Vehicles Smoke Monitoring Using Internet of Things and Machine Learning P. Dhavakumar, Selvakumar Samuel Sustainable Resource Management in Next Generation Computational Constrained Networks, 2025 Global warming is the most important problem of our time. CO 2 emissions through various means are the main reason for this problem. One of the major contributors among the means of CO 2 emissions is vehicle smoke. In this chapter, this issue has been discussed. A system has been proposed using the Internet of Things and a convolutional neural network–support vector machine hybrid machine learning model. This system can help monitor the level of vehicle emissions and alert the Road Transport Department if CO 2 emissions exceed the permitted level. This system can help the government alleviate the CO 2 emission problems of vehicles to some extent. This is a small initiative to support the green environment.
GSHetero - Grouping and Heterogeneity-Aware Data Placement to Improve MapReduce Performance in Hadoop Vengadeswaran S, Dhavakumar P, Viji Viswanathan IEEE Networking Letters, 2025 The execution of MapReduce (MR) applications in Hadoop cluster poses significant challenges due to the non consideration of 1. Grouping semantics in Data-intensive applications, 2. Heterogeneity in the computing nodes resulting in suboptimal block distribution, concentrating execution on fewer nodes, thereby increasing processing time and reducing data locality. This letter proposes improved data placement by exploiting grouping semantics and heterogeneity (GSHetero) to boost MR performance. Initially, the execution traces will be analyzed to identify the data access pattern. The grouping semantics are extracted by applying the MCL algorithm. Then GSHetero algorithm is proposed which re-organises the default data layouts based on grouping semantics to ensure higher parallelism. The efficiency of the GSHetero is demonstrated by the 10-node Hadoop cluster deployed on the cloud by executing the Linear Regression over the weather dataset. The results show that GSHetero improves data locality by 27.4% and CPU utilization by 47%. The efficiency of the GSHetero is also demonstrated by executing Hadoop benchmark (WordCount) on varying cluster sizes (15, 20 nodes) for varying workloads.
Intelligent Voice-Controlled Domestic Electrical Appliances B.S. Nivethitha, M.A Inayathullaah, Dhavakumar P, V. Ankit 5th IEEE International Conference on Innovations in Power and Advanced Computing Technologies I Pact 2025, 2025 The increasing demand for smart home solutions has led to the development of innovative systems that enhance user convenience. This project focuses on creating an Intelligent Voice-Controlled Domestic Electrical Appliance System, which utilizes an AT89S52 microcontroller to interpret voice commands and control appliances wirelessly. By integrating Voice Activity Detection (VAD) and Automatic Speech Recognition (ASR) algorithms, the system allows users to operate devices such as LED lights, doors, fans, and air conditioners via an Android application. Commands are transmitted through Bluetooth using the HC05 module, enabling seamless interaction. The system's architecture includes a power management unit and relay controls, ensuring safe operation of household appliances. Testing revealed an approximate 90 (%) accuracy in voice recognition under various ambient conditions, demonstrating the feasibility of this approach. The project addresses accessibility challenges faced by users with mobility impairments,paving the way for broader adoption of smart technologies in everyday life.
Aggressive Behaviour Detection Using CNNs for Violence and Non-Violence Classification M. Marimuthu, D. Vidyabharathi, G. Mohanraj, P. Dhavakumar, V. Sathiyamoorthi, V. Sathiyapriya International Conference on Emerging Technologies in Electronics and Green Energy Iceteg 2025, 2025 The increasing prevalence of online and offline violence, there is an urgent need for intelligent surveillance systems which automatically monitor violent behaviour in real time. In this study, a deep learning-based model based on Convolutional Neural Networks (CNNs) along with You Only Look Once (YOLO) algorithm is proposed for classifying a video-frame/image as violent or non-violent. YOLO algorithm:(You only look once) real-time object detection that identifies the aggressive actions in the sequences of video. Spatial and temporal feature extraction using CNNs can improve the performance of the model to classify violent and non-violent behaviours, respectively. In this work a large-scale set of images depicting violence is used to provide labelled dataset and the system is capable to detect detection with high accuracy and efficiency appropriate for real time surveillance system. The method includes, preprocessing of video frames, augmenting data followed by Feature extraction with CNNs and final detection using Yolo which runs it on real-time. In this work, we benchmark the proposed model against existing deep learning architectures, and we show its superiority in speed and accuracy. According to experimental results, the integration of YOLO with CNNs provides a solid backbone for the detection of aggressive behaviour in public spaces, social media content, and police prosecution contexts. This kind of research will expand public safety and give way to detecting and preventing violence automatically.
