MADHUCHHANDA BASAK

@brainwareuniversity.ac.in

ASSISTANT PROFESSOR, COMPUTER SCIENCE AND ENGINEERING DEPARTMENT
BRAINWARE UIVERSITY

MADHUCHHANDA BASAK


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

EDUCATION

PHD PERSUNING

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
17

Scopus Publications

41

Scholar Citations

3

Scholar h-index

3

Scholar i10-index

Scopus Publications

  • Optimizing Schizophrenia Detection from EEG with Monarch Butterfly Optimization and Machine Learning Models
    Madhuchhanda Basak, Diptadip Maiti
    Lecture Notes in Networks and Systems, 2026
  • Dual-Head Lightweight ResNet Framework for Brain Tumor Segmentation and Multi-Class Diagnosis
    Diptadip Maiti, Madhuchhanda Basak
    Proceedings of the 4th IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation Iatmsi 2026, 2026
  • Deep Latent Representation Learning for Pan-Cancer Classification with Explainable Boosting from High-Dimensional Gene Expression Data
    Diptadip Maiti, Madhuchhanda Basak
    Esic 2026 Proceedings 6th International Conference on Emerging Systems and Intelligent Computing, 2026
    High-dimensional gene expression data pose substantial challenges for predictive modeling due to noise, redundancy, and the curse of dimensionality. This work introduces a hybrid machine learning framework that integrates a Variational Autoencoder (VAE) for nonlinear dimensionality reduction with an Explainable Boosting Machine (EBM) for transparent multiclass cancer classification. The VAE compresses over 20,000 transcriptomic features into a 64-dimensional latent space while preserving biologically meaningful structure, yielding improved separability across tumor types. These latent representations are then classified using an EBM, enabling inherently interpretable predictions supported by global feature importance and SHAPbased local explanations. Experiments on the TCGA Pan-Cancer dataset demonstrate the effectiveness of the proposed pipeline, achieving 0.98 accuracy, 0.99 macro-precision, 0.97 macro-recall, and 0.98 macro-F1, with per-class F1-scores ranging from 0.95 to 1.00. The results highlight that the VAE-EBM framework provides both high predictive performance and clinical interpretability, offering a promising direction for precision oncology.
  • A review on fingerprint based authentication-its challenges and applications
    Diptadip Maiti, Madhuchhanda Basak, Debashis Das
    Computer Science Review, 2025
  • Impact of Bio-inspired Optimization Techniques on EEG Signal Classification for Psychiatric Disorder Diagnosis
    Madhuchhanda Basak, Diptadip Maiti
    International Conference on Computing Intelligence and Application Ciacon 2025, 2025
    This study investigates the classification of psychiatric disorders using electroencephalogram (EEG) data, with a focus on enhancing feature selection and classification accuracy through advanced optimization techniques. The methodology comprises several stages: EEG signal acquisition, preprocessing, feature extraction, and clinical-based class labelling. Given the inherent challenges of high-dimensional data and class imbalance in EEG datasets, five bio-inspired optimization algorithms are employed to optimize feature selection: Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO), Monarch Butterfly Optimization (MBO), Harris Hawks Optimization (HHO), and Glowworm Swarm Optimization (GSO). These algorithms aim to identify the most relevant features while minimizing computational overhead. An Artificial Neural Network (ANN) classifier is trained on the optimized feature sets to predict psychiatric disorders. A comparative analysis of the optimization methods reveals that HHO offers the fastest execution time, MBO excels in selecting a diverse set of features, and ABC provides a strong balance between efficiency and classification accuracy. The findings underscore the significance of selecting suitable optimization strategies tailored to computational resources and data characteristics to improve EEG-based psychiatric disorder classification.
  • Patch-wise Deep Learning with Attention and Hybrid Supervision for Fundus-Based Glaucoma Screening
    Diptadip Maiti, Madhuchhanda Basak
    Proceedings of the International Conference on Research in Computational Intelligence and Communication Networks Icrcicn, 2025
    Glaucoma is a significant cause of permanent blindness. Accurate detection of fundus imagery is crucial for timely action. We present a unique patch-driven deep learning model that includes EfficientNet-B0 backbones, an attentionbased ensemble mechanism, and hybrid loss functions. The model processes eight image patches in parallel and leverages intermodel consistency via KL divergence, label smoothing, and cosine similarity to improve robustness. We detail the methodology, mathematical formulations, and implementation, and validate the model on the ACRIMA dataset, achieving significant improvements over baseline methods.
