Machine Learning-Driven Cryptography Automating the Design of Robust Encryption Algorithms Subhashini Peneti Communications on Applied Nonlinear Analysis, 2025 By automating the creation of strong encryption algorithms, the application of machine learning (ML) to cryptography offers a revolutionary way to improve data security. In order to find weaknesses and improve cryptography systems—thereby enabling quicker, more effective encryption mechanisms—this research investigates the application of diverse machine learning approaches. Our goal is to create powerful encryption systems that can withstand more complex dangers, such as hazards associated with quantum computing and sophisticated cyberattacks, by utilizing algorithms that can evaluate patterns within large datasets. The equilibrium between algorithmic performance and cryptographic security is also evaluated in this work to guarantee that solutions maintain their efficacy and efficiency. Furthermore, we emphasize responsible AI methods in cryptographic applications, which addresses ethical problems. The ultimate goal of this research is to advance the rapidly expanding field of AI-driven cryptography by offering a foundation for upcoming developments that will greatly increase the security of private data against illegal access.
Algebraic Topology in Modern Cryptography: A Cross-Disciplinary Perspective Riya Raju Panamerican Mathematical Journal, 2025 In order to clarify how topological ideas might improve cryptographic techniques, this study explores the relationship between algebraic topology and contemporary cryptography. The work provides new insight into cryptographic diversity by examining algebraic structures and their uses. It suggests that rearranging cryptographic pieces using algebraic binary relations can result in systems that are safer and more efficient. The approach demonstrates the ramifications of using topological concepts to address current cryptographic problems by combining theoretical studies with real-world applications. The study also emphasises the value of interdisciplinary approaches by exposing possible developments in data integrity and secure communications. The results highlight how crucial it is to incorporate mathematical frameworks into cryptography, which could lead to the development of innovative cryptographic solutions in a world that is becoming more digital. This approach promotes more multidisciplinary research by establishing algebraic topology as an essential tool for improving the resilience and versatility of cryptographic systems.
Semantic segmentation of urban environments: Leveraging U-Net deep learning model for cityscape image analysis T. S. Arulananth, P. G. Kuppusamy, Ramesh Kumar Ayyasamy, Saadat M. Alhashmi, M. Mahalakshmi, K. Vasanth, P. Chinnasamy Plos One, 2024 Semantic segmentation of cityscapes via deep learning is an essential and game-changing research topic that offers a more nuanced comprehension of urban landscapes. Deep learning techniques tackle urban complexity and diversity, which unlocks a broad range of applications. These include urban planning, transportation management, autonomous driving, and smart city efforts. Through rich context and insights, semantic segmentation helps decision-makers and stakeholders make educated decisions for sustainable and effective urban development. This study investigates an in-depth exploration of cityscape image segmentation using the U-Net deep learning model. The proposed U-Net architecture comprises an encoder and decoder structure. The encoder uses convolutional layers and down sampling to extract hierarchical information from input images. Each down sample step reduces spatial dimensions, and increases feature depth, aiding context acquisition. Batch normalization and dropout layers stabilize models and prevent overfitting during encoding. The decoder reconstructs higher-resolution feature maps using "UpSampling2D" layers. Through extensive experimentation and evaluation of the Cityscapes dataset, this study demonstrates the effectiveness of the U-Net model in achieving state-of-the-art results in image segmentation. The results clearly shown that, the proposed model has high accuracy, mean IOU and mean DICE compared to existing models.
IoT-Enabled Smart Recycling Vending Machine Using Raspberry Pi for Waste Management B. Gopi, P. Dass, P. G. Kuppusamy, Anuradha Balasubramaniam, Madona B Sahaai 8th International Conference on Electronics Communication and Aerospace Technology Iceca 2024 Proceedings, 2024 In the modern world, recycling requires efficient strategies for waste management. Due to environmental concerns, recycling, a crucial component of contemporary society, is expected to rise dramatically worldwide. The waste recycling system assists in the separation of recyclable waste and non-recyclable waste, rewards recyclers, and inspires others to recycle. This work aims to create an IoT-enabled vending machine for trash and waste recycling that improves recycling rates, fosters environmental consciousness, and streamlines waste management via real-time data analytics. This garbage management candy machine labels garbage containers with consistent marks. The barcode shows whether the Garbage may be recycled or not. These bags are put on a conveyor belt, where a barcode reader scans them to identify the waste within. Servo motor components push the bags into the appropriate bins at the end of the conveyor. The remainder of the waste can garbage is thrown out, and the user is given money based on the weight of recyclable waste.
Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model T. S. Arulananth, S. Wilson Prakash, Ramesh Kumar Ayyasamy, V. P. Kavitha, P. G. Kuppusamy, P. Chinnasamy IEEE Access, 2024 There is a substantial worldwide effect, both in terms of disease and death, that is caused by pediatric pneumonia, which is a disorder that affects children under the age of five. Even while Streptococcus pneumoniae is the most prevalent agent responsible for this sickness, it may also be brought on by other bacteria, viruses, or fungi. An efficient approach utilizing deep-learning methods to forecast pediatric pneumonia reliably using chest X-ray images has been developed. The current study presents an updated version of the DenseNet-121 deep-learning model developed for identifying scans of pediatric pneumonia. The batch normalization, maximum pooling, and dropout layers introduced into the standard model were done so to improve its accuracy. The activations of the preceding layers are scaled and normalized using batch normalization, leading to a mean value of zero and a variance of one. This helps decrease internal variability during training, which speeds up the training process, promotes model stability, and improves the model’s overall capacity to generalize. Max pooling is a beneficial technique for reducing the number of model parameters, making the model more computationally effective. Meanwhile, dropout is a preventative measure against overfitting by decreasing the co-dependence of neurons. As a result, the network acquires more durable and adaptive features. Classifying instances of pediatric pneumonia with the help of the proposed model resulted in an exceptional accuracy rate of 97.03%.
The Development of Blockchain Technology with the Internet of Things: Transforming the Way We Manage Assets, Communicate Securely Online, and the Supply Chain P. G. Kuppusamy, Monisha M, K. A. Arokiaraj, D. Parameswari, Badi Alekhya, Vijaya Vardan Reddy S P Proceedings of International Conference on Emerging Technologies and Innovation for Sustainability Emergin 2024, 2024 In conjunction with the Internet of Things (IoT), the rapid development of blockchain technology is bringing about a revolution in the administration of assets, the provision of secure online communication, and the procedures involved in supply chain management. This study investigates the potential synergy between blockchain technology and the Internet of Things (IoT), focusing on how the combination of these two technologies can improve transparency, security, and efficiency across a variety of industries. Since blockchain technology offers a distributed and unchangeable record that guarantees the authenticity and provenance of data, it is ideally suited for the management of assets in a manner that is open and transparent. In the meantime, Internet of Things devices produce enormous volumes of data that can be safely shared and recorded on blockchain, which ultimately makes real-time monitoring and traceability much easier to accomplish. Among the applications that are investigated in this study are smart contracts, which are able to automate transactions; secure identity verification systems; and enhanced supply chain management, which increases visibility and responsibility. Furthermore, the paper analyzes the difficulties that are associated with putting this technology into practice, including scalability, energy consumption, and interoperability on a variety of different platforms. In the end, this paper highlights the revolutionary impact of combining blockchain technology with the Internet of Things (IoT). It presents a roadmap for future innovations and applications that have the potential to redefine how we manage assets, ensure secure communications, and streamline supply chain processes.
A long-reach radio over free space optics (Ro-FSO) system using hybrid orthogonal frequency division multiplexing (OFDM)-multibeam concept with enhanced detection Peramandai Govindasamy Kuppusamy, Kotteswaran Rajkumar, Rajagopal Maheswar, Soundarapandian Sheeba Rani, Iraj Sadegh Amiri Journal of Optical Communications, 2023 This paper focuses on designing of a 10 Gbit/s-10GHz hybrid Orthogonal frequency division multiplexing (FDM) based Radio over Free Space Optics (Ro-FSO) transmission link using optical single sideband modulation format and its performance has been compared using a different number of transmission beams. The proposed link has been simulated and compared using 1-beam, 2-beam, and 4-beam in the system. We show that by using the 4-beam system in the OFDM-Ro-FSO link, a 3000 m range has been achieved reliably, which a notable improvement when compared to previous work is. Also, we show an improved performance of the system by using an enhanced detection mechanism using a Square root module (SRm) at the receiver side.
