Classification of chest radiographs into healthy/pneumonia using Harris-Hawks Algorithm optimized deep-features K. Vijayakumar, Mohammad Nazmul Hasan Maziz, Swaetha Ramadasan, Seifedine Kadry, S. Arunmozhi Discover Computing, 2025 Pneumonia is a pulmonary infection that causes thoracic discomfort, typically caused by bacteria, or viruses. The pneumonia in children and elderly is medical emergency and hence appropriate diagnosis and treatment is necessary. Clinical-level screening of pneumonia is frequently executed using the chest X-ray and its analysis will help in treatment planning and execution. Recently, several pre-trained deep-learning (PDL) based systems are developed to identify disease in different imaging modalities, including the chest X-ray. This study aims to develop a PDL-based tool to analyse chest X-ray dataset to identify the pneumonia. This PDL-tool performs the following tasks on the X-ray database; (i) detection of healthy/pneumonia, and (ii) detecting the viral/bacterial pneumonia. Along with the traditional deep-features based classification using the SoftMax, this work also considered Harris-Hawks Algorithm (HHA) algorithm based features optimization and serial features integration to generate fused-features vector (FFV). The experimental outcome authenticates that this PDL-tool helps to offer improved accuracy with the HHA-optimized features. This work provided an accuracy of 99.3750% during healthy/pneumonia detection with FFV and Support Vector Machine (SVM), and detection accuracy of 88.5417% during viral/bacterial pneumonia detection with FFV and SVM.
Lightweight Deep-Learning Based Metal/Plastic Trash Detection with Fused Features S. Arunmozhi, S. Prabha 2024 International Conference on System Computation Automation and Networking Icscan 2024, 2024 Recently, several approaches have been proposed for the proper management of waste to achieve environmental sustainability and resource conservation. Proper garbage disposal reduces pollution and prevents the contamination of water and soil. This study proposes a deep-learning tool (DLT) for the automatic detection of metal/plastic waste to enhance the recycling process. This work created the DLT by utilizing a Lightweight Deep Learning (LWDL) model to establish a more efficient and less intricate method. The stages in this tool encompass: the collection of trash images and their resizing to 224x224x3 pixels, feature extraction utilizing the selected LWDL model, performance evaluation through binary classification with three-fold cross-validation, and the identification of the top two LWDL models to produce fused deep features (FDF) to enhance classification accuracy. The experimental method employs the SoftMax utilizing individual LWDL features and FDF, and the findings affirm that the proposed tool yields superior metal/plastic waste classification results compared to the individual features. In the future, this technique may be utilized to categorize authentic waste photographs captured with a digital camera.
Normal/Cataract Detection in Fundus Image Using Individual and Fused ResNet Features S. Arunmozhi, P. Arunagiri, S. Prabha 2024 International Conference on System Computation Automation and Networking Icscan 2024, 2024 The visual sensory information collected by the eyes is crucial for accurate perception and decision-making in the brain. Any ocular ailment will disrupt this process, perhaps resulting in mild to severe vision-related complications. Ocular ailments are primarily attributable to disease or senescence. Age-related eye illness is a prevalent concern that necessitates prompt detection and intervention. Cataract is a prevalent age-related ocular condition that results in mild to severe visual impairment and necessitates a small surgical intervention for correction. The image-guided identification of cataracts is a clinical practice, and this research intends to present a Deep Learning (DL) method to categorize Retinal Fundus Images (RFI) as normal or cataract. The proposed scheme comprises several phases: (i) image acquisition and resizing to 224×224 pixels, (ii) feature extraction utilizing a DL- model, (iii) optimal model selection, feature reduction with 50% dropout, and concatenation of serial features, and (iv) classification accompanied by 3-fold cross-validation to validate performance. This study evaluates the efficacy of the suggested DL-tool utilizing both traditional and fused-features. The experimental results of this work demonstrate that the fused-features technique achieves > 98% accuracy when applied to SM-based categorization.
Healthy/Unhealthy Tomato Fruit Grading Using Deep-Learning with Features Fusion M. Jayekumar, S. Arunmozhi, S. Prabha 2024 International Conference on System Computation Automation and Networking Icscan 2024, 2024 Food products automatic grading is a necessary process for appropriate selection, packaging, and marketing. Food grading based on artificial-intelligence (AI) technique for automating the whole process. This work considered the tomato for the study and this procedure is employed to categorize vegetables according to their grade. Proposed work implements a Deep-Learning (DL) based technique to grade the tomato. The stages of this research includes; image collection and resizing, feature extraction with a chosen model, feature reduction with 50% dropout and serial features integration to generate Fused-features Vector (FV), and classification using 3-fold cross validation and confirmation. The efficacy of this tool is evaluated using different DL-model using the chosen image data and this work achieved a detection accuracy >98% when FV based classification is executed using SoftMax. This result confirms that the proposed scheme helps to achieve a better result on the chosen tomato image data.
