Amit Kumar Sinha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Amit Kumar Sinha has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Ankush Anand
School of Mechanical Engineering Shri Mata Vaishno Devi University 182320 Katra Jammu and Kashmir India
5 shared publicationsVikrant Charak
2 shared publicationsA. Sharma
Department of Mechanical Engineering, Shri Mata Vaishno Devi University, Katra, Jammu and Kashmir, India-182320
1 shared publication- Aditya Mahajan
Department of Electrical and Computer Engineering, McGill University, Montreal, Canada
1 shared publication - Akhilesh Kumar
Department of Information Technology, Gaya College, Gaya, India
1 shared publication - Ankush Anand
Shri Mata Vaishno Devi University
1 shared publication
Latest Publications
- Open Access
- 1 November 2024
- Published by EDP Sciences in RAIRO - Operations Research
- Vol. 58 (6) , 5185-5209
Development of industry 4.0 based technology selection index using multi criteria decision making
Selecting an appropriate technology to perform a specific operation has always been an uphill task while setting up a new industry. There exist a large number of decision making challenges, while selecting a technology related to industry 4.0 in a manufacturing environment, as it augments the analysis of various technological elements, which are otherwise not considered in traditional manufacturing systems. The analysis of attributes is a holistic exercise, which needs understanding the co-relationship among the identified attributes from industry 4.0 perspective (i.e., data analysis, cloud, IIoT, real time data monitoring, sensors, etc). In this research paper, an effort has been made to address the issue of selecting appropriate technology using graph theory based multi criteria decision making approach in industry 4.0 environment. The proposed methodology has been applied to two case studies. The first case study is for illustration purpose. However, to validate the concept, the second case study has been included for the benefit of readers.
- 1 November 2024
- Published by EDP Sciences in RAIRO - Operations Research
- Vol. 58 (6) , 5185-5209
Open AccessDevelopment of industry 4.0 based technology selection index using multi criteria decision making
Selecting an appropriate technology to perform a specific operation has always been an uphill task while setting up a new industry. There exist a large number of decision making challenges, while selecting a technology related to industry 4.0 in a manufacturing environment, as it augments the analysis of various technological elements, which are otherwise not considered in traditional manufacturing systems. The analysis of attributes is a holistic exercise, which needs understanding the co-relationship among the identified attributes from industry 4.0 perspective (i.e., data analysis, cloud, IIoT, real time data monitoring, sensors, etc). In this research paper, an effort has been made to address the issue of selecting appropriate technology using graph theory based multi criteria decision making approach in industry 4.0 environment. The proposed methodology has been applied to two case studies. The first case study is for illustration purpose. However, to validate the concept, the second case study has been included for the benefit of readers.
- 22 April 2024
- Published by Springer Nature in Process Integration and Optimization for Sustainability
- Vol. 8 (4) , 1051-1064
Assessment of Green Supply Chain Management Practices Using Fuzzy Analytical Hierarchy Process
- 22 April 2024
- Published by Springer Nature in Process Integration and Optimization for Sustainability
- Vol. 8 (4) , 1051-1064
Assessment of Green Supply Chain Management Practices Using Fuzzy Analytical Hierarchy Process
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 23, 7810-7816
Asymmetric Actor-Critic with Approximate Information State
Reinforcement learning (RL) for partially observable Markov decision processes (POMDPs) is a challenging problem because decisions need to be made based on the entire history of observations and actions. However, in several scenarios, state information is available during the training phase. We are interested in exploiting the availability of this state information during the training phase to efficiently learn a history-based policy using RL. Specifically, we consider actor-critic algorithms, where the actor uses only the history information but the critic uses both history and state. Such algorithms are called asymmetric actor-critic, to highlight the fact that the actor and critic have asymmetric information. Motivated by the recent success of using representation losses in RL for POMDPs [1], we derive similar theoretical results for the asymmetric actor-critic case and evaluate the effectiveness of adding such auxiliary losses in experiments. In particular, we learn a history representation-called an approximate information state (AIS)-and bound the performance loss when acting using AIS.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 23, 7810-7816
Asymmetric Actor-Critic with Approximate Information State
Reinforcement learning (RL) for partially observable Markov decision processes (POMDPs) is a challenging problem because decisions need to be made based on the entire history of observations and actions. However, in several scenarios, state information is available during the training phase. We are interested in exploiting the availability of this state information during the training phase to efficiently learn a history-based policy using RL. Specifically, we consider actor-critic algorithms, where the actor uses only the history information but the critic uses both history and state. Such algorithms are called asymmetric actor-critic, to highlight the fact that the actor and critic have asymmetric information. Motivated by the recent success of using representation losses in RL for POMDPs [1], we derive similar theoretical results for the asymmetric actor-critic case and evaluate the effectiveness of adding such auxiliary losses in experiments. In particular, we learn a history representation-called an approximate information state (AIS)-and bound the performance loss when acting using AIS.
