Improving UAV disaster response with DenseNet and AF-RCNN: a framework for accurate emergency spot detection Prasanna Kumar K R, Mallegowda M, Manoj Kumar D P, Swathi H Y, Ananda Babu J Cogent Engineering, 2026 Unmanned aerial vehicles (UAVs), commonly known as drones, have emerged as valuable tools in disaster response due to their ability to access remote and hard-to-reach areas. Equipped with camera sensors, UAVs facilitate real-time monitoring of disaster-stricken regions, including collapsed buildings, floods, and fires, enabling faster mitigation efforts. However, integrating deep learning (DL) models into UAVs for disaster detection introduces significant computational overhead, limiting their use in low-latency scenarios where rapid decision-making is critical. To address this challenge, this paper proposes a novel model for precise emergency spot detection that combines feature extraction from DenseNet, hyperparameter tuning using Penguin Search Optimization (PESO), and classification through an Augmented Feature Regional Convolutional Neural Network (AF-RCNN). The model introduces several innovations, including the Small Spots Feature Enrichment Extractor (SSFEE) for enhanced detection of small-scale disaster spots, the SCM Loss function for balancing feature uniqueness and commonality across varying spot sizes, and a one-to-one computation approach for optimized data sampling. Furthermore, Duck Swarm Optimization (DSOA) is employed to fine-tune the AF-RCNN parameters. The proposed model is evaluated using the AIDER dataset, and experimental results demonstrate superior performance compared to existing models, achieving faster processing speeds—up to 20 times quicker—while maintaining or surpassing accuracy. These findings highlight the potential of the proposed model for real-time, efficient emergency detection in disaster response scenarios.
Enhancing Genetic Algorithm Efficiency: A Comparative Study of Serial and Parallel Computation for TSP M Mallegowda, Tresa Maria Josylin, Anusha M 2025 IEEE International Conference on Electronics Computing and Communication Technologies Conecct 2025, 2025 The Traveling Salesman Problem (TSP) is a well-known NP-hard combinatorial optimization problem with applications in logistics, transportation, and network design. Traditional approaches, including exact and heuristic methods, often struggle with large problem instances due to their high computational complexity. Genetic Algorithms (GAs) have emerged as an effective metaheuristic for solving TSP, but their performance can be further enhanced using parallelization techniques. This paper presents a Parallel Genetic Algorithm (PGA) framework for solving TSP by leveraging distributed and multi-threaded computing architectures. The proposed approach implements parallelism at different levels, including population distribution, fitness evaluation, and genetic operations, to accelerate convergence and improve solution quality. We analyse the impact of various parallelization strategies on performance metrics such as execution time, scalability, and solution accuracy. Experimental results demonstrate that the proposed PGA significantly outperforms traditional sequential GAs, achieving faster convergence and better route optimization. Additionally, we explore the tradeoffs between computational efficiency and solution optimality across different parallel execution models. The findings highlight the effectiveness of parallel genetic algorithms in tackling large-scale TSP instances and provide insights into designing efficient evolutionary algorithms for combinatorial optimization problems.
Secure and Efficient CI/CD Deployment in Cloud Platforms: Bridging Hypervisor Performance and Pipeline Security Mallegowda M, M. S. Swaroop, C S Darshan, Dinesh P 2025 5th Asian Conference on Innovation in Technology Asiancon 2025, 2025 Cloud-native applications require secure automation and high-performance infrastructure. This paper introduces a unified framework that combines secure Continuous Integration Continuous Deployment (CI/CD) processes and hypervisor-level performance analysis in cloud environments. From systematic literature review and benchmarking experiments, we analyze the influence of hypervisor selection—VMware ESXi and AWS Nitro—on CI/CD pipeline performance, security, and scalability. Jenkins, GitHub Actions, SonarQube, Trivy, and Docker are benchmarked against virtualisation platforms to determine interaction bottlenecks and architectural benefits. We conclude that AWS Nitro’s hardware-based isolation accelerates pipeline responsiveness by an order of magnitude and reduces attack surfaces, while VMware ESXi is best with enterprise-grade customizable deployments. By mapping hypervisor performance metrics to pipeline execution and security posture, this work gives actionable advice to DevOps engineers, cloud architects, and researchers who must balance speed, security, and cost in real-world deployments.
