Dr NITHYASHRI J

@srmist.edu.in

Assistant Professor, Engineering & Technology
SRM Institute of Science and Technology

Dr NITHYASHRI J


                  Download Compact PDF  
https://researchid.co/nithyashri
, received her Doctoral degree from Sathyabama university, Chennai. Published more than 25 research articles in various International/ National Journals and Conferences. She has more than 21 years of teaching experience in various Engineering Colleges. Her research area includes Computer Vision, Image Processing and Pattern Recognition.

EDUCATION

Ph.D., (2008–2016) , Department of Computer Science & Engineering,
Sathyabama University, Chennai, India.
M.E., (2003 – 2005), Department of Computer Science & Engineering,
Sathyabama University, Chennai, India.
FIRST CLASS
BE., (1996–2000), Department of Computer Science & Engineering,
VRS College of Engineering & Technology,University of Madras, Chennai, India.
FIRST CLASS

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Vision and Pattern Recognition, Human-Computer Interaction
13

Scopus Publications

192

Scholar Citations

5

Scholar h-index

5

Scholar i10-index

Scopus Publications

  • An intelligent classification of emotions in human speech using CNN and LSTM
    J. Nithyashri, Harsh Goel, Manvendra Singh Hada
    Aip Conference Proceedings, 2026
  • Augmenting Convolution Neural Networks with Graph Models (GNN) for Skin Disease Classification
    Bhagya Lakshmi Raghupathy, Nithyashri J
    Proceedings of the 6th International Conference on Inventive Research in Computing Applications Icirca 2025, 2025
    Skincare diagnosis classification represents a vital component of dermatology which strives to create automatic diagnosis systems and deliver timely correct medical decisions to healthcare providers. CNNs already prove effective for image-based classification and achieve excellent results while maintaining difficulty in processing complex image relationships. The analysis studies how Graph Neural Networks with CNNs create improvements to skin disease classification functions. This hybrid model draws additional power from both CNNs for extracting features and GNNs for recognizing spatial relationships and relational dependencies with the purpose of improving classification results and reliability. The designed system handles dermatological images to detect skin diseases which generates medical knowledge for healthcare staff to make swift diagnoses and start treatment earlier. The research describes the creation and testing of an integrated CNNGNN solution which demonstrates potential as an automatic system for skin disease detection.
  • VisionAid: Enhancing Accessibility for the Visually Impaired with YOLO and gTTS
    Bhagya Lakshmi Raghupathy, J Nithyashri
    Proceedings of International Conference on Visual Analytics and Data Visualization Icvadv 2025, 2025
    Daily environment navigating and accessing visual information are critical problems for people with vision disabilities. To reduce this discrepancy VisionAid, an assistive application was introduced to make visually challenged person have better accessibility via integration of YOLO for real-time object detection and gTTS which is library used for text-to-speech conversion. It recognizes objects, speaks text aloud and promotes good navigation skills that improve mobility and independence. VisionAid augments vision loss with modern technologies like GPS and SLAM for navigation, rather than traditional aids. This paper presents VisionAid as an end-to-end solution, fills the gaps in existing models and brings more autonomy to its users.
  • Dual-Attention Graph Neural Networks for SpatioTemporal Crime Forecasting and Patrol Optimization
    Mudit Srivastava, Sanya Raj, Nithyashri J
    2025 7th International Workshop on Artificial Intelligence and Education Waie 2025, 2025
    The prediction of urban crime is crucial for proactive law enforcement and the allocation of resources. We introduce an innovative Dual-Attention Graph Neural Network (DA-GNN) designed for spatio-temporal crime forecasting and the optimization of patrol strategies. This model effectively captures spatial relationships through Graph Attention Networks (GATs) and improves upon on temporal patterns via a parallel Long Short-Term Memory (LSTM) pathway, our previous research. A dual-attention approach dynamically adjusts the significance of influential neighbors and historical time intervals. To improve precision, we include external covariates such as weather conditions, holidays, and seasonal influences. Additionally, we utilize Quantum-behaved Particle Swarm Optimization (QPSO) to facilitate the automation of hyperparameter tuning. Although the model is trained on a recent subset (January-March 2023) for computational feasibility, it leverages the full 2001-2023 dataset for graph construction, seasonal pattern extraction, and feature enrichment. DA-GNN consistently outperforms classical baselines (ARIMA, random forests), deep learning models (LSTM, CNNLSTM), and prior GNN-based approaches. Finally, the model produces interpretable attention maps and district-level risk visualizations, supporting ethical deployment and data-driven patrol strategy design.
