Debjani Chakraborty
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Debjani Chakraborty has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Debashree Guha
School of Medical Science and Technology, Indian Institute of Technology Kharagpur, Kharagpur, India
5 shared publications - Debdas Ghosh
Department of Mathematical Sciences Indian Institute of Technology (BHU) 221005 Varanasi Uttar Pradesh India
5 shared publications - Vishnu Pratap Singh
Department of Mathematics, Visvesvaraya National Institute of Technology, Nagpur, India
5 shared publications - Ali Ebrahimnejad
Department of Mathematics, QaS.C., Islamic Azad University, Qaemshahr, Iran
4 shared publications - Debashree Guha
School of Medical Science and Technology, Indian Institute of Technology Kharagpur, Kharagpur, India
4 shared publications Debdas Ghosh
Indian Institute of Technology (BHU) Varanasi
4 shared publications
Latest Publications
- 22 July 2026
- Published by Springer Nature in Evolving Systems
- Vol. 17 (3) , 96
MTRBO: multiple trust-region based Bayesian optimization
- 22 July 2026
- Published by Springer Nature in Evolving Systems
- Vol. 17 (3) , 96
MTRBO: multiple trust-region based Bayesian optimization
- 23 June 2026
- Published by Taylor & Francis in International Journal of Systems Science
- p. 1-24
Inter observer variability assessment through ordered weighted belief divergence measure in MAGDM
1. Multi-attribute group decision-making (MAGDM) is a crucial part of modern decision sciences, which has been extensively used in various potential fields, such as pattern recognition (Kumar & Kum...
- 23 June 2026
- Published by Taylor & Francis in International Journal of Systems Science
- p. 1-24
Inter observer variability assessment through ordered weighted belief divergence measure in MAGDM
1. Multi-attribute group decision-making (MAGDM) is a crucial part of modern decision sciences, which has been extensively used in various potential fields, such as pattern recognition (Kumar & Kum...
- Open Access
- 13 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Adaptive queue management in healthcare using supervised Q-learning with time-varying reward and cost structures
Efficient patient management in hospitals requires adaptive decision-making under time-varying demand and dynamic service environments. This study proposes a heterogeneous medical patient queueing model that integrates reinforcement learning with stochastic queue dynamics to minimize overall patient waiting time. The model distinguishes between two categories of service providers (SPs): those attending first-time patients and those serving returning patients. Each category may differ in service rate but not in medical specialty. Patient arrivals follow a non-homogeneous Poisson process (NHPP) to capture realistic time-dependent flow variations. A Q-learning framework with a supervised ε-greedy policy is developed to determine optimal operational actions, such as adding or reallocating service providers, based on system state and event type. Separate Q-tables are maintained for arrival and departure events to account for differing cost and reward dynamics. Simulation results demonstrate that the proposed model significantly reduces total waiting time and system cost compared with conventional homogeneous queue models. This approach provides a data-driven mechanism for dynamic hospital queue management and can be extended to broader healthcare resource optimization scenarios.
- 13 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessAdaptive queue management in healthcare using supervised Q-learning with time-varying reward and cost structures
Efficient patient management in hospitals requires adaptive decision-making under time-varying demand and dynamic service environments. This study proposes a heterogeneous medical patient queueing model that integrates reinforcement learning with stochastic queue dynamics to minimize overall patient waiting time. The model distinguishes between two categories of service providers (SPs): those attending first-time patients and those serving returning patients. Each category may differ in service rate but not in medical specialty. Patient arrivals follow a non-homogeneous Poisson process (NHPP) to capture realistic time-dependent flow variations. A Q-learning framework with a supervised ε-greedy policy is developed to determine optimal operational actions, such as adding or reallocating service providers, based on system state and event type. Separate Q-tables are maintained for arrival and departure events to account for differing cost and reward dynamics. Simulation results demonstrate that the proposed model significantly reduces total waiting time and system cost compared with conventional homogeneous queue models. This approach provides a data-driven mechanism for dynamic hospital queue management and can be extended to broader healthcare resource optimization scenarios.