Improving Vehicle Perception Through Image Stitching: A Serial and Parallel Evaluation Mallegowda M, N Gowri Viswanath, Nimai Polepalli, Nikith Ganga 2025 4th Opju International Technology Conference on Smart Computing for Innovation and Advancement in Industry 5 0 Otcon 2025, 2025 Image stitching is important in a large number of applications, particularly enhancing decision making in vehicular systems by providing an expansive view from different perspectives. This work discusses the merit of serial versus parallel implementations of an image stitching algorithm which uses the ORB method for feature identification and the RANSAC algorithm for homography calculation. Serial implementation stitches procedures sequentially, while the parallel variant makes use of multicore processing to distribute tasks such as feature extraction, matching, and homography computation across multiple cores. We evaluate both methodologies using metrics such as runtime, with Python, OpenCV, and multiprocessing. The findings of this study reveal a notable acceleration in the parallel implementation, indicating its applicability for real-time functions within autonomous vehicles, where swift image processing is crucial. This comparative examination underscores the benefits of parallel computing in the realm of image stitching, aimed at improving vehicle perception and facilitating decision-making processes.
Intelligent Resource Scheduling Using Proximal Policy Optimization in Heterogeneous Cloud Environments Mallegowda M, Nikhlil K Rohidekar, Pavan Reddy T, Anita Kanavalli 2025 5th Asian Conference on Innovation in Technology Asiancon 2025, 2025 Cloud computing presents complex challenges in efficiently allocating heterogeneous resources to dynamic workloads. This paper proposes a novel approach to intelligent resource scheduling using the Proximal Policy Optimization (PPO) algorithm. The system models cloud environments with varied virtual machine (VM) configurations and task demands, optimizing resource allocation through reinforcement learning. The PPO model is trained and evaluated in a simulated environment, outperforming traditional heuristic-based and static scheduling policies. Results demonstrate an average reward improvement of 0.47 over baseline approaches and show increased adaptability and resource utilization efficiency. The proposed method highlights the effectiveness of deep reinforcement learning in addressing real-time scheduling challenges, offering a scalable and intelligent alternative for cloud infrastructure management.
Intrusion Detection System using Hybrid Reverse - Binary Meerkat Optimization Algorithm and Support Vector Machine with Improved Random Forest International Journal of Intelligent Engineering and Systems, 2025 The rapid advancement of technology and the growth of the internet have made network security a major concern, with various attacks being addressed using Machine Learning (ML).However, as the demand for network systems continues to increase, existing approaches struggle to process relevant features, impacting performance.This research proposes a Hybrid Reverse Strategy with a Binary Meerkat Optimization Algorithm (HRMOA) combined with a Support Vector Machine and Improved Random Forest (SVMIRF) to efficiently analyze various attacks in an Intrusion Detection System (IDS) and achieve better accuracy.Data collected from the UNSW-NB15 and NSL-KDD datasets is pre-processed using Min-Max normalization to ensure that all features are treated equally, preventing bias caused by differences in feature scales.Feature selection using MOA efficiently finds the dynamic search space by utilizing the hybrid reverse strategy, avoiding local optima while ensuring the exploration phase identifies optimal features.The SVM-IRF method for classification effectively manages complex feature boundaries and highdimensional data, integrating with RF to ensure decision-making and achieve better classification accuracy.The proposed method achieves an accuracy of 99.36% on the UNSW-NB15 dataset and 99.24% on the NSL-KDD dataset when compared with existing Long Short-Term Memory (LSTM) technique.
Optimizing Fine-Tuning Strategies for Large Language Models: A Comparative Study of Serial and Parallel Computation Paradigms Mallegowda M, Amala Rashmi Kumar, S Meena Kumari, Tanvi Rao, Tavishi S Shetty 2025 4th Opju International Technology Conference on Smart Computing for Innovation and Advancement in Industry 5 0 Otcon 2025, 2025 Fine-tuning Large Language Models (LLMs) is essential for domain-specific adaptation. This study compares serial and parallel computation paradigms for fine-tuning using the EvoL Instruct framework. Parallel computation reduced training time by 35%, improved memory efficiency by 25%, and achieved 2% higher model accuracy on large datasets. Serial methods, however, demonstrated greater stability in dependency-sensitive tasks with consistent performance across smaller datasets. The evaluation highlights trade-offs between simplicity and scalability, offering insights into optimizing fine-tuning strategies for diverse applications. These findings provide practical guidance for selecting computation paradigms based on resource availability and task requirements.
