G Sukanya

@sathyabama.ac.in

Assistant Professor,School of Computing
Sathyabama Institute of Science and Technology

G Sukanya


                     Download Compact PDF  
https://researchid.co/sukanya123

EDUCATION

M.E., PhD

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Language and Linguistics, Computer Engineering, Information Systems
8

Scopus Publications

87

Scholar Citations

5

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • Fine Tuned Hybrid Deep Learning Model for Effective Judgment Prediction
    G. Sukanya, J. Priyadarshini
    CMES Computer Modeling in Engineering and Sciences, 2025
    Advancements in Natural Language Processing and Deep Learning techniques have significantly propelled the automation of Legal Judgment Prediction, achieving remarkable progress in legal research. Most of the existing research... | Find, read and cite all the research you need on Tech Science Press
  • Enhanced Hybrid Deep Learning Model With Improved Self-Attention Mechanism for Legal Judgment Prediction
    G. Sukanya, J. Priyadarshini
    IEEE Access, 2025
    The dawn of Natural Language Processing in the legal research field has achieved great heights. Legal Judgment Prediction (LJP) is one of the important tasks in legal intelligence that can assist attorneys and litigators in predicting judgments. Although current research techniques work effectively, they still have many drawbacks. Firstly, encoding lengthy case facts into vectors without losing information is one of the challenging tasks in LJP. Choosing an encoder that captures the syntax, semantics, and contexts of words can be extremely important for all downstream natural language tasks. Secondly, the features on which the deep learning model is trained also play an important role in testing the real-time cases. This research focuses on Indian cases that follow the common law, unlike civil law. Most of the existing LJP considers only civil law and does not emphasize the extraction of textual features. A novel LJP approach has been suggested in this research to overcome the issues raised above by improving the encoding part using the hybrid embedding method ELMo (Embeddings from Language Model) with Improved Principal Component Analysis (IPCA). Training a crucial set of features is done with a hybrid model, with a combination of Bi-GRU along with a modified attention mechanism and a deep-max-out network. The proposed Hybrid Deep Learning Model with Score Level Fusion (HDLMSF) is experimented with real-time Madras High Court criminal cases and compared with baseline classifier models. The results show that the proposed HDLMSF model has better prediction accuracy, 94.16% than other baseline classifiers.
  • Enhancing Decision-Making in Indian Legal Systems: Automating Document Analysis with Named Entity Recognition
    Gaurav Pendharkar, G. Sukanya, J. Priyadarshini
    Decision Making for Sustainable Technological Innovation Strategies and Applications in Industry 5 0, 2025
    Most of the data in the legal industry are in the form of raw text documents, which finds its application in the domain of natural language processing. Based on region, there is a large variety of document formats and languages used for such documents. All legal documents have a plethora of information in them that can help in automating the process of delivering the judgments for a new case. Hence, using information extraction techniques, these useful data can be extracted from these legal documents. This paper aims to propose a named entity recognition model to extract legal entities, particularly sections, acts, and articles from Madras High Court judgment proceedings. To the best of our knowledge, there is no research work investigated for Madras High Court documents. Moreover, we fine-tune the pretrained model from SpaCy using the annotated data. Finally, the fine-tuned model achieves an F score of 72.20% and a precision of 83.90%. The legal entities predicted by the resultant model can be used to make legal predictions using machine learning and deep learning, information retrieval systems, and data engineering tasks.
  • Classification of Indian Legal Judgment Documents Through Innovative Technology to Aid in Decision-Making
    Ujjwal Pandey, G. Sukanya, J. Priyadarshini
    Decision Making for Sustainable Technological Innovation Strategies and Applications in Industry 5 0, 2025
    Machine learning and deep learning techniques have revolutionized various fields such as art, science, math, and so on. However, these techniques have not been widely utilized in the legal domain, particularly in the Indian judiciary system, where most work is still done manually. In this study, we suggest a deep learning method for classifying the 18 categories established by the Supreme Court of India into which Indian court judgment documents fall. The approach outlined in this paper offers a more efficient way for legal professionals to classify and organize legal documents without the need for extensive manual review. Our approach uses a multichannel convolutional neural network (CNN) with multigram term frequency-inverse document frequency (TF-IDF) vectors as input and demonstrates superior performance compared to traditional machine learning and deep learning methods such as support vector machine, random forest, BERT, TextCNN, and so on in multilabel settings.
  • Analysis on word embedding and classifier models in legal analytics
    G. Sukanya, J. Priyadarshini
