Adaptive Edge aware and K-means cluster-based Manhattan regularization for deblurring (EA-KCMRD) D. Sangeetha, P. Deepa, S. Padmapriya, S.R. Mugunthan Imaging Science Journal, 2026 Imperfections in imaging systems and object motion introduce blur in images, leading to an inaccurate analysis. Users are typically unaware of the blurring present in an image, and for accurate analysis, the blur in the images needs to be removed using blind image deblurring. Blind image deblurring serves as a viable method for addressing various sources of blur without prior knowledge of the blur kernel. This paper proposes an edge-aware and K-means cluster-based Manhattan regularization for deblurring (EA-KCMRD). The proposed blind image deblurring algorithm addresses the real-world and synthetic blur by integrating explicit and implicit methods for salient edge selection. The proposed EA-KCMRD introduces a hybrid edge selection framework that combines adaptive Canny edge detection with mutually guided image filtering (explicit strategy) and K-means clustering with Manhattan regularization (implicit strategy). This integration preserves both prominent and structural details, making the kernel estimation process more robust under noise and low-contrast conditions. Furthermore, EA-KCMRD employs a multi-scale framework that supports image deblurring for different image sizes across diverse datasets. Experimental results have validated the feasibility of the proposed method on RealBlur-R, GoPro, HIDE, RS-Blur, and MC-Blur dataset. The proposed EA-KCMRD method has been compared with state-of-the-art techniques using objective metrics and subjective visual perception of deblurred images to demonstrate its effectiveness.
Single-Nucleus RNA Sequencing Data for Cell-Type-Specific Gene Prioritization and Predictive Modeling of Autism Spectrum Disorder S Padmapriya, Sree S Jayanthi, N Iswarya, B Vijayalakshmi, C Ramkumar Artificial Intelligence in Detecting Autism, 2026 A complicated neurodevelopmental disorder, autism spectrum disorder (ASD) is marked by substantial genetic and phenotypic variability. Although many potential genes linked to ASD have been found by traditional genome-wide investigations, validation and clinical application are still difficult. Single-nucleus RNA sequencing (snRNA-seq) has made it feasible to investigate gene expression at the level of specific brain cell types. In this study, we developed cell-type-specific predictive models for ASD using snRNA-seq data from the prefrontal and anterior cingulate cortex of ASD and normal brains. Using edgeR, BASiCS, and DEsingle, we were able to identify differentially expressed (DE) genes that are exclusive to 17 different types of brain cells. Stochastic gradient boosting models for the categorization of ASD were then constructed using these DE genes. According to our findings, certain cell types—such as AST-PP astrocytes, L2/3, L4, and L5/6-CC excitatory neurons—show clear dysregulation and superior predictive accuracy. Additionally, we identified considerable overlap with known SFARI ASD genes by prioritizing ASD-associated genes within each cell type. Functional enrichment analysis highlighted the cellular heterogeneity of ASD by identifying unique dysregulated pathways in various cell types. This technique offers novel ideas on the underlying pathophysiology of ASD along with promising biomarkers for diagnostic and treatment targeting.
Hybrid Parallel Prefix Adders for Error-Tolerant Applications: Design and Implementation S. Balasaraswathi, S. Padmapriya 2025 2nd International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems Itech Secom 2025, 2025 In error-tolerant applications such as multimedia processing, machine learning, and image filtering, a trade-off between accuracy and performance can enable significant energy and delay savings. Approximate computing offers a powerful design paradigm by intentionally sacrificing computational precision to improve efficiency. This paper presents a class of Hybrid Parallel Prefix Adders (HyPPA) where the Least Significant Bits (LSBs) are computed using approximate adder architectures—such as Lower-part OR Adder (LOA), Copy Adder, and Error-Tolerant Adder Type 1 (ETA-1)—while the Most Significant Bits (MSBs) are computed using accurate parallel prefix adders (PPAs) like Kogge-Stone or Brent-Kung. These hybrid designs are synthesized, implemented, and evaluated using 90nm CMOS technology. Results show up to 57% power reduction, 65% energy savings, and minimal accuracy degradation, making the proposed architectures ideal for energy-efficient and error-resilient digital systems.