  • INTEGRATING AI AND OR FOR REAL-TIME OPTIMIZATION IN DIGITAL TWIN ECOSYSTEMS AND METAVERSE ENGINEERING
    Nithyashri J., Naveeth Babu C., Jayaraj Velusamy, Cowsigan S.P., Balakrishnan S., Anitha R.
    Engineering Review, 2025
    Digital twins are essential in metaverse engineering, serving as a foundation for optimization, simulation, and analysis. However, these digital replicas are vulnerable to malicious software, potentially compromising data and allowing unauthorized access. AI enhances digital twins by enabling them to learn from real-time data, making autonomous decisions. AI algorithms allow for simulating complex environments that react instantly to human input, creating immersive experiences. This article introduces an AI-based study aimed at optimizing digital twin ecosystems and metaverse engineering platforms in real-time (AI-DTE-ME). By integrating metaverse technology with digital twins, realistic and interactive virtual worlds can be created. Continuous data analysis allows digital twins to detect patterns, predict issues, and adapt processes dynamically. This capability brings the Metaverse to life, enabling the creation of intelligent, interactive digital objects. The study highlights the effectiveness of combining AI with operations research (OR) for the real-time optimization of Metaverse engineering and Digital Twin ecosystems.
  • Automated Diagnosis of Cancer Disease with Human Tissues using Haralick Texture Features and Deep Learning Techniques
    S. Balakrishnan, N.S. Simonthomas, J. Nithyashri, B. Suchitra, G. Umamaheswari, D. Pradeep
    International Journal of Computational and Experimental Science and Engineering, 2024
    The increasing use of automated cancer diagnosis based on histopathological images is significant because it is likely to increase the accuracy of diagnosis and decrease the workload on pathologists. This research introduces a hybrid methodology that integrates Haralick texture features with deep learning strategies to improve the automated identification of cancer in human tissue specimens. Haralick texture features, obtained from the Gray-Level Co-Occurrence Matrix (GLCM), offer essential information regarding the spatial relationships and textural characteristics present in tissue samples, which frequently signal the presence of cancerous alterations. The integration of these interpretable texture features with convolutional neural networks (CNNs) makes our approach use the strengths of both traditional texture analysis and deep learning's ability to learn complex patterns. This will process raw image data with the Haralick features leading to a powerful model that, hopefully, makes better classification along with interpretability. These features, handcrafted and capturing features like contrast, correlation, energy, and homogeneity, provide differences in the texture of the tissue that classify between normal cells and abnormal ones. Experimental results were presented in distinguishing cancerous and non-cancerous tissues with high accuracy. The diagnostic efficiency was also enhanced while at the same time providing a reliable and scalable tool that may assist pathologists during clinical decision-making, which consequently leads to efficient cancer diagnosis and patient care.
  • An intelligent diagnosis of anemia using tensor flow: Potentially effective in AI and quantum network-based medical applications
    J. Nithyashri, Pasala Sree Ramya, Isha Mathur
    AI and Quantum Network Applications in Business and Medicine, 2024
    Typically, hemoglobin levels are measured in the patient's blood to make the diagnosis. But as research develops, techniques other than assessing the conjunctival pallor may be used to determine hemoglobin levels. A framework consisting of decision tree, logistic regression comparison techniques, as well as the Histogram of Oriented Gradient (HOG), attempts to diagnose diabetes from connected photos. A consensus was reached on issues like room size 8x8, block size 8x8, bin number 15, L2Hys block normalization and entropy process, the best discriminator, random state is 10, minimum pollution reduction is 0.15, and the system can produce 82.5% of the test images, which had an image size of 256x128 based on the results of HOG and decision tree. As for the logistic regression is concerned, the best is blocking normalization and random state with unit size 16x16, block size 8x8, number of bins 11, L2Hys 30, system capacity, utilizing the Stochastic Gradient Descent (SGD) optimizer method. 92.5% of the best outcomes were produced in 24.20 seconds of calculation time.
