A5057744481- Advanced Control Systems Optimization
- Process Optimization and Integration
- Advanced Multi-Objective Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Fault Detection and Control Systems
- Energy and Environment Impacts
- Evolutionary Algorithms and Applications
- Hybrid Renewable Energy Systems
- DNA and Biological Computing
- Advanced biosensing and bioanalysis techniques
- Modular Robots and Swarm Intelligence
- Mineral Processing and Grinding
- Extremum Seeking Control Systems
- Reservoir Engineering and Simulation Methods
- Integrated Energy Systems Optimization
- Microbial Metabolic Engineering and Bioproduction
- Advanced Polymer Synthesis and Characterization
- Machine Learning in Materials Science
- AI in cancer detection
- Biofuel production and bioconversion
- Catalysts for Methane Reforming
- Catalytic Processes in Materials Science
- Viral Infectious Diseases and Gene Expression in Insects
- Water-Energy-Food Nexus Studies
- Radiomics and Machine Learning in Medical Imaging
Indian Institute of Technology Delhi
2015-2024
Indian Institute of Technology Kanpur
2008-2017
Indian Institute of Technology Indore
2014
Institute of Chemical and Engineering Sciences
2011-2013
Agency for Science, Technology and Research
2011-2012
Indian Institute of Technology Bombay
2009
The advent of machine learning (ML) techniques in solving problems related to materials science and chemical engineering is driving expectations give faster predictions material properties.
Managing waste plastic is a serious global challenge since most of this either landfilled, incinerated, burned in the open, or littered. Each these approaches has large environmental impact. Establishing circular economy plastics requires its recovery and recycling, much effort now focused direction. The body literature on for managing end life growing exponentially, making it increasingly difficult to segregate relevant information across multiple articles. Such work extremely time-...
DNA has been extensively used for molecular computing because of its highly precise Watson-Crick base pairing. In this study, we have exploited epigenetic variations in to construct simple Boolean...
An extraordinary adsorption capacity of 359 and 1679 mg g<sup>−1</sup> for the adsorptive removal Cr<sub>2</sub>O<sub>7</sub><sup>2−</sup> methyl orange (MO), respectively, was observed by using a low surface area (SA<sub>BET</sub> 10 m<sup>2</sup> g<sup>−1</sup>) organosilica.
Abstract A machine learning (ML) approach implementing the gradient boosting regressor (GBR) algorithm is applied to predict binding energies of oxygen (E O ) and carbon C atoms on single atom alloys (SAAs) Cu, Ag Au. Readily available periodic properties transition metals are utilized as input features in model. Their relative contribution adsorbate‐metal interaction assessed develop a comprehensive descriptor. In test runs, ML model observed E with significantly reduced errors (∼0.2 eV)....
Monoclonal antibodies (mAb) are biopharmaceutical products that improve human immunity. In this work, we propose a multi-actor proximal policy optimization-based reinforcement learning (RL) for the control of mAb production. Here, manipulated variable is flowrate and concentration. Based on root mean square error (RMSE) values convergence performance, it has been observed PPO performed better as compared to other RL algorithms. It predicts 40 % reduction in number days reach desired...
Scheduling is widely studied in process systems engineering and typically solved using mathematical programming. Although popular for many other optimization problems, evolutionary algorithms have not found wide applicability such combinatorial problems with large numbers of variables constraints. Here we demonstrate that scheduling involve a network units streams graph structure which can be exploited to offer sparse problem representation enables efficient stochastic optimization. In the...
Distillation is an energy-intensive non-stationary process represented using non-linear model equations and involves multiple objectives. For such processes, data-based multi-objective optimization methods are more suitable compared to conventional methods. Therefore, a surrogate-assisted (SAMOO) approach developed by hybridizing artificial neural network (ANN) genetic algorithm (GA) simultaneously minimize the annualized capital expenditure cost (ACAPEX) operational (AOC) for methanol...