupancy rate and time-related variables. The real-world urban traffic data are used to carry out a case study to investigate the performance of the model. The results in the experiment show that the hybrid RF-LSTM model is better than the baseline models in its prediction accuracy, robustness and generalization ability.

Index Term–Urban Traffic Congestion Prediction, Random Forest, Long Short-Term Memory (LSTM), Hybrid Machine Learning Model, Intelligent Transportation Systems.

Reference to this paper should be made as follows:  Ganesh R. Pathak and Ram Kumar Solanki, (2025), “Predicting urban traffic congestion levels using hybrid random forest and lstm models: a case study”, Int. J. Electronics Engineering and Applications, Vol. 13, No. 4, pp. 19-38.

 

Title–THE ROLE OF SOCIAL MEDIA ALGORITHMS IN SHAPING POLITICAL POLARIZATION AMONG GEN Z: A QUALITATIVE EXPLORATION OF USER PERCEPTIONS 

Author– Sri Krishna Ravulapalli

Abstract

With the high growth rate of social media sites, political communication has been largely altered, especially among the Generation Z (Gen Z) who are slaves to the algorithm-driven digital space when it comes to news and civic participation. The present study analyzes the political polarization of Gen Z within the context of social media algorithm to identify how user perceptions influence political polarization. Based on in-depth interviews and thematic analysis, the study presents the role of personalized content feeds, recommendation systems and engagement-based ranking mechanisms in exposing people to political information, reinforcing ideological opinions and becoming part of the echo chamber. The results show that algorithms increase relevant content and user interaction, but also restrict the exposure to a variety of opinions, increase confirmation bias, and amplify emotionally charged or partisan content. The awareness of the algorithms was different among the participants with many being aware of filter bubbles but with a perception that they had minimal control over them. The paper shows the intricate interplay between personalization in algorithms, formation of political identities, and online literacy in Gen Z. This study will add to the current debate in the field of digital sociology, political communication, and media studies regarding the necessity of transparent algorithmic governance, educational critical digital literacy, and platform responsibility, which will help reduce polarization without sacrificing the discourse of democracy.

Index Term–Social Media Algorithms, Political Polarization, Generation Z, Echo Chambers, Filter Bubbles, Digital Literacy, Algorithmic Personalization, Political Communication.

Reference to this paper should be made as follows:  Sri Krishna Ravulapalli, (2026), “The Role Of Social Media Algorithms In Shaping Political Polarization Among Gen Z: A Qualitative Exploration Of User Perceptions” Int. J. Electronics Engineering and Applications, Vol. 13, No. 4, pp. 39-56.

Title– EVALUATING THE ACCURACY OF MACHINE LEARNING ALGORITHMS FOR PREDICTING STUDENT ACADEMIC RISK IN HIGHER EDUCATION INSTITUTIONS 

Author– Abhay Gyan P. Kujur, Vijay Pandey and Rajesh Kumar Tiwari

Abstract

Early identification of at-risk students in academics is one of the most important issues that need to be addressed by institutions of higher learning in order to enhance retention, academic performance, and success of students. This paper assesses how well several Machine Learning (ML) models can make predictions about the academic risk of students based on institutional academic, demographic, and behavioral data. The proposed model considers data preprocessing, the selection of features, and optimization of the models to improve the predictive performance. A number of supervised learning models, such as Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), K-Nearest Neighbors (KNN) and Gradient Boosting are applied and compared in terms of performance. The models are analyzed based on the common performance measures, including accuracy, precision, recall, F1-score, and Area Under the ROC Curve (AUC). Experimental findings have shown that ensemble based models especially Random Forest and Gradient Boosting are superior to ordinary classifiers in overall prediction accuracy and resilience. The analysis of feature importance indicates that the patterns of attendance, previous academic achievements, continuous evaluation results, and engagement measures are among the important predictors of academic risk.

Index Term–Student Academic Risk Prediction, Machine Learning, Educational Data Mining, Learning Analytics, Early Warning Systems, Classification Algorithms .

Reference to this paper should be made as follows:  Abhay Gyan P. Kujur, Vijay Pandey and Rajesh Kumar Tiwari, (2025), “Evaluating the accuracy of machine learning algorithms for predicting student academic risk in higher education institutions” Int. J. Electronics Engineering and Applications, Vol. 13, No. 4, pp. 57-75.

Title– A COMPARATIVE PERFORMANCE ANALYSIS OF LOW-COST IOT SENSORS FOR REAL-TIME AIR QUALITY MONITORING IN INDUSTRIAL ZONES 

Author– Rohith Varma Vegesna

Abstract

The high rates of air pollution in industrial areas and semi-urban areas in rapid industrialization put a serious threat on human health and environment sustainability. Though traditional air quality monitoring stations are accurate, they are costly and not widely spread to enable real time localized evaluation of pollution. In this paper, a comparative performance study of low-cost Internet of Things (IoT)-based air quality sensors with real-time monitoring in industrial settings will be introduced. Various commercially off-the-shelf inexpensive sensors were tested on the major pollutants such as particulate matter (PM 2.5 and PM 10), carbon monoxide (CO), nitrogen dioxide (NO 2 ), as well as volatile organic compounds (VOCs). The sensors were implemented in certain industrial areas and were experimented under different environmental conditions. Measures of performance like correctness, accuracy, response time, and stabilization, consistency of data, and relationship to reference-grade monitoring tools were examined. Quantitative comparison was done by use of statistical error measures such as Mean Absolute Error (MAE), Root Mean square error (RMSE) and correlation coefficient (R 2 ). The results of the experiment suggest that although the low-cost IoT sensors have some calibration and drift constraints, some models can be used with reasonably high reliability in real-time trend analysis and the prompt observation of pollution. The article reveals trade-offs between cost, performance, and scalability and offers viable insights on the large-scale implementation of affordable IoT-based air quality monitoring systems in industrial areas.

Index Term–Low-Cost IoT Sensors, Air Quality Monitoring, Industrial Zones, Real-Time Environmental Sensing, Sensor Calibration, Performance Evaluation.

Reference to this paper should be made as follows:  Rohith Varma Vegesna, (2026), “A Comparative Performance Analysis Of Low-Cost IoT Sensors For Real-Time Air Quality Monitoring In Industrial Zones” Int. J. Electronics Engineering and Applications, Vol. 13, No. 4, pp. 76-93.