SATHISH KUMAR M

@drmcet.ac.in

Assistant Professor(SS) and Department of CSE(AIML)
Dr.Mahalingam College of Engineering and Technology

SATHISH KUMAR M


                     Download Compact PDF  
https://researchid.co/sathish870

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Artificial Intelligence, Multidisciplinary
8

Scopus Publications

34

Scholar Citations

3

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • Enhancing Diagnostic Accuracy and Early Detection Through the Application of Deep Learning Techniques to the Segmentation of Colon Cancer in Histopathological Images
    Mahaveerakannan R, Shailee Lohmor Choudhary, Rinku Sharma Dixit, Srikanth Mylapalli, M. Sathish Kumar
    8th International Conference on I Smac Iot in Social Mobile Analytics and Cloud I Smac 2024 Proceedings, 2024
    Youth and elderly deaths are rising due to cancer. If it is not discovered early in cancer cell development, mortality will increase since it is deadly. Colon cancer arises when colon or rectum cells grow abnormally. Early colorectal cancer screening can prevent these abnormal growths from becoming cancerous. In health care systems, colon cancer diagnosis and categorization are crucial. Histopathology slide images are used to train a deep learning algorithm to detect colon cancer. The suggested model uses Vision Transformer (ViT) and Swin Transformer, a new type of ViT. Using an upgraded Swin Transformer model, the model accurately classifies tumours as benign or malignant. Effectiveness of colorectal diagnostics and precision cancer due to optimization concerns Their upgraded CNN models, ResNet34 and EfficientNet34, may not be enough to prevent optimization concerns from lowering colorectal cancer classification accuracy and efficiency. ResNet-101, Swin Transformer, ViT, and a revised Swin Transformer are also compared in this study. The proposed method uses LC25000 for training and testing. The test model has 99.80% precision using the modified Swin Transformer technique, 99.64% using the Swin Transformer itself, 99.36% using the ViT model, and 98.27% using ResNet-101.
  • Data-Driven Lung Cancer Staging: Integrating Clinical Parameters and Molecular Insights for Accurate Detection
    M.S. Praavin Kumar, Rathan Ramm Khanna, C. Jothi Kumar, C. Ashok Kumar, Shanmugam S
    2024 1st International Conference on Innovations in Communications Electrical and Computer Engineering Icicec 2024, 2024
    Lung Cancer diagnosis and treatment have made significant advancements in recent years, with the introduction of targeted chemotherapy and precise radiotherapy techniques. Nevertheless, improving the cancer patient’s survival rate is still a big challenge. To meet the required challenges of improving the survival rate of lung cancer patients, we developed machine learning models to predict the level of lung cancer based on various risk factors and biomarkers. This model utilizes a combination of supervised learning algorithms to examine patient records and identify patterns that may indicate the presence of the level of lung cancer. By training the model on a diverse dataset of patient records and genetic information, we aim to improve the accuracy of early detection and provide personalized treatment recommendations. Our approach integrates features such as location, histology, patient demographics, and lifestyle factors to create a comprehensive and robust predictive tool. The machine learning model holds the potential to identify the way lung cancer is diagnosed and managed, ultimately contributing to better patient outcomes and enhanced overall survival rates.
  • Automated Framework for Exploring Potential Biomarkers in Lung Cancer
    Mohan Kumar Sunil Kumar, S Venkataramanan, Palaniappan Sambandam, A Aashiq Shareef, S Saifuddin
    Proceedings of the 5th International Conference on Smart Electronics and Communication Icosec 2024, 2024
