Sandeep Saini

ORCID: 0000-0002-8906-8639
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Low-power high-performance VLSI design
  • Human Pose and Action Recognition
  • Hand Gesture Recognition Systems
  • Analog and Mixed-Signal Circuit Design
  • Natural Language Processing Techniques
  • Context-Aware Activity Recognition Systems
  • Topic Modeling
  • CCD and CMOS Imaging Sensors
  • VLSI and FPGA Design Techniques
  • Gait Recognition and Analysis
  • Chaos-based Image/Signal Encryption
  • Speech and dialogue systems
  • Neural Networks and Applications
  • VLSI and Analog Circuit Testing
  • Smart Agriculture and AI
  • Plant-Microbe Interactions and Immunity
  • Quantum-Dot Cellular Automata
  • Cryptographic Implementations and Security
  • Quantum Computing Algorithms and Architecture
  • Stock Market Forecasting Methods
  • Electromagnetic Compatibility and Noise Suppression
  • Energy Load and Power Forecasting
  • Advancements in PLL and VCO Technologies
  • Plant Disease Management Techniques
  • Handwritten Text Recognition Techniques

Schaeffler (Germany)
2025

LNM Institute of Information Technology
2015-2024

Banasthali University
2024

Christian Medical College & Hospital
2017-2024

Christian Medical College
2017-2024

Myanmar Institute of Information Technology
2020

RKDF University
2018-2019

National Bureau of Agriculturally Important Microorganisms
2017

Malaviya National Institute of Technology Jaipur
2015

Institute of Engineering
2014

Predicting the correct values of stock prices in fast fluctuating high-frequency financial data is always a challenging task. A deep learning-based model for live predictions aimed to be developed here. The authors' have proposed two models different applications. first one based on Fast Recurrent Neural Networks (Fast RNNs). This used price time this work. second hybrid learning by utilising best features FastRNNs, Convolutional Networks, and Bi-Directional Long Short Term Memory predict...

10.1049/cit2.12052 article EN cc-by-nc CAAI Transactions on Intelligence Technology 2021-06-24

Language translation is one task in which machine definitely lagging behind the cognitive powers of human beings. Statistical Machine Translation conventional ways solving problem translation. This method requires huge data sets and performs well on similar grammar structured language pairs. In recent years, Neural (NMT) has emerged as an alternate way addressing same issue. this paper, we explore different configurations for setting up a System Indian Hindi. We have experimented with eight...

10.1109/infrkm.2018.8464781 article EN 2018-03-01

<div class="section abstract"><div class="htmlview paragraph">Accurate estimation of the state charge (SoC) battery cells is crucial for efficient management and longevity systems, particularly in electric vehicles renewable energy storage. This paper presents an approach utilizing a nonlinear autoregressive exogenous (NARX) model to estimate SoC cells. The proposed method leverages hyperparameter optimization determine optimal configuration neural network, including number...

10.4271/2025-01-8210 article EN SAE technical papers on CD-ROM/SAE technical paper series 2025-04-01

Machine Translation pertains to translation of one natural language other by using automated computing. The main objective is fill the gap between two different languages speaking people, communities or countries. In India, we have multiple and hugely diverse scripts, hence scope need immense. this paper, focus on current scenario research in machine India. We reviewed various important Systems (MTS) presented preliminary comparison core methodology as used them.

10.1109/cict.2015.123 article EN 2015-02-01

A potential antagonist, Bacillus sp. strain A(5) F was isolated from soybean rhizosphere following in vitro dual plate screening. The bacterium displayed strong inhibitory activity against stem rot pathogen, Sclerotinia sclerotiorum. culture supernatant of completely suppressed the mycelial growth indicating that suppression due to presence antifungal compounds filtrate. filtrate also other phytopathogenic fungi including Fusarium oxysporum and Macrophomina phaseolina, suggesting a broad...

10.1002/jobm.201100463 article EN Journal of Basic Microbiology 2012-02-23

The paper presents a novel approach of measuring blood pressure using Photoplethysmography (PPG). It is non-invasive, cuffless and painless technique that deploys infrared light to detect small variation in volume the tissues with each cardiac cycle. Few specific features (viz. systolic upstroke time (ST), diastolic (DT) delay between peak (T1)) waveform obtained via this were examined correlated arterial 22 subjects two age groups i) 18-25 years ii) 26-50 years. was observed there good...

10.1109/tenconspring.2014.6863037 article EN 2014 IEEE REGION 10 SYMPOSIUM 2014-04-01

<div class="section abstract"><div class="htmlview paragraph">This paper demonstrates a data-driven methodology for the system-level design of high-power traction motor drives in modern battery electric vehicles. With immense growth vehicles this transformative decade, expected time to develop and market these powertrain components is becoming significantly shorter than internal combustion engines. This rising demand further complicated due more stringent cost, efficiency power...

10.4271/2024-01-2172 article EN SAE technical papers on CD-ROM/SAE technical paper series 2024-04-09

In interconnect bus coding techniques the presence of buffers is often ignored. Buffers are used to restore signal level affected by parasitics. However have a certain switching time that contribute overall delay. Further transition happens in interconnects also crosstalk Thus delay due combined effect both buffer and Here replacement with Schmitt trigger has been proposed for same purpose restoration. Due lower threshold voltage can rise early large noise margin schmitt helps reducing...