  • Inter-Generational Fingerprint Correlation Analysis: Unveiling Inherited Patterns and Identification Reliability
    Diptadip Maiti, Madhuchhanda Basak, Debashis Das
    Smart Innovation Systems and Technologies, 2025
  • Automated Seizure Detection from EEG Using Hilbert-Huang Transform and Autoencoder-Based Classification
    Madhuchhanda Basak, Diptadip Maiti, Debashis Das
    Lecture Notes in Networks and Systems, 2025
  • NeuroExplain: An Explainable Deep Learning Framework for Multiclass Emotion Recognition from Gameplay EEG
    Diptadip Maiti, Madhuchhanda Basak, Sudipta Hazra
    2025 5th International Conference on Emerging Research in Electronics Computer Science and Technology Icerect 2025, 2025
    This paper presents a novel framework for emotion detection from electroencephalogram (EEG) signals, integrating both deep learning and traditional machine learning approaches to enhance classification accuracy and model interpretability. The proposed pipeline includes preprocessing, feature extraction, class balancing using SMOTE, and the evaluation of multiple classifiers, including XGBoost, Random Forest, Support Vector Machine (SVM), and a deep Artificial Neural Network (ANN). Among these, XGBoost achieved the highest accuracy of 94.98%, followed by Random Forest (93.49%) and ANN (93.00%). The performance of these models was evaluated using metrics such as accuracy, F1-score, and confusion matrix. Additionally, the interpretability of the top-performing models was further enhanced using explainable AI techniques, such as SHAP and Integrated Gradients (IG), which provided valuable insights into the key EEG features contributing to emotion classification. The results demonstrate the effectiveness of ensemble-based methods and deep learning for EEG-based emotion detection, while highlighting the importance of model transparency in real-world applications. The framework holds significant potential for improving emotion detection systems and offers avenues for future research, including the exploration of advanced feature extraction methods, real-time classification, and further optimization of explainability techniques.
  • Region based Image Contrast Enhancement Depending on Local Dominant Colour Component
    Debashis Das, Diptadip Maiti
    Proceedings 2024 8th International Conference on Imaging Signal Processing and Communications Icispc 2024, 2024
    In this paper, we propose an image contrast enhancement mechanism by analysing the dominant colour component of every contributory pixel. The contrast enhancement is performed on the regions having similar dominating colour components by employing local histogram equalization. The process ensures the increment of the colour purity by preserving the level of brightness which is a major drawback of histogram equalization-based methods. The proposed method provides satisfactory results without any learning mechanism applied in the system which reduces the execution time of the process as well. The proposed algorithm is formulated, experimented and tested on a large set of standard colour images, in RGB format, collected from various databases. We compare the proposed method with both standalone and learning based image enhancement algorithms from the literature. The comparative analysis establishes the efficacy of the proposed method.
  • Deep Learning Method for Multi-Attribute Analysis of Fingerprint Images
    Diptadip Maiti, Madhuchhanda Basak, Debashis Das
    Computer Science Journal of Moldova, 2024
  • Fingerprint-Based Asymmetric Bio-Cryptographic Key Generation Using Convolution Network
    Diptadip Maiti, Madhuchhanda Basak, Debashis Das
    Lecture Notes in Networks and Systems, 2024
  • Synthetic Fingerprint Generation: Bridging the Gap Between Privacy and Security with Variational Auto-Encoders
    Diptadip Maiti, Madhuchhanda Basak, Debashis Das
    Lecture Notes in Networks and Systems, 2024
  • Advancing Fingerprint Template Generation and Matching With Recast Minutiae Clustering and mRBFN
    Diptadip Maiti, Madhuchhanda Basak, Debashis Das
    Advances in Artificial Intelligence and Machine Learning, 2024
  • Gender and Hand Identification Based on Dactyloscopy Using Deep Convolutional Neural Network
    Diptadip Maiti, Debashis Das
    Lecture Notes in Networks and Systems, 2023
  • A Hybrid Approach Of Differential Evolution And Multistage LSTM For Diagnosis Of Psychiatric Disorder Using EEG
    Madhuchhanda Basak, Diptadip Maiti, Debashis Das
    Proceedings of the 2023 IEEE International Conference on Computer Vision and Machine Intelligence Cvmi 2023, 2023
  • Enhancing Seizure Detection from EEG Signals-Optimization Driven Feature Selection and Classification using Artificial Neural Networks
    Madhuchhanda Basak, Diptadip Maiti, Debashis Das
    Conference Proceedings 2023 IEEE Silchar Subsection Conference Silcon 2023, 2023