IDaPS — Improved data-locality aware data placement strategy based on Markov clustering to enhance MapReduce performance on Hadoop S. Vengadeswaran, S.R. Balasundaram, P. Dhavakumar Journal of King Saud University Computer and Information Sciences, 2024 The execution of Map-Reduce applications on the Hadoop cluster poses significant challenges due to the non-consideration of data locality, i.e., assigning tasks to compute nodes where input data sets are located. Due to such non-consideration, high data transfer overheads are caused. Further, it increases latency, which may arise if input data needs to be transferred across the network, thereby significantly increasing execution time. To address this issue, an Improved DAta Placement Strategy IDaPS based on the intra-dependency among the data is proposed. IDaPS re-organizes the default data layouts in HDFS to ensure higher degree of parallelism. The efficiency of IDaPS is demonstrated in Hadoop clusters (10 and 15 nodes) by executing Hadoop Benchmark performance tests viz. WordCount, Grep on Project-Gutenberg book dataset (50GB) and Least Square Linear Regression (LSLR) on weather dataset (10.67GB). The results were compared with state-of-the-art algorithms viz. Hadoop Default Data Placement (HDDP), Load-Balancer and literary work RENDA. The results demonstrate that IDaPS significantly reduces execution time by 28.2% and 38.4% in 10-node and 15-node clusters while executing WordCount, and 35% and 38.1% in 10-node and 15-node clusters for Grep. Similarly, for LSLR, it reduces execution time by 32.7%.
A Cryptographically Secure Image Steganography Scheme Based On Arduino Microcontrollers Aqib Khan, P Dhavakumar Proceedings of the 2024 10th International Conference on Communication and Signal Processing Iccsp 2024, 2024 In today’s digitally pervasive environment, safeguarding sensitive information concealed within images has become increasingly critical. Conventional steganographic techniques may prove inadequate against sophisticated detection algorithms and statistical analysis. To address this challenge, integrating a pseudo-random number generator with hardware based entropy sources into the channel selection process offers a dynamic and adaptive solution to enhance information hiding security in images. As machine learning techniques for steganography become more sophisticated, they often introduce significant computational overhead. These ML-based algorithms require extensive computational resources for training, inference, and analysis, leading to increased complexity in terms of both time and computational power. By capitalizing on the inherent randomness introduced by the watchdog timer’s RC oscillator in an arduino embedded microcontroller, we can amplify the unpredictability of channel selection during embedding. This paper proposes a novel hybrid model integrating Hardware Random Number Generators and Pseudo-Random Number Generators to augment entropy in the channel selection process within steganography. An examination of the performance of this hybrid model is presented.
Automated Email and SMS Notification System for Unauthorized Entry using Yolov9 Eeshaan Dhanuka, P Dhavakumar Proceedings of the 2024 10th International Conference on Communication and Signal Processing Iccsp 2024, 2024 Security breaches present a serious risk in a variety of settings, thus strong detection and alerting systems are required to efficiently reduce risks. This study proposes a novel way for developing an Automated Email and SMS Notification System customized for unauthorized entrance detection using the YOLOv9 object identification model. By utilizing the capabilities of YOLOv9, the system quickly detects unwanted people or things in the monitored areas and sends out automatic emails and SMS notifications to selected stakeholders. Our technology improves security measures by combining cutting-edge machine learning techniques with communication technologies. This allows for the rapid response to possible attacks through real-time notifications. Test results show that the system is effective in identifying unwanted entries and reducing false positives, strengthening security protocols in many contexts.