Design of a Twin-Mode Adaptive Fir Filter Using Distributed Arithmetic Technique Ashvika D, Deepshikaa K, Harita M, Sivaani Srinivasan Gurusami, S Padmapriya 2025 International Conference on Next Generation Computing Systems Intelligent System for Sustainable Development Icngcs 2025 Conference Proceedings, 2025 This paper proposes an Optimized Adaptive Reconfigurable (OAR) FIR Filter Architecture for speech signal processing, addressing the need for low-power, area-efficient, and high-performance adaptive filtering. The design supports two dynamically switchable modes: a conventional LMS-based filter for precise adaptation and a multiplierless Distributed Arithmetic (DA) mode for resource efficiency. Mode selection is driven by a real-time decision mechanism based on input amplitude and filter coefficient thresholds. Functional validation was performed through simulation, while hardware performance metrics like power and area were evaluated to be reduced by 30% (approx.).
High Throughput and Less Error Approximate Compressor Design for Partial Product Reduction in Multipliers Vidhyalakshmi M, Padmapriya. S International Conference on Smart Systems for Electrical Electronics Communication and Computer Engineering Icsseec 2024 Proceedings, 2024 Multiplication plays a major role in the signal and image processing applications. The reduction of partial products was done using full adders and half adders, which increases the computation complexity, area and power. This paper presents a highly efficient four to two approximate compressor with less error probability and applied in multipliers of various configurations. The proposed approximate compressor is implemented in the design of Wallace tree multiplier. Experimental results shows increase in performance, less area and less power compared with adder based partial product reduction, exact compressor and state of art approximate compressors.
Optimized Vedic Multiplier N*N using adder approximations and Modified Carry look ahead adders Gayatri V, Amirtha T, S. Padmapriya Proceedings of 2024 International Conference on Science Technology Engineering and Management Icstem 2024, 2024 This paper introduces an innovative approach to enhancing Vedic multipliers using approximate full adders with 2X1 multipliexers. The study compares this novel design with traditional multipliers, highlighting its superior performance in terms of area utilization, processing speed, and power efficiency. Furthermore, the research extends the application of this design by implementing it with 4-bit approximate carry look-ahead adders, showcasing its adaptability and scalability across different bit widths. The experimental findings demonstrate the significant advantages of the proposed approach over conventional designs, establishing it as a promising solution for achieving efficient arithmetic operations in digital circuits.
Sustainable Low-Power ALU and Multiplexer based AI Accelerator Design and Optimization Using Cadence S. Padmapriya, Sarveshware S, Durai Murugan S, K Shree Harini, Raga Vendran R M International Conference on Smart Systems for Electrical Electronics Communication and Computer Engineering Icsseec 2024 Proceedings, 2024 In today's fast-paced world, where time is of the essence and AI-generated content is becoming increasingly prevalent, the demand for efficient hardware accelerators is paramount. Accelerators are crucial for enhancing AI algorithms, requiring components like Arithmetic Logic Units, SRAM registers, memory elements, and multiplexers. Balancing performance with low power consumption is essential, driving researchers to focus on optimizing power, area, and frequency. To address these challenges, we propose leveraging Pass Transistor Logic to enhance power efficiency and reduce the Power-Delay Product and area in AI accelerators. By modifying components such as the ALU and Multiplexer blocks, we achieve significant reductions in power consumption and time delay. Our findings indicate substantial power savings (e.g., from 4.89mW to 2.5mW for the ALU block) and reduced delays (e.g., from 6 sec to 0.799 sec for the ALU block), showcasing the effectiveness of Pass Transistor Logic in improving both power efficiency and performance. This work contributes to the development of low-power, high-efficiency AI accelerators, aligning with the demands of our modernized society.
Efficient Fault Detection Methods in Printed Circuit Boards using Machine Learning Techniques V Anbumani, S Padmapriya, R. RajaRaja, N Vikram, S Ranjith, B T Abhinav 2024 15th International Conference on Computing Communication and Networking Technologies Icccnt 2024, 2024 Printed circuit boards (PCBs) becoming more complex as technology advances, adding new components and changing their architecture. One of the most crucial quality control procedures is PCB surface inspection since even little flaws in a signal trace may have a significant detrimental effect on the system. It has always been difficult to determine the pass/fail criteria in traditional machine vision systems based on small failure samples, despite the advancements in sensor technology. Suggesting a sophisticated PCB inspection method built on a skip-connected convolutional auto encoder to address these issues suggested to enhance the PCB inspection system by using convolutional autoencoders. The original, fault-free photos and the damaged ones were used to train the deep autoencoder model. The defect location was then located by comparing the decoded images with the input image. Using proper image augmentation to enhance the model training performance in order to get over the tiny and uneven dataset in the early phases of production. Printed circuit boards, or PCBs, are essential parts of electronic gadgets and are very significant to the electronics sector. While ensuring PCB quality and reliability is crucial, manual inspection techniques are often labour and error-intensive. The proposed novel machine learning (ML)-based method for identifying PCB defects demonstrates a significant improvement in detection rates compared to traditional methods, offering a promising solution for the electronics manufacturing industry.