    Lung cancer has experienced a concerning increase in incidence with smoking, genetics, and air pollution identified as major contributing factors. Early detection is crucial for improving patient outcomes, as the disease can be difficult to diagnose in its early stages. This research presents a machine learning-based approach to predict lung cancer risk by identifying potential biomarkers. The proposed framework utilizes a streamlined pipeline of validated tools, ensuring a user-friendly and efficient process. By analyzing genetic data and identifying predictive biomarkers, this research aims to empower individuals with a family history of cancer or early symptoms to take proactive steps towards prevention and early detection. This approach contributes to the fight against lung cancer by providing valuable insights into disease risk and facilitating timely intervention.
  • Retracted: Development of Modified Homomorphic Encryption for IIoT on Textual Data (2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC) DOI: 10.1109/ICOCWC60930.2024.10470692)
    P. Rathinakumar, R. Dhivya, S. Prasath, K N Jayapriya, M.Sathish Kumar
    2024 International Conference on Optimization Computing and Wireless Communication Icocwc 2024, 2024
    Digitalizing existing systems for mass production is what's known as “Smart Industry” or the Industrial Internet of Things (IIoT). As a result of the interoperability of modern industrial equipment with IoT devices, a dizzying array of manufactured goods is being created. Problems with device availability, product dependability and product mobility for smart implementation, performance, security, scalability, interoperability, and energy efficiency are some of the research hurdles in Industrial IoT. This study presents a novel homomorphic encryption technique with improved performance. An analysis is conducted to assess the appropriateness of Homomorphic encryption for the Industrial Internet of Things (IIoT), and a refined version of the current algorithm is suggested and put into practice. The method's findings are compared to those of current algorithms in terms of performance metrics such as encryption time, decryption time, and throughput. It is determined that the technique is effective for different sizes of plain text blocks.
  • Development of Modified Homomorphic Encryption for IIoT on Textual Data
    P. Rathinakumar, R. Dhivya, S. Prasath, K N Jayapriya, M.Sathish Kumar
    2024 International Conference on Optimization Computing and Wireless Communication Icocwc 2024, 2024
    Digitalizing existing systems for mass production is what's known as “Smart Industry” or the Industrial Internet of Things (IIoT). As a result of the interoperability of modern industrial equipment with IoT devices, a dizzying array of manufactured goods is being created. Problems with device availability, product dependability and product mobility for smart implementation, performance, security, scalability, interoperability, and energy efficiency are some of the research hurdles in Industrial IoT. This study presents a novel homomorphic encryption technique with improved performance. An analysis is conducted to assess the appropriateness of Homomorphic encryption for the Industrial Internet of Things (IIoT), and a refined version of the current algorithm is suggested and put into practice. The method's findings are compared to those of current algorithms in terms of performance metrics such as encryption time, decryption time, and throughput. It is determined that the technique is effective for different sizes of plain text blocks.
  • Detection and Classification of Skin Cancer Using Molecular-Imaging Machine Learning (MIML) Algorithm
    R. Naveen, U. Arunkumar, S. Praveen Chakkravarthy, M. Sathish Kumar
    7th International Conference on Electronics Communication and Aerospace Technology Iceca 2023 Proceedings, 2023
    Skin cancer is among the most prevalent forms of the disease. The abnormal multiplication and spread of skin cells is the root cause of this disorder. And it's potent enough to infect the rest of your body as well. Skin cancer has the best prognosis and response rate to early detection. Excessive time spent in the sun's direct rays is the primary cause of skin cancer. Pale persons with compromised immune systems are at a higher risk of developing skin cancer. It occurs by a drop in melanin (pigment) synthesis in skin cells. The suggested model is constantly following and monitoring the human body. If there are suspicious changes, the proposed model will use Molecular-Imaging Machine Learning (MIML) to compare skin changes. A tissue test is often performed to confirm the diagnosis of skin disease if the patient has some serious symptoms. Since metastatic spread of basal cell carcinoma is so uncommon, a diagnosis is not often required for further testing.
