Subramaniam Ganesan

ORCID: 0000-0003-0233-9940
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Embedded Systems Design Techniques
  • Parallel Computing and Optimization Techniques
  • Real-time simulation and control systems
  • Electronic Packaging and Soldering Technologies
  • Real-Time Systems Scheduling
  • Interconnection Networks and Systems
  • Autonomous Vehicle Technology and Safety
  • Sensor Technology and Measurement Systems
  • Vehicular Ad Hoc Networks (VANETs)
  • VLSI and Analog Circuit Testing
  • Analog and Mixed-Signal Circuit Design
  • Blind Source Separation Techniques
  • Image and Object Detection Techniques
  • Experimental Learning in Engineering
  • Manufacturing Process and Optimization
  • Advanced Neural Network Applications
  • Image and Signal Denoising Methods
  • Embedded Systems and FPGA Design
  • Vehicle License Plate Recognition
  • Advanced Adaptive Filtering Techniques
  • Neural Networks and Applications
  • Energy Efficient Wireless Sensor Networks
  • Brain Tumor Detection and Classification
  • Mobile Agent-Based Network Management
  • Distributed and Parallel Computing Systems

Karpagam Academy of Higher Education
2025

Oakland University
2015-2024

Jouf University
2024

Bridge University
2024

Southern Illinois University Carbondale
2024

University of Toledo
2024

Gas Turbine Research Establishment
2023

University of Tabuk
2021-2022

Islamic University of Madinah
2022

University of Rochester
1991-2014

The Internet of Things (IoT) has lately developed into an innovation for developing smart environments. Security and privacy are viewed as main problems in any technology's dependence on the IoT model. Privacy security issues arise due to different possible attacks caused by intruders. Thus, there is essential need develop intrusion detection system attack anomaly identification system. In this work, we have proposed a deep learning-based method Deep Belief Network (DBN) algorithm model...

10.1109/access.2020.2986013 article EN cc-by IEEE Access 2020-01-01

Purpose The purpose of this paper is to provide a brief overview condition based maintenance (CBM) with definitions various terms, some history, recent developments, applications, and research challenges in the CBM domain. Design/methodology/approach article presents insight into strategies provides their respective merits demerits aspects. It then detailed discussion that includes applications methodologies technologies are being implemented field. Finally, it ends open implementing...

10.1108/13552511211281552 article EN Journal of Quality in Maintenance Engineering 2012-10-19

Internet of Things (IoT) technology has recently been applied in healthcare systems as an Medical (IoMT) to collect sensor information for the diagnosis and prognosis heart disease. The main objective proposed research is classify data predict disease using medical images. model a classification prediction that operates two stages. If result from first stage efficient predicting disease, there no need two. In stage, gathered sensors affixed patient's body were classified; then, two,...

10.3390/s22020476 article EN cc-by Sensors 2022-01-09

The paper addresses the general problem of detection vehicle license plates from road scenes, for purpose tracking. It describes an algorithm detecting a plate scene acquired by CCD camera, using image processing techniques, where authors have used Hough transform (HT) line (the shape is defined lines) because it fits well into this application as facilitates selection lines specific areas and orientations within image. This followed brief description system on which has been implemented....

10.1109/rttas.1995.516201 article EN Proceedings - Real-Time Technology and Applications Symposium 2002-11-19

In this study, a survey of multiple sclerosis (MS) classification and segmentation process is presented, which based on magnetic resonance imaging. Knowledge MS lesions gained by determining the number sample in order that lesion development level can be followed precisely; therefore, effects pharmaceuticals medical tests accurately assessed. Accurate recognition images an additionally complex because their changing shapes sizes very difficult to identify anatomical positions various...

10.1049/iet-spr.2019.0543 article EN IET Signal Processing 2020-03-20

One of the major shortcomings existing image dehazing algorithms is in estimating scene transmittance, which has assumed many items algorithms. key assumption been pixel uniformity and smoothness. In this paper, we propose to solve problem using a combination single-pass CNN with graph cut It considers transmittance based on differential pixel-based variance, local global patches energy functions improve transmission map. The proposed algorithm was tested different images evaluated various...

10.1109/access.2021.3059115 article EN cc-by-nc-nd IEEE Access 2021-01-01

Breast cancer (BrCa) is the most common disease in women worldwide. Classifying BrCa image extremely important for finding at an earlier stage and monitoring during treatment. The computer-aided detection methods have been used to interpret improve of screening treatment stages. However, if a new generated treatment, it will not classify correctly. main objective this research images newly images. model performs preprocessing, segmentation, feature extraction, classification. In hybrid...

10.1155/2023/8509433 article EN cc-by International Journal of Intelligent Systems 2023-02-21

Breast cancer (BrC) stands as the most prevalent affecting women globally, comprising 24.5% of all female diagnoses and contributing to 15.0% total cancer-related fatalities. The timely detection precise categorization breast play pivotal roles in enhancing patient prognosis treatment outcomes. main goal is enhance precision classifying mammogram images, thus offering vital support radiology experts diagnosing BrCs. proposed model encompasses several stages, including pre-processing, feature...

10.1016/j.asej.2024.102734 article EN cc-by-nc-nd Ain Shams Engineering Journal 2024-03-14

An expedient transition to lead-free electronics has become necessary for most industry sectors, considering the European directives [The Waste of Electrical and Electronic Equipment (WEEE) directive requires manufacturers reduce disposal waste electrical electronic products by reuse, recycling, other forms recovery. The Restriction Use Certain Hazardous Substances in (RoHS) legislation restricts use lead, as well cadmium, mercury, hexavalent chromium, two halide-containing flame retardants,...