Mitigation of Cyber Attacks in Software Defined Networking Framework Kiruthika V, Padmapriya S, Ganga M, Anupriya V 2023 1st International Conference on Advances in Electrical Electronics and Computational Intelligence Icaeeci 2023, 2023 Day by Day the communication technology are evolving with new emerging technologies for sharing the information across the globe. The Fifth Generation is an effective technology to share the information by efficient utilization of spectrum. Since the Fifth Generation is an application oriented technology, Software Defined Networking is an efficient framework which paves the way for controlling the applications in 5G network. This Software Defined Networking framework divides both control plane and the data plane which programmatically controls all the networking operations. It is highly vulnerable to severe security based attacks and the possible major attacks are Denial of Service (DoS) Attack and Man In The Middle (MITM) attack. The proposed NAND Logic Based IP Address Encryption Decryption Algorithm (NLBIAEDA) defends MITM attack by encrypting and decrypting the IP address in both sender side and the receiver side. To mitigate the Denial of Service attack, the proposed Acceptance Based DOS Mitigation (ABDM) algorithm mitigates the DOS attack and reduces the network traffic automatically. The simulation results show that the IP address is more secure and the time of encryption and the time of decryption is reduced due to the usage of NAND gates which defends both Man in The Middle Attack and Denial of Service Attack.
Anti-Theft Alarm System and Tracking in Coal Mines Roupesh R, Sujith Sivan R, Swatha M, Jagadeeswari M, Padmapriya S 2023 9th International Conference on Advanced Computing and Communication Systems Icaccs 2023, 2023 Coal is a valuable resource and extraction of coal is highly complex, time-consuming, and costlier. The work and the workforce needed to extract this is also huge and as we all know coal is extracted from underground mines or open pit mines. The recent news states that these trucks which contain coal as raw materials or the finished products are being hijacked by duplicating the number plates. So, to control this robbery a robust system must be created. Our idea is to create a robust system using RFID (Radio Frequency Identification). Using an RFID module, the original number of the vehicle is extracted and checked with the number plate number. If both matches the vehicle is allowed inside or else the vehicle is not allowed inside and the vehicle is caught and the alert is sent to the authorized person who oversees the coal mine.
Design of Reconfigurable Reversible Low Power Adders Sangeetha T, Sahithya S, Mouliga P, S. Padmapriya, M. Jagadeeswari, V. Anbumani Proceedings of the 3rd International Conference on Artificial Intelligence and Smart Energy Icais 2023, 2023
COVID Detection using Deep Learning M. Jagadeeswari, S. Padmapriya, Shri Lalitha G, Suvetha S., Sharmila D 4th International Conference on Inventive Research in Computing Applications Icirca 2022 Proceedings, 2022
An Early Alert System for Sleep Apnea Disorder Using IoT B Vijayalakshmi, S Anusha, S Padmapriya, C Ramkumar, S Prasanth Bharadhwaaj, R Priyanka Icdcs 2020 2020 5th International Conference on Devices Circuits and Systems, 2020
Design of hardware trojan detection architecture in digital circuits Journal of Advanced Research in Dynamical and Control Systems, 2019
Smart Tribal Alert: An IoT Enabled Solution for Wildlife Intrusion Detection S Padmapriya, PS Abarna, S Pavalarajan, CM Devi 2025 6th International Conference on Electronics and Sustainable … , 2025 2025 Citations: 1
Development of Dual Cluster Head Selection Mechanism in WSN Based on IoT for Energy-Efficient Data Transmission in Smart City Applications R Arunachalam, D Jayashree, KN Tripathi, A Punitha, S Padmapriya, ... AD HOC & SENSOR WIRELESS NETWORKS 61 (1-2), 29-61 , 2025 2025
Development of Recommender Systems for Better Services and Products using Data Science S Padmapriya, R Thamizhamuthu, S Jagadeesh, DMK Selvi, MA Shariff 2023 4th International Conference on Electronics and Sustainable … , 2023 2023 Citations: 3