  • Analysis of Lung Cancer for Developing Smart Healthcare with the Help of BGWO Based TSA-XGBoost Model
    Mahaveerakannan R, Murali Dhar M S, Sohan Goswami, P. Gopala Krishna, K. Jayanthi, M. Sathish Kumar
    International Conference on Self Sustainable Artificial Intelligence Systems Icssas 2023 Proceedings, 2023
    Given the circumstances the healthcare system, the Internet of Things (IoT) is crucial. IoT gadgets offer patient data for the framework of healthcare monitoring. IoT is a key component in every aspect of the health care management system since people can use smart devices to check on their health. Lung cancer is a fatal malignancy, and the likelihood of survival is increased by early identification. Because of the computational difficulty involved in gathering characteristics, it is imperative to design an approach using machine learning techniques for categorising cancer disease because the classification results given by the current methods are inadequate. With the use of the synthetic minority oversampling methods (SMOTE) methodology, the incoming data is pre-processed and balanced. With the help of the binary grey wolf optimisation algorithm (BGWOA), the pertinent features are best chosen. Finally, the suggested model's hyper-parameters are best chosen by the tunicate swarm optimisation (TSA) model, and the classification is carried out by the extreme gradient boosting (XGBoost) model. The experimental analysis demonstrates that the suggested model attained accuracy and recall values of 98% and 95%, respectively, compared to 95% and 95%, respectively, for the identical proposed model without the feature selection (FS) method.
  • A binary Bird Swarm Optimization technique for cloud computing task scheduling and load balancing
    Magesh Kumar B, M Sathish Kumar, Finney Daniel Shadrach, Subba Rao Polamuri, Poonkodi R, Vasudeva Naidu Pudi
    Proceedings of the 2022 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2022, 2022
    Cloud computing is a new paradigm for highperformance computation that combines a wide collection of autonomous mixed devices with a flexible computational construction to manage and deliver services. High-performance cloud computation is a subset of cloud computation. When it derives to improving the overall performance of cloud computation, task preparation is one of the most difficult things to improve. This can include response time, make span, and the degree of imbalance. When it comes to reducing power usage, processing time and increasing profit for service providers, task scheduling is vital. Heuristic methods like Binary bird swarm optimization (BBSO) were created to address the problem of inefficient procedures. However, if these algorithms are not paired with additional experiential or meta-heuristic procedures, the optimal solution will not be produced. Because of their high temporal complexity, these algorithms are less useful in real-world scenarios. BSO’s binary form is being proposed for cloud computing workload scheduling and balancing in the NP-problem. Our goal function determines if heterogeneous VMs have the greatest completion time difference by taking into account the updating and optimization limits discussed in this research. We developed a technique for updating particle positions in conjunction with load balancing. Metaheuristics and heuristics fail to outperform the proposed technique when it comes to job scheduling and load balancing. Achieved this level of success thanks to the deployment of an artificial neural network. In terms of resource allocation, ANN has shown encouraging outcomes. CNNs are more accurate and faster in predicting targets than multilayer perceptron networks.

