Alaka Das
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alaka Das has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Nibaran Das
Department of Computer Science and Engineering, Jadavpur University, Kolkata, India
5 shared publications - Somenath Kuiry
Jadavpur University
5 shared publications - Mita Nasipuri
Department of Computer Science and Engineering, Jadavpur University, Kolkata, India
3 shared publications - Hiya Mondal
Department of Applied Science, RCC Institute of Information Technology, Beliaghata, India
2 shared publications - Mita Nasipuri
Jadavpur University
2 shared publications Sujay Biswas
Department of Mathematics, Deshbandhu College for Girls, Kolkata, India
2 shared publications
Latest Publications
- 8 December 2025
- Published by Springer Nature in The European Physical Journal Plus
- Vol. 140 (12) , 1182
Linear theory of Rayleigh–Bénard magnetoconvection in presence of both gravity and temperature modulations
- 8 December 2025
- Published by Springer Nature in The European Physical Journal Plus
- Vol. 140 (12) , 1182
Linear theory of Rayleigh–Bénard magnetoconvection in presence of both gravity and temperature modulations
- 12 February 2025
- Published by Springer Nature
- p. 257-269
Regularizing CNNs Using Confusion Penalty Based Label Smoothing for Histopathology Images
- 12 February 2025
- Published by Springer Nature
- p. 257-269
Regularizing CNNs Using Confusion Penalty Based Label Smoothing for Histopathology Images
- 12 February 2025
- Published by Springer Nature
- p. 100-112
COVID-CT-H-UNet: A Novel COVID-19 CT Segmentation Network Based on Attention Mechanism and Bi-Category Hybrid Loss
- 12 February 2025
- Published by Springer Nature
- p. 100-112
COVID-CT-H-UNet: A Novel COVID-19 CT Segmentation Network Based on Attention Mechanism and Bi-Category Hybrid Loss
- 1 February 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 34 (01)
GA-RISE: Posthoc Model Agnostic Explanations of Black-Box Classifiers Using Genetic Algorithm-Based Optimized Masks — A Case Study on Chest X-ray Images
The intricate and recursive nature of deep learning models often obscures their inner workings, limiting their applications in high-risk domains like medical image analysis. The development of Explainable AI (XAI) methods has addressed this limitation by providing human-readable insights into these black-box models, which are widely used in image-based tasks such as classification, segmentation, and localization. One popular and effective XAI technique is Randomized Input Sampling for Explanation (RISE), which uses a large number of random masks to visualize model behavior. However, RISE’s requirement for numerous masks leads to high space complexity. In this paper, we propose a modified RISE technique that optimizes the use of a relatively small number of masks through a Genetic Algorithm to enhance comprehensibility. Experiments with state-of-the-art classifier models on a publicly available Chest X-ray dataset demonstrate that our approach outperforms other commonly used post hoc model-agnostic and non-model-agnostic techniques in terms of explanation quality and faithfulness metrics.
- 1 February 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 34 (01)
GA-RISE: Posthoc Model Agnostic Explanations of Black-Box Classifiers Using Genetic Algorithm-Based Optimized Masks — A Case Study on Chest X-ray Images
The intricate and recursive nature of deep learning models often obscures their inner workings, limiting their applications in high-risk domains like medical image analysis. The development of Explainable AI (XAI) methods has addressed this limitation by providing human-readable insights into these black-box models, which are widely used in image-based tasks such as classification, segmentation, and localization. One popular and effective XAI technique is Randomized Input Sampling for Explanation (RISE), which uses a large number of random masks to visualize model behavior. However, RISE’s requirement for numerous masks leads to high space complexity. In this paper, we propose a modified RISE technique that optimizes the use of a relatively small number of masks through a Genetic Algorithm to enhance comprehensibility. Experiments with state-of-the-art classifier models on a publicly available Chest X-ray dataset demonstrate that our approach outperforms other commonly used post hoc model-agnostic and non-model-agnostic techniques in terms of explanation quality and faithfulness metrics.
