Sudipta Debroy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sudipta Debroy has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Arjun Sil
National Institute of Technology Silchar
3 shared publications Arjun Sil
Department of Civil Engineering National Institute of Technology Silchar Assam India
1 shared publication
Latest Publications
- Open Access
- 21 December 2024
- Published by Institution of Engineering and Technology (IET) in Digital Twins and Applications
- Vol. 2 (1)
CNN‐based multi‐output regression model to estimate infrastructural surface crack dimensions adopting a generalised patch size and FWHM‐based width quantification
To cater the need for real‐time crack monitoring of infrastructural facilities, a CNN‐regression model is proposed to directly estimate the crack properties from patches. RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square pixels that are classified with a pre‐trained deep convolution neural network, the true positives are segmented, and crack properties are extracted using two different methods. The first method is primarily based on active contour models and level‐set segmentation and the second method consists of the domain adaptation of a mathematical morphology‐based method known as FILFINDER. A statistical test has been performed for the comparison of the stated methods and a database prepared with the more suitable method. An advanced convolution neural network‐based multi‐output regression model has been proposed which was trained with the prepared database and validated with the held‐out dataset for the prediction of crack‐length, crack‐width, and width‐uncertainty directly from input image patches. The proposed model has been tested on crack patches collected from different locations. Huber loss has been used to ensure the robustness of the proposed model selected from a set of 288 different variations of it. Additionally, an ablation study has been conducted on the top 3 models that demonstrated the influence of each network component on the prediction results. Finally, the best performing model HHc‐X among the top 3 has been proposed that predicted crack properties which are in close agreement to the ground truths in the test data.
- 21 December 2024
- Published by Institution of Engineering and Technology (IET) in Digital Twins and Applications
- Vol. 2 (1)
Open AccessCNN‐based multi‐output regression model to estimate infrastructural surface crack dimensions adopting a generalised patch size and FWHM‐based width quantification
To cater the need for real‐time crack monitoring of infrastructural facilities, a CNN‐regression model is proposed to directly estimate the crack properties from patches. RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square pixels that are classified with a pre‐trained deep convolution neural network, the true positives are segmented, and crack properties are extracted using two different methods. The first method is primarily based on active contour models and level‐set segmentation and the second method consists of the domain adaptation of a mathematical morphology‐based method known as FILFINDER. A statistical test has been performed for the comparison of the stated methods and a database prepared with the more suitable method. An advanced convolution neural network‐based multi‐output regression model has been proposed which was trained with the prepared database and validated with the held‐out dataset for the prediction of crack‐length, crack‐width, and width‐uncertainty directly from input image patches. The proposed model has been tested on crack patches collected from different locations. Huber loss has been used to ensure the robustness of the proposed model selected from a set of 288 different variations of it. Additionally, an ablation study has been conducted on the top 3 models that demonstrated the influence of each network component on the prediction results. Finally, the best performing model HHc‐X among the top 3 has been proposed that predicted crack properties which are in close agreement to the ground truths in the test data.
- Open Access
- 23 August 2024
- Published by Springer Nature in Research Square
Empirical models for non-destructive evaluation of in-situ compressive strength of structural concrete with the objective of encompassing global uncertainty factors
The compressive strength of concrete, although, conventionally, used to be determined either by destructive tests of cubes cast in-situ, or from concrete cores extracted from an existing structure, can be easily estimated at present with the help of empirical correlations with inputs from non-destructive test results of Rebound Hammer and Ultrasonic Pulse Velocity. The main contribution of this paper lies in the proposition of empirical correlations for compressive strength determination from a global uncertainty perspective, not considered previously to the best of the authors’ knowledge. To fulfil this objective, correlation equations published worldwide for both univariate and bivariate relationships have been collected and the most suitable ones selected based on their statistical reliability. Further, linear and non-linear regression analysis have been performed on justifiably chosen datasets for the predictor variables. Finally, Linear, Polynomial, Power and Exponential models are developed with appreciable metrics outcomes for all three types of correlations and the best three models proposed after successful validation on country-wise in-situ data accumulated from various literatures.
- 23 August 2024
- Published by Springer Nature in Research Square
Open AccessEmpirical models for non-destructive evaluation of in-situ compressive strength of structural concrete with the objective of encompassing global uncertainty factors
The compressive strength of concrete, although, conventionally, used to be determined either by destructive tests of cubes cast in-situ, or from concrete cores extracted from an existing structure, can be easily estimated at present with the help of empirical correlations with inputs from non-destructive test results of Rebound Hammer and Ultrasonic Pulse Velocity. The main contribution of this paper lies in the proposition of empirical correlations for compressive strength determination from a global uncertainty perspective, not considered previously to the best of the authors’ knowledge. To fulfil this objective, correlation equations published worldwide for both univariate and bivariate relationships have been collected and the most suitable ones selected based on their statistical reliability. Further, linear and non-linear regression analysis have been performed on justifiably chosen datasets for the predictor variables. Finally, Linear, Polynomial, Power and Exponential models are developed with appreciable metrics outcomes for all three types of correlations and the best three models proposed after successful validation on country-wise in-situ data accumulated from various literatures.
- Open Access
- 15 January 2024
- Published by Springer Nature in Research Square
CNN based multi-output regression model to estimate infrastructural surface crack dimensions adopting a generalized patch size and FWHM-based width quantification
To cater the need for real-time crack monitoring of infrastructural facilities, a CNNRegression model is proposed to directly estimate the crack properties from patches. RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square-pixels that are classified with a pre-trained Deep Convolution Neural Network, the True Positives are segmented and crack properties extracted using two different methods. A statistical test has been performed for comparison and a database prepared with the more suitable method which is then fed into the neural network model to predict crack-length, crack-width and widthuncertainty directly. The proposed model has been tested on crack patches collected from different locations. Huber Loss has been used to ensure robustness of the proposed model selected from a set of 288 different variations of it. In spite of using a limited sized data set, quite satisfactory results have been achieved.
- 15 January 2024
- Published by Springer Nature in Research Square
Open AccessCNN based multi-output regression model to estimate infrastructural surface crack dimensions adopting a generalized patch size and FWHM-based width quantification
To cater the need for real-time crack monitoring of infrastructural facilities, a CNNRegression model is proposed to directly estimate the crack properties from patches. RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square-pixels that are classified with a pre-trained Deep Convolution Neural Network, the True Positives are segmented and crack properties extracted using two different methods. A statistical test has been performed for comparison and a database prepared with the more suitable method which is then fed into the neural network model to predict crack-length, crack-width and widthuncertainty directly. The proposed model has been tested on crack patches collected from different locations. Huber Loss has been used to ensure robustness of the proposed model selected from a set of 288 different variations of it. In spite of using a limited sized data set, quite satisfactory results have been achieved.