RECENT SCHOLAR PUBLICATIONS

  • Autonomous Agent-Driven RAG Framework for Continuous Knowledge Integration in Dynamic Document Ecosystems
    SRD M.Sathish Kumar, G.Abiraami Shree, M.Balaji
    Smart AI Systems and Data Intelligence (ICSASDI 2026) , 2026
    2026
  • DAPE: Decentralized Autonomous Programming Environment for Tamil NLG Code Generation
    MSK Midun Thangavel
    5th International conference on Advances in Science,Engineering &Technology … , 2026
    2026
  • INTELLIGENT TRAFFIC MANAGEMENT SYSTEM
    M.SATHISH KUMAR, DR.P.VIVEKANANDAN, T.HARISH, S.PRABHAHARAN, D.VIMALRAJ
    IN Patent App. 202,541,132,962 , 2026
    2026
  • REAL-TIME PUBLIC TRANSPORT TRACKING FOR SMALL CITIES
    PSMMMC M.Sathish Kumar, V.Geetha
    International Conference on Emerging Innovations in Computational … , 2026
    2026
  • Detection and Classification of Skin Cancer Using Molecular-Imaging Machine Learning (MIML) Algorithm
    MSK R. Naveen,U. Arunkumar,S. Praveen Chakkravarthy
    IEEE, 843-848 , 2024
    2024
  • Development of Modified Homomorphic Encryption for IIoT on Textual Data
    KNJ M.Sathish Kumar, P. Rathinakumar, R.Dhivya, S.Prasath
    2024 International Conference on Optimization Computing and Wireless … , 2024
    2024
  • Analysis of Lung Cancer for Developing Smart Healthcare with the Help of BGWO Based TSA-XGBoost Model
    MSK Mahaveerakannan R,Murali Dhar M S,Sohan Goswami,P. Gopala Krishna,K ...
    IEEE, 910–916 , 2023
    2023
    Citations: 4
  • A binary Bird Swarm Optimization technique for cloud computing task scheduling and load balancing
    MS Kumar, FD Shadrach, SR Polamuri, VN Pudi
    2022 International Conference on Innovative Computing, Intelligent … , 2022
    2022
    Citations: 20
  • Artificial Intelligence Based Calorie Level Detecting And Food Suggesting Equipment
    M.Sathish Kumar , Dr. A. Chandra Babu, Dr. Praveen Kumar, Dr. Deepankar ...
    IN Patent App. 202,241,046,270 , 2022
    2022
  • Artificial Intelligence Based Construction on Mechanically Developed Machine Motion Prediction System To Reduce Worksite Hazards
    MSST Dr. K. Arun Vasantha Geethan,Dr.D.Sengeni,Rajat Srivastava,Dr. Shivappa ...
    IN Patent App. 202141024097 A , 2021
    2021
  • An Efficient Elliptic Curve Strategy For Secure Medium Communication
    MS Kumar
    International Journal of Advanced Engineering Science and Information … , 2021
    2021
  • A review: smart farming using IoT in the area of crop monitoring
    KK Devi, J Premkumar, K Kavitha, P Anitha, MS Kumar, ...
    Annals of the Romanian Society for Cell Biology 25 (5), 3887-3896 , 2021
    2021
    Citations: 10
  • Android Based Document Sharing System
    MS Kumar
    4th National Conference on Innovations and Advancements in Electrical Sciences , 2019
    2019
  • Moving Zone Routing Protocol Vehicle Communication
    MS Kumar
    2nd International Conference On Advances in Science, Engineering and Management , 2018
    2018
  • Effective Data Gathering in Wireless Sensor Network and Combine TSP Hard Reduce Approach
    MS Kumar
    International Conference on Green, Intelligent Computing and Communication … , 2017
    2017
  • Effective Assignment of Periodic Feedback Channels in Broadband Wireless Networks
    MS Kumar
    International Journal Of Advanced and Innovative Research 5 (8) , 2016
    2016
  • Sleep Scheduling Algorithm for Reduction of Power and Energy in Wireless Sensor Network
    MS Kumar
    3rd International Conference on Emerging Trends in Engineering and Technology , 2016
    2016
  • Trust and Secure Based Scheme for Multi-Hop Wireless Networks Using Shortest Reliable Route
    MS Kumar
    Recent Advances in Computer Sciences , 2014
    2014
  • Trust And Secure Based Scheme For Multi-Hop Wireless Networks Using Shortest Reliable Route
    MS Kumar
    International Journal Of Research in Computer Applications and Robotics 2 (3) , 2014
    2014
  • Enhanced Sleep Scheduling for Reduction of Power and Energy in WSN
    MS Kumar
    First National level Conference on Recent Trends in Information and … , 2013
    2013

