Ben M. Jebin

@karunya.edu

Assistant Professor, Division of Digital Sciences
Karunya Institute of Technology and Sciences

Ben M. Jebin


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Computer Science Applications
7

Scopus Publications

Scopus Publications

  • Retraction Note: Neonatal Seizure detection using GLCM feature extraction & AlexNet classification (Multimedia Tools and Applications, (2024), 83, 35, (83139-83155), 10.1007/s11042-024-18779-8)
    Ben M. Jebin, M. Anline Rejula, G. Eberlein
    Multimedia Tools and Applications, 2026
  • Brain tumor detection and classification using u-net and CNN with brain texture pattern analysis
    Ben M. Jebin, S. Immaculate Shyla, Koen Bel, C. Jaspin Jeba Sheela
    Biomedical Signal Processing and Control, 2025
  • Skin lesion classification using adjacent dynamic and fixed convolutional kernel CNN for the extraction of fine texture descriptors
    Ben M. Jebin, C. Thinkal Dayana, C. Jaspin Jeba Sheela
    Multimedia Tools and Applications, 2025
  • A New Hybrid Structure for Bidirectional DC-DC Converters with High Conversion Ratios for Electric Vehicles using War Strategy Optimization-WSO
    Ananth Angel Z, Kumar S S, Ben M Jebin
    Ssrg International Journal of Electrical and Electronics Engineering, 2025
    This work uses War Strategy Optimization (WSO) to build a new hybrid design for electric vehicle bidirectional DC DC converters with high conversion ratios. Low voltage load on semiconductors, high voltage conversion ratios, a steady current at the low voltage port, and a steady potential differential between the lower voltage and the high voltage ports' grounds are some of the features of the suggested converter. The converter's efficiency is raised by using synchronous rectification. The primary benefit of the suggested structure is that it may be utilized with various energy sources with various voltage-current characteristics. Furthermore, the battery may be charged in breaking mode because of the bidirectional nature of the proposed design. New energy automobiles are increasingly using the method for energy storage that is a hybrid of "fuel cell/power battery plus supercapacitors" to improve the powertrain's longevity and dynamic performance. This converter is a great substitute for DC-DC converters because of its high voltage gain and the aforementioned characteristics for electric vehicles. The WSO approach showed that charge prices dropped by 12.45% and 3.61%, respectively, while waiting times dropped by 11.17% and 39.09%; these findings imply that the WSO algorithm has the potential to increase both the efficacy and affordability of EV management systems, particularly in scenarios with inadequate charging infrastructure. The charge and discharge states can produce the highest efficiency, 98%, respectively, based on experimental results.
  • Intelligent Waste Management System using Digital Twin Technology
    Velumani Thiyagarajan, L Jaya Singh Dhass, Vensila C, Ben M. Jebin, Seethalakshmy Anantharaman
    Proceedings of 8th International Conference on Computing Methodologies and Communication Iccmc 2025, 2025
    Every household in ancient Athens engaged in the routine activity of collecting rubbish and disposing of it in dumps. The most crucial aspect was self-waste management. Every day, people ought to have gone to every street to remove the trash from the community. The drivers of waste collection trucks in the regular waste management system proceed along an established route without checking the level of the containers. Because this technology is unable to detect the levels in the containers, half-filled containers may be emptied. Additionally, the system's collection routes result in time waste, increased fuel consumption, and unnecessary resource use when trucks collect the empty bins. Therefore, this approach is introduced to address these problems. In this system machine learning technique (Decision Tree) is used for Smart Waste Management System. So, by using this system, dust bin can predict in each and every area by taking last data as input values (such as weight of dustbin and time taken to fill the dustbin) and trained with machine learning technique. Hence, by using this system dustbin can be predicated accurately.
  • Detection of Acute Lymphoblastic Leukemia Using a Novel Bone Marrow Image Segmentation
    M. Anline Rejula, Ben M JebIn, Ravi Selvakumar, S. Amutha, Eberlein George
    Tsinghua Science and Technology, 2025
    In our study, we present a novel method for automating the segmentation and classification of bone marrow images to distinguish between normal and Acute Lymphoblastic Leukaemia (ALL). Built upon existing segmentation techniques, our approach enhances the dual threshold segmentation process, optimizing the isolation of nucleus and cytoplasm components. This is achieved by adapting threshold values based on image characteristics, resulting in superior segmentation outcomes compared to previous methods. To address challenges, such as noise and incomplete white blood cells, we employ mathematical morphology and median filtering techniques. These methods effectively denoise the images and remove incomplete cells, leading to cleaner and more precise segmentation. Additionally, we propose a unique feature extraction method using a hybrid discrete wavelet transform, capturing both spatial and frequency information. This allows for the extraction of highly discriminative features from segmented images, enhancing the reliability of classification. For classification purposes, we utilize an improved Adaptive Neuro-Fuzzy Inference System (ANFIS) that leverages the extracted features. Our enhanced classification algorithm surpasses traditional methods, ensuring accurate identification of acute lymphoblastic leukaemia. Our innovation lies in the comprehensive integration of segmentation techniques, advanced denoising methods, novel feature extraction, and improved classification. Through extensive evaluation on bone marrow samples from the Acute Lymphoblastic Leukemia Image DataBase (ALL-IDB) for Image Processing database using MATLAB 10.0, our method demonstrates outstanding classification accuracy. The segmentation accuracy for various cell types, including Band cells (96%), Metamyelocyte (99%), Myeloblast (96%), N. myelocyte (97%), N. promyelocyte (97%), and Neutrophil cells (98%), further underscores the potential of our approach as a high-quality tool for ALL diagnosis.
  • Neonatal Seizure detection using GLCM feature extraction & AlexNet classification
    Ben M. Jebin, M. Anline Rejula, G. Eberlein
    Multimedia Tools and Applications, 2024