https://www.i-scholar.in/index.php/IJCT/issue/feed ICTACT Journal on Communication Technology 2024-02-08T13:00:05+00:00 Dr. Aditya Ghose K raghav@ictact.in Open Journal Systems ICTACT Journal on Communication Technology (IJCT) is a peer-reviewed International Journal published quarterly. IJCT welcomes Scientists, Researchers, Engineers to submit their original research papers which is neither published nor currently under review by other journals or conferences. Papers should emphasize original results relating to the theory and/or applications of Communication Technology. Review articles, focusing on multidisciplinary views of communication, are also welcome. The Journal will highlight the continued growth and new challenges in Communication technology, for both basic research and application development. https://www.i-scholar.in/index.php/IJCT/article/view/224213 Wireless Traffic and Routing Enhancement Using Emperor Penguin Optimizer Guided by Conditional Generative Adversarial Nets 2024-02-08T13:00:05+00:00 K. Prabhu Chandran P. T. Kalaivaani Venkatesh Kavididevi M. Ganesha The escalating demand for efficient wireless communication systems has prompted researchers to explore innovative solutions to optimize traffic flow and routing. The existing wireless communication infrastructure faces challenges such as congestion, latency, and suboptimal routing, impeding the seamless transmission of data. Traditional optimization approaches fall short in adapting to dynamic network conditions, necessitating the exploration of advanced methodologies. Despite recent advancements in optimization techniques, a notable research gap exists in the integration of bio-inspired algorithms like the Emperor Penguin Optimizer with machine learning models such as Conditional Generative Adversarial Nets for the purpose of wireless traffic and routing enhancement. Bridging this gap is crucial for achieving adaptive and robust wireless communication systems. This study addresses the challenges posed by the dynamic nature of wireless networks, aiming to enhance their performance through the synergistic application of the Emperor Penguin Optimizer (EPO) and Conditional Generative Adversarial Nets (CGANs). This research leverages the inherent strengths of the EPO, inspired by the collective foraging behavior of emperor penguins, to dynamically optimize the wireless network parameters. Concurrently, CGAN are employed to intelligently learn and adapt routing strategies based on real-time network conditions. The symbiotic integration of these two methodologies creates a powerful framework for adaptive wireless traffic and routing. The results indicate a significant improvement in traffic flow, reduced latency, and optimized routing paths in comparison to conventional methods. The EPO-CGAN framework demonstrates adaptability to varying network conditions, showcasing its potential to revolutionize wireless communication systems. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224214 Gated Dual-path Rnn Empowered Adaptive Dimensional Search for Cognitive Radio in Software-defined Networks 2024-01-25T08:52:46+00:00 V. Kiruthika S. Padmapriya M. Ganga In the ever-evolving landscape of wireless communication, the demand for efficient spectrum utilization is paramount. The research begins by acknowledging the existing challenges in CR within SDNs, particularly the need for adaptive strategies to dynamically allocate spectrum resources. A critical research gap lies in the absence of an approach that seamlessly integrates Gated Dual-Path RNNs and Adaptive Dimensional Search to enhance the adaptability and efficiency of CR systems. The proposed methodology leverages the power of Gated Dual-Path RNNs for real-time learning and decision-making, coupled with an Adaptive Dimensional Search algorithm for dynamic spectrum allocation. This study introduces a novel approach, the Gated Dual-Path Recurrent Neural Network (RNN) Empowered Adaptive Dimensional Search, tailored for Cognitive Radio (CR) in Software-Defined Networks (SDNs). The escalating proliferation of wireless devices and applications has exacerbated the spectrum scarcity problem, necessitating intelligent solutions to optimize spectrum utilization. This dual-path architecture enables the CR system to capture temporal dependencies in the spectrum environment and adaptively adjust its parameters for optimal performance. The experimental results demonstrate the efficacy of the proposed approach, showcasing significant improvements in spectrum utilization efficiency, throughput, and adaptability compared to traditional methods. The Gated Dual-Path RNN Empowered Adaptive Dimensional Search proves to be a robust solution for enhancing CR capabilities in SDNs, paving the way for more intelligent and adaptive wireless communication systems. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224215 Ultra Wide-band Systems with Ensembles of Classifiers Based Latent Graph Predictor FM for Optimal Resource Prediction 2024-02-08T13:00:05+00:00 B. Ebenezer Abishek A. Vijayalakshmi Blessy Sharon Gem P. Sathish Kumar The proliferation of Ultra Wide-Band (UWB) systems has introduced new challenges in predicting optimal resource allocation, necessitating advanced methodologies to enhance efficiency. Current resource prediction models for UWB systems often struggle to accurately forecast optimal resource allocation due to the dynamic and complex nature of the communication environment. This study aims to overcome these limitations by introducing a novel framework that integrates machine learning ensembles and latent graph predictor FM to achieve more accurate and reliable resource predictions. While various resource prediction models exist, a noticeable gap remains in achieving optimal predictions for UWB systems in dynamic scenarios. Existing models lack the adaptability and precision required for efficient resource allocation. This research bridges this gap by introducing a comprehensive approach that leverages ensembles of classifiers and latent graph predictor FM to enhance prediction accuracy. This study addresses the existing gaps in resource prediction by proposing an innovative approach that combines ensembles of classifiers with a Latent Graph Predictor FM. Our methodology involves the development of an integrated model that combines the strengths of machine learning ensembles and latent graph predictor FM. The ensemble of classifiers captures diverse patterns and features, while the latent graph predictor FM refines predictions based on latent relationships within the communication network. This dual-layered approach ensures robust and accurate resource prediction in UWB systems. The experimental results demonstrate a significant improvement in resource prediction accuracy compared to existing models. The proposed framework effectively adapts to dynamic UWB environments, providing optimal resource allocation in real-time scenarios. The study showcases the potential of ensembles of classifiers and latent graph predictor FM in addressing the challenges of resource prediction in UWB systems. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224216 Emogan Label-changing Approach for Emotional State Analysis in Mobile Communication Using Monkey Algorithm 2024-01-25T08:52:46+00:00 P. Ramesh Babu R. Nandhi Kesavan A. Sivaramakrishnan G. Sai Chaitanya Kumar In mobile communication, understanding and analyzing emotional states plays a pivotal role in enhancing user experience and communication dynamics. Existing emotional state analysis methods often face challenges in accurately capturing dynamic changes in users' emotions during mobile communication. The lack of adaptability and real-time responsiveness hinders the effectiveness of these methods, highlighting the need for a novel approach. Despite the advancements in emotion analysis techniques, there is a gap in addressing real-time label-changing requirements in mobile communication. Existing methods lack the flexibility to adjust emotional labels dynamically, limiting their applicability in capturing the nuances of evolving emotional states. This research addresses the need for an efficient emotional state analysis approach by introducing the EmoGAN Label-Changing Methodology, utilizing the innovative Monkey Algorithm. The EmoGAN Label-Changing Approach integrates Generative Adversarial Networks (GANs) with the Monkey Algorithm to enable real-time label adjustments based on evolving emotional cues. This hybrid methodology leverages GANs for generating diverse emotional labels and employs the Monkey Algorithm for adaptive learning and quick adjustments, ensuring the model's responsiveness to changing emotional states. The experimental results demonstrate the superior performance of the EmoGAN Label-Changing Approach compared to traditional emotion analysis methods. The model successfully adapts to real-time emotional fluctuations, providing more accurate and timely insights into users' emotional states during mobile communication. