Bakkia Lakshmi

@srmist.edu.in

Assistant Professor/ Department of Computing Technologies
SRM institute of Science and Technology

Bakkia Lakshmi


                        Download Compact PDF  
https://researchid.co/bakyam21

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Science, Artificial Intelligence, Human-Computer Interaction
19

Scopus Publications

70

Scholar Citations

6

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • GENI: A Multi-module AI Assistant
    Manas Goel, V. S. Bakkialakshmi, Nagender Aneja
    Cognitive Science and Technology, 2026
    GENI, our groundbreaking AI application, introduces a fresh approach to artificial intelligence. It consists of two integral modules. The first module effectively blends API responses from various large language models (LLMs) available in the market. The second module focuses on comparing answers. As GENI recognizes the user, it seeks an appropriate response to the user's question, enhanced by the added functionality of voice-based question-answer. All of this is facilitated by LangChain, the heart of GENI. GENI also boasts the functionality of automated fine-tuning, setting it apart from other options in the market. This feature positions GENI as the perfect tool for organizations to support customers. The combination of response mixing, user recognition, and automated fine-tuning makes GENI a cost-effective and broad-ranging AI assistant.
  • Multi-model ensemble deep learning framework for robust stock market forecasting: Integration of economic indicators and temporal dependencies
    PRASHAM JAIN, Dwij Bishnoi, Neel Bishnoi, Bakkialakshmi V.S, Lenin Mookiah
    Proceedings of SPIE the International Society for Optical Engineering, 2025
    Our research work investigates how ensemble based machine learning methods can enhance stock market forecasting. A novel framework named XML is introduced, integrating XGBoost, MLP, and LSTM models to achieve higher predictive accuracy in stock price prediction. We evaluated the performance of the model with various baseline machine learning algorithms, including neural networks, support vector machines, and random forests, to predict stock prices. The research utilizes historical stock price data, trading volume, and news sentiment analysis as input features for the models. The study evaluates the performance of the models using metrics such as Mean squared error (MSE), Mean Absolute Error (MAE), and R-Squared. This study seeks to explore how machine learning techniques can enhance stock price forecasting and supports the advancement of more precise and dependable predictive models within financial markets. Preliminary results indicate promising performance of the machine learning models in predicting stock prices.
  • Machine Learning Prediction of ADHD Metrics From Conners' CPT-II Data and Demographics
    Jonnalagedda Sai Satvik, Suseendiran Raghu, V.S Bakkialakshmi
    3rd IEEE International Conference on Networks Multimedia and Information Technology Nmitcon 2025, 2025
    The investigation of objective, data-driven methods is spurred by the subjectivity and scalability issues with traditional ADHD evaluation. Using the publicly available HYPERAKTIV dataset, this study aimed to develop and evaluate machine learning models for predicting several clinically relevant ADHD T-scores and the ADHD Confidence Index using raw Conners' Continuous Performance Test II (CPT-II) scores and basic demographic information (age, sex). We used a LightGBM model to forecast the confidence index and a MultiOutputRegressor with XGBoost to forecast T-scores. RMSE, MAE, and R2 measures as well as traditional train/test splitting were used to assess performance. The findings showed that both models successfully mastered the mapping between existing clinical scales and indicators and the CPT-II inputs and demographics. A step toward datadriven solutions that might assist and possibly expedite ADHD screening and clinical diagnosis, this work demonstrates the potential of gradient boosting algorithms applied to standard neuropsychological test data for producing quantitative, objective insights.
  • An Analysis of COVID-19 Symptoms Using Machine Learning Algorithm
    V. S. Bakkialakshmi, T. Sudalaimuthu, R. Anandhi
    Aip Conference Proceedings, 2024
  • Individual Human Emotion Detection with Multimodal Synchronous Health Detectors
    V. S. Bakkialakshmi, Vamsi Krishna Minnal Sundar Rajan, T. Sudalaimuthu
    Aip Conference Proceedings, 2024
  • Affective analysis in machine learning using AMIGOS with Gaussian expectation-maximization model
    Balamurugan Kaliappan, Bakkialakshmi Vaithialingam Sudalaiyadumperumal, Sudalaimuthu Thalavaipillai
    International Journal of Reconfigurable and Embedded Systems, 2024
    <p>Investigating human subjects is the goal of predicting human emotions in the stock market. A significant number of psychological effects require (feelings) to be produced, directly releasing human emotions. The development of effect theory leads one to believe that one must be aware of one's sentiments and emotions to forecast one's behavior. The proposed line of inquiry focuses on developing a reliable model incorporating neurophysiological data into actual feelings. Any change in emotional affect will directly elicit a response in the body's physiological systems. This approach is named after the notion of Gaussian mixture models (GMM). The statistical reaction following data processing, quantitative findings on emotion labels, and coincidental responses with training samples all directly impact the outcomes that are accomplished. In terms of statistical parameters such as population mean and standard deviation, the suggested method is evaluated compared to a technique considered to be state-of-the-art. The proposed system determines an individual's emotional state after a minimum of 6 iterative learning using the Gaussian expectation-maximization (GEM) statistical model, in which the iterations tend to continue to zero error. Perhaps each of these improves predictions while simultaneously increasing the amount of value extracted.</p>
  • Unique Covariate Identity (UCI) Detection for Emotion Recognition Through EEG Signals
    V. S. Bakkialakshmi, T. Sudalaimuthu
    Lecture Notes in Electrical Engineering, 2024
  • NewApt: A Python Wrapper for Improving APT Package Manager
    V. S. Bakkialakshmi, Anubhav Vardhan, Bhaskar
    Lecture Notes in Networks and Systems, 2024
  • The Digital Mirror - Reflecting Human Emotions through Machine Learning-Based Facial Gesture Recognition
    V S Bakkialakshmi, Nikhil Kar, Vicky Kumar
    2024 1st International Conference on Cognitive Green and Ubiquitous Computing IC Cgu 2024, 2024
    This research project is a pivotal exploration at the crossroads of the use of machine learning for facial gesture detection, which involves interpreting facial emotions. Key steps in the process include data gathering, preprocessing, feature extraction, and model building. Facial expressions are emphasized as crucial for conveying emotions and fostering social connections. The role of AI in facial emotion recognition, utilizing machine learning and computer vision, is also acknowledged. In conclusion, the integration of nuanced facial gestures with AI-driven facial emotion recognition holds significant potential for improving interactions and applications.
  • Emotion Recognition from RGB Kinect Videos and Physiological Signals Using Pre-Trained CNN Model
    Shruthi Anand, Lenin Mookiah, Bakkialakshmi V S, S Sembon Surakshitha
    Proceedings of the 3rd International Conference on Intelligent Computing and Next Generation Networks Icngn 2024, 2024
    This study presents an innovative approach to emotion recognition by integrating RGB Kinect video data with physiological signals, including electroencephalography (EEG), electrocardiography (ECG), and galvanic skin response (GSR). Using the AMIGOS dataset, which includes video recordings and self-assessment emotional ratings, we improve emotion prediction through a comprehensive multimodal analysis. Our method involves feature extraction and averaging from both video and physiological signals, emphasizing the connection between visual cues and emotional responses. A pre-trained ResNet model is used for advanced feature extraction from video data. Various machine learning algorithms are applied to evaluate predictive models against self-assessment labels. Results indicate that the combination of ResNet-based visual features and physiological signals enhances emotion prediction accuracy, underscoring the value of a multimodal approach in capturing complex emotional dynamics.
  • SAGA-Integrating AI for Enhanced Recruitment: ASystem with Audio-Video Proctoring and Comprehensive Evaluation
    Nishad Mathur, Ashutosh Sharma, Shubh Kaushik, V S Bakkialakshmi, Vishishta Kavadiya, et al.
    2024 2nd International Conference on Advances in Computation Communication and Information Technology Icaiccit 2024, 2024
  • Exploring the Potential of Deep Learning in the Classification and Early Detection of Parkinson's Disease
    V S Bakkialakshmi, V Arulalan, Gowdham Chinnaraju, Hritwik Ghosh, Irfan Sadiq Rahat, Ankit Saha
    Eai Endorsed Transactions on Pervasive Health and Technology, 2024
  • Emo-Spots: Detection and Analysis of Emotional Attributes Through Bio-Inspired Facial Landmarks
    V. S. Bakkialakshmi, T. Sudalaimuthu, B. Umamaheswari
    Lecture Notes in Electrical Engineering, 2023
  • AMIGOS: a robust emotion detection framework through Gaussian ResiNet
    Bakkialakshmi V. S., Sudalaimuthu Thalavaipillai
    Bulletin of Electrical Engineering and Informatics, 2022
  • EMO-NET ARTIFICIAL NEURAL NETWORK: A ROBUST AFFECTIVE COMPUTING PREDICTION SYSTEM FOR EMOTIONAL PSYCHOLOGY USING AMIGOS
    Bakkialakshmi V. S, Sudalaimuthu T.
    Indian Journal of Computer Science and Engineering, 2022
  • Anomaly Detection in Social Media Using Text-Mining and Emotion Classification with Emotion Detection
    V. S. Bakkialakshmi, T. Sudalaimuthu
    Communications in Computer and Information Science, 2022
  • Students Emotional Psychology on Online Learning During Pandemic Period
    V.S. Bakkialakshmi, T. Sudalaimuthu
    2022 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2022, 2022
  • Dynamic Cat-Boost Enabled Keystroke Analysis for User Stress Level Detection
    Bakkialakshmi V. S, T. Sudalaimuthu
    Proceedings of International Conference on Computational Intelligence and Sustainable Engineering Solution Cises 2022, 2022
  • A Survey on Affective Computing for Psychological Emotion Recognition
    V. S Bakkialakshmi, T. Sudalaimuthu
    2021 5th International Conference on Electrical Electronics Communication Computer Technologies and Optimization Techniques Iceeccot 2021 Proceedings, 2021