  • Intelligent Classification of Liver Diseases using Ensemble Machine Learning Techniques
    Nithyashri, Harsh Goel, Manvendra Singh Hada
    2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things Icoici 2024 Proceedings, 2024
    Liver disease is a more challenging health crisis which affects millions of people worldwide. Early detection and treatments are essential for improving patient outcomes, but diagnosis at early stage is more challenging. Machine learning algorithms were significantly used to improve the accuracy and efficiency of liver disease diagnosis. This study developed a machine learning model to predict the stage of liver disease using a variety of clinical features. The LR Hyperparameter tuned model is used to improve the accuracy to 83% on a test set, much higher than traditional diagnostic methods. This suggests that the model could be used to develop a non-invasive, cost-effective, and highly accurate tool for diagnosing and monitoring liver disease patients. Additionally, the model could identify high-risk patients for developing liver disease complications, such as cirrhosis and liver failure. This information could inform personalized treatment plans to prevent the development of complications. Overall, the machine learning model has the potential to transform the early detection and management of liver disease.
  • IOT based prediction of rainfall forecast in coastal regions using deep reinforcement model
    J. Nithyashri, Ravi Kumar Poluru, S. Balakrishnan, M. Ashok Kumar, P. Prabu, S. Nandhini
    Measurement Sensors, 2023
    This research proposes an IoT based technique for predicting rainfall forecast in coastal regions using a deep reinforcement learning model. The proposed technique utilizes Long Short-Term Memory (LSTM) networks to capture the temporal dependencies between the rainfall data collected from the coastal regions and the prediction model parameters. The proposed technique is evaluated on a dataset of rainfall data collected from the coastal regions of India and compared to traditional methods of rainfall forecasting. The accuracy and reliability of these models are evaluated by comparing them to prior models. Precipitation in coastal locations may be predicted with an average accuracy of 89% using the suggested model, as shown by the results. The suggested framework is computationally efficient and can be trained with little input. The results of this research give strong evidence that the proposed model is an effective tool for coastal precipitation forecasting.
  • A Novel Analysis and Detection of Autism Spectrum Disorder in Artificial Intelligence Using Hybrid Machine Learning
    Senthil G. A, R. Prabha, J. Nithyashri, Suganthi. P, I. Thamarai, Sridevi S
    International Conference on Innovative Data Communication Technologies and Application Icidca 2023 Proceedings, 2023
    Heart Disease or Cardiovascular Disease refers to the range of heart conditions like cardiac arrest, coronary artery disease. Heart disease can be very well hindered through certain lifestyle changes. There is a significant increase in the mortality rate recently due to the distinctive heart diseases. Machine learning uses mathematical models to work efficiently with the enormous amount of data. It plays a crucial role in medical science in the prediction of distinctive diseases. Cardiologists inspects the heart functionality using electrocardiography, computed tomography. These tests are quite expensive for a common man. Recent times, the life span of a human is guaranteed only with the support of medications. As prevention is better than the cure, machine learning helps to predict the vulnerability of a heart disease with few elemental symptoms and health factors. It is been fed by the basic data of the patients like age and sex. Machine learning helps to predict the vulnerability in advance which provides the cardiologists with great acumen for the adaption of the treatment. Machine learning algorithms have proven to produce reliable and accurate output with the help of the inputs. The algorithms used in the article include K-Nearest Neighbour (KNN) and decision tree classifier which is compared to yield the desired and efficient output.
  • Comparison analysis of IoT based industrial automation and improvement of different processes - Review
    V. Kamatchi Sundari, J. Nithyashri, S. Kuzhaloli, Jayasudha Subburaj, P. Vijayakumar, P. Subha Hency Jose
    Materials Today Proceedings, 2021
  • A Gaussian mixture model for classifying the human age using DWT and Sammon map
    J. Nithyashri, G. Kulanthaivel
    Journal of Computer Science, 2014
  • Classification of human age based on Neural Network using FG-NET Aging database and Wavelets
    J. Nithyashri, G. Kulanthaivel
    4th International Conference on Advanced Computing Icoac 2012, 2012