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224217 Chaotic Equilibrium Optimization Algorithm Based Cooperative Spectrum Sensing and Energy Efficient Cognitive Radio Networks 2024-01-25T08:52:46+00:00 Praveen Hipparge Shivkumar S. Jawaligi The need for wireless communication in the present and the future is for green communication. The cognitive radio network must meet the requirements for green communication in order to be the next-generation communication network. So improving energy efficiency is a must for the development of cognitive radio networks. However, sensor performance must be reduced in order to improve energy efficiency. In order to consider the two key indicators of sensing performance and energy efficiency, this research suggests a Chaotic Equilibrium Optimization (CEO) method that may effectively boost energy efficiency while enhancing spectrum sensing performance. The algorithm first learns the initial reliability value of the nodes by training, sorts them based on highest reliability, selects an even number of nodes with highest reliability, divides the chosen nodes into two groups, and then alternates the operation of the two groups of nodes. While they wait for additional instructions from the fusion center, the other nodes that are not now participating in cooperative spectrum sensing are in a state of silence. Experimental demonstrations are effectuated and analyzed the performances of the performances of the proposed work. The proposed work effectively senses the spectrum than the other approaches. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224218 Analysis of Online Intrusion Detection Models to Incorporate Secured Digital Cash Transaction in Mobile Smart Systems 2024-01-25T08:52:46+00:00 R. Bhuvaneswari V. Vasanthi M. Paul Arokiadass Jerald I. Benjamin Franklin The major Objective of this research paper is to design the Mobile Smart Device Digi Cash Intrusion Detection Framework (MSDDID) for assessing Intrusion Detection (ID) techniques and evaluating ID parameters that has to be rectified for enhancing the security of Digital Cash Transactions in Mobile Smart devices. The Research examined the Intrusion Detection dataset with 41 predictive features and 1 class feature for evaluating prediction in its novel form. The Framework was examined in WEKA with RapidMiner for analysis. The Results of classifiers Decision Table (98.7%), Random Forest Tree (99.79%), AdaBoost (94.37%), CART Model (99.61%), LazyIBK (99.44%), Naïve Bayesian (89.66%) signified that Smart devices security in Digi cash transactions could be predicted with refinement of data during transaction as deployed in this research work. The cluster analysis again conformed that num_root, su_attempted and num_compromised were the three parameters predominantly used for intrusions in the network and has to be addressed in the model. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224219 Securing It Networking Environment in Cran Using Dehaene–changeux Model Driven Moth-flame Optimization 2024-01-25T08:52:46+00:00 Rahul Laxmanrao Paikrao Prashant Laxmanrao Paikrao In the dynamic landscape of telecommunications, the evolution of Communication Radio Access Networks (CRAN) has introduced unprecedented challenges to the security of IT networking environments. As the demand for high-speed connectivity and seamless data transmission grows, safeguarding CRAN becomes paramount. With the proliferation of cyber-attacks and the complexity of CRAN architecture, conventional security measures prove insufficient, necessitating an innovative and adaptive approach. Existing methodologies lack the adaptability required to combat emerging threats effectively. This research bridges this gap by proposing the integration of the Dehaene–Changeux Model, renowned for its applicability in cognitive neuroscience, with Moth-Flame Optimization, a nature-inspired algorithm known for its efficiency in solving complex optimization problems. This research addresses the pressing need for a robust security framework using the Dehaene–Changeux Model Driven Moth-Flame Optimization approach. It elucidates the utilization of the Dehaene–Changeux Model to mimic cognitive responses, coupled with Moth-Flame Optimization for real-time adaptability. These models form a dynamic defense mechanism against evolving security threats in the CRAN environment. Results obtained from simulation and testing validate the efficacy of the proposed security model. The adaptive nature of the Dehaene–Changeux Model, combined with the optimization capabilities of Moth-Flame Optimization, showcases a significant enhancement in CRAN security. The research contributes a pioneering solution to fortify IT networking environments in CRAN, ensuring resilience against current and future cyber threats. 