Computer Networks and Communications, Computer Science, Artificial Intelligence, Computer Vision and Pattern Recognition
11
Scopus Publications
Scopus Publications
Cloud computing environment based hierarchical anomaly intrusion detection system using artificial neural network Mangalapalli Vamsikrishna, Garapati Swarna Latha, Gajjala Venkata Ramesh Babu, Koppisetti Giridhar, Lakshmeelavanya Alluri, Giddaluru Somasekhar, Bhimunipadu Jestadi Job Karuna Sagar, Naresh Dondapati International Journal of Electrical and Computer Engineering, 2025 Nowadays, computer technology is essential to everyday life, including banking, education, entertainment, and communication. Network security is essential in the digital era, and detecting intrusion threats is the most difficult problem. As a result, the network is monitored for unusual activity using this hierarchical anomaly intrusion detection system, and when these actions are detected, an alert is generated. This hierarchical anomaly intrusion detection system, which uses artificial neural network (ANN) and is implemented on a cloud computing environment, analyzes data even in the high levels of traffic and protects computer networks and data from malicious activity. As a result, this system shows better detection, accuracy, and precision rates.
IoT-driven sport activity recognition system empowered by deep learning and wearable technology Koppisetti Giridhar, Dharmavaram Hyndhavi, Shaik Nayab Mohammed Hayath, Kamsala Devichandu, Deshmukh Faris Khan Computational Methods in Science and Technology Proceedings of the 4th International Conference on Computational Methods in Science and Technology Iccmst 2024, 2025 This article affords an innovative type of system for wearable sporting sports that utilises a deep studying algorithm to accurately locate various sports. Two inertial sensor modules are covered within the machine, which athletes wear on their wrists and ankles to record movement of sporting activities. By employing a deep convolutional neural community (CNN). Each inertial sensing module consists of a triaxial accelerometer, microcontroller, triaxial gyroscope, RF wireless transmission module. Furthermore, a website has been advanced using HTML, CSS, and JavaScript, allowing athletes to examine their overall performance. The proposed deep getting to know-based class algorithm encompasses various steps such as CNN-primarily based type, photograph resizing, spectrogram era, normalisation, movement segmentation, and signal processing, enabling the identification of ten forms of athletic endeavours. The cautioned machine and algorithm are successful in successfully figuring out a number of athletic sports, as established by means of the effects of the experiments.
Dual-Band Antennas for AI-Enabled Autonomous Vehicle-to-Infrastructure Communication Koppisetti Giridhar, Dheepika G B, Anusha Preetham, Monica G K, Arun Kumar N, N. Nandhagopal Proceedings Iceconf 2025 2025 2nd International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, 2025 The complexity of the modern systems also needs more effective optimization techniques which must scale, be accurate and robust in a single product. Traditional techniques have discouraged the ability to deal with large sizes in the search space and reaching. the best solutions. To eliminate these shortcomings, topresent an innovative hybrid structure of optimization between quasi -oppositional learning and genetic search to improve performance in GUI test case generation. The validation of the proposed technique was applied to the benchmark datasets and experimental simulations. The findings have indicated that the performance indicators have been improved greatly based on the current approaches: 97.8% accuracy, 96.9% precision, 97.4% recall, and an F1-score of 97.2%. The increase in system efficiency was 15%, the reduction of the computational overhead by 12%, and the adaptability to varied testing environments by 18%. The results justify the effectiveness of the proposed solution and present a feasible and smart model that can be used to perform dependable software testing.
EEG-Based Brain-Computer Interfaces Using Gazelle Optimization Algorithm with Deep Learning for Motor-Imagery Classification K. K., , , , , , Abullaıs Nehal Ahmed, K. Kalaiarasi, Koppisetti Giridhar, S. Thenappan Fusion Practice and Applications, 2024 Brain-computer interface (BCI) is a procedure of connecting the central nervous system to the device. In the past few years, BCI was conducted by Electroencephalography (EEG). By linking EEG with other neuro imaging technologies like functional Near Infrared Spectroscopy (fNIRS), promising outcomes were attained. An important stage of BCI is brain state identification from verified signal properties. Classifying EEG signals for motor imagery (MI) is a common use in the BCI system. Motor imagery includes imagining the movement of certain body parts without executing the physical movement. Deep Artificial Neural Network (DNN) obtained unprecedented complex classification outcomes. Such performances were obtained by an effective learning algorithm, improved computation power, restricted or back-fed neuron connection, and valuable activation function. Therefore, this study develops a Gazelle Optimization Algorithm with Deep Learning based Motor-Imagery Classification (GOADL-MIC) technique for EEG-Based BCI. The GOADL-MIC technique aims to exploit hyperparameter-tuned DL model for the recognition and identification of MI signals. To achieve this, the GOADL-MIC model initially undergoes the conversion of one dimensional-EEG signals into 2D time-frequency amplitude one. Besides, the EfficientNet-B3 system is applied for the effectual derivation of feature vector and its hyperparameters can be selected by using GOA. Finally, the classification of MIs takes place using bi-directional long short-term memory (Bi-LSTM). The experimentation result analysis of the GOADL-MIC method is verified utilizing the BCI dataset and the results demonstrate the promising results of the GOADL-MIC algorithm over its counter techniques
