Kamal Deep Garg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kamal Deep Garg has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Ajit Kumar
Multani Mal modi College
3 shared publications- Sushil Kumar Narang
Chitkara University Institute of Engineering and Technology, Chitkara University
3 shared publications - Vandana Mohindru
Chitkara University Institute of Engineering and Technology, Chitkara University
3 shared publications Vishal Goyal
Punjabi University
3 shared publications- Ankit Bansal
Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, India
2 shared publications - Divya Gupta
Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, India
2 shared publications
Latest Publications
- 13 July 2024
- Published by Springer Nature
- p. 379-392
Text Summarization Techniques for the Bengali Language: Survey
- 13 July 2024
- Published by Springer Nature
- p. 379-392
Text Summarization Techniques for the Bengali Language: Survey
- 30 September 2023
- Published by Springer Nature
- p. 593-603
Optimization of Classification Algorithm for Improving Semantic-Based Text Classification
- 30 September 2023
- Published by Springer Nature
- p. 593-603
Optimization of Classification Algorithm for Improving Semantic-Based Text Classification
- 15 September 2023
- Published by Taylor & Francis
- p. 1-9
Nanomaterials for Cyber-Physical Systems
Cyber-physical systems (CPSs) are a new type of engineered system that combines cyber and physical components. The constantly evolving technology trends have enlarged the use of devices day by day, so efforts have been made to link all devices through the internet for better communication and processing. CPSs have been identified as a critical area of research, and they are anticipated to show a significant part in the design and sustainable development of future systems. New nanomaterial discoveries are likely to play a significant role in addressing current and forthcoming challenges in computation and communication. Nanomaterials enable ultra-high-speed short-range and long-range transmission, movable and energy-efficient computing devices, large memory and logic density, ultra-fast interconnects, and self-directed and robust energy-saving devices for retrieving ambient intelligence and desired information. In this chapter, we discuss the importance of nanomaterials in cyber-physical systems for future intelligent communication technology. The goal of this chapter is to provide researchers and system designers with insights into working on the design of nