Jayanthi Sree S

@psgitech.ac.in

Assistant Professor (Senior Grade), Electronics & Communication Engineering
PSG Institute of Technology & Applied Research

Jayanthi Sree S


                     Download Compact PDF  
https://researchid.co/jayanthisrees

RESEARCH, TEACHING, or OTHER INTERESTS

Electrical and Electronic Engineering, Computer Vision and Pattern Recognition, Hardware and Architecture, Artificial Intelligence
9

Scopus Publications

41

Scholar Citations

4

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • Performance Evaluation of ML and DL Approaches for Early Diagnosis of Autism Spectrum Disorder and Development of Autism Care Hub
    Karishma Kaine T, Priyanka Panda, Dhanya Shree M, Jayanthi Sree S, Prithish Goutam S
    2025 International Conference on Next Generation Computing Systems Intelligent System for Sustainable Development Icngcs 2025 Conference Proceedings, 2025
    Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder with social interaction, communication, and repetitive behavior problems. Early diagnosis is the key to facilitating on-time intervention and enhancing patient outcomes. This paper is an evaluation of comparative performance of different machine learning (ML) and deep learning (DL) algorithms for early ASD diagnosis based on behavioural and demographic information from AQ-10 screening tests. Supervised machine learning algorithms like K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, XGBoost, and Logistic Regression are compared with unsupervised cluster algorithms like K-Means, Agglomerative, Spectral, Gaussian Mixture Models (GMM), and BIRCH. Deep learning models consisting of Dense layers, Dropout, Batch Normalization, Long Short-Term Memory (LSTM), Residual connections, and Sigmoid activation functions are investigated. Random Forest Classifier is used for feature selection, which asserts that behavioural markers are the most powerful predictors for ASD, and demographic indicators are not very influential. The comparative analysis indicates the strengths and weaknesses of ML and DL algorithms, and the best performing model is chosen, and that model is used to develop an Autism Care Hub platform for early screening, diagnosis, and continuous monitoring of ASD. Experimental results show the efficacy of ensemble ML techniques and DL networks and uncover their potential in real-world clinical deployment.
  • Deep Learning Technique for COVID 19 Prediction using CT Scan Images
    Raghul M, Sharaj K, Ragul Sankar S, Jayanthi Sree S
    Proceedings of the 2nd International Conference on Electronics and Sustainable Communication Systems Icesc 2021, 2021
    Corona Disease Virus (COVID-19) is a rapidly spreading contagious viral disease that causes respiratory contaminations and is currently generating a worldwide medical crisis. It has caused a massive influence on people's lives, general well-being, and the global economy. Henceforth, it is critical to straightaway analyze the positive cases in order to keep the illness from spreading further and to regard infected patients as fast as could really be expected. Both patients and specialists will be benefitted by the early recognizable capability of outrageous COVID-19 by utilizing chest CT to examine biomedical images. RT-PCR (switch record polymerase chain response) based tests help to identify COVID-19, which has numerous limits. In this work, different CNN based Classifier model methodologies are utilized to follow the presence of COVID-19 from chest CT filter images of patients. In true indicative situations, a profound CNN-based methodology could be amazingly valuable in accomplishing quick COVID-19 testing. By utilizing irregularity data obtained from sifted images, image expansion enhances the number of profitable models for creating the CNN model. The proposed model has a grouping exactness of 95% for CT examines utilizing this strategy. With picture expansion, CT check pictures have an affectability of 94.78%and a particularity of 95.98%. The trial results were contrasted with ResNet-18, ResNet-50, and VGG-16 models, with freely available datasets containing CT images.
  • Retraction: Texture based Clustering Technique for Fetal Ultrasound Image Segmentation
    S Jayanthi Sree, V Kiruthika, C Vasanthanayaki
    Journal of Physics Conference Series, 2021
    Segmentation of fetal ultrasound image is an important and necessary task in the automation of fetal biometric measurement. Fetal ultrasound image segmentation is tedious because of the fuzzy nature and textured appearance of fetal structures. Hence, texture based Clustering is proposed for segmenting fetal ultrasound images. Clustering is performed using texture properties of the images which are used for segmenting ultrasound images of fetus. Texture based clustering technique can be used for segmenting all fetal anatomies specifically abdomen, the boundaries of which are very vague and difficult to delineate. Synthetic, simulated ultrasound images and 120 ultrasound fetal images were used for validating the method achieving an accuracy of 90%.
  • Traffic Sign Recognition using Deeplearning for Autonomous Driverless Vehicles
    A Suriya Prakash, D Vigneshwaran, R Seenivasaga Ayyalu, S Jayanthi Sree