A Delay Phase Precoder Design For Terahertz Massive MIMO Beyond 5G Communication System R. Valli, Jayekumar M., Madhumitha. A, S. Arunmozhi 2024 International Conference on System Computation Automation and Networking Icscan 2024, 2024 The future of wireless communication systems beyond 5G (B5G) is expected to leverage the terahertz (THz) band to achieve unprecedented data rates. Delay phase precoding in massive MIMO beyond 5G is like making sure each antenna talks at the right time and in the right way to improve communication. The proposed technique leverages the distinctive characteristics of the THz band, such as highly directional transmissions and sparse channel responses, to mitigate channel impairments and enhance signal quality. The design aims to exploit the spatial domain by incorporating delay and phase adjustments, ensuring efficient signal transmission and reception. By leveraging the unique properties of THz frequencies and massive MIMO configurations, the proposed precoder design enhances spectral efficiency and system reliability, thus facilitating the realization of high-data-rate communication systems beyond the capabilities of current 5G networks. This technique helps reduce interference and makes wireless signals stronger and more reliable, which is super important for faster and better connections in the next generation of wireless technology. The impact of hardware constraints, such as phase shifters and analog-to-digital converters (ADCs), on the practical implementation of the proposed precoding algorithm are explored. The proposed delay phase precoder is designed to selects the optimal delay and phase precoding Matrix at the transmitter end. Our simulation results also validates the improvement in performance in terms of spectral efficiency and energy efficiency.
ReDiaSafe: A Novel Approach for Predicting 30-Day Diabetes Patient Readmission Risk Auxilia Michael, Hema Arularasi Murugan, Arthi Manikandan, Jayapratha Natarajan, S. Arunmozhi 2024 International Conference on System Computation Automation and Networking Icscan 2024, 2024 Diabetes is an ailment where life becomes dangerous because most readmissions occur within 30 days since patients do not have any means of awareness towards controlling this health issue. Hospital readmission prevention, especially regarding inpatient or outpatient care, has always been very important in improving patient care, satisfaction, and cost benefits in health care. This paper is on ReDiaSafe as a machine learning tool for predicting the probability of 30-day hospital readmissions in a diabetic patient. It intended to identify useful data attributes and build predictive models that are able to classify readmission risks with accuracy. Thorough research on user input data had been conducted and feature analysis done to elicit significant parameters that influence readmission likelihood. Several machine learning technologies, notably LightGBM and logistic regression; have been applied to classify patients into risk categories: low, medium, and high risk. Our results showed several features with strong relationships to readmission risk, including demographic variables, past admissions, lab results, and medication use patterns. Out of all models tested, the one found most promising with regard to predictions was LightGBM, as this learned well to differentiate risk categories. Furthermore, the combining with an interactive AI chatbot provides individual healthcare suggestions and recommendations based on personalized risk assessments to better engage and support the users. This is further enhanced by the ReDiaSafe tool, which goes a long way in harnessing state-of-the-art machine learning techniques for appalling and really meaningful hospital readmission risk estimates for diabetic patients. This way, better quality of life for the patients is achieved with this method towards life preservation. However, this will also potentially offer general healthcare practitioners segmented interventions towards a much more reduced readmission rate.
ResNet/ResNetV2 Supported Framework for Rice-Plant Disease Detection Using Leaf Data R. Santhosh, S. Arunmozhi, Nilanjan Tewari 2023 International Conference on System Computation Automation and Networking Icscan 2023, 2023 Computer algorithm supported data-analysis is one of the common practices to solve the chosen data-evaluation tasks. Recently, the computer algorithm assisted image-evaluation is emerged as one of the capable research field. The purpose of this research is to use leaf information to create a deep learning scheme to investigate rice plant disease (RD). This approach consists of three stages: (i) gathering and resizing leaf images; (ii) extracting deep features using selected DS; and (iii) using SoftMax based binary classification with 5-fold cross validation. In this work, 1000 photos from each class are examined, and the categorization result that is obtained is confirmed. This study considered the ResNet and ResNetV2 variants for the examination and the achieved result is separately verified for 50, 101 and 152 layered schemes. This investigation task confirms that the ResNet variants provided >91% accuracy and the ResNetV2 variants provided an accuracy of >94%. This demonstrates that the proposed method performs satisfactorily on the selected leaf data, and going forward, real-time data may be taken into consideration to validate the technique's effectiveness for RD detection.