Different modulation schemes for direct and external modulators based on various laser sources Hazem M. El-Hageen, P.G. Kuppusamy, Aadel M. Alatwi, M. Sivaram, Z. Ahamed Yasar, Ahmed Nabih Zaki Rashed Journal of Optical Communications, 2023 Different types of laser source modulation techniques have been used in various applications depending on the objective. As optical systems extract the laws and the best solutions from experiments and simulations, the present study uses simulation software with different modulation types so the output signals can be compared. The modulators used are Mach-Zehnder, which is an external modulator, and electro-absorption modulator and laser rate equation modulator, which are direct modulators. All these types have an optical link multimode (MM) fiber with a photodiode in the receiver end that can be modeled. The input and output signals are analyzed using different types of modulations.
Analysis, design and development of patch antenna for S-band applications International Journal of Control Theory and Applications, 2016
Implementation of soft error tolerant filters for error detection and correction using ECC Global Journal of Pure and Applied Mathematics, 2016
High speed pipeline architecture using mixture of domino logic gates Global Journal of Pure and Applied Mathematics, 2016
Design of nano square spiral antenna in terahertz region for solar energy harvesting International Journal of Control Theory and Applications, 2016
Biomedical signal processing using memristor emulator CT FIR filter International Journal of Control Theory and Applications, 2016
Specific absorption rate (SAR) assessment and measurement of temperature change on human head due to radiations by mobile phone antenna International Journal of Applied Engineering Research, 2015
Design of level shifter using dual cascode voltage switch for low power application International Journal of Applied Engineering Research, 2015
Review of light fidelity technology for wireless communication International Journal of Applied Engineering Research, 2015
A new power gating scheme using multi-mode power switches for static power reduction International Journal of Applied Engineering Research, 2015
A VLSI based framework for iterative and adaptive based image filter for impulse noise removal International Review on Computers and Software, 2013
RECENT SCHOLAR PUBLICATIONS
Automated ASD Screening from Children's Facial Images Using MTCNN-Enhanced DenseNet121 with LIME Interpretability K Sravani, P Kuppusamy 2025 IEEE 2nd International Conference for Women in Computing (InCoWoCo), 1-6 , 2025 2025
EHO-Q-LGAN: an EHO-based Q-learning GAN for the timely diagnosis of diabetic retinopathy M Vadduri, P Kuppusamy IEEE Access , 2025 2025 Citations: 5
Probabilistic luminance estimation and optimized gamma correction for Wireless capsule endoscopy KY Devi, JS Priyan, PG Kuppusamy, DB Thiyam, V Venugopal, ... Biomedical Signal Processing and Control 104, 107558 , 2025 2025 Citations: 7
HAMF: A Novel Hierarchical Attention-Based Multi-Modal Fusion Model for Parkinson’s Disease Classification and Severity Prediction AR Palakayala, P Kuppusamy, D Kothandaraman, G Archana, J Gera IEEE Access 13, 81252-81278 , 2025 2025 Citations: 9
Deep Learning Model for COPD Classification Using XiResNet-50 with Explainable AI YSSK Assish, P Kuppusamy 2025 International Conference on Data Science and Business Systems (ICDSBS), 1-6 , 2025 2025
E-CNN: Ensemble-Based Convolutional Neural Network for Animal Species Identification P Kuppusamy, NC CA 2025 International Conference on Data Science and Business Systems (ICDSBS), 1-6 , 2025 2025 Citations: 2