Development of Deep Neural Framework for Human Activity Recognition Madisetty Tharun Kumar, Natarajan B, Murali P, Chellammal P, Dhavakumar. P, Muruganantham T Proceedings of Icwite 2024 IEEE International Conference for Women in Innovation Technology and Entrepreneurship, 2024
Solar Irradiance Prediction Model Based on LSTM Swarna Venkata Naga Aditya, R Bhuvaneswari, B Natarajan, P Dhavakumar 2023 3rd Asian Conference on Innovation in Technology Asiancon 2023, 2023
Enhancing software quality using fuzzy logic and program slicing International Journal of Control Theory and Applications, 2016
RECENT SCHOLAR PUBLICATIONS
A comparative evaluation of EEG-based deep learning models for schizophrenia detection with cross-dataset validation and explainable AI J SJ, S GS, B Chandrasekaran, S Byju, D P Neurological Research, 1-36 , 2026 2026
Software defect prediction using graph sample and aggregate-attention network optimized with nomadic people optimizer for enhancing the software reliability P Dhavakumar, S Vengadeswaran Computer Standards & Interfaces 95, 104033 , 2026 2026 Citations: 4
Hybrid deep learning framework for magnetic resonance imaging-based classification of Alzheimer’s disease R Komal, P Dhavakumar, K Rahul, B Jaswanth, R Preeth Brain Network Disorders , 2025 2025 Citations: 9
Aggressive Behaviour Detection Using CNNs for Violence and Non-Violence Classification M Marimuthu, D Vidyabharathi, G Mohanraj, P Dhavakumar, ... 2025 International Conference on Emerging Technologies in Electronics and … , 2025 2025
Intelligent Voice-Controlled Domestic Electrical Appliances BS Nivethitha, MA Inayathullaah, V Ankit 2025 Innovations in Power and Advanced Computing Technologies (i-PACT), 1-5 , 2025 2025
Vehicles Smoke Monitoring Using Internet of Things and Machine Learning P Dhavakumar, S Samuel Sustainable Resource Management in Next‐Generation Computational Constrained … , 2025 2025
GSHetero-Grouping and Heterogeneity-Aware Data Placement to Improve MapReduce Performance in Hadoop S Vengadeswaran, P Dhavakumar IEEE Networking Letters , 2025 2025 Citations: 1
Dynamic Traffic Signal Timing and Predictive Traffic Management Using R-CNN and Probe Vehicle Data to Improve Urban Mobility P Dhavakumar, S Samuel, S Jesvanth, P Saravanan Proceedings of Eighth International Conference on Information System Design … , 2025 2025
Automated Image Caption Generator for Visually Impaired Using VGG16 and LSTM K Vigyat, P Dhavakumar International Conference on Data & Information Sciences, 109-119 , 2024 2024
Enhancing Software Reliability through Naive Bayes-based Defect Prediction P Dhavakumar, K Lakshmikant 2024
Automated email and sms notification system for unauthorized entry using yolov9 E Dhanuka, P Dhavakumar 2024 10th International conference on communication and signal processing … , 2024 2024 Citations: 5
A Cryptographically Secure Image Steganography Scheme Based On Arduino Microcontrollers A Khan, P Dhavakumar 2024 10th International Conference on Communication and Signal Processing … , 2024 2024 Citations: 1
IDaPS—Improved data-locality aware data placement strategy based on Markov clustering to enhance MapReduce performance on Hadoop S Vengadeswaran, SR Balasundaram, P Dhavakumar Journal of King Saud University-Computer and Information Sciences 36 (3), 101973 , 2024 2024 Citations: 11
Development of deep neural framework for human activity recognition MT Kumar, B Natarajan, P Murali, P Chellammal, T Muruganantham 2024 IEEE international conference for women in innovation, technology … , 2024 2024 Citations: 2
Solar irradiance prediction model based on LSTM SVN Aditya, R Bhuvaneswari, B Natarajan, P Dhavakumar 2023 3rd Asian Conference on Innovation in Technology (ASIANCON), 1-5 , 2023 2023 Citations: 8
A comprehensive survey of the security issues, attacks and trust & reputation-based solutions towards VANET SR Pandiyanathan Murugesan, Udayabalan B, Dhavakumar P, Ashwini S, Nanda Ashwin Journal of neuroquantology 20 (7), 3519-3536 , 2022 2022
An efficient parameter optimization of software reliability growth model by using chaotic grey wolf optimization algorithm. J Ambient Intell Humaniz Comput 12: 3177–3188 P Dhavakumar, N Gopalan 2021 Citations: 2
Automated Facial Recognition Entry Management System Using Image Processing Technique B Kavimuhil, MM Hakkim, MN Ahamed, P Dhavakumar Turkish Journal of Computer and Mathematics Education 12 (10), 1435-1439 , 2021 2021