RECENT SCHOLAR PUBLICATIONS

  • Decoding Dyslexia from EEG Signals Using Graph Based Neural Network
    M Basak, D Maiti, D Chaudhury
    AI, Computer Science and Robotics Technology , 2026
    2026
  • A Neuro-Symbolic Kolmogorov–Arnold Network Model for Dyslexia Detection from EEG Signals
    D Maiti, M Basak
    2026 IEEE Madhya Pradesh Section Conference (MPCON), 816-822 , 2026
    2026
  • Dual-Head Lightweight ResNet Framework for Brain Tumor Segmentation and Multi-Class Diagnosis
    D Maiti, M Basak
    2026 IEEE International Conference on Interdisciplinary Approaches in … , 2026
    2026
  • Deep Latent Representation Learning for Pan-Cancer Classification with Explainable Boosting from High-Dimensional Gene Expression Data
    D Maiti, M Basak
    2026 International Conference on Emerging Systems and Intelligent Computing … , 2026
    2026
  • Equilibrium-Based Feature Selection and Explainable Boosting for Pan-Cancer Prediction from Gene Expression Data
    D Maiti, M Basak
    2026 International Conference on Computing, Electronics & Communications … , 2026
    2026
  • Decoding Dyslexia from Electroencephalogram Signals Using a Graph-Based Neural Network
    M Basak, D Maiti, D Chaudhury
    AI , 2026
    2026
  • Patch-wise Deep Learning with Attention and Hybrid Supervision for Fundus-Based Glaucoma Screening
    D Maiti, M Basak
    2025 Seventh International Conference on Research in Computational … , 2025
    2025
  • Optimizing Schizophrenia Detection from EEG with Monarch Butterfly Optimization and Machine Learning
    M Basak, D Maiti
    Communication and Intelligent Systems: Proceedings of ICCIS 2024, Volume 2 2, 95 , 2025
    2025
  • NeuroExplain: An Explainable Deep Learning Framework for Multiclass Emotion Recognition from Gameplay EEG
    D Maiti, M Basak, S Hazra
    2025 5th International Conference on Emerging Research in Electronics … , 2025
    2025
  • A review on fingerprint based authentication-its challenges and applications
    D Maiti, M Basak, D Das
    Computer Science Review 57, 100735 , 2025
    2025
    Citations: 10
  • Impact of Bio-inspired Optimization Techniques on EEG Signal Classification for Psychiatric Disorder Diagnosis
    M Basak, D Maiti
    2025 International Conference on Computing, Intelligence, and Application … , 2025
    2025
  • Using Hilbert-Huang Transform
    M Basak, D Maiti, D Das
    Fifth Congress on Intelligent Systems: CIS 2024, Volume 2 2, 97 , 2025
    2025
  • Enhancing ECG Abnormality Detection Using Image Processing and Transfer Learning Approach
    D Maiti, M Basak
    International Conference on Computational Intelligence, 115-132 , 2024
    2024
    Citations: 1
  • Optimizing Schizophrenia Detection from EEG with Monarch Butterfly Optimization and Machine Learning Models
    M Basak, D Maiti
    International Conference on Communication and Intelligent Systems, 95-110 , 2024
    2024
  • Automated Seizure Detection from EEG Using Hilbert-Huang Transform and Autoencoder-Based Classification
    M Basak, D Maiti, D Das
    Congress on Intelligent Systems, 97-113 , 2024
    2024
  • Multimodal biometric integration: Trends and insights from the past quinquennial
    D Maiti, M Basak, D Das
    World Journal of Advanced Research and Reviews 23 (3), 1590-1605 , 2024
    2024
    Citations: 11
  • EEG innovations in neurological disorder diagnostics: a Five-Year review
    M Basak, D Maiti, D Das
    Asian Journal of Research in Computer Science 17 (6), 226-249 , 2024
    2024
    Citations: 11
  • Emotion Detection from EEG by Gated Recurrent Unit Along with Particle Swarm Optimization
    M Basak, D Maiti, D Das
    International Conference on Security, Surveillance and Artificial … , 2024
    2024
  • Deep Learning Method for Multi-Attribute Analysis of Fingerprint Images.
    D Maiti, M Basak, D Das
    Computer Science Journal of Moldova 32 (2) , 2024
    2024
    Citations: 1
  • Synthetic Fingerprint Generation: Bridging the Gap Between Privacy and Security with Variational Auto-Encoders
    D Maiti, M Basak, D Das
    International Conference on Computing and Machine Learning, 221-235 , 2024
    2024
    Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