OEL: Optimized Ensemble Learning for Datadriven Rice Yield Prediction P Kuppusamy, DA Devi, BUS Manoj, TK Gundu 2025 International Conference on Data Science and Business Systems (ICDSBS), 1-6 , 2025 2025 Citations: 1
A Synergistic Approach of Coffee Leaf Pathology Segmentation with Self-Attentive U-Net P Kuppusamy, P Pranavi, R Jyothsna, BS Sahana, L Meghana 2025 IEEE International Conference on Emerging Technologies and Applications … , 2025 2025
Analysis of reason to global warming based on heat pattern using hyperspectral imaging: Artificial intelligence application TS Arulananth, M Mahalakshmi, PG Kuppusamy, NR Palepu, ... Remote Sensing in Earth Systems Sciences 7 (4), 379-388 , 2024 2024 Citations: 3
IoT-enabled smart recycling vending machine using Raspberry Pi for waste management B Gopi, P Dass, PG Kuppusamy, A Balasubramaniam, MB Sahaai 2024 8th International Conference on Electronics, Communication and … , 2024 2024 Citations: 1
A qualitative and quantitative approach using machine learning and non-motor symptoms for Parkinson’s disease classification. A hierarchical study AR Palakayala, P Kuppusamy Applied Computer Science 20 (3), 171-191 , 2024 2024 Citations: 3
Optimized deep convolutional neural network for autism spectrum disorder detection using structural MRI and DTPSO K Sravani, P Kuppusamy IEEE Access 12, 110035-110051 , 2024 2024 Citations: 30
CNNAH: Modified CNN to Arrhythmia Heatbeat Classification using ECG signals A Vadlamudi, SS Reddy, G Chandana 2024 Asia Pacific Conference on Innovation in Technology (APCIT), 1-8 , 2024 2024 Citations: 1
EL-RFHC: Optimized ensemble learners using RFHC for intrusion attacks classification P Kuppusamy, D Kapadia, EG Manvitha, S Dhahbi, C Iwendi, MI Khan, ... Ain Shams Engineering Journal 15 (7), 102807 , 2024 2024 Citations: 2
AttentionLUNet: A hybrid model for Parkinson’s disease detection using MRI brain AR Palakayala, P Kuppusamy IEEE Access 12, 91752-91769 , 2024 2024 Citations: 18
Semantic segmentation of urban environments: Leveraging U-Net deep learning model for cityscape image analysis TS Arulananth, PG Kuppusamy, RK Ayyasamy, SM Alhashmi, ... Plos one 19 (4), e0300767 , 2024 2024 Citations: 56
GEWO: An Efficient Prioritised Task Scheduling in Cloud Fog Computing Environment SK Medishetti, G Swapna, K Anusha, GR Karri 2024 International Conference on Wireless Communications Signal Processing … , 2024 2024 Citations: 34
MAO: An efficient resource utilization of task scheduling in cloud fog environment K Anusha, SK Medishetti, P Archana, GR Karri 2024 International Conference on Wireless Communications Signal Processing … , 2024 2024 Citations: 59
Parkinson’s disease classification based on enhanced ensemble learning and brain MRI AR Palakayala Majlesi Journal of Electrical Engineering 18 (1), 283-309 , 2024 2024 Citations: 6
Classification of paediatric pneumonia using modified DenseNet-121 deep-learning model TS Arulananth, SW Prakash, RK Ayyasamy, VP Kavitha, PG Kuppusamy, ... IEEE Access 12, 35716-35727 , 2024 2024 Citations: 107
MOST CITED SCHOLAR PUBLICATIONS
A study and comparison of OLSR, AODV and TORA routing protocols in ad hoc networks P Kuppusamy, K Thirunavukkarasu, B Kalaavathi 2011 3rd International Conference on Electronics Computer Technology 5, 143-147 , 2011 2011 Citations: 135
Classification of paediatric pneumonia using modified DenseNet-121 deep-learning model TS Arulananth, SW Prakash, RK Ayyasamy, VP Kavitha, PG Kuppusamy, ... IEEE Access 12, 35716-35727 , 2024 2024 Citations: 107
A Comparative Study on 4G and 5G Technology for Wireless Applications PGK B.G.Gopal IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) 10 (6 … , 2015 2015 Citations: 97