An efficient parameter optimization of software reliability growth model by using chaotic grey wolf optimization algorithm GNP Dhavakumar P Ambient Intelligence and Humanized Computing , 2020 2020 Citations: 43
Defect Prediction and Dimension Reduction Methods for Achieving Better Software Quality DPG N.P International Journal of Recent Technology and Engineering 8 (2), 2168 – 2179 , 2019 2019
MOST CITED SCHOLAR PUBLICATIONS
An efficient parameter optimization of software reliability growth model by using chaotic grey wolf optimization algorithm GNP Dhavakumar P Ambient Intelligence and Humanized Computing , 2020 2020 Citations: 43
IDaPS—Improved data-locality aware data placement strategy based on Markov clustering to enhance MapReduce performance on Hadoop S Vengadeswaran, SR Balasundaram, P Dhavakumar Journal of King Saud University-Computer and Information Sciences 36 (3), 101973 , 2024 2024 Citations: 11
Hybrid deep learning framework for magnetic resonance imaging-based classification of Alzheimer’s disease R Komal, P Dhavakumar, K Rahul, B Jaswanth, R Preeth Brain Network Disorders , 2025 2025 Citations: 9
Solar irradiance prediction model based on LSTM SVN Aditya, R Bhuvaneswari, B Natarajan, P Dhavakumar 2023 3rd Asian Conference on Innovation in Technology (ASIANCON), 1-5 , 2023 2023 Citations: 8
Automated email and sms notification system for unauthorized entry using yolov9 E Dhanuka, P Dhavakumar 2024 10th International conference on communication and signal processing … , 2024 2024 Citations: 5
Software defect prediction using graph sample and aggregate-attention network optimized with nomadic people optimizer for enhancing the software reliability P Dhavakumar, S Vengadeswaran Computer Standards & Interfaces 95, 104033 , 2026 2026 Citations: 4
Soft Computing Techniques for Enhancing Software Reliability VPM Dhavakumar P, Shankar.S International Journal of Latest Trends in Engineering and Technology, 133-140 , 2018 2018 Citations: 3
Development of deep neural framework for human activity recognition MT Kumar, B Natarajan, P Murali, P Chellammal, T Muruganantham 2024 IEEE international conference for women in innovation, technology … , 2024 2024 Citations: 2
An efficient parameter optimization of software reliability growth model by using chaotic grey wolf optimization algorithm. J Ambient Intell Humaniz Comput 12: 3177–3188 P Dhavakumar, N Gopalan 2021 Citations: 2
GSHetero-Grouping and Heterogeneity-Aware Data Placement to Improve MapReduce Performance in Hadoop S Vengadeswaran, P Dhavakumar IEEE Networking Letters , 2025 2025 Citations: 1
A Cryptographically Secure Image Steganography Scheme Based On Arduino Microcontrollers A Khan, P Dhavakumar 2024 10th International Conference on Communication and Signal Processing … , 2024 2024 Citations: 1
A comparative evaluation of EEG-based deep learning models for schizophrenia detection with cross-dataset validation and explainable AI J SJ, S GS, B Chandrasekaran, S Byju, D P Neurological Research, 1-36 , 2026 2026
Aggressive Behaviour Detection Using CNNs for Violence and Non-Violence Classification M Marimuthu, D Vidyabharathi, G Mohanraj, P Dhavakumar, ... 2025 International Conference on Emerging Technologies in Electronics and … , 2025 2025
Intelligent Voice-Controlled Domestic Electrical Appliances BS Nivethitha, MA Inayathullaah, V Ankit 2025 Innovations in Power and Advanced Computing Technologies (i-PACT), 1-5 , 2025 2025
Vehicles Smoke Monitoring Using Internet of Things and Machine Learning P Dhavakumar, S Samuel Sustainable Resource Management in Next‐Generation Computational Constrained … , 2025 2025
Dynamic Traffic Signal Timing and Predictive Traffic Management Using R-CNN and Probe Vehicle Data to Improve Urban Mobility P Dhavakumar, S Samuel, S Jesvanth, P Saravanan Proceedings of Eighth International Conference on Information System Design … , 2025 2025
Automated Image Caption Generator for Visually Impaired Using VGG16 and LSTM K Vigyat, P Dhavakumar International Conference on Data & Information Sciences, 109-119 , 2024 2024
Enhancing Software Reliability through Naive Bayes-based Defect Prediction P Dhavakumar, K Lakshmikant 2024
A comprehensive survey of the security issues, attacks and trust & reputation-based solutions towards VANET SR Pandiyanathan Murugesan, Udayabalan B, Dhavakumar P, Ashwini S, Nanda Ashwin Journal of neuroquantology 20 (7), 3519-3536 , 2022 2022
Automated Facial Recognition Entry Management System Using Image Processing Technique B Kavimuhil, MM Hakkim, MN Ahamed, P Dhavakumar Turkish Journal of Computer and Mathematics Education 12 (10), 1435-1439 , 2021 2021