- 28 September 2023
- Published by Springer Nature in Journal of the Korean Physical Society
- Vol. 83 (12) , 909-920
Hysteresis and synchronization in an inhomogeneous system
- 28 September 2023
- Published by Springer Nature in Journal of the Korean Physical Society
- Vol. 83 (12) , 909-920
Hysteresis and synchronization in an inhomogeneous system
- 5 February 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (7) , 9385-9402
Deep Learning-Based Outdoor Object Detection Using Visible and Near-Infrared Spectrum
- 5 February 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (7) , 9385-9402
Deep Learning-Based Outdoor Object Detection Using Visible and Near-Infrared Spectrum
- 21 January 2022
- Published by IOP Publishing in Fluid Dynamics Research
- Vol. 54 (1) , 015503
Energy-conserving model of hexagonal pattern in Rayleigh-Bénard convection
We have constructed an energy-conserving 16 mode dynamical system to model hexagonal pattern in Rayleigh-Bénard convection of Boussinesq fluids with symmetric stress-free thermally conducting boundaries. The model shows stable roll pattern at the onset of convection. Hexagon is found to appear in the system via sausage and (or) stationary rhombus patterns. Both up and down hexagons arise periodically or chaotically with roll, sausage and rhombus patterns. Hexagonal pattern exists for all values of the Prandtl number, 1 ≤ P r ≤ 5 explored here. However, the pattern is more prominent for small Pr and k < k c , where k denotes the wave number. The plot of Nusselt number matches with previous theoretical result. In dissipationless limit, the total energy and the unavailable energy are constants though the kinetic energy, the potential energy and the available energy vary with time. The derived model does not diverge for large values of Rayleigh number Ra .
- 21 January 2022
- Published by IOP Publishing in Fluid Dynamics Research
- Vol. 54 (1) , 015503
Energy-conserving model of hexagonal pattern in Rayleigh-Bénard convection
We have constructed an energy-conserving 16 mode dynamical system to model hexagonal pattern in Rayleigh-Bénard convection of Boussinesq fluids with symmetric stress-free thermally conducting boundaries. The model shows stable roll pattern at the onset of convection. Hexagon is found to appear in the system via sausage and (or) stationary rhombus patterns. Both up and down hexagons arise periodically or chaotically with roll, sausage and rhombus patterns. Hexagonal pattern exists for all values of the Prandtl number, 1 ≤ P r ≤ 5 explored here. However, the pattern is more prominent for small Pr and k < k c , where k denotes the wave number. The plot of Nusselt number matches with previous theoretical result. In dissipationless limit, the total energy and the unavailable energy are constants though the kinetic energy, the potential energy and the available energy vary with time. The derived model does not diverge for large values of Rayleigh number Ra .
- Open Access
EDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation
In the literature, many fusion techniques are registered for the segmentation of images, but they primarily focus on observed output or belief score or probability score of the output classes. In the present work, we have utilized inter source statistical dependency among different classifiers for ensembling of different deep learning techniques for semantic segmentation of images. For this purpose, in the present work, a class-wise Copula-based ensembling method is newly proposed for solving the multi-class segmentation problem. Experimentally, it is observed that the performance has improved more for semantic image segmentation using the proposed class-specific Copula function than the traditionally used single Copula function for the problem. The performance is also compared with three state-of-the-art ensembling methods.
Open AccessEDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation
In the literature, many fusion techniques are registered for the segmentation of images, but they primarily focus on observed output or belief score or probability score of the output classes. In the present work, we have utilized inter source statistical dependency among different classifiers for ensembling of different deep learning techniques for semantic segmentation of images. For this purpose, in the present work, a class-wise Copula-based ensembling method is newly proposed for solving the multi-class segmentation problem. Experimentally, it is observed that the performance has improved more for semantic image segmentation using the proposed class-specific Copula function than the traditionally used single Copula function for the problem. The performance is also compared with three state-of-the-art ensembling methods.
- 9 November 2018
- Published by Elsevier in Physics Letters A
- Vol. 383 (5) , 421-431
Directed percolation phase transition at the onset of STI in an inhomogeneous coupled map lattice
- 9 November 2018
- Published by Elsevier in Physics Letters A
- Vol. 383 (5) , 421-431
Directed percolation phase transition at the onset of STI in an inhomogeneous coupled map lattice