Different modulation schemes for direct and external modulators based on various laser sources HM El-Hageen, PG Kuppusamy, AM Alatwi, M Sivaram, ZA Yasar, ... Journal of Optical Communications 44 (s1), s697-s706 , 2024 2024 Citations: 96
The Engagement of Hybrid Ultra High Space Division Multiplexing with Maximum Time Division Multiplexing Techniques for High-Speed Single-Mode Fiber Cable Systems MRTPY I. S. Amiri, P. G. Kuppusamy, Ahmed Nabih Zaki Rashed, P. Jayarajan Journal of Optical Communications 4 (4), 333-338 , 2019 2019 Citations: 84
Tricore photonic crystal fibre based refractive index sensor for glucose detection A Natesan, KP Govindasamy, TR Gopal, V Dhasarathan, AH Aly IET Optoelectronics 13 (3), 118-123 , 2019 2019 Citations: 84
Deep learning based energy efficient optimal timetable rescheduling model for intelligent metro transportation systems P Kuppusamy, S Venkatraman, CA Rishikeshan, YCAP Reddy Physical Communication 42, 101131 , 2020 2020 Citations: 74
Survey and challenges of Li-Fi with comparison of Wi-Fi P Kuppusamy, S Muthuraj, S Gopinath 2016 International Conference on Wireless Communications, Signal Processing … , 2016 2016 Citations: 68
MAO: An efficient resource utilization of task scheduling in cloud fog environment K Anusha, SK Medishetti, P Archana, GR Karri 2024 International Conference on Wireless Communications Signal Processing … , 2024 2024 Citations: 59
Data privacy and confidentiality in healthcare applications of IoT-enabled wireless sensor networks G Premi, P Solainayagi, C Srinivasan, PG Kuppusamy 2023 Second International Conference on Smart Technologies for Smart Nation … , 2023 2023 Citations: 58
Semantic segmentation of urban environments: Leveraging U-Net deep learning model for cityscape image analysis TS Arulananth, PG Kuppusamy, RK Ayyasamy, SM Alhashmi, ... Plos one 19 (4), e0300767 , 2024 2024 Citations: 56
Human abnormal behavior detection using CNNs in crowded and uncrowded surveillance–A survey P Kuppusamy, VC Bharathi Measurement: Sensors 24, 100510 , 2022 2022 Citations: 56
Enhancing ocular healthcare: deep learning-based multi-class diabetic eye disease segmentation and classification M Vadduri, P Kuppusamy IEEe Access 11, 137881-137898 , 2023 2023 Citations: 52
Optimized traffic control and data processing using IoT P Kuppusamy, R Kalpana, PV Venkateswara Rao Cluster Computing 22 (Suppl 1), 2169-2178 , 2019 2019 Citations: 44
Job scheduling problem in fog-cloud-based environment using reinforced social spider optimization P Kuppusamy, NMJ Kumari, WY Alghamdi, H Alyami, R Ramalingam, ... Journal of Cloud Computing 11 (1), 99 , 2022 2022 Citations: 41
Refractive index sensor using dual core photonic crystal fiber–glucose detection applications S Maheswaran, P Kuppusamy, S Ramesh, T Sundararajan, P Yupapin Results Phys 11 (3), 577-578 , 2018 2018 Citations: 37
Human action recognition using CNN and LSTM-RNN with attention model P Kuppusamy, C Harika Int. J. Innov. Technol. Explor. Eng 8, 1639-1643 , 2019 2019 Citations: 35
GEWO: An Efficient Prioritised Task Scheduling in Cloud Fog Computing Environment SK Medishetti, G Swapna, K Anusha, GR Karri 2024 International Conference on Wireless Communications Signal Processing … , 2024 2024 Citations: 34
Optimized deep convolutional neural network for autism spectrum disorder detection using structural MRI and DTPSO K Sravani, P Kuppusamy IEEE Access 12, 110035-110051 , 2024 2024 Citations: 30
A comparative analysis of transformer based models for figurative language classification T Junaid, D Sumathi, AN Sasikumar, S Suthir, J Manikandan, R Khilar, ... Computers and Electrical Engineering 101, 108051 , 2022 2022 Citations: 30