Monitoring Street light using Power Line Carrier Communication (PLCC) & SCADA A. Baskaran, S. Arunmozhi, S. Vishnu 2023 International Conference on System Computation Automation and Networking Icscan 2023, 2023 Streetlights provide illumination at night and provides safety on roads. Conventional monitoring of streetlights involves periodic human inspection which is time consuming, costly and sometimes unsafe. We proposed a remote monitoring and control of streetlights mounted on power transmission line posts using Power Line Carrie r Communication (PLCC) technology. PLC C allows transmission of data over existing power cables and does not require additional infrastructure. A PLCC modem is installed at each streetlight fixture which transmits status updates like lamp ON/OFF, voltage, current drawn etc. to a data concentrator unit via the low frequency power line network. The concentrator unit sends this information to a control center via a wireless or wired backhaul network. Such a solution ensures 24x7 monitoring of streetlights with minimum additional hardware investment. Mathematical models of different PLCC modulation schemes are developed and their performance is analyzed and compared through simulations. These Data were synchronized with SCADA to monitor the Streetlight. Practical implementation issues are also discussed.
Detection of TB from Chest X-ray: A Study with EfficientNet A. Rama, M. P. Rajakumar, N. Mythili, S. Arunmozhi, Mazin Abed Mohammed, V. Rajinikanth 2023 International Conference on System Computation Automation and Networking Icscan 2023, 2023 The lung is one of the prime organs, and any disease in the lung causes mild to severe breathing problems; untreated lung disease will lead to several complications. Tuberculosis (TB) is a lung ailment that needs premature recognition and handling. The primary objective is to employ the deep-learning (DL) based TB detection using chest $X$-rays. Various stages of the proposed scheme consist of (i) data collection and resizing, (ii) DL-supported feature extraction, (iii) binary classification and five-fold cross-validation, and (iv) comparison with earlier results and confirming the merit of the scheme. This research implements EfficientNet (EN) variants to classify the chosen $\\mathrm{X}$-rays into healthy/TB classes using the SoftMax classifier. The proposed scheme with EN_B2 (ENB2) has been successful in providing an accuracy of $96{\\% }$ as far as detection accuracy is considered when compared to other methods. The superiority of the suggested strategy is also confirmed by an analysis using the most recent technology, which confirms the worth of the proposed system on the chosen $\\mathrm{X}$-ray imagery.
CNN Framework for Automatic Segmentation of Breast Section from Thermal Images A. Rama, K.B. Sudeepa, S. Arunmozhi, Mazin Abed Mohammed, Aqeel Ali, V. Rajinikanth 2023 International Conference on System Computation Automation and Networking Icscan 2023, 2023 Breast cancer is considered a severe illness in the female society, and if left untreated, it can be fatal. It is always desirable to detect the BC early utilizing a selected imaging strategy. Thermogram supported breast abnormality detection is one of the recent technique and this gives the necessary information in the form of the distributed thermal pattern. This research aims to implement the Convolutional-Neural-Network (CNN) based segmentation technique to extract breast region from the chosen thermogram. This scheme's multiple stages include: (i) data collecting and processing, (ii) implementation of CNN segmentation to extract the breast, (iii) comparing it to the binary-mask and computing performance metrics, and (iv) performance evaluation and verification of the chosen CNN techniques. Pre-trained CNN segmentations are used in this work to extract the necessary section from the thermogram, and the experimental results show that the VGG-UNet methodology helps to extract the essential region with an enhanced accuracy of 97.260.64% when compared to other CNN approaches.