    Aip Conference Proceedings, 2024
    Legal Analytics is a blooming field of research that draws attraction from various fields such as computational linguistics, natural language processing, machine learning, and data science. Improvement in text analytics has paved the way to a great level in eCommerce, banking, medical and legal sectors after the incoming of deep learning models. The large quantity of digital information in the legal domain and the challenges faced has made this an important area of legal research. Historically, judges and other legal personnel have frequently been required to manually review legal documents to acquire an inclusive judgment justification. This practice is highly challenging also laborious and time-consuming. Most of the existing works predict the legal outcomes based on case facts, but predicting judgment solely on Casefact gives low efficiency. Automation in judgment prediction systems is at the budding stage. Choosing the appropriate word embedding technique in language modeling, Classifier model and loss functions pave way for better results. Selecting the appropriate learning algorithm for text classification on real-time problems is a great challenge as legal documents are lengthy and unstructured. This paper emphasizes the limitations and important aspects of different components of NLP such as tokenization, word embeddings, and classifiers which makes the computer interpret and extract maximum contextual information from documents to provide the best performance for assisting litigants for verdict prediction of countries that use common law system. It also reviews different ideas applicable to legal case facts in a broad manner.
  • Hybrid CNN: An Empirical Analysis of Machine Learning Models for Predicting Legal Judgments
    G. Sukanya, J. Priyadarshini
    International Journal of Advanced Computer Science and Applications, 2024
    Artificial Intelligence with NLP has revolutionized the legal industry, which was previously under-digitized, and it's eager to adopt digital technologies for increased efficiency. Case backlog issues, exacerbated by population growth, can be alleviated by AI's potential in decision prediction for laypeople, litigants, and adjudicators. Legal judgment prediction (LJP) is viewed as a text classification cum prediction problem, with encoding models crucial for accurate textual representation and downstream tasks. These models capture syntax, semantics, and context, varying in performance based on the task and dataset. Selecting the right model, whether traditional ML or DL, using different evaluation metrics, is complex. This paper addresses the above research gap by reviewing 12 cutting-edge ML models and 10 DL models with two embedding methods on real-time Madras High Court criminal cases from Manupatra. The comprehensive comparison of classifier models on real-time case documents provides insights for researchers to innovate despite challenges and limitations. Evaluation metrics like accuracy, F1 score, precision, and recall show that Support Vector Machines (SVM), Logistic Regression, and SGD with Doc2Vec (D2V) encoding and shallow neural networks perform well. Although Transformers process longer input sequences with parallel word analysis and self-attention layers, they have weaknesses on real-time datasets. This article proposes a novel hybrid CNN with a transformer model to predict binary judgments, outperforming traditional ML and DL models in precision, recall, and accuracy. Finally, we summarise the most important ramifications, potential research avenues, and difficulties facing the legal research field.
  • Modified Hierarchical-Attention Network model for legal judgment predictions
    G. Sukanya, J. Priyadarshini
    Data and Knowledge Engineering, 2023
  • A Meta Analysis of Attention Models on Legal Judgment Prediction System
    G. Sukanya, J.Priyadarshini -
    International Journal of Advanced Computer Science and Applications, 2021
    Artificial Intelligence in legal research is transforming the legal area in manifold ways. Pendency of court cases is a long-lasting problem in the judiciary due to various reasons such as lack of judges, lack of technology in legal services and the legal loopholes. The judicial system has to be more competent and more reliable in providing justice on time. One of the major causes of pending cases is the lack of legal intelligence to assist the litigants. The study in this paper reviews the challenges faced by judgment prediction system due to lengthy case facts using deep learning model. The Legal Judgment prediction system can help lawyers, judges and civilians to predict the win or loss rate, punishment term and applicable law articles for new cases. Besides, the paper reviews current encoding and decoding architecture with attention mechanism of transformer model that can be used for Legal Judgment Prediction system. Natural Language Processing using deep learning is an exploring field and there is a need for research to evaluate the current state of the art at the intersection of good text processing and feature representation with a deep learning model. This paper aims to develop a systematic review of existing methods used in the legal judgment prediction system and about the Hierarchical Attention Neural network model in detail. This can also be used in other applications such as legal document classification, sentimental analysis, news classification, text translation, medical reports and so on.

