Ravindra D. Gudi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ravindra D. Gudi has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
Abhilasha Maheshwari
Department of Chemical Engineering
6 shared publications- Shamik Misra
Chemical Engineering Department, Indian Institute of Technology, Bombay, Mumbai, India
4 shared publications - Buddhadev Goswami
Indian Institute of Technology Bombay
3 shared publications - Mani Bhushan
Department of Chemical Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India
3 shared publications - Sharad Bhartiya
Indian Institute of Technology Bombay
3 shared publications Aadil Bharucha
Department of Chemical Engineering
2 shared publications
Latest Publications
- 18 February 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65 (8) , 4471-4488
Maximal Flow Unit Network: Superstructure-Based Integration of Batch Scheduling and Sustainable Water Network Design
- 18 February 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65 (8) , 4471-4488
Maximal Flow Unit Network: Superstructure-Based Integration of Batch Scheduling and Sustainable Water Network Design
- 16 October 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64 (43) , 20679-20691
Optimizing Asset Value and Operational Costs for Sustainability in Industrial Water Systems: A Case Study of a Steel Plant
- 16 October 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64 (43) , 20679-20691
Optimizing Asset Value and Operational Costs for Sustainability in Industrial Water Systems: A Case Study of a Steel Plant
- 24 April 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64 (18) , 9287-9302
Neural Network-Based Model Predictive Control Framework Incorporating First-Principles Knowledge for Process Systems
- 24 April 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64 (18) , 9287-9302
Neural Network-Based Model Predictive Control Framework Incorporating First-Principles Knowledge for Process Systems
- 5 December 2024
- Published by Springer Nature
- p. 18-30
Classifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data
- 5 December 2024
- Published by Springer Nature
- p. 18-30
Classifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data
- 30 November 2024
- Published by Springer Nature
- p. 318-332
Detection of Oral Potentially Malignant Lesions Through Transformer-Based Segmentation Models
- 30 November 2024
- Published by Springer Nature
- p. 318-332
Detection of Oral Potentially Malignant Lesions Through Transformer-Based Segmentation Models
- Open Access
Classifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data
Hematological disorders, which involve a variety of malignant conditions and genetic diseases affecting blood formation, present significant diagnostic challenges. One such major challenge in clinical settings is differentiating Erythroblast from WBCs. Our approach evaluates the efficacy of various machine learning (ML) classifiers$\unicode{x2014}$SVM, XG-Boost, KNN, and Random Forest$\unicode{x2014}$using the ResNet-50 deep learning model as a backbone in detecting and differentiating erythroblast blood smear images across training splits of different sizes. Our findings indicate that the ResNet50-SVM classifier consistently surpasses other models' overall test accuracy and erythroblast detection accuracy, maintaining high performance even with minimal training data. Even when trained on just 1% (168 images per class for eight classes) of the complete dataset, ML classifiers such as SVM achieved a test accuracy of 86.75% and an erythroblast precision of 98.9%, compared to 82.03% and 98.6% of pre-trained ResNet-50 models without any classifiers. When limited data is available, the proposed approach outperforms traditional deep learning models, thereby offering a solution for achieving higher classification accuracy for small and unique datasets, especially in resource-scarce settings.
Open AccessClassifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data
Hematological disorders, which involve a variety of malignant conditions and genetic diseases affecting blood formation, present significant diagnostic challenges. One such major challenge in clinical settings is differentiating Erythroblast from WBCs. Our approach evaluates the efficacy of various machine learning (ML) classifiers$\unicode{x2014}$SVM, XG-Boost, KNN, and Random Forest$\unicode{x2014}$using the ResNet-50 deep learning model as a backbone in detecting and differentiating erythroblast blood smear images across training splits of different sizes. Our findings indicate that the ResNet50-SVM classifier consistently surpasses other models' overall test accuracy and erythroblast detection accuracy, maintaining high performance even with minimal training data. Even when trained on just 1% (168 images per class for eight classes) of the complete dataset, ML classifiers such as SVM achieved a test accuracy of 86.75% and an erythroblast precision of 98.9%, compared to 82.03% and 98.6% of pre-trained ResNet-50 models without any classifiers. When limited data is available, the proposed approach outperforms traditional deep learning models, thereby offering a solution for achieving higher classification accuracy for small and unique datasets, especially in resource-scarce settings.
- Open Access
A Short-Term Planning Framework for the Operation of Tanker-Based Water Distribution Systems in Urban Areas
Tanker-based distribution systems have been prevalent in developing countries to supply clean and pure water in different regions. To efficiently operate such tanker service systems, a large fleet of tanker trucks are required to transport water among several water sources, water treatment plants and consumers spanning across the regions. This requires tighter coordination between water suppliers, treatment plant operations, and user groups to use available water resources in a sustainable manner, along with the assurance of water quality and timely delivery. This paper proposes a novel formulation to assist decision-making for optimizing tanker-based water distribution systems and treatment operations, with an overall objective of minimizing the total operating cost such that all of the constraints related to the water demand, supply operations, and environmental and social aspects are honored while supplying water to a maximum number of users. The problem is formulated and solved as a mixed integer linear programming (MILP) optimization framework and captures all of the nuances related to (i) water availability limitations and quality constraints from different sources, (ii) maintaining water quality as it transports via tankers, (iii) water demands for various end-use purposes, and (iv) transportation across a water supply chain. The proposed novel framework is applied to a realistic urban model to find the optimal tanker delivery schedule, ensuring appropriate treatment and timely delivery of water. The results of the case study conducted on a representative-scale problem also elucidate several aspects of treatment plant operation and consumer demand fulfillment for the efficient planning and management of tanker-based water distribution systems.