- 27 February 2023
- Published by Taylor & Francis in Australian Journal of Mechanical Engineering
- Vol. 22 (4) , 1-15
A holistic approach of reconfigurable mould based fused deposition modelling for producing overhanging parts
Fused decomposition modelling (FDM) is a sustainable additive manufacturing process of the 21st century. Due to the increasing trend of customer-oriented manufacturing processes, FDM can provide a better solution for the manufacturing industry. However, it suffers from a lot of hindrances like high build time, inadequate strength, low surface roughness, the requirement of the support structure, and materials constraint during producing overhanging parts. Therefore a holistic approach to producing overhanging parts is required for any FDM industry. Based on a vast literature survey and performing pilot basis experiments, some good technical and managerial insights have been suggested for improving the quality of FDM products in terms of surface roughness, strength, and proper selection of materials. Another salient feature of the research paper is to provide an integrated reconfigurable mould based FDM approach for producing overhanging parts. The proposed integrated systems not only eliminate the requirement for a support structure but also decrease the build time. Some pilot basis experiments have been carried out for producing overhanging parts, which reveal that the proposed integrated systems eliminate the requirement of the support structure and, it also decreases build time approximately by 15% and materials requirement by 30%. GRAPHICAL ABSTRACT
- 27 February 2023
- Published by Taylor & Francis in Australian Journal of Mechanical Engineering
- Vol. 22 (4) , 1-15
A holistic approach of reconfigurable mould based fused deposition modelling for producing overhanging parts
Fused decomposition modelling (FDM) is a sustainable additive manufacturing process of the 21st century. Due to the increasing trend of customer-oriented manufacturing processes, FDM can provide a better solution for the manufacturing industry. However, it suffers from a lot of hindrances like high build time, inadequate strength, low surface roughness, the requirement of the support structure, and materials constraint during producing overhanging parts. Therefore a holistic approach to producing overhanging parts is required for any FDM industry. Based on a vast literature survey and performing pilot basis experiments, some good technical and managerial insights have been suggested for improving the quality of FDM products in terms of surface roughness, strength, and proper selection of materials. Another salient feature of the research paper is to provide an integrated reconfigurable mould based FDM approach for producing overhanging parts. The proposed integrated systems not only eliminate the requirement for a support structure but also decrease the build time. Some pilot basis experiments have been carried out for producing overhanging parts, which reveal that the proposed integrated systems eliminate the requirement of the support structure and, it also decreases build time approximately by 15% and materials requirement by 30%. GRAPHICAL ABSTRACT
- 24 July 2022
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering
- Vol. 236 (5) , 2229-2239
Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform
Additive manufacturing, also commonly referred to as 3D printing, has enabled the rapid production of parts possessing complex geometry. Despite Fused Deposition Modeling (FDM) being the most popular process, it still suffers from certain limitations, such as production time and material required to build the material support structure for overhang parts. This results in increased total build time and material requirement. This article aims to eliminate these limitations by using a proposed hybrid reconfigurable pin FDM system. A hybrid system is proposed to eliminate the problem of support build time and material requirements. The proposed hybrid FDM is the combination of traditional FDM with a reconfigurable pins platform. The proposed hybrid system has been implemented for printing an overhang test part. The result analysis also reveals that the proposed hybrid system is an effective way of producing overhang parts without material support structures. A real-life case example is considered for validation of the proposed reconfigurable pins platform.
- 24 July 2022
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering
- Vol. 236 (5) , 2229-2239
Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform
Additive manufacturing, also commonly referred to as 3D printing, has enabled the rapid production of parts possessing complex geometry. Despite Fused Deposition Modeling (FDM) being the most popular process, it still suffers from certain limitations, such as production time and material required to build the material support structure for overhang parts. This results in increased total build time and material requirement. This article aims to eliminate these limitations by using a proposed hybrid reconfigurable pin FDM system. A hybrid system is proposed to eliminate the problem of support build time and material requirements. The proposed hybrid FDM is the combination of traditional FDM with a reconfigurable pins platform. The proposed hybrid system has been implemented for printing an overhang test part. The result analysis also reveals that the proposed hybrid system is an effective way of producing overhang parts without material support structures. A real-life case example is considered for validation of the proposed reconfigurable pins platform.
- RetractedOpen Access
- 21 April 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-10
Identification and Classification of Depressed Mental State for End-User over Social Media
In researching social network data and depression, it is often necessary to manually label depressed and non-depressed users, which is time-consuming and labor-intensive. The aim of this study is that it explores the relationship between social network data and depression. It can also contribute to detecting and identifying depression. Through collecting and analyzing college students’ microblog social data, a preliminary screening algorithm for college students’ suspected depression microblogs based on depression keywords, and semantic expansion is researched; a comprehensive lexical grammar was proposed. This research provided has a preliminary screening method based on depression keywords and semantic expansion for college students’ suspected depression microblogs, with a screening accuracy. This method forms a depression keyword table by constructing the basic keyword table and the semantic expansion based on the word embedding learning model Word2Vec. Finally, the word table is used to calculate the semantic similarity of the tested microblogs and then identify whether it is a suspected depression microblog. The experimental results on the microblog dataset of college students show that the comprehensive lexical method is better than the SDS questionnaire segmentation method and the expert lexical method in terms of screening accuracy; the comprehensive lexical approach can quickly and automatically screen out a tiny proportion of suspected doubts from a large number of college students’ microblogs. Depression Weibo can reduce the workload of experts’ annotation, improve annotation efficiency, and provide a suitable data processing basis for the subsequent accurate identification (classification problem) of patients with depression.