- Open Access
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 21137-21147
Ranking Feature Importance Objectives for Explainable Classification
Recent studies on explainable machine learning models often analyse feature importance after training, but this results in a model that doesn’t capture feature dependencies and requires extra computational resources for explainability. We propose a method for training a supervised learning model through multi-objective optimisation that considers accuracy and feature importance in a unified framework. This method provides an explainable training procedure that consistently minimises the model’s loss and maximises individual feature importance objectives, improving classification decision-making. We explore interpretable model training using many-objective and bi-objective optimisation formulations. Choosing an interpretable framework from these pathways is challenging, so we propose outranking them by constructing a credibility index based on performance metrics. Our experiments on the UCI repository and medical image datasets show the benefits of capturing feature importance early, ensuring intrinsic explainability.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 21137-21147
Open AccessRanking Feature Importance Objectives for Explainable Classification
Recent studies on explainable machine learning models often analyse feature importance after training, but this results in a model that doesn’t capture feature dependencies and requires extra computational resources for explainability. We propose a method for training a supervised learning model through multi-objective optimisation that considers accuracy and feature importance in a unified framework. This method provides an explainable training procedure that consistently minimises the model’s loss and maximises individual feature importance objectives, improving classification decision-making. We explore interpretable model training using many-objective and bi-objective optimisation formulations. Choosing an interpretable framework from these pathways is challenging, so we propose outranking them by constructing a credibility index based on performance metrics. Our experiments on the UCI repository and medical image datasets show the benefits of capturing feature importance early, ensuring intrinsic explainability.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 145116-145132
Bayesian Fuzzy Optimization With Gaussian Fuzzy Process
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 145116-145132
Open AccessBayesian Fuzzy Optimization With Gaussian Fuzzy Process
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (1) , 425-435
Bonferroni Mean Pre-aggregation Operator Assisted Dynamic Fuzzy Histogram Equalization for Retinal Vascular Segmentation
Vasculature feature segmentation from the fundus images is critical for the identification of retinal diseases. However, automated vessel segmentation is challenging owing to variability in vessel structure and color gradients, low contrast between vessels, and pathologies. The state-of-the-art approaches address the challenges of emerging hand-crafted filters to apprehend vessel- like patterns. More recently, deep learning-based methods have evolved for the vessel segmentation task, which employs annotations to train the model. These approaches ignore the vessel's geometrical characteristics in the fundus images, leading to inaccuracies. Herein, we propose a novel unsupervised segmentation method based on interrelationship handling, Bonferroni mean pre-aggregation operator, with the aid of dynamic fuzzy histogram equalization, namely BMPDFHESeg. The method extracts the vascular information by fusing color channels by constructing an interrelationship handling pre-aggregation operator. The operator enables finding the direction of increasingness to segment large vessels and vessel feature enhancement through a dynamic fuzzy histogram equalization process using the prior feature intensity information. BMPDFHESeg is assessed qualitatively and quantitatively using the DRIVE, STARE, and HRF datasets, demonstrating enhanced efficacy and computational speed. Further, the results were validated by ophthalmologists for the accuracy of the vessel segmentation and usefulness for the diagnosis of retinal disorders.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (1) , 425-435
Bonferroni Mean Pre-aggregation Operator Assisted Dynamic Fuzzy Histogram Equalization for Retinal Vascular Segmentation
Vasculature feature segmentation from the fundus images is critical for the identification of retinal diseases. However, automated vessel segmentation is challenging owing to variability in vessel structure and color gradients, low contrast between vessels, and pathologies. The state-of-the-art approaches address the challenges of emerging hand-crafted filters to apprehend vessel- like patterns. More recently, deep learning-based methods have evolved for the vessel segmentation task, which employs annotations to train the model. These approaches ignore the vessel's geometrical characteristics in the fundus images, leading to inaccuracies. Herein, we propose a novel unsupervised segmentation method based on interrelationship handling, Bonferroni mean pre-aggregation operator, with the aid of dynamic fuzzy histogram equalization, namely BMPDFHESeg. The method extracts the vascular information by fusing color channels by constructing an interrelationship handling pre-aggregation operator. The operator enables finding the direction of increasingness to segment large vessels and vessel feature enhancement through a dynamic fuzzy histogram equalization process using the prior feature intensity information. BMPDFHESeg is assessed qualitatively and quantitatively using the DRIVE, STARE, and HRF datasets, demonstrating enhanced efficacy and computational speed. Further, the results were validated by ophthalmologists for the accuracy of the vessel segmentation and usefulness for the diagnosis of retinal disorders.
- 12 December 2025
- Published by Springer Nature in Journal of Materials Engineering and Performance
- Vol. 35 (13) , 12916-12927
Parametric Optimization of Multicomponent Laser Surface Alloying of AISI 316L Stainless Steel using Taguchi’s Grey Relational Analysis
- 12 December 2025
- Published by Springer Nature in Journal of Materials Engineering and Performance
- Vol. 35 (13) , 12916-12927
Parametric Optimization of Multicomponent Laser Surface Alloying of AISI 316L Stainless Steel using Taguchi’s Grey Relational Analysis
- 7 November 2025
- Published by Springer Nature
- p. 109-120
Feature-Importance Aware Deep Neural Network Model for Explainable Recommender Systems
- 7 November 2025
- Published by Springer Nature
- p. 109-120
Feature-Importance Aware Deep Neural Network Model for Explainable Recommender Systems
- 23 August 2025
- Published by Springer Nature in OPSEARCH
- p. 1-24
A hybrid clustering and greedy routing approach to solve a two-level location allocation and a static dial-a-ride problem
- 23 August 2025
- Published by Springer Nature in OPSEARCH
- p. 1-24
A hybrid clustering and greedy routing approach to solve a two-level location allocation and a static dial-a-ride problem