MOST CITED SCHOLAR PUBLICATIONS

  • A binary Bird Swarm Optimization technique for cloud computing task scheduling and load balancing
    MS Kumar, FD Shadrach, SR Polamuri, VN Pudi
    2022 International Conference on Innovative Computing, Intelligent … , 2022
    2022
    Citations: 20
  • A review: smart farming using IoT in the area of crop monitoring
    KK Devi, J Premkumar, K Kavitha, P Anitha, MS Kumar, ...
    Annals of the Romanian Society for Cell Biology 25 (5), 3887-3896 , 2021
    2021
    Citations: 10
  • Analysis of Lung Cancer for Developing Smart Healthcare with the Help of BGWO Based TSA-XGBoost Model
    MSK Mahaveerakannan R,Murali Dhar M S,Sohan Goswami,P. Gopala Krishna,K ...
    IEEE, 910–916 , 2023
    2023
    Citations: 4
  • Autonomous Agent-Driven RAG Framework for Continuous Knowledge Integration in Dynamic Document Ecosystems
    SRD M.Sathish Kumar, G.Abiraami Shree, M.Balaji
    Smart AI Systems and Data Intelligence (ICSASDI 2026) , 2026
    2026
  • DAPE: Decentralized Autonomous Programming Environment for Tamil NLG Code Generation
    MSK Midun Thangavel
    5th International conference on Advances in Science,Engineering &Technology … , 2026
    2026
  • INTELLIGENT TRAFFIC MANAGEMENT SYSTEM
    M.SATHISH KUMAR, DR.P.VIVEKANANDAN, T.HARISH, S.PRABHAHARAN, D.VIMALRAJ
    IN Patent App. 202,541,132,962 , 2026
    2026
  • REAL-TIME PUBLIC TRANSPORT TRACKING FOR SMALL CITIES
    PSMMMC M.Sathish Kumar, V.Geetha
    International Conference on Emerging Innovations in Computational … , 2026
    2026
  • Detection and Classification of Skin Cancer Using Molecular-Imaging Machine Learning (MIML) Algorithm
    MSK R. Naveen,U. Arunkumar,S. Praveen Chakkravarthy
    IEEE, 843-848 , 2024
    2024
  • Development of Modified Homomorphic Encryption for IIoT on Textual Data
    KNJ M.Sathish Kumar, P. Rathinakumar, R.Dhivya, S.Prasath
    2024 International Conference on Optimization Computing and Wireless … , 2024
    2024
  • Artificial Intelligence Based Calorie Level Detecting And Food Suggesting Equipment
    M.Sathish Kumar , Dr. A. Chandra Babu, Dr. Praveen Kumar, Dr. Deepankar ...
    IN Patent App. 202,241,046,270 , 2022
    2022
  • Artificial Intelligence Based Construction on Mechanically Developed Machine Motion Prediction System To Reduce Worksite Hazards
    MSST Dr. K. Arun Vasantha Geethan,Dr.D.Sengeni,Rajat Srivastava,Dr. Shivappa ...
    IN Patent App. 202141024097 A , 2021
    2021
  • An Efficient Elliptic Curve Strategy For Secure Medium Communication
    MS Kumar
    International Journal of Advanced Engineering Science and Information … , 2021
    2021
  • Android Based Document Sharing System
    MS Kumar
    4th National Conference on Innovations and Advancements in Electrical Sciences , 2019
    2019
  • Moving Zone Routing Protocol Vehicle Communication
    MS Kumar
    2nd International Conference On Advances in Science, Engineering and Management , 2018
    2018
  • Effective Data Gathering in Wireless Sensor Network and Combine TSP Hard Reduce Approach
    MS Kumar
    International Conference on Green, Intelligent Computing and Communication … , 2017
    2017
  • Effective Assignment of Periodic Feedback Channels in Broadband Wireless Networks
    MS Kumar
    International Journal Of Advanced and Innovative Research 5 (8) , 2016
    2016
  • Sleep Scheduling Algorithm for Reduction of Power and Energy in Wireless Sensor Network
    MS Kumar
    3rd International Conference on Emerging Trends in Engineering and Technology , 2016
    2016
  • Trust and Secure Based Scheme for Multi-Hop Wireless Networks Using Shortest Reliable Route
    MS Kumar
    Recent Advances in Computer Sciences , 2014
    2014
  • Trust And Secure Based Scheme For Multi-Hop Wireless Networks Using Shortest Reliable Route
    MS Kumar
    International Journal Of Research in Computer Applications and Robotics 2 (3) , 2014
    2014
  • Enhanced Sleep Scheduling for Reduction of Power and Energy in WSN
    MS Kumar
    First National level Conference on Recent Trends in Information and … , 2013
    2013