Varadarajan, Vijayakumar
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : International Journal of Reconfigurable and Embedded Systems (IJRES)

Exploring the landscape of approximate subtraction methods in ASIC platform Priyadharshni, M.; Thinakaran, Rajermani; Naga Jyothi, Grande; Varadarajan, Vijayakumar; Murthy, C. Srinivasa
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 14, No 2: July 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v14.i2.pp388-397

Abstract

Approximate computing has emerged as a crucial technique in modern computing, offering significant benefits for error-resilient applications. Error resilient applications include signal, image, audio processing, and multimedia. These applications will accept the errored results with some degree of tolerance. This approach allows these applications to process and embrace data that may deviate slightly from perfect accuracy. The utility of approximate computing extends to both hardware and software domains. In hardware, arithmetic units are particularly important, among that approximate subtractors have gained attention for their role in these units. A comparative study was conducted on various approximate subtractors from existing literature, considering structural analysis in all scenarios. These approximate subtractors are coded in Verilog hardware description language (HDL) and synthesized in Synopsys electronic design automation (EDA) Tool using Taiwan Semiconductor Manufacturing Company (TSMC) 65 nm technology. Out of the available choices, approximate subtractor 3 is particularly well-suited for processing higher bit data due to its reduced hardware complexity and minimal error. Notably, it outperforms exact subtractors by achieving a notable reduction of 20% in the area delay product (ADP) and 15% in the power delay product (PDP) as process innovation. These improvements highlight the efficiency and effectiveness of approximate subtractor 3, making it a compelling option for various computing applications which accept the inaccurate results.
Inquisitive biometric feature analysis and implementation for recognition tasks using camouflaged segmentation with AI and IoT Shankarrao Patil, Mahesh; J. Sarode, Harsha; Banubakode, Abhijit; Tukaram Patil, Prakash; Patil, Nutan; Varadarajan, Vijayakumar; Arrova Dewi, Deshinta
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 15, No 1: March 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v15.i1.pp119-129

Abstract

A vital role in reconfigurable and embedded systems which are deployed in smart environements and healthcare monitoring applications is played by human activity recognition (HAR). However, the potential leakage of sensitive user attributes raises serious privacy issues due to collection of data from the end devices and it needs to be transmitted to more powerful platforms for inference. Addressing this key challenge is principally crucial for resource-constrained embedded systems where efficiency of energy is a chief design requirement. The aim of this paper is present an energy-aware, privacy-preserving HAR framework appropriate for low-power embedded platforms. A machine learning–based camouflaged signal segmentation technique is proposed to transform the data collected from the sensor by eliminating sensitive information while preserving activity-relevant features. For characterization of trade off between the energy consumption and accuracy of recognition, parameters are extensively tuned by careful optimization in this proposed model. Experimental evaluations demonstrate that the method significantly reduces the inference of sensitive attributes such as gender, age, height, and weight, with minimal impact on HAR accuracy. Furthermore, the system supports configurable trade-offs between energy usage and classification performance, making it suitable for implementation on low-power embedded devices.