Artificial Vision Based Smart Urban Parking System Ajanthwin Prabagar, N. Sri Madhavaraja, S. Arunmozhi, K. Suresh Manic 2021 International Conference on System Computation Automation and Networking Icscan 2021, 2021
Healthcare Framework for Risk Analysis of Hypertension Anukirthika T. S., Dellecta Jessy Rashmi R, N. Sri Madhavaraja, S. Arunmozhi, K. Suresh Manic 2021 International Conference on System Computation Automation and Networking Icscan 2021, 2021
A novel complexity PAPR reduction scheme for MIMO-OFDM systems IEEE International Conference on Advances in Engineering Science and Management Icaesm 2012, 2012
RECENT SCHOLAR PUBLICATIONS
Innovative Deep Learning Approaches for Robust Medical Image Denoising: A Study of Contemporary Techniques and Future Prospects B Godavarthi, S Arunmozhi 2025 2nd International Conference on Artificial Intelligence for Innovations … , 2025 2025
Classification of chest radiographs into healthy/pneumonia using Harris-Hawks Algorithm optimized deep-features K Vijayakumar, MNH Maziz, S Ramadasan, S Kadry, S Arunmozhi Discover Computing 28 (1), 115 , 2025 2025
Normal/Cataract Detection in Fundus Image Using Individual and Fused ResNet Features S Arunmozhi, P Arunagiri, S Prabha 2024 International Conference on System, Computation, Automation and … , 2024 2024 Citations: 10
Lightweight Deep-Learning Based Metal/Plastic Trash Detection with Fused Features S Arunmozhi, S Prabha 2024 International Conference on System, Computation, Automation and … , 2024 2024 Citations: 6
ReDiaSafe: A Novel Approach for Predicting 30-Day Diabetes Patient Readmission Risk A Michael, HA Murugan, A Manikandan, J Natarajan, S Arunmozhi 2024 International Conference on System, Computation, Automation and … , 2024 2024
A Delay Phase Precoder Design For Terahertz Massive MIMO Beyond 5G Communication System R Valli, M Jayekumar, S Arunmozhi 2024 International Conference on System, Computation, Automation and … , 2024 2024
Healthy/Unhealthy Tomato Fruit Grading Using Deep-Learning with Features Fusion M Jayekumar, S Arunmozhi, S Prabha 2024 International Conference on System, Computation, Automation and … , 2024 2024 Citations: 1
ResNet/ResNetV2 supported framework for rice-plant disease detection using leaf data R Santhosh, S Arunmozhi, N Tewari 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 9
Automatic concrete surface crack recognition using EfficientNetV2 variants A Rama, R Damaševičius, S Arunmozhi, MA Mohammed, R Hussam, ... 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 6
Monitoring Street light using Power Line Carrier Communication (PLCC) & SCADA A Baskaran, S Arunmozhi, S Vishnu 2023 International Conference on System, Computation, Automation and … , 2023 2023
Lightweight deep-learning based music genre classification: a study A Rama, N Mythili, MP Rajakumar, S Arunmozhi, MA Mohammed, ... 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 2
CNN framework for automatic segmentation of breast section from thermal images A Rama, KB Sudeepa, S Arunmozhi, MA Mohammed, A Ali, V Rajinikanth 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 7
Detection of TB from chest x-ray: A study with EfficientNet A Rama, MP Rajakumar, N Mythili, S Arunmozhi, MA Mohammed, ... 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 17
Design and Implementation of a Sweep Generator for Precise Frequency Control AS Vishnu.S, Baskaran.A METSZET 8 (6), 373-377 , 2023 2023
Multi-Purpose Potential of RFID Technology for Access Control, Asset Tracking, and SOS Messaging Integration. Baskaran.A, Arunmozhi.S, Vishnu.S METSZET 8 (6), 245-251 , 2023 2023
A study on segmentation of leukocyte image with Shannon's entropy NSM Raja, S Arunmozhi, H Lin, N Dey, V Rajinikanth Research Anthology on Improving Medical Imaging Techniques for Analysis and … , 2023 2023 Citations: 12
Retracted D Nigam, SN Patel, PD Raj Vincent, K Srinivasan, S Arunmozhi Biometric Authentication for Intelligent and Privacy‐Preserving Healthcare … , 2022 2022 Citations: 5
[Retracted] Biometric Authentication for Intelligent and Privacy‐Preserving Healthcare Systems D Nigam, SN Patel, PMD Raj Vincent, K Srinivasan, S Arunmozhi Journal of Healthcare Engineering 2022 (1), 1789996 , 2022 2022 Citations: 31
Digital Future of Healthcare VR S. Arunmozhi, Vaddi Satya Sai Sarojini, T. Pavithra, Varsha Varghese, V ... 2021