10.1109/tcapt.2005.859353 article EN IEEE Transactions on Components and Packaging Technologies 2005-12-01

Life consumption monitoring is a prognostic method to assess the remaining life of product in its actual life-cycle environment by continuously or periodically measuring product's performance parameters and environmental conditions. This work discusses generic process conduct for electronic products. Two case studies on circuit card assembly an automobile under-hood are presented as application examples process. Temperature vibration were identified dominant factors failure assembly. The...

10.1109/aero.2004.1368151 article EN 2005-02-22

The technologies in the automotive industry are becoming smarter and more advanced than before. Complexity of vehicle electronics is a greater issue often caused by interfaces, connections, displays, user demand features suppliers. This means there great need to supply system updates ensure higher quality improve functionality. paper introduces new solution for that will help OEMs reduce cost, recalls, increase quality, ease take better control vehicles fleet market. consists updating ECUs...

10.1109/eit.2014.6871751 article EN IEEE International Conference on Electro Information Technology 2014-06-01

Today, every electronic control system in the car, such as Instrument Cluster, Infotainment, Anti-lock braking system, Engine Management System, Transmission Control Unit, and Body is a self-sufficient unit with its own sources like ROM, RAM memory, microprocessor or microcontroller, I/O power supply. The idea of automotive domain controller to replace multiple distributed ECUs single powerful central computer multi-core. Multi-core processing technologies integrate into one chip. In...

10.1109/iccit-144147971.2020.9213824 article EN 2020 International Conference on Computing and Information Technology (ICCIT-1441) 2020-09-09

Isolated tracks of single-domain magnetic islands have been fabricated using focused ion beam lithography. Islands were in thin films having either perpendicular or longitudinal anisotropy, and both cases writing reading individual was demonstrated a static write/read tester. Additionally, we investigated the synchronization requirements (write margin) needed for different flavors patterned media. We found that write margin is strongly dependent on switching field distribution head gradient....

10.1109/tmag.2003.816285 article EN IEEE Transactions on Magnetics 2003-09-01

In this paper, we discuss the real time implementation of adaptive noise cancellation based on an improved Wiener filter Texas Instruments TMS320C6713 DSK. Its performance is compared with Leepsilas filter. LabVIEW models are illustrated for using National TI DSP test integration toolkit and filters toolkit. These tested noisy wavelet data sets speech/wave files. Furthermore, a model design LMS Simulink implemented C6713. The profile statistics auto-code generated by Real Time Workshop...

10.1109/eit.2008.4554341 article EN IEEE International Conference on Electro Information Technology 2008-05-01

The process of using the Hough transform (HT) to detect lines in an image involves computation HT for entire image, accumulating votes accumulator array and searching peaks which hold information potential present input image. peak formation generates a butterfly shaped spread array. authors have used this property adaptively define windows interest around detected facilitate description multiple line segments within terms coordinates their end points. developed technique has been employed...

10.1109/icip.1998.723460 article EN 2002-11-27

Whiskers are elongated single crystals of pure tin that have been reported to grow more than 10 mm (250 mils) in length (though they typically 1 or less) and from 0.3 /spl mu/m. diameter typical 1-3 mu/m). spontaneously without an applied electric field moisture (unlike dendrites) independent atmospheric pressure (they vacuum). may be straight, kinked, hooked, forked some hollow. Their outer surfaces usually striated. can nonfilament types which sometimes called lumps flowers. Whisker growth...

10.1109/tcapt.2004.831955 article EN IEEE Transactions on Components and Packaging Technologies 2004-06-01

This study investigates the effects of printed circuit board (PCB) material on interconnect durability lead free assemblies. The assemblies involve soldering various packages (array and peripheral) to FR4, high glass transition temperature (T <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">g</inf> ) FR4 Polyimide (PI) boards using Sn3Ag0.5Cu solder alloy. these materials ranges from 130°C 230°C. Thermomechanical properties, such as elastic...

10.1109/polytr.2005.1596504 article EN 2006-03-21

In this paper, we have evaluated five prediction approaches from two disciplines for condition‐based maintenance. It also includes a case study vehicle tire pressure monitoring as an example application. Main focus of paper is on widely used areas in prediction: (i) statistics, (ii) neural networks. well known that these wide applications forecasting. Statistical and network techniques are very powerful predicting the future states based current previous system or subsystem. Application ARAR...

10.1002/qre.1392 article EN Quality and Reliability Engineering International 2012-03-21

Abstract: The future of transportation is being reshaped by autonomous vehicles (AVs), which promise to revolutionize road safety, accessibility, and environmental sustainability. Central their evolution are advancements in artificial intelligence (AI), enable real-time perception, decision-making, control. This paper explores the trajectory AI AVs, highlighting innovative paradigms such as explainable AI, federated learning, adaptive regulatory frameworks. It delves into development...

10.20944/preprints202408.0974.v1 preprint EN 2024-08-14

In recent times, the majority of e-commerce applications are designed using asymmetric cryptography to assure authentication concerned parties. Conversely, an increasing requirement for mobile devices has geared a shift towards applications. This research work emphasizes that existing protocols, based on RSA not suitable such due their confines in computing power, memory capacity, key sizes and cryptographic support. For reason, efficient protocol resource constrained platforms attain level...

10.1109/icacc.2010.5486928 article EN 2010-01-01

In this paper, driver drowsiness detection algorithm based on the state of eyes which is determined by his iris visibility has been implemented. If remain in one either open or closed longer than expected time as well if not looking straight front, it an indication that drowsy and then system warns driver. System capable detecting with without regular glasses. Matlab image processing tools used to process provided a camera. creates Object using Viola_Jones detect objects such nose, mouth...

10.1109/eit.2018.8500272 article EN 2018-05-01
Coming Soon ...