A Centralized Blockchain Architecture with Optimum Sharing V Ramasamy, S Padmapriya, G Kavitha, D Lekha 2023 8th International Conference on Communication and Electronics Systems … , 2023 2023 Citations: 1
Effective data aggregation in WSN for enhanced security and data privacy B Murugeshwari, SA Sabatini, L Jose, S Padmapriya arXiv preprint arXiv:2304.14654 , 2023 2023 Citations: 30
Timer Entrenched Baited Scheme to Locate and Remove Attacks in MANET. S Padmapriya, R Shankar, R Thiagarajan, N Partheeban, A Daniel, ... Intelligent Automation & Soft Computing 35 (1) , 2023 2023 Citations: 3
Applications of Machine Learning and Deep Learning in Smart Agriculture R Krishnamoorthy, R Thiagarajan, S Padmapriya, I Mohan, S Arun, ... Machine Learning Algorithms for Signal and Image Processing, 371-395 , 2022 2022 Citations: 12
A scholastic study of energy-efficient routing protocol for body area network in IoT ecosystem BS Liya, S Arun, S Padmapriya AIP Conference Proceedings 2519 (1), 030073 , 2022 2022
IOT TESTBED WITH A DISTRIBUTED DENIAL OF SERVICE ATTACK USING NETWORK SECURITY SPDAPDS Arun, R Krishnamoorthy, S Padmapriya NeuroQuantology 20 (10), 3060-3069 , 2022 2022
IoT based rainfall surveillance system with sensor integrated infrastructure VK Singh, MM Kumar, J Yuvaraj, T Rubeshkumar, S Kumar, ... 2022 7th International Conference on Communication and Electronics Systems … , 2022 2022 Citations: 5
Regressive based classifier analytics for the mechanism of cryptosystems security using EHE scheme KCK Chakrapani, P Malathi, U Iniyan, R Thiagarajan, S Padmapriya, ... 2022 8th International Conference on Smart Structures and Systems (ICSSS), 1-5 , 2022 2022 Citations: 5
Convolution neural network based Discrete Social Sharing Emotions on Covid-19 G Saritha, S Famitha, P Malathi, A Priyadharshini, S Arun, S Padmapriya 2022 8th International Conference on Smart Structures and Systems (ICSSS), 1-6 , 2022 2022
Preservation of higher accuracy computing in resource-constrained devices using deep neural approach R Manikandan, T Mathumathi, C Ramesh, S Arun, R Krishnamoorthy, ... 2022 Second International Conference on Artificial Intelligence and Smart … , 2022 2022 Citations: 11
Proposed GA algorithm with H-heed protocol for network optimization using machine learning in wireless sensor networks AD Gupta, K Sathiyasekar, R Krishnamoorthy, S Arun, R Thiyagarajan, ... 2022 Second International Conference on Artificial Intelligence and Smart … , 2022 2022 Citations: 21
Optimal route design for sensor network with effective area with coverage S Padmapriya, S Soundararajan, S Arun, YW Su, R Krishnamoorthy Neuroquantology 2, 3047-3059 , 2022 2022 Citations: 1
A High Energy Efficient Approach for Handling Dynamic Network Using AOMDV Routing Protocol R Thiagarajan, B Gunasundari, S Padmapriya, BS Liya, R Shankar, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 1
Medical Image Processing from Large Datasets Using Deep Learning P Kalyani, S Srivastava, A Reddyprasad, R Krishnamoorthy, S Arun, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 6
Task Clustering and Scheduling in Fault Tolerant Cloud Using Dense Neural Network S Ramachandra, S Srivastava, M Roshini, S Arun, S Padmapriya, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 4
Preserving privacy scheme using data-caac mechanism in e-health based on hybrid edge computing S Padmapriya, R Shankar, R Thiagarajan, S Arun, BS Liya, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 2
Categorizing the heart syndrome condition by predictive analysis using machine learning approach R Krishnamoorthy, BS Liya, S Arun, S Padmapriya, R Thiagarajan 2021 3rd international conference on advances in computing, communication … , 2021 2021 Citations: 23
MOST CITED SCHOLAR PUBLICATIONS
Effective data aggregation in WSN for enhanced security and data privacy B Murugeshwari, SA Sabatini, L Jose, S Padmapriya arXiv preprint arXiv:2304.14654 , 2023 2023 Citations: 30
A survey on cloud computing security threats and vulnerabilities SVK Kumar, S Padmapriya Int. J. Innov. Res. Electr. Electron. Instrum. Control Eng 2 (1), 622-625 , 2014 2014 Citations: 26