Analysis of optimization Techniques for Dynamic Neural Networks Mallegowda M, Saanvi Nair, Sahil Khirwal, Manik Animesh, Vasuman Mishra, Anita Kanavalli Proceedings of the 3rd International Conference on Intelligent and Innovative Technologies in Computing Electrical and Electronics Iitcee 2025, 2025
Fruit Classification Based On Freshness Mallegowda M, Sanskar R G, VISHVESHWARA N, Safwan G A, Vivek J, Anita Kanavalli Proceedings of the 2024 International Conference on Emerging Techniques in Computational Intelligence Icetci 2024, 2024
Fake Product Identification System Using Blockchain Mallegowda M, Anita Kanavalli, M.N. Thippeswamy, Kushagra Gupta, Lakshya Khandelwal, Vishal Bhattad, Himanshu Vaswani 4th International Conference on Circuits Control Communication and Computing I4c 2022, 2022
Energy efficient transmission using adaptive technique for WSNs International Journal of Recent Technology and Engineering, 2019
Digital Twin-Driven Flood Evacuation System using Graph Algorithms M Mallegowda, AB Ray, A Ajit, DD Shah, A Kanavalli 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
Performance Analysis of Serial and Parallel Computing Techniques for Natural Language Processing Tasks M Mallegowda, V Chaurasia, V Nahar, U Kamal, S Seervi 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
An Integrated Solution for Agricultural Decision Support Systems M Mallegowda, PK KR, SJ Patil, SS Kumar, VV Divate, V Patel 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
A Comparative Study of MongoDB on MongoDB Atlas, AWS EC2, Local Docker Containers, and Local Self Machine M Mallegowda, K Anand, CS Darshan, DP Abhishek, KN Yogesh, ... 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
SakhiSuraksha: an AI and IoT-Based Intelligent Emergency Response System for Women's Safety M Mallegowda, MS Sharanya 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
Improving UAV disaster response with DenseNet and AF-RCNN: a framework for accurate emergency spot detection Prasanna Kumar K R , Mallegowda M , Manoj Kumar D, Swathi H Y, Ananda Babu J Cogent Engineering 13 (1) , 2026 2026
Enhancing Genetic Algorithm Efficiency: A Comparative Study of Serial and Parallel Computation for TSP AM Mallegowda M, Tresa Maria Josylin 025 IEEE International Conference on Electronics, Computing and … , 2025 2025
WebGPU: Comparing Parallelism Over Serial Execution in Web Graphics A Mallegowda, M., Hegde, T., Alex, S.A., Kanavalli ICCAML 2024 2538, pp 219–224 , 2025 2025
Intelligent Resource Scheduling Using Proximal Policy Optimization in Heterogeneous Cloud Environments M Mallegowda, NK Rohidekar, A Kanavalli 2025 5th Asian Conference on Innovation in Technology (ASIANCON), 1-6 , 2025 2025
Secure and Efficient CI/CD Deployment in Cloud Platforms: Bridging Hypervisor Performance and Pipeline Security M Mallegowda, MS Swaroop, CS Darshan, P Dinesh 2025 5th Asian Conference on Innovation in Technology (ASIANCON), 1-6 , 2025 2025
Decrypting Faster: Synergizing Serial and Parallel Processing for Dictionary Attacks M Mallegowda, PK KR, MJ Peter, S Sadath, SU Farooq, A Kanavalli 2025 4th OPJU International Technology Conference (OTCON) on Smart Computing … , 2025 2025
Improving vehicle perception through image stitching: A serial and parallel evaluation M Mallegowda, NG Viswanath, N Polepalli, N Ganga 2025 4th OPJU International Technology Conference (OTCON) on Smart Computing … , 2025 2025 Citations: 2
Optimizing Fine-Tuning Strategies for Large Language Models: A Comparative Study of Serial and Parallel Computation Paradigms M Mallegowda, AR Kumar, SM Kumari, T Rao, TS Shetty 2025 4th OPJU International Technology Conference (OTCON) on Smart Computing … , 2025 2025
Intrusion Detection System using Hybrid Reverse-Binary Meerkat Optimization Algorithm and Support Vector Machine with Improved Random Forest. NMM Sathynarayna Rao, KN Shreenath, NKA Nemirajaiah, AVK Mohan International Journal of Intelligent Engineering & Systems 18 (4) , 2025 2025
Performance Comparison of Serial and Parallel Fruit Classification Using Pretrained Neural Networks M Mallegowda, A Parkavi, S Sanath, S Satyavolu, MR Gowda International Conference on Computing and Communication Systems for … , 2025 2025
Analysis of optimization Techniques for Dynamic Neural Networks M Mallegowda, S Nair, S Khirwal, M Animesh, V Mishra, A Kanavalli 2025 International Conference on Intelligent and Innovative Technologies in … , 2025 2025
Fruit classification based on freshness M Mallegowda, RG Sanskar, N Vishveshwara, GA Safwan, J Vivek 2024 International Conference on Emerging Techniques in Computational … , 2024 2024 Citations: 9
Revolutionizing Knee Surgery Education Using Virtual Reality in Medical Training N Subash, M Mallegowda 2024 IEEE International Conference on Electronics, Computing and … , 2024 2024 Citations: 1