RECENT SCHOLAR PUBLICATIONS

  • AI ENABLED DEVICE FOR DETECTION OF NEUROLOGICAL DISORDERS
    et al. J Nithyashri, D Sumathi,Hardeep Singh,Arvind Raja
    IN Patent 426451-001 , 2026
    2026
  • An intelligent classification of emotions in human speech using CNN and LSTM
    J Nithyashri, H Goel, MS Hada
    AIP Conference Proceedings 3345 (1), 020133 , 2026
    2026
  • An intelligent classification of emotions using human speech using CNN and LSTM
    MSH J.Nithyashri,Harsh Goel
    AIP Conference Proceedings 3345 , 2026
    2026
  • Integrating AI and OR for real-time optimization in digital twin ecosystems and metaverse engineering.
    R Nithyashri, J., Babu, N., Velusamy, J., Cowsigan, S. P., Balakrishnan, S ...
    Engineering Review Journal 45 (3), 55-73 , 2025
    2025
  • Spatio-Temporal Crime Prediction Using Deep Learning: A CNN-LSTM Based Approach
    M Srivastava, S Raj, J Nithyashri
    Available at SSRN 5853142 , 2025
    2025
  • Dual-Attention Graph Neural Networks for SpatioTemporal Crime Forecasting and Patrol Optimization
    NJ Sanya Raj, Mudit Srivatsava
    7th IEEE International Workshop on Artificial Intelligence and Education … , 2025
    2025
  • Smart Agro Connect Using ARIMA Model
    DNJ Sri Venkata Vaishnavi.M, Chintapalli Someswara Rao
    International Conference on Computing and Communication Networks(ICCCNet … , 2025
    2025
  • Spatio-Temporal Crime Prediction using Deep Learning: A CNN and LSTM based approach
    NJ Sanya Raj, Mudit Srivatsava
    International Conference on Computing and Communication Networks(ICCCNet … , 2025
    2025
  • Advanced Text Classification Utilizing Long Short-Term Memory (LSTM) Networks for Enhanced Natural Language Processing Applications
    HK Nithyashri J, Rajathi V, Siddhanth Janawade
    16th INTERNATIONAL IEEE CONFERENCE ON COMPUTING, COMMUNICATION AND … , 2025
    2025
  • Quantum-enhanced climate models for predicting and mitigating environmental change
    JN P. Thilagavathi, R. Geetha, Ramesh S., S. Vidhya
    Emerging Technologies In Sustainable Innovation, Management and Development … , 2025
    2025
    Citations: 1
  • Decentralized edge AI for real-time environmental monitoring and sustainability
    JN Ramesh S., R. Geetha, P. Thilagavathi, S. Vidhya
    Emerging Technologies In Sustainable Innovation, Management and Development … , 2025
    2025
  • Designing carbon-aware cloud architectures for sustainable computing
    PTNJ S. Vidhya, S.Ramesh, R.Geetha
    Emerging Technologies In Sustainable Innovation, Management and Development … , 2025
    2025
  • Bio-inspired optimization for sustainable smart city infrastructure
    SVNJ R. Geetha, S. Ramesh, P. Thilagavathi
    Emerging Technologies In Sustainable Innovation, Management and Development … , 2025
    2025
  • AI-driven strategies for enhancing circular economy and reducing industrial waste
    Nithyashri J, S. Ramesh, R. Geetha, P. Thilagavathi, and S. Vidhya
    Emerging Technologies In Sustainable Innovation, Management and Development … , 2025
    2025
  • Augmenting Convolutional Neural Networks with Graph Models for Skin Disease Classification
    BLRD Nithyashri J
    International Conference on Inventive Research in Computer Applications … , 2025
    2025
  • Agricultural Marketing Analysis using ARIMA model
    NJ Venkata Vaishanavi.M, Chintapalli Someswara Rao
    International Conference on Internet of Things(ICIoT 2025) , 2025
    2025
  • Automated Diagnosis of Cancer Disease with Human Tissues using Haralick Texture Features and Deep Learning Techniques
    DP S.Balakrishnan,N.S.Simonthomas,J.Nithyashri ,B.Suchitra,G.Umamaheswari
    International Journal of Computational and Experimental Science and … , 2025
    2025
    Citations: 1
  • VisionAid: Enhancing Accessibility for the visually impaired with YOLO and gTTS
    NJ Bhagyalakshmi .R
    International Conference on Visual Analytics and Data Visualization (ICVADV … , 2025
    2025
  • IOT Enabled Solar Step Lights for Outdoor
    KSK T.R.Saravanan, J.Nithyashri,P.Kanmani
    IN Patent 439924-001 , 2025
    2025
  • Advanced Mathematical Applications of Cryptographic protocols in Distributed Ledger Technologies and Digital Currency systems
    SSJN Senthil G.A, R.Prabha, R.Avudainayaki
    International Conference on Optimization Techniques in the Field of Engineering , 2025
    2025