- 21 April 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-10
RetractedOpen AccessIdentification and Classification of Depressed Mental State for End-User over Social Media
In researching social network data and depression, it is often necessary to manually label depressed and non-depressed users, which is time-consuming and labor-intensive. The aim of this study is that it explores the relationship between social network data and depression. It can also contribute to detecting and identifying depression. Through collecting and analyzing college students’ microblog social data, a preliminary screening algorithm for college students’ suspected depression microblogs based on depression keywords, and semantic expansion is researched; a comprehensive lexical grammar was proposed. This research provided has a preliminary screening method based on depression keywords and semantic expansion for college students’ suspected depression microblogs, with a screening accuracy. This method forms a depression keyword table by constructing the basic keyword table and the semantic expansion based on the word embedding learning model Word2Vec. Finally, the word table is used to calculate the semantic similarity of the tested microblogs and then identify whether it is a suspected depression microblog. The experimental results on the microblog dataset of college students show that the comprehensive lexical method is better than the SDS questionnaire segmentation method and the expert lexical method in terms of screening accuracy; the comprehensive lexical approach can quickly and automatically screen out a tiny proportion of suspected doubts from a large number of college students’ microblogs. Depression Weibo can reduce the workload of experts’ annotation, improve annotation efficiency, and provide a suitable data processing basis for the subsequent accurate identification (classification problem) of patients with depression.
- 19 April 2022
- Published by Springer Nature in Soft Computing
- Vol. 26 (22) , 12235-12255
Development of a sustainable supply chain network for the cement manufacturing industry using real-coded genetic algorithm
- 19 April 2022
- Published by Springer Nature in Soft Computing
- Vol. 26 (22) , 12235-12255
Development of a sustainable supply chain network for the cement manufacturing industry using real-coded genetic algorithm
- 19 April 2021
- Published by Springer Nature in Soft Computing
- Vol. 25 (13) , 8371-8389
Development of a supply chain configuration model for new product development: a multi-objective solution approach
- 19 April 2021
- Published by Springer Nature in Soft Computing
- Vol. 25 (13) , 8371-8389
Development of a supply chain configuration model for new product development: a multi-objective solution approach
- 30 June 2020
- Published by Springer Nature
- p. 671-675
A Graph-Theoretic Approach for Sustainable New Product Development (SNPD) in Supply Chain Environment
- 30 June 2020
- Published by Springer Nature
- p. 671-675
A Graph-Theoretic Approach for Sustainable New Product Development (SNPD) in Supply Chain Environment
- Open Access
- 1 January 2019
- Published by Fringe Global Scientific Press in International Journal of Advance Research and Innovation
- Vol. 7 (1) , 102-105
Sustainable Supplier Selection for New Product Development: A Multi-Objective Framework
Availability of emerging technology, globalization scenario, use of information and communication technology (ICT), and decreasing transportation cost (logistic optimal fleet selection) are responsible for rapid variation in product demand and these demands can be handled by using the concept of new product development (NPD) under sustainable supply chain (SSC) environment. In today’s manufacturing environment, it is a challenging task for practitioners and researchers, how to handle new product development (NPD) in a sustainable supply chain environment. In general, economical, social, and environmental are three aspects of sustainability. Individual aspect of SSC issues for NPD has been found in the literature but integration of all the three aspects for NPD is an emerging topic. Therefore, in this paper, we tried to provide a holistic approach for integrating SSC concerns with NPD.
- 1 January 2019
- Published by Fringe Global Scientific Press in International Journal of Advance Research and Innovation
- Vol. 7 (1) , 102-105
Open AccessSustainable Supplier Selection for New Product Development: A Multi-Objective Framework
Availability of emerging technology, globalization scenario, use of information and communication technology (ICT), and decreasing transportation cost (logistic optimal fleet selection) are responsible for rapid variation in product demand and these demands can be handled by using the concept of new product development (NPD) under sustainable supply chain (SSC) environment. In today’s manufacturing environment, it is a challenging task for practitioners and researchers, how to handle new product development (NPD) in a sustainable supply chain environment. In general, economical, social, and environmental are three aspects of sustainability. Individual aspect of SSC issues for NPD has been found in the literature but integration of all the three aspects for NPD is an emerging topic. Therefore, in this paper, we tried to provide a holistic approach for integrating SSC concerns with NPD.