RECENT SCHOLAR PUBLICATIONS

  • HID-AG: Elevating cybersecurity with HybridIDNet and PCA-anomalyguard for intrusion detection excellence
    BKST Bakkialakshmi VS.
    Journal of Information & Optimization Sciences 46 (No. 6,), pp.1995–2004 , 2025
    2025
  • Multi-model ensemble deep learning framework for robust stock market forecasting: integration of economic indicators and temporal dependencies
    P Jain, D Bishnoi, N Bishnoi, B VS, L Mookiah
    Seventh International Conference on Image, Video Processing, and Artificial … , 2025
    2025
  • Machine Learning Prediction of ADHD Metrics From Conners' CPT-II Data and Demographics
    JS Satvik, S Raghu, VS Bakkialakshmi
    2025 Third International Conference on Networks, Multimedia and Information … , 2025
    2025
  • Body gesture recognition using crow search algorithm enhanced probabilistic neural network for human-computer interaction
    B VS, P Chawengsaksopark, M Sathiyanarayanan
    F1000Research 14, 149 , 2025
    2025
  • GENI: A Multi-module AI Assistant
    M Goel, VS Bakkialakshmi, N Aneja
    International Conference on Cognitive and Intelligent Computing, 417-424 , 2024
    2024
  • SAGA-Integrating AI for Enhanced Recruitment: A System with Audio-Video Proctoring and Comprehensive Evaluation
    N Mathur, A Sharma, S Kaushik, VS Bakkialakshmi, V Kavadiya, N Aneja
    2024 2nd International Conference on Advances in Computation, Communication … , 2024
    2024
  • Emotion Recognition from RGB Kinect Videos and Physiological Signals Using Pre-Trained CNN Model
    S Anand, L Mookiah, SS Surakshitha
    2024 International Conference on Intelligent Computing and Next Generation … , 2024
    2024
  • An analysis of COVID-19 symptoms using machine learning algorithm
    VS Bakkialakshmi, T Sudalaimuthu, R Anandhi
    AIP Conference Proceedings 3075 (1), 020218 , 2024
    2024
    Citations: 1
  • Individual human emotion detection with multimodal synchronous health detectors
    VS Bakkialakshmi, VKM Sundar Rajan, T Sudalaimuthu
    AIP Conference Proceedings 3075 (1), 020284 , 2024
    2024
  • Affective analysis in machine learning using AMI-GOS with Gaussian expectation-maximization model
    B Kaliappan, BV Sudalaiyadumperumal, S Thalavaipillai
    Int J Reconfigurable & Embedded Syst 13 (1), 201-209 , 2024
    2024
    Citations: 2
  • The Digital Mirror-Reflecting Human Emotions through Machine Learning-Based Facial Gesture Recognition
    VS Bakkialakshmi, N Kar, V Kumar
    2024 1st International Conference on Cognitive, Green and Ubiquitous … , 2024
    2024
    Citations: 1
  • Exploring the Potential of Deep Learning in the Classification and Early Detection of Parkinson's Disease.
    VS Bakkialakshmi, V Arulalan, G Chinnaraju, H Ghosh, IS Rahat, A Saha
    EAI Endorsed Transactions on Pervasive Health & Technology 10 (1) , 2024
    2024
    Citations: 9
  • NewApt: A Python Wrapper for Improving APT Package Manager
    VS Bakkialakshmi, A Vardhan, Bhaskar
    International Conference on Cognitive Computing and Cyber Physical Systems … , 2023
    2023
  • Unique Covariate Identity (UCI) Detection for Emotion Recognition Through EEG Signals