Block-chain Enabled Strategies for Efficient Power Loss Management in Distribution Networks M. Rama Prasad Reddy, Pradeep Babu, K. Giridhar, S J Rudresha, Chodagam Srinivas, et al. International Journal of Electrical and Electronics Research, 2024 This study proposes a novel methodology for optimizing capacitor placement in distribution networks, employing the War Strategy Optimization (WSO) algorithm integrated with adaptive parameter tuning and block-chain technology. The WSO algorithm, inspired by military strategies, strategically positions fixed kVAR capacitors at variable locations to minimize power losses and enhance voltage profiles. The adaptive parameter tuning dynamically adjusts algorithm parameters to improve optimization efficiency, while the incorporation of block-chain ensures secure and verifiable optimization results. The methodology is tested on the IEEE 33-bus test system under different loading conditions (80%, 100%, and 120%), representing light, normal, and heavy load scenarios. Simulation results demonstrate significant reductions in power losses and improvements in voltage stability compared to traditional methods. The adaptive parameter tuning within WSO enhances the algorithm's performance, demonstrating better convergence speed and solution quality. Additionally, the block-chain integration provides a robust verification mechanism, ensuring data integrity and security. This research highlights the advantages of using WSO with adaptive parameter tuning and block-chain in optimizing capacitor placement, offering a reliable and efficient solution for improving the performance of electrical distribution systems.
Energy efficient clustering with Heuristic optimization based Ro/uting protocol for VANETs Koppisetti Giridhar, C. Anbuananth, N. Krishnaraj Measurement Sensors, 2023 Vehicle networks have been the subject of increasing amounts of study from both academia and industry as a way of enhancing traffic safety and providing real-time data to motorists and passengers. But beyond that, the need for a safe and secure network in moving vehicles is what's pushing the spread of VANETs. Intelligent, on-the-road vehicles that can exchange data with one another and with fixed roadside infrastructure make up what are known as ad hoc vehicular networks. It's anticipated that it will soon provide a wide variety of exciting new services. There are a lot of distinguishing features of ad hoc networks in autos, such as their adaptability to a wide range of situations. Vehicular Ad hoc Networks (VANET) use a network of moving automobiles as nodes to create a wireless network. Clustering and routing can be thought of as a multi-objective minimization issue that can be handled with metaheuristic optimization methods. With this in view, this work proposes the ANFC-QGSOR protocol for VANET, which combines adaptive neural fuzzy clustering (ANFC) and quantum glowworm swarm optimization-based routing (QGSOR). The presented ANFC-QGSOR technique initially allows the vehicles to communicate with one another. For effective cluster head (CH) selection and cluster assembly, the ANFC technique is used with three input parameters: residual energy, distance, and node degree. In addition, by developing a fitness function, the QGSOR approach is used to select the best routes to the destination. Network Simulator is used to simulate the proposed ANFC-QGSOR method (NS3 tool). The experimental results demonstrated that the ANFC-QGSOR technique surpassed earlier state-of-the-art technologies in a variety of evaluation variables.
Optimal Route Selection Using Hill Climbing Based Red Deer Algorithm in Vehicular Ad-Hoc Networks to Improve Energy Efficiency Koppisetti Giridhar, C. Anbuananth Anbuananth, N. Krishnaraj International Journal of Computer Networks and Applications, 2022 – One of the effective technologies that have been found useful in a number of real-time applications to increase the safety of roadways is called a vehicular ad hoc network, or VANET for short. In spite of the many advantages of the VANET, one of the most difficult aspects of this network is still the creation of an efficient routing protocol. The fact that VANET involves dynamic factors in its routing process makes it a difficult task to do successfully. It is possible to build a wide variety of route selection strategies in order to make efficient use of the available networking resources and to improve the efficacy of the routing. To achieve a higher level of resource utilization within VANET, the development of an efficient routing protocol is an absolute necessity. As a result of this impetus, the purpose of this research is to present an energy efficient hill climbing based red deer algorithm known as EEHC-RDA for use as an optimal route selection technique in VANET. In order to increase both the system's lifetime and its energy efficiency, the EEHC-RDA technique that has been presented prioritizes the selection of the most effective routes to the final destination. In addition, the EEHC-RDA method improves the convergence rate since it combines the mating behaviour of red deer with the hill climbing (HC) ideas. In addition to this, the EEHC-RDA method computes a fitness function for selecting the best possible routes, which takes into account a variety of input factors. In order to show that the EEHC-RDA approach offers a higher level of performance, a broad range of simulations are carried out. The outcomes of these simulations show that the suggested model has an enhanced performance in contrast to the existing methods in terms of a wide variety of different metrics, which demonstrates that the present state of approaches is not optimal.