    Proceedings 5th International Conference on Computing Methodologies and Communication Iccmc 2021, 2021
    Recently, the smart world, smart cars, and so on plays a major role. To ensure Traffic Safety, the development of smart cars requires the detection and recognition of traffic signs. The algorithm is the extended work on the classical LeNet-5 CNN model. The proposed technique makes use of Gabor based kernel followed by a normal convolutional kernel after the pooling layer. The optimizer technique used here is the Adams method. Hue, Saturation Value color space features have a speed of detection is faster and low suffering from illumination. The proposed technique for traffic sign recognition is evaluated using the German Traffic Sign Recognition Benchmark. The proposed technique gives an accuracy of nearly 99%.
  • Fetal ultrasound image segmentation using fuzzy connectedness algorithm
    S. Jayanthi Sree, C. Vasanthanayaki
    Advances in Mathematics Scientific Journal, 2020
    A BSTRACT . Biometric measurements are important for fetal growth monitoring and anomaly detection. Manual measurement is time consuming and cumbersome in fetal ultrasound scans. Hence, Fuzzy Connectedness segmentation is proposed for segmenting fetal ultrasound images. The Fuzzy Connectedness Segmentation adapts to the fuzzy nature of the ultrasound images and this is a semi-automatic technique. The method could be used for specific anatomical segmentation for fetal biometric measurements with the use of seed points. The segmentation algorithm was validated on simulated ultrasound images and 300ultrasound fetal images achieving an accuracy of 90%.
  • Texture-Based Fuzzy Connectedness Algorithm for Fetal Ultrasound Image Segmentation for Biometric Measurements
    S. Jayanthi Sree, C. Vasanthanayaki
    Advances in Intelligent Systems and Computing, 2020
  • De-Speckling of Ultrasound Images Using Local Statistics-Based Trilateral Filter
    S. Jayanthi Sree, C. Vasanthanayaki
    Journal of Circuits Systems and Computers, 2019
    Speckle noise in ultrasound images is a major hindrance for the automation of segmentation, detection, classification and measurements of region of interest, to assist clinician for diagnosing pathologies. Speckle noise occurs due to constructive and destructive interference of the echo signals reflected from the target and has a granular appearance. Various techniques have been devised for speckle reduction. Most of these techniques are based on adaptive filters, wavelet transform and anisotropic diffusion filters. In this paper, a new speckle reduction technique based on the trilateral filter and local statistics of the image has been developed. The local speckle content of the image influences the trilateral filtering. The trilateral filter is a robust edge preserving filter which considers the similarity of neighboring regions in terms of adjacency, intensity and edge details. Hence, the new method preserves the finer details of the ultrasound images in the process of filtering speckle noise. The proposed technique is validated using synthetic, simulated and real-time clinical ultrasound images. Comparison of the proposed technique with the existing speckle removal algorithms in terms of quality metrics such as MSE, PSNR, UQI, SSI, FoM has been made and best results are obtained for the proposed technique.
  • Ultrasound fetal image segmentation techniques: A review
    S. Jayanthi Sree, C. Vasanthanayaki
    Current Medical Imaging Reviews, 2019
    Background: This paper reviews segmentation techniques for 2D ultrasound fetal images. Fetal anatomy measurements derived from the segmentation results are used to monitor the growth of the fetus. </P><P> Discussion: The segmentation of fetal ultrasound images is a difficult task due to inherent artifacts and degradation of image quality with gestational age. There are segmentation techniques for particular biological structures such as head, stomach, and femur. The whole fetal segmentation algorithms are only very few. Conclusion: This paper presents a review of these segmentation techniques and the metrics used to evaluate them are summarized.
  • Edge preserving algorithm for impulse noise removal using FPGA
    S. Jayanthi Sree, S. Ashwin, S. Aravind Kumar
    2012 International Conference on Machine Vision and Image Processing Mvip 2012, 2012
    Impulse noise is caused by malfunctioning pixels in camera sensors, faulty memory locations in hardware, or transmission in a noisy channel. Several distortions limit the quality of digital images during image acquisition, formation, storage and transmission. Impulse noise is introduced in the images from some digital sources due to acquisition error or transmission error or a problem in the ground processing systems. In this paper, an efficient edge preserving impulse noise removal technique has been proposed. The algorithm has been simulated on MATLAB and implemented using FPGA. The results show that the proposed technique preserves the finer edge details of the image during the impulse noise removal process. The technique has high performance in terms of qualitative analysis as well as visual quality using PSNR and MAE. Also, synthesis results prove that the design is of low computational complexity and lesser hardware cost.