RECENT SCHOLAR PUBLICATIONS

  • Classification of Indian Legal Judgment Documents Through Innovative Technology to Aid in Decision‐Making
    U Pandey, G Sukanya, J Priyadarshini
    Decision‐Making Techniques and Methods for Sustainable Technological … , 2025
    2025.0
  • Enhancing Decision‐Making in Indian Legal Systems: Automating Document Analysis with Named Entity Recognition
    G Pendharkar, G Sukanya, J Priyadarshini
    Decision‐Making Techniques and Methods for Sustainable Technological … , 2025
    2025.0
  • Enhanced hybrid deep learning model with improved Self-Attention mechanism for legal judgment prediction
    G Sukanya, J Priyadarshini
    IEEE Access , 2025
    2025.0
    Citations: 4
  • Fine Tuned Hybrid Deep Learning Model for Effective Judgment Prediction.
    G Sukanya, J Priyadarshini
    Computer Modeling in Engineering & Sciences (CMES) 142 (3) , 2025
    2025.0
    Citations: 6
  • Hybrid CNN: An Empirical Analysis of Machine Learning Models for Predicting Legal Judgments.
    G Sukanya, J Priyadarshini
    International Journal of Advanced Computer Science & Applications 15 (7) , 2024
    2024.0
    Citations: 6
  • Analysis on word embedding and classifier models in legal analytics
    G Sukanya, J Priyadarshini
    AIP Conference Proceedings 2802 (1), 140001 , 2024
    2024.0
    Citations: 7
  • Modified Hierarchical-Attention Network model for legal judgment predictions
    G Sukanya, J Priyadarshini
    Data & knowledge engineering 147, 102203 , 2023
    2023.0
    Citations: 23
  • A meta analysis of attention models on legal judgment prediction system
    G Sukanya, J Priyadarshini
    International Journal of Advanced Computer Science and Applications 12 (2) , 2021
    2021.0
    Citations: 41
  • Data Integration of System J-Curve and Management Joint Analysis and System learning using N-Perception Process Using Nozaka’s Data Analysis Model
    VSS T. Shantha Kumar1
    Shodhshauryam, International Scientific Refereed Research Journal 2 (1) , 2019
    2019.0
  • Implementation of playfair cipher by using 7 by 9 matrix and colour substitution
    VSS Subramanian C.S
    International Journal of Engineering Research , 0

MOST CITED SCHOLAR PUBLICATIONS

  • A meta analysis of attention models on legal judgment prediction system
    G Sukanya, J Priyadarshini
    International Journal of Advanced Computer Science and Applications 12 (2) , 2021
    2021.0
    Citations: 41
  • Modified Hierarchical-Attention Network model for legal judgment predictions
    G Sukanya, J Priyadarshini
    Data & knowledge engineering 147, 102203 , 2023
    2023.0
    Citations: 23
  • Analysis on word embedding and classifier models in legal analytics
    G Sukanya, J Priyadarshini
    AIP Conference Proceedings 2802 (1), 140001 , 2024
    2024.0
    Citations: 7
  • Fine Tuned Hybrid Deep Learning Model for Effective Judgment Prediction.
    G Sukanya, J Priyadarshini
    Computer Modeling in Engineering & Sciences (CMES) 142 (3) , 2025
    2025.0
    Citations: 6
  • Hybrid CNN: An Empirical Analysis of Machine Learning Models for Predicting Legal Judgments.
    G Sukanya, J Priyadarshini
    International Journal of Advanced Computer Science & Applications 15 (7) , 2024
    2024.0
    Citations: 6
  • Enhanced hybrid deep learning model with improved Self-Attention mechanism for legal judgment prediction
    G Sukanya, J Priyadarshini
    IEEE Access , 2025
    2025.0
    Citations: 4
  • Classification of Indian Legal Judgment Documents Through Innovative Technology to Aid in Decision‐Making
    U Pandey, G Sukanya, J Priyadarshini
    Decision‐Making Techniques and Methods for Sustainable Technological … , 2025
    2025.0
  • Enhancing Decision‐Making in Indian Legal Systems: Automating Document Analysis with Named Entity Recognition
    G Pendharkar, G Sukanya, J Priyadarshini
    Decision‐Making Techniques and Methods for Sustainable Technological … , 2025
    2025.0
  • Data Integration of System J-Curve and Management Joint Analysis and System learning using N-Perception Process Using Nozaka’s Data Analysis Model
    VSS T. Shantha Kumar1
    Shodhshauryam, International Scientific Refereed Research Journal 2 (1) , 2019
    2019.0
  • Implementation of playfair cipher by using 7 by 9 matrix and colour substitution
    VSS Subramanian C.S
    International Journal of Engineering Research , 0