    VS Bakkialakshmi, T Sudalaimuthu
    International Conference on Big Data, Machine Learning, and Applications … , 2023
    2023
  • Emo-spots: detection and analysis of emotional attributes through bio-inspired facial landmarks
    VS Bakkialakshmi, T Sudalaimuthu, B Umamaheswari
    International Conference on IoT, Intelligent Computing and Security: Select … , 2023
    2023
    Citations: 4
  • Anomaly Detection in Social Media Using Text-Mining and Emotion Classification
    VS Bakkialakshmi, T Sudalaimuthu
    Cognition and Recognition: 8th International Conference, ICCR 2021, Mandya … , 2023
    2023
  • Students emotional psychology on online learning during pandemic period
    VS Bakkialakshmi, T Sudalaimuthu
    2022 International Conference on Data Science, Agents & Artificial … , 2022
    2022
    Citations: 6
  • Effective prediction system for affective computing on emotional psychology with artificial neural network
    VS Bakkialakshmi, T Sudalaimuthu, S Winkler
    Easy Chair Preprint , 2022
    2022
    Citations: 2
  • AMIGOS: a robust emotion detection framework through Gaussian ResiNet
    VS Bakkialakshmi, S Thalavaipillai
    Bulletin of Electrical Engineering and Informatics 11 (4), 2142-2150 , 2022
    2022
    Citations: 9
  • Emo-net artificial neural network: A robust affective computing prediction system for emotional psychology using Amigos
    ST Bakkialakshmi.V.S
    INDIAN JOURNAL OF COMPUTER SCIENCE AND ENGINEERING 13 (4), 1040-1055 , 2022
    2022
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • A survey on affective computing for psychological emotion recognition
    VS Bakkialakshmi, T Sudalaimuthu
    2021 5th International Conference on Electrical, Electronics, Communication … , 2021
    2021
    Citations: 14
  • Dynamic cat-boost enabled keystroke analysis for user stress level detection
    T Sudalaimuthu
    2022 international conference on computational intelligence and sustainable … , 2022
    2022
    Citations: 10
  • Exploring the Potential of Deep Learning in the Classification and Early Detection of Parkinson's Disease.
    VS Bakkialakshmi, V Arulalan, G Chinnaraju, H Ghosh, IS Rahat, A Saha
    EAI Endorsed Transactions on Pervasive Health & Technology 10 (1) , 2024
    2024
    Citations: 9
  • AMIGOS: a robust emotion detection framework through Gaussian ResiNet
    VS Bakkialakshmi, S Thalavaipillai
    Bulletin of Electrical Engineering and Informatics 11 (4), 2142-2150 , 2022
    2022
    Citations: 9
  • Anomaly detection in social media using text-mining and emotion classification with emotion detection
    VS Bakkialakshmi, T Sudalaimuthu
    International Conference on Cognition and Recongition, 67-78 , 2021
    2021
    Citations: 9
  • Students emotional psychology on online learning during pandemic period
    VS Bakkialakshmi, T Sudalaimuthu
    2022 International Conference on Data Science, Agents & Artificial … , 2022
    2022
    Citations: 6
  • Emo-spots: detection and analysis of emotional attributes through bio-inspired facial landmarks
    VS Bakkialakshmi, T Sudalaimuthu, B Umamaheswari