The power of virtual reality-next-gen radiology training A Ahmed, S Rajarajeswari, M Mallegowda, N Subash 2024 15th International Conference on Computing Communication and Networking … , 2024 2024 Citations: 6
Developing virtual reality applications in medical education for osteotomy knee surgery N Subash, M Mallegowda, S Rajarajeswari, A Ahmed 2024 15th International Conference on Computing Communication and Networking … , 2024 2024 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
Research on software testing techniques and software automation testing tools K Sneha, GM Malle 2017 international conference on energy, communication, data analytics and … , 2017 2017 Citations: 164
Fruit classification based on freshness M Mallegowda, RG Sanskar, N Vishveshwara, GA Safwan, J Vivek 2024 International Conference on Emerging Techniques in Computational … , 2024 2024 Citations: 9
Fake product identification system using blockchain M Mallegowda, A Kanavalli, MN Thippeswamy, K Gupta, L Khandelwal, ... 2022 4th International Conference on Circuits, Control, Communication and … , 2022 2022 Citations: 7
The power of virtual reality-next-gen radiology training A Ahmed, S Rajarajeswari, M Mallegowda, N Subash 2024 15th International Conference on Computing Communication and Networking … , 2024 2024 Citations: 6
Movement Mode Harmony Search Based Multi-objective Firefly Algorithm Feature Selection for Detecting the Security Threats in Virtual Machine. ANN Kumar, M Mallegowda, AVK Mohan, KN Shreenath, CK Raju International Journal of Intelligent Engineering & Systems 17 (1) , 2024 2024 Citations: 6
Prediction of air quality index using machine data learning on atmospheric. M Mallegowda, A Kanavalli, Y Verma, SJK Vamsi, T Mukesh, ... 2021 Citations: 6
Intelligent transportation system based on the principles of service-oriented architecture M Mallegowda, V Nete, A Kanavalli 2015 Twelfth International Conference on Wireless and Optical Communications … , 2015 2015 Citations: 4
Developing virtual reality applications in medical education for osteotomy knee surgery N Subash, M Mallegowda, S Rajarajeswari, A Ahmed 2024 15th International Conference on Computing Communication and Networking … , 2024 2024 Citations: 3
Enhancing Image Fidelity through Denoising and Style GAN Techniques with Serial and Parallel Computation M Mallegowda, P Rajodiya, S Samruddha, SA Alex, A Kanavalli 2024 International Conference on Intelligent and Innovative Technologies in … , 2024 2024 Citations: 3
SOA-Based Middleware Framework for IoT Applications M Mallegowda, P Sarashetti, A Kanavalli Proceedings of Second International Conference on Sustainable Expert Systems … , 2022 2022 Citations: 3
Improving vehicle perception through image stitching: A serial and parallel evaluation M Mallegowda, NG Viswanath, N Polepalli, N Ganga 2025 4th OPJU International Technology Conference (OTCON) on Smart Computing … , 2025 2025 Citations: 2
Crop-Wise precision farming with integration of ML and IoT M Mallegowda, A Kanavalli, SJ Patil, SS Kumar, VV Divate, MSV Patel International Conference on Advances in Information Communication Technology … , 2024 2024 Citations: 2
Interpreting Fake Reviews Using Machine Learning and Deep Learning MQ Bhat, DS Jayalakshmi, M Mallegowda, J Geetha World Conference on Information Systems for Business Management, 277-286 , 2023 2023 Citations: 2
Revolutionizing Knee Surgery Education Using Virtual Reality in Medical Training N Subash, M Mallegowda 2024 IEEE International Conference on Electronics, Computing and … , 2024 2024 Citations: 1
Digital Twin-Driven Flood Evacuation System using Graph Algorithms M Mallegowda, AB Ray, A Ajit, DD Shah, A Kanavalli 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
Performance Analysis of Serial and Parallel Computing Techniques for Natural Language Processing Tasks M Mallegowda, V Chaurasia, V Nahar, U Kamal, S Seervi 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
An Integrated Solution for Agricultural Decision Support Systems M Mallegowda, PK KR, SJ Patil, SS Kumar, VV Divate, V Patel 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
A Comparative Study of MongoDB on MongoDB Atlas, AWS EC2, Local Docker Containers, and Local Self Machine M Mallegowda, K Anand, CS Darshan, DP Abhishek, KN Yogesh, ... 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
SakhiSuraksha: an AI and IoT-Based Intelligent Emergency Response System for Women's Safety M Mallegowda, MS Sharanya 2026 International Conference on Intelligent and Innovative Technologies in … , 2026 2026
Improving UAV disaster response with DenseNet and AF-RCNN: a framework for accurate emergency spot detection Prasanna Kumar K R , Mallegowda M , Manoj Kumar D, Swathi H Y, Ananda Babu J Cogent Engineering 13 (1) , 2026 2026