RECENT SCHOLAR PUBLICATIONS

  • Texture based clustering technique for fetal ultrasound image segmentation
    SJ Sree, V Kiruthika, C Vasanthanayaki
    Journal of Physics: Conference Series 1916 (1), 012014 , 2021
    2021
    Citations: 3
  • Fetal ultrasound image segmentation using fuzzy connectedness algorithm
    SJ SREE, C VASANTHANAYAKI
    Advances in Mathematics: Scientific Journal 9 (10), 8293-8301 , 2020
    2020
    Citations: 2
  • Texture-based fuzzy connectedness algorithm for fetal ultrasound image segmentation for biometric measurements
    S Jayanthi Sree, C Vasanthanayaki
    Soft Computing for Problem Solving: SocProS 2018, Volume 1, 91-103 , 2019
    2019
    Citations: 4
  • Fetal Standard Plane Detection in Freehand Ultrasound Using Multi Layered Extreme Learning Machine
    SJ Sree, C Vasanthanayaki
    Advances in Computerized Analysis in Clinical and Medical Imaging, 135-142 , 2019
    2019
  • De-speckling of ultrasound images using local statistics-based trilateral filter
    S Jayanthi Sree, C Vasanthanayaki
    Journal of Circuits, Systems and Computers 28 (09), 1950150 , 2019
    2019
    Citations: 4
  • Ultrasound fetal image segmentation techniques: a review
    SJ Sree, C Vasanthanayaki
    Current Medical Imaging Reviews 15 (1), 52-60 , 2019
    2019
    Citations: 11
  • Study of the contemporary motion estimation techniques for video coding
    S Ashwin, SJ Sree, SA Kumar
    Int. J. Recent Technol. Eng.(IJRTE), ISSN, 2277-3878 , 2013
    2013
    Citations: 5
  • Edge preserving algorithm for impulse noise removal using FPGA
    SJ Sree, S Ashwin, SA Kumar
    2012 International Conference on Machine Vision and Image Processing (MVIP … , 2012
    2012
    Citations: 11
  • Jitter removal in images and video sequences using robust decision based adaptive spatio temporal median algorithm
    SA Kumar, SJ Sree, S Ashwin, MJ Sharma, S Dhakshnamoorthy
    2010 International Conference on Information, Networking and Automation … , 2010
    2010
    Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

  • Ultrasound fetal image segmentation techniques: a review
    SJ Sree, C Vasanthanayaki
    Current Medical Imaging Reviews 15 (1), 52-60 , 2019
    2019
    Citations: 11
  • Edge preserving algorithm for impulse noise removal using FPGA
    SJ Sree, S Ashwin, SA Kumar
    2012 International Conference on Machine Vision and Image Processing (MVIP … , 2012
    2012
    Citations: 11
  • Study of the contemporary motion estimation techniques for video coding
    S Ashwin, SJ Sree, SA Kumar
    Int. J. Recent Technol. Eng.(IJRTE), ISSN, 2277-3878 , 2013
    2013
    Citations: 5
  • Texture-based fuzzy connectedness algorithm for fetal ultrasound image segmentation for biometric measurements
    S Jayanthi Sree, C Vasanthanayaki
    Soft Computing for Problem Solving: SocProS 2018, Volume 1, 91-103 , 2019
    2019
    Citations: 4
  • De-speckling of ultrasound images using local statistics-based trilateral filter
    S Jayanthi Sree, C Vasanthanayaki
    Journal of Circuits, Systems and Computers 28 (09), 1950150 , 2019
    2019
    Citations: 4
  • Texture based clustering technique for fetal ultrasound image segmentation
    SJ Sree, V Kiruthika, C Vasanthanayaki
    Journal of Physics: Conference Series 1916 (1), 012014 , 2021
    2021
    Citations: 3
  • Fetal ultrasound image segmentation using fuzzy connectedness algorithm
    SJ SREE, C VASANTHANAYAKI
    Advances in Mathematics: Scientific Journal 9 (10), 8293-8301 , 2020
    2020
    Citations: 2
  • Jitter removal in images and video sequences using robust decision based adaptive spatio temporal median algorithm
    SA Kumar, SJ Sree, S Ashwin, MJ Sharma, S Dhakshnamoorthy
    2010 International Conference on Information, Networking and Automation … , 2010
    2010
    Citations: 1
  • Fetal Standard Plane Detection in Freehand Ultrasound Using Multi Layered Extreme Learning Machine
    SJ Sree, C Vasanthanayaki
    Advances in Computerized Analysis in Clinical and Medical Imaging, 135-142 , 2019
    2019