MOST CITED SCHOLAR PUBLICATIONS

  • Classification of human age based on Neural Network using FG-NET Aging database and Wavelets
    J Nithyashri, G Kulanthaivel
    2012 Fourth international conference on advanced computing (ICoAC), 1-5 , 2012
    2012
    Citations: 59
  • IOT based prediction of rainfall forecast in coastal regions using deep reinforcement model
    SN J. Nithyashri, Ravi kumar Poluru,S. Balakrishnan, M. Ashok kumar, P. Prabu
    Measurment:Sensors 29 , 2023
    2023
    Citations: 51
  • Comparison analysis of IoT based industrial automation and improvement of different processes-review
    PSHJ V Kamatchi sundari, J Nithyashri,S kuzhaloli,Jayasudha Subburaj, P ...
    Materials Today:Proceedings , 2021
    2021
    Citations: 29
  • A novel analysis and detection of autism spectrum disorder in artificial intelligence using hybrid machine learning
    R Prabha, J Nithyashri, I Thamarai
    2023 International Conference on Innovative Data Communication Technologies … , 2023
    2023
    Citations: 18
  • An Intelligent System for Plant Disease Diagnosis and Analysis Based on Deep Learning and Augmented Reality
    DJN Dr.G.A.Senthil, Dr.R.Prabha
    4th International Conference on Data Intelligence and Cognitive Informatics , 2023
    2023
    Citations: 14
  • System Software
    J Nithyashri
    TataMcgraw Hill Publications , 2008
    2008
    Citations: 4
  • Facial Age Classification Using Discrete Wavelet Transform and K-Nearest Neighbour Algorithm
    JNG kulanthaivel
    Journal of Computer Science Engineering and Information Technology Research … , 2014
    2014
    Citations: 3
  • An intelligent Blood Bank Management and Blood Monitoring System Using Machine Learning
    DJN Yellagada Pradeep, Jatin Singhania
    African Journal of Biological Science 6 (10), 960 - 966 , 2024
    2024
    Citations: 2
  • Intelligent assistant to predict and control the home appliances in user environment through brain computer interface using hybrid deep learning model
    MDSA Dr. V. Mohan Raj, Dr. J. Nithyashri, Dr. V. Priyanka Brahmaiah, Dr. A ...
    Journal of Complementary Medicine Research 14 (2), 150-156 , 2023
    2023
    Citations: 2
  • A Study On Online Spam Review Detection Methods by Machine Learning Approach
    DSJR Dr.Sudha Rajesh, Dr.M.Mercy Theresa, Dr.J.Nithyashri
    Turkish Journal of Computer and Mathematics Education 12 (9), 1292-1304 , 2021
    2021
    Citations: 2
  • Classifying the human age using Discrete Wavelet Transform, KNN and MORPH database
    DGK J.Nithyashri
    Journal of Computer Applications 6 (4), 102-106 , 2013
    2013
    Citations: 2
  • Quantum-enhanced climate models for predicting and mitigating environmental change
    JN P. Thilagavathi, R. Geetha, Ramesh S., S. Vidhya
    Emerging Technologies In Sustainable Innovation, Management and Development … , 2025
    2025
    Citations: 1
  • Automated Diagnosis of Cancer Disease with Human Tissues using Haralick Texture Features and Deep Learning Techniques
    DP S.Balakrishnan,N.S.Simonthomas,J.Nithyashri ,B.Suchitra,G.Umamaheswari
    International Journal of Computational and Experimental Science and … , 2025
    2025
    Citations: 1
  • A Novel Meta Analysis and classification of Herbal Medicinal Plant Raw Materials for food consumption prediction using Hybrid Deep Learning Techniques based on Augumented …
    A G. A. Senthi, R. Prabha, S. Sridevi,J. Nithyashri
    5th World Conference on Artificial Intelligence : Advances and Applications a , 2024
    2024
    Citations: 1
  • Surveillance and patrolling of women safety using visual trigger automation
    S Vinodhkumar, J Nithyashri, D Brindha, S Balakrishnan
    Mathematical Statistician and Engineering Applications 71 (4), 1440-1446 , 2022
    2022
    Citations: 1
  • Intelligent Classification of Liver Images Using Back Propagation Neural Network
    SFS J.Nithyasshri
    International Journal of Engineering Science and Computing 9 (3) , 2019
    2019
    Citations: 1
  • cervical cancer detection using support vector machine
    B J.Nithyashri
    International Journal of Emerging Trends in Science & Technology 4 (3) , 2017
    2017
    Citations: 1
  • AI ENABLED DEVICE FOR DETECTION OF NEUROLOGICAL DISORDERS
    et al. J Nithyashri, D Sumathi,Hardeep Singh,Arvind Raja
    IN Patent 426451-001 , 2026
    2026
  • An intelligent classification of emotions in human speech using CNN and LSTM
    J Nithyashri, H Goel, MS Hada
    AIP Conference Proceedings 3345 (1), 020133 , 2026
    2026
  • An intelligent classification of emotions using human speech using CNN and LSTM
    MSH J.Nithyashri,Harsh Goel
    AIP Conference Proceedings 3345 , 2026
    2026