Automated detection of COVID-19 lesion in lung CT slices with VGG-UNet and handcrafted features S Arunmozhi, VSS Sarojini, T Pavithra, V Varghese, V Deepti, ... Digital future of healthcare, 185-200 , 2021 2021 Citations: 10
MOST CITED SCHOLAR PUBLICATIONS
Automated classification of retinal images into AMD/non-AMD Class—a study using multi-threshold and Gassian-filter enhanced images V Rajinikanth, R Sivakumar, DJ Hemanth, S Kadry, JR Mohanty, ... Evolutionary Intelligence 14 (2), 1163-1171 , 2021 2021 Citations: 47
[Retracted] Biometric Authentication for Intelligent and Privacy‐Preserving Healthcare Systems D Nigam, SN Patel, PMD Raj Vincent, K Srinivasan, S Arunmozhi Journal of Healthcare Engineering 2022 (1), 1789996 , 2022 2022 Citations: 31
Assesment of Tumor in Breast MRI using Kapur's Thresholding and Active Contour Segmentation A Kirthika, NSM Raja, R Sivakumar, S Arunmozhi 2020 international conference on system, computation, automation and … , 2020 2020 Citations: 29
Deep-learning based automated detection of pneumonia in chest radiographs S Arunmozhi, V Rajinikanth, MP Rajakumar 2021 International conference on system, computation, automation and … , 2021 2021 Citations: 20
Detection of TB from chest x-ray: A study with EfficientNet A Rama, MP Rajakumar, N Mythili, S Arunmozhi, MA Mohammed, ... 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 17
ABCD rule implementation for the skin melanoma assesment–a study V Rajinikanth, NSM Raja, S Arunmozhi 2019 IEEE International Conference on System, Computation, Automation and … , 2019 2019 Citations: 15
Image fusion practice to improve the ischemic-stroke-lesion detection for efficient clinical decision making DJ Hemanth, V Rajinikanth, VS Rao, S Mishra, NMS Hannon, ... Evolutionary Intelligence 14 (2), 1089-1099 , 2021 2021 Citations: 14
Machine learning based intrusion detection framework using recursive feature elimination method JDS WS, B Parvathavarthini 2020 International Conference on System, Computation, Automation and … , 2020 2020 Citations: 13
A study on segmentation of leukocyte image with Shannon's entropy NSM Raja, S Arunmozhi, H Lin, N Dey, V Rajinikanth Research Anthology on Improving Medical Imaging Techniques for Analysis and … , 2023 2023 Citations: 12
Normal/Cataract Detection in Fundus Image Using Individual and Fused ResNet Features S Arunmozhi, P Arunagiri, S Prabha 2024 International Conference on System, Computation, Automation and … , 2024 2024 Citations: 10
Automated detection of COVID-19 lesion in lung CT slices with VGG-UNet and handcrafted features S Arunmozhi, VSS Sarojini, T Pavithra, V Varghese, V Deepti, ... Digital future of healthcare, 185-200 , 2021 2021 Citations: 10
ResNet/ResNetV2 supported framework for rice-plant disease detection using leaf data R Santhosh, S Arunmozhi, N Tewari 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 9
Enhancement of energy storage capacity in lithium polymer batteries incorporated with zirconium oxide nano powders D Murugandhan, R Valli, N Senthilkumar, S Arunmozhi Materials Today: Proceedings 37, 1313-1319 , 2021 2021 Citations: 9
CNN framework for automatic segmentation of breast section from thermal images A Rama, KB Sudeepa, S Arunmozhi, MA Mohammed, A Ali, V Rajinikanth 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 7
A novel complexity PAPR reduction scheme for MIMO-OFDM systems L Arunjeeva, S Arunmozhi IEEE-International Conference On Advances In Engineering, Science And … , 2012 2012 Citations: 7
Lightweight Deep-Learning Based Metal/Plastic Trash Detection with Fused Features S Arunmozhi, S Prabha 2024 International Conference on System, Computation, Automation and … , 2024 2024 Citations: 6
Automatic concrete surface crack recognition using EfficientNetV2 variants A Rama, R Damaševičius, S Arunmozhi, MA Mohammed, R Hussam, ... 2023 International Conference on System, Computation, Automation and … , 2023 2023 Citations: 6
Retracted D Nigam, SN Patel, PD Raj Vincent, K Srinivasan, S Arunmozhi Biometric Authentication for Intelligent and Privacy‐Preserving Healthcare … , 2022 2022 Citations: 5
A study on brain tumor extraction using various segmentation techniques S Arunmozhi, G Sivagurunathan, PK Meenakshi, S Karishma, ... 2020 international conference on system, computation, automation and … , 2020 2020 Citations: 5
A study on segmentation of leukocyte image with Shannon’s entropy. Histopathol Image Anal Med Decis Mak 1–27 NSM Raja, S Arunmozhi, H Lin, N Dey, V Rajinikanth 2019 Citations: 5