Open AccessA Short-Term Planning Framework for the Operation of Tanker-Based Water Distribution Systems in Urban Areas
Tanker-based distribution systems have been prevalent in developing countries to supply clean and pure water in different regions. To efficiently operate such tanker service systems, a large fleet of tanker trucks are required to transport water among several water sources, water treatment plants and consumers spanning across the regions. This requires tighter coordination between water suppliers, treatment plant operations, and user groups to use available water resources in a sustainable manner, along with the assurance of water quality and timely delivery. This paper proposes a novel formulation to assist decision-making for optimizing tanker-based water distribution systems and treatment operations, with an overall objective of minimizing the total operating cost such that all of the constraints related to the water demand, supply operations, and environmental and social aspects are honored while supplying water to a maximum number of users. The problem is formulated and solved as a mixed integer linear programming (MILP) optimization framework and captures all of the nuances related to (i) water availability limitations and quality constraints from different sources, (ii) maintaining water quality as it transports via tankers, (iii) water demands for various end-use purposes, and (iv) transportation across a water supply chain. The proposed novel framework is applied to a realistic urban model to find the optimal tanker delivery schedule, ensuring appropriate treatment and timely delivery of water. The results of the case study conducted on a representative-scale problem also elucidate several aspects of treatment plant operation and consumer demand fulfillment for the efficient planning and management of tanker-based water distribution systems.
- Open Access
An Operational Scheduling Framework for Tanker-based Water Distribution System under Uncertainty
Tanker water systems play critical role in providing adequate service to meet potable water demands in the face of acute water crisis in many cities globally. Managing tanker movements among the supply and demand sides requires an efficient scheduling framework that could promote economic feasibility, ensure timely delivery, and avoid water wastage. However, to realize such a sustainable water supply operation, inherent uncertainties related to consumer demand and tanker travel time need to accounted in the operational scheduling. Herein, a two-stage stochastic optimization model with a recourse approach is developed for scheduling and optimization of tanker based water supply and treatment facility operations under uncertainty. The uncertain water demands and tanker travel times are combinedly modelled in a computationally efficient manner using a hybrid Monte Carlo simulation and scenario tree approach. The maximum demand fulfillment, limited extraction of groundwater, and timely delivery of quality water are enforced through a set of constraints to achieve sustainable operation. A representative urban case study is demonstrated, results are discussed for two uncertainty cases (i) only demand, and (ii) integrated demand-travel time. Value of stochastic solution over expected value and perfect information model solutions are analyzed and features of the framework for informed decision-making are discussed.
Open AccessAn Operational Scheduling Framework for Tanker-based Water Distribution System under Uncertainty
Tanker water systems play critical role in providing adequate service to meet potable water demands in the face of acute water crisis in many cities globally. Managing tanker movements among the supply and demand sides requires an efficient scheduling framework that could promote economic feasibility, ensure timely delivery, and avoid water wastage. However, to realize such a sustainable water supply operation, inherent uncertainties related to consumer demand and tanker travel time need to accounted in the operational scheduling. Herein, a two-stage stochastic optimization model with a recourse approach is developed for scheduling and optimization of tanker based water supply and treatment facility operations under uncertainty. The uncertain water demands and tanker travel times are combinedly modelled in a computationally efficient manner using a hybrid Monte Carlo simulation and scenario tree approach. The maximum demand fulfillment, limited extraction of groundwater, and timely delivery of quality water are enforced through a set of constraints to achieve sustainable operation. A representative urban case study is demonstrated, results are discussed for two uncertainty cases (i) only demand, and (ii) integrated demand-travel time. Value of stochastic solution over expected value and perfect information model solutions are analyzed and features of the framework for informed decision-making are discussed.
- 19 June 2024
- Published by Royal Society of Chemistry (RSC) in Sustainable Energy & Fuels
- Vol. 8 (16) , 3688-3703
System-level feasibility analysis of a novel chemical looping combustion integrated with electrochemical CO 2 reduction
A schematic of an integrated polygeneration process combining chemical looping combustion with electrochemical CO 2 reduction to produce electric power and ethylene.
- 19 June 2024
- Published by Royal Society of Chemistry (RSC) in Sustainable Energy & Fuels
- Vol. 8 (16) , 3688-3703
System-level feasibility analysis of a novel chemical looping combustion integrated with electrochemical CO 2 reduction
A schematic of an integrated polygeneration process combining chemical looping combustion with electrochemical CO 2 reduction to produce electric power and ethylene.
- 1 June 2024
- Published by Springer Nature
- p. 269-344
Additive Fertigung als die Zukunft der grünen chemischen Ingenieurwissenschaften
- 1 June 2024
- Published by Springer Nature
- p. 269-344
Additive Fertigung als die Zukunft der grünen chemischen Ingenieurwissenschaften