Categorizing the heart syndrome condition by predictive analysis using machine learning approach R Krishnamoorthy, BS Liya, S Arun, S Padmapriya, R Thiagarajan 2021 3rd international conference on advances in computing, communication … , 2021 2021 Citations: 23
Proposed GA algorithm with H-heed protocol for network optimization using machine learning in wireless sensor networks AD Gupta, K Sathiyasekar, R Krishnamoorthy, S Arun, R Thiyagarajan, ... 2022 Second International Conference on Artificial Intelligence and Smart … , 2022 2022 Citations: 21
Detection of stomach cancer using deep neural network in healthcare sector K Lokesh, S Srivastava, MP Kumar, S Arun, S Padmapriya, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 15
Applications of Machine Learning and Deep Learning in Smart Agriculture R Krishnamoorthy, R Thiagarajan, S Padmapriya, I Mohan, S Arun, ... Machine Learning Algorithms for Signal and Image Processing, 371-395 , 2022 2022 Citations: 12
E-TRACKING SYSETEM FOR MUNICIPAL SOLID WASTE MANAGEMENT USING RFID TECHNOLOGY SM Dr.S.PadmaPriya, G. Aruna Devi, L.S.Kavitha International Journal of Advanced Research in Electronics, Communication … , 2014 2014 Citations: 12
Preservation of higher accuracy computing in resource-constrained devices using deep neural approach R Manikandan, T Mathumathi, C Ramesh, S Arun, R Krishnamoorthy, ... 2022 Second International Conference on Artificial Intelligence and Smart … , 2022 2022 Citations: 11
Management of encrypted data and de-duplication of big data in cloud computing S Srivastava, R Thiagarajan, R Krishnamoorthy, S Arun, S Padmapriya 2021 3rd international conference on advances in computing, communication … , 2021 2021 Citations: 9
A survey on healthcare monitoring system using wireless sensor networks (WSN) K Premkumar, S Padmapriya, R Priyadharshani, K Priyanka Int. J. Pure Appl. Math 118 (14), 485-492 , 2018 2018 Citations: 9
An efficient recommender system for predicting study track to students using data mining techniques SVK Kumar, S Padmapriya International Journal of Advanced Research in Computer and Communication … , 2014 2014 Citations: 8
Wireless sensor networks to monitor Glucose level in blood VSD 3. Dr .S. Padmapriya, V.Abhishek Chowdary International Journal of Advancements in Research & Technology, 2 (4) , 2013 2013 Citations: 8
Medical Image Processing from Large Datasets Using Deep Learning P Kalyani, S Srivastava, A Reddyprasad, R Krishnamoorthy, S Arun, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 6
IoT based rainfall surveillance system with sensor integrated infrastructure VK Singh, MM Kumar, J Yuvaraj, T Rubeshkumar, S Kumar, ... 2022 7th International Conference on Communication and Electronics Systems … , 2022 2022 Citations: 5
Regressive based classifier analytics for the mechanism of cryptosystems security using EHE scheme KCK Chakrapani, P Malathi, U Iniyan, R Thiagarajan, S Padmapriya, ... 2022 8th International Conference on Smart Structures and Systems (ICSSS), 1-5 , 2022 2022 Citations: 5
Metaclassifiers for predicting the robotic navigational performance S Padmapriya, S., Jimreeves, J.S.R., Kalaiselvi, P., Nageswaran, A., Arun International Journal of Innovative Technology and Exploring Engineering … , 2019 2019 Citations: 5
Enhanced cyber security for big data challenges S Padmapriya, S., Partheeban, N., Kamal, N., Suresh, A., Arun International Journal of Innovative Technology and Exploring Engineering … , 2019 2019 Citations: 5
Task Clustering and Scheduling in Fault Tolerant Cloud Using Dense Neural Network S Ramachandra, S Srivastava, M Roshini, S Arun, S Padmapriya, ... 2021 3rd International Conference on Advances in Computing, Communication … , 2021 2021 Citations: 4
Conversion of non-audible murmur to normal speech through Wi-Fi transceiver for speech recognition based on GMM model TR Kumar, S Padmapriya 2nd International Conference on Electronics and Communication Systems (ICECS … , 2015 2015 Citations: 4
Conversion of non-audible murmur to normal speech through Wi-Fi transceiver for speech recognition based on GMM model GR Kumar, T.R., Padmapriya, S., Bai, V.T., Beulah Devamalar, P.M., Suresh 2nd International Conference on Electronics and Communication Systems, ICECS … , 2015 2015 Citations: 4