  • Multimodal biometric integration: Trends and insights from the past quinquennial
    D Maiti, M Basak, D Das
    World Journal of Advanced Research and Reviews 23 (3), 1590-1605 , 2024
    2024
    Citations: 11
  • EEG innovations in neurological disorder diagnostics: a Five-Year review
    M Basak, D Maiti, D Das
    Asian Journal of Research in Computer Science 17 (6), 226-249 , 2024
    2024
    Citations: 11
  • A review on fingerprint based authentication-its challenges and applications
    D Maiti, M Basak, D Das
    Computer Science Review 57, 100735 , 2025
    2025
    Citations: 10
  • Fingerprint bio-metric: Confronting challenges, embracing evolution, and extending utility—A review
    D Maiti, M Basak, D Das
    J. Eng. Res. Sci 3, 26-60 , 2024
    2024
    Citations: 2
  • A hybrid approach of differential evolution and multistage lstm for diagnosis of psychiatric disorder using eeg
    M Basak, D Maiti, D Das
    2023 IEEE International Conference on Computer Vision and Machine … , 2023
    2023
    Citations: 2
  • Deep Gender Identification Model with Biometric Fingerprint Data
    D Maiti, M Basak
    International Journal of Innovative Science and Research Technology 8 (2 … , 2023
    2023
    Citations: 2
  • Enhancing ECG Abnormality Detection Using Image Processing and Transfer Learning Approach
    D Maiti, M Basak
    International Conference on Computational Intelligence, 115-132 , 2024
    2024
    Citations: 1
  • Deep Learning Method for Multi-Attribute Analysis of Fingerprint Images.
    D Maiti, M Basak, D Das
    Computer Science Journal of Moldova 32 (2) , 2024
    2024
    Citations: 1
  • Synthetic Fingerprint Generation: Bridging the Gap Between Privacy and Security with Variational Auto-Encoders
    D Maiti, M Basak, D Das
    International Conference on Computing and Machine Learning, 221-235 , 2024
    2024
    Citations: 1
  • Decoding Dyslexia from EEG Signals Using Graph Based Neural Network
    M Basak, D Maiti, D Chaudhury
    AI, Computer Science and Robotics Technology , 2026
    2026
  • A Neuro-Symbolic Kolmogorov–Arnold Network Model for Dyslexia Detection from EEG Signals
    D Maiti, M Basak
    2026 IEEE Madhya Pradesh Section Conference (MPCON), 816-822 , 2026
    2026
  • Dual-Head Lightweight ResNet Framework for Brain Tumor Segmentation and Multi-Class Diagnosis
    D Maiti, M Basak
    2026 IEEE International Conference on Interdisciplinary Approaches in … , 2026
    2026
  • Deep Latent Representation Learning for Pan-Cancer Classification with Explainable Boosting from High-Dimensional Gene Expression Data
    D Maiti, M Basak
    2026 International Conference on Emerging Systems and Intelligent Computing … , 2026
    2026
  • Equilibrium-Based Feature Selection and Explainable Boosting for Pan-Cancer Prediction from Gene Expression Data
    D Maiti, M Basak
    2026 International Conference on Computing, Electronics & Communications … , 2026
    2026
  • Decoding Dyslexia from Electroencephalogram Signals Using a Graph-Based Neural Network
    M Basak, D Maiti, D Chaudhury
    AI , 2026
    2026
  • Patch-wise Deep Learning with Attention and Hybrid Supervision for Fundus-Based Glaucoma Screening
    D Maiti, M Basak
    2025 Seventh International Conference on Research in Computational … , 2025
    2025
  • Optimizing Schizophrenia Detection from EEG with Monarch Butterfly Optimization and Machine Learning
    M Basak, D Maiti
    Communication and Intelligent Systems: Proceedings of ICCIS 2024, Volume 2 2, 95 , 2025
    2025
  • NeuroExplain: An Explainable Deep Learning Framework for Multiclass Emotion Recognition from Gameplay EEG
    D Maiti, M Basak, S Hazra
    2025 5th International Conference on Emerging Research in Electronics … , 2025
    2025
  • Impact of Bio-inspired Optimization Techniques on EEG Signal Classification for Psychiatric Disorder Diagnosis
    M Basak, D Maiti
    2025 International Conference on Computing, Intelligence, and Application … , 2025
    2025
  • Using Hilbert-Huang Transform
    M Basak, D Maiti, D Das
    Fifth Congress on Intelligent Systems: CIS 2024, Volume 2 2, 97 , 2025
    2025