10.1109/tencon.2009.5396104 article EN 2009-11-01

Agriculture has been practiced in conventional ways for centuries and supported with mechanical systems the last few decades. With evolution of robotic equipment sensors, researchers are focusing on introducing smart farming. In this paper, we propose improved algorithms infection detection leaves field classification targeting a heterogeneous system. Image processing methods have used plants to calculate percentage crops elementary machine learning algorithm k-means clustering classifying...

10.1504/ijshc.2019.101602 article EN International Journal of Social and Humanistic Computing 2019-01-01

India is a multilingual and multi-script country large part of its population speaks more than one language. It has been noted that such speakers switch between languages while communicating informally. The code-mixed language very common in informal communication social media, extracting sentiments from these sentences challenging task. In this work, we have worked on sentiment classification for the most pairs i.e. Hindi-English. conventional analysis techniques designed single don't...

10.1109/indicon49873.2020.9342241 article EN 2021 IEEE 18th India Council International Conference (INDICON) 2020-12-10

India is a multilingual country and large portion of its population speaks more than one language. It has been observed that such speakers switch between the languages while communicating informally. Such code-mixed sentences not only contain words from different but also grammar rules in single sentence. In this work, we have focused on coded-mixed language pair i.e. Punjabi-English. informal communication social media, very popular, analyzing sentiment mixed challenging task. We verified...

10.1109/icccs49678.2020.9277309 article EN 2020 5th International Conference on Computing, Communication and Security (ICCCS) 2020-10-14

In VLSI interconnect buffers are used to restore the signal level affected by parasitics. However have a certain switching time that contributes overall delay. Further transitions occur in interconnects also contribute crosstalk Thus delay is due combined effect of both buffer and this work replacement with Schmitt trigger proposed for same purpose restoration. Due lower threshold voltage can rise early large noise margin helps reducing glitches as well. Simulation results shows approach...

10.1109/vlsi.design.2010.53 article EN 2010-01-01

Reversible logic has received great importance in the recent years because of its feature reduction power dissipation. It finds applications low digital designs, quantum computing, nanotechnology, DNA computing etc. Large number researches are currently ongoing on sequential and combinational circuits using reversible logic. Decoders one most important used Different approaches have been proposed for their design. In this article, we a novel design 2:4 decoder it to build 3:8 decoder. The...

10.1109/icspcom.2015.7150670 article EN 2015-03-01

This paper presents an improved multiplexer based encoder for flash analog-to-digital converters. The proposed is designed using 2 : 1 multiplexers. can be configured to operate on thermometer-code with reduced resolution without any extra overhead. shows the re-configurable property i.e. higher as lower encoder. self used in adaptive ADCs. Gray codes are mainly glitch free fast circuit design and communication error correction digital modulation techniques. Simulation results indicate that...

10.1109/ispacs.2013.6704602 article EN International Symposium on Intelligent Signal Processing and Communication Systems 2013-11-01

<div class="section abstract"><div class="htmlview paragraph">The performance of an electromechanical actuator largely depends on the control strategy implemented and calibrated. The purpose this paper is to analyze shortcomings existing methods practices involved in manual tuning a Proportional-Integral-Derivative (PID) controller Brushless DC (BLDC) motor therefore, propose improved auto-tuning method. investigated 3-stage cascaded PID, where outermost loop position-based...

10.4271/2023-01-0435 article EN SAE technical papers on CD-ROM/SAE technical paper series 2023-04-07

Human Activity Recognition (HAR) is a significant challenge in research. Traditional pattern recognition methods have faced limitations terms of classification efficiency. In this paper, novel deep learning architecture, Convolutional-Bidirectional Long Short-Term Memory and Gated Recurrent Unit (ConvBiLSTM-GRU) has been proposed. The model comprises Convolutional Neural Network (CNN), Bidirectional Unit, fully connected layer. We created compared our dataset with available datasets, i.e.,...

10.1109/gcaiot61060.2023.10385107 article EN 2023-12-10

In Digital Signal Processing, the convolution and deconvolution with a very long sequence is ubiquitous in many application areas. The basic blocks de-convolution implementation are multiplier divider. They consume much of time. This paper presents direct method computing discrete linear convolution, circular deconvolution. approach easy to learn because similarities multiplication two numbers. most significant aspect proposed development divider architecture based on Ancient Indian Vedic...

10.1109/ecticon.2014.6839756 article EN 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) 2014-05-01

Reversible logic has received great importance in the recent years because of its in-cogitative feature reduction power dissipation which is key requirement low digital designs. It wide applications advanced computing, CMOS design, optical information processing, DNA bio information, quantum computing and nanotechnology. In this paper a new reversible gate proposed called SG gate. The encoding decoding been explained with help an algorithm example. This proposes full adder, N bit adder N*N...

10.1109/iscit.2014.7011941 article EN 2014-09-01

The performance of any processor solely depends upon its power, area and delay. In order to get an effective processor, delay should be less. Division is always considered bulky one the most difficult operations in arithmetic hence all implementations division algorithms VLSI architecture have higher orders time space complexities. Vedic Mathematics on other hand offers a new holistic approach mathematics. Its range extends from concrete values numerical computation abstract aspects dynamics...

10.1109/ecticon.2014.6839877 article EN 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) 2014-05-01
Coming Soon ...