    International Conference on IoT, Intelligent Computing and Security: Select … , 2023
    2023
    Citations: 4
  • Affective analysis in machine learning using AMI-GOS with Gaussian expectation-maximization model
    B Kaliappan, BV Sudalaiyadumperumal, S Thalavaipillai
    Int J Reconfigurable & Embedded Syst 13 (1), 201-209 , 2024
    2024
    Citations: 2
  • Effective prediction system for affective computing on emotional psychology with artificial neural network
    VS Bakkialakshmi, T Sudalaimuthu, S Winkler
    Easy Chair Preprint , 2022
    2022
    Citations: 2
  • Emo-net artificial neural network: A robust affective computing prediction system for emotional psychology using Amigos
    ST Bakkialakshmi.V.S
    INDIAN JOURNAL OF COMPUTER SCIENCE AND ENGINEERING 13 (4), 1040-1055 , 2022
    2022
    Citations: 2
  • An analysis of COVID-19 symptoms using machine learning algorithm
    VS Bakkialakshmi, T Sudalaimuthu, R Anandhi
    AIP Conference Proceedings 3075 (1), 020218 , 2024
    2024
    Citations: 1
  • The Digital Mirror-Reflecting Human Emotions through Machine Learning-Based Facial Gesture Recognition
    VS Bakkialakshmi, N Kar, V Kumar
    2024 1st International Conference on Cognitive, Green and Ubiquitous … , 2024
    2024
    Citations: 1
  • Emo-Gem: An Impacted Affective Emotional Psychology Analysis through Gaussian Model using AMIGOS
    T.Sudalaimuthu, Bakkialakshmi V. S
    Journal of Positive School Psychology (ISSN 2717-7564) 6 (No. 3), 6417–6424 , 2022
    2022
    Citations: 1
  • HID-AG: Elevating cybersecurity with HybridIDNet and PCA-anomalyguard for intrusion detection excellence
    BKST Bakkialakshmi VS.
    Journal of Information & Optimization Sciences 46 (No. 6,), pp.1995–2004 , 2025
    2025
  • Multi-model ensemble deep learning framework for robust stock market forecasting: integration of economic indicators and temporal dependencies
    P Jain, D Bishnoi, N Bishnoi, B VS, L Mookiah
    Seventh International Conference on Image, Video Processing, and Artificial … , 2025
    2025
  • Machine Learning Prediction of ADHD Metrics From Conners' CPT-II Data and Demographics
    JS Satvik, S Raghu, VS Bakkialakshmi
    2025 Third International Conference on Networks, Multimedia and Information … , 2025
    2025
  • Body gesture recognition using crow search algorithm enhanced probabilistic neural network for human-computer interaction
    B VS, P Chawengsaksopark, M Sathiyanarayanan
    F1000Research 14, 149 , 2025
    2025
  • GENI: A Multi-module AI Assistant
    M Goel, VS Bakkialakshmi, N Aneja
    International Conference on Cognitive and Intelligent Computing, 417-424 , 2024
    2024
  • SAGA-Integrating AI for Enhanced Recruitment: A System with Audio-Video Proctoring and Comprehensive Evaluation
    N Mathur, A Sharma, S Kaushik, VS Bakkialakshmi, V Kavadiya, N Aneja
    2024 2nd International Conference on Advances in Computation, Communication … , 2024
    2024
  • Emotion Recognition from RGB Kinect Videos and Physiological Signals Using Pre-Trained CNN Model
    S Anand, L Mookiah, SS Surakshitha
    2024 International Conference on Intelligent Computing and Next Generation … , 2024
    2024