2023-09-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224220 Differential Evolution Framework to Improve the Network Lifetime of IOT-MANETS 2024-01-25T08:52:46+00:00 Suresh Chandrasekaran In the dynamic landscape of Internet of Things Mobile Ad Hoc Networks (IOT-MANETs), optimizing the network lifetime is paramount for sustained and efficient operation. The research begins by recognizing the inherent complexities of IOT-MANETs and the inadequacies of current methodologies. The identified research gap revolves around the lack of a comprehensive framework specifically tailored to optimize network lifetime in these dynamic environments. To bridge this gap, the proposed methodology leverages the powerful optimization capabilities of Differential Evolution—a nature-inspired algorithm that mimics the process of natural selection. This research endeavors to address the pressing challenge of enhancing the longevity of IOT-MANETs by proposing a novel framework based on Differential Evolution (DE). The DE-based framework employs a systematic approach to adaptively optimize network parameters, considering factors such as energy consumption, routing efficiency, and communication reliability. The methodology integrates seamlessly with the inherent characteristics of IOT-MANETs, ensuring adaptability to changing network dynamics. Rigorous simulations and experiments validate the effectiveness of the proposed framework, demonstrating substantial improvements in network lifetime compared to existing methods. The results underscore the significance of the DE-based framework in substantially extending the operational lifespan of IOT-MANETs. This research contributes a valuable tool to the arsenal of solutions for enhancing the sustainability and efficiency of IoT-based mobile ad hoc networks, paving the way for more resilient and long-lasting deployments. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224221 Vehicular Network Optimization via KESHTel Algorithm with Insights from Leabra Models 2024-02-08T13:00:04+00:00 B. Priya J. M. Nandhini S. Samundeswari In vehicular communication networks, optimizing connectivity and efficiency is paramount for ensuring seamless and reliable communication among vehicles. The identified problem centers on the inadequacies of traditional optimization approaches in addressing the dynamic and complex nature of vehicular networks. The absence of a comprehensive solution that combines the adaptive capabilities of the KESHTel algorithm with the cognitive insights gained from Leabra models. Existing methodologies often fall short in adapting to real-time changes and fail to capitalize on cognitive principles for efficient decision-making. This research addresses the need for enhanced vehicular network optimization by proposing the utilization of the KESHTel algorithm, coupled with insights derived from Leabra models. The method details the integration of the KESHTel algorithm, known for its adaptive learning capabilities, with insights from Leabra models, which are inspired by the neural architecture of the brain. This hybrid approach leverages machine learning and cognitive principles to optimize communication routes, minimize latency, and allocate resources intelligently within the vehicular network. Results from simulations and experiments demonstrate the effectiveness of the proposed approach in improving communication reliability, reducing congestion, and enhancing overall network performance. The findings indicate a significant advancement in vehicular network optimization, showcasing the potential of the KESHTel algorithm and cognitive insights from Leabra models in addressing the complex challenges inherent in dynamic vehicular environments. 2023-12-30T00:00:00+00:00 https://www.i-scholar.in/index.php/IJCT/article/view/224222 Causal Convolution Employing Almeida–Pineda Recurrent Backpropagation for Mobile Network Design 2024-02-08T13:00:05+00:00 Vidyabharathi Dakshinamurthi Syed Ibad Ali T. Karthikeyan Nanda Satish Kulkarni Designing efficient mobile networks is crucial for meeting the growing demand for high-speed, reliable communication. However, existing convolutional neural network (CNN) architectures face challenges in capturing temporal dependencies, hindering their performance in mobile network design. The introduction highlights the increasing importance of mobile networks and identifies the limitations of current CNN architectures in capturing temporal dynamics. The problem statement emphasizes the need for an enhanced model that can effectively address temporal dependencies in mobile network design. This research addresses this problem by proposing a novel approach: Causal Convolution employing Almeida–Pineda Recurrent Backpropagation (CC-APRB). The causal convolution captures temporal dependencies by considering only past and present inputs, while the recurrent backpropagation optimizes the model parameters based on sequential data. The integration of these techniques aims to enhance the model ability to capture temporal features in mobile network data. The results indicate significant improvements in the performance of the CC-APRB model compared to traditional CNN architectures. The model demonstrates enhanced accuracy and efficiency in capturing temporal dependencies, making it well-suited for mobile network design applications. 2023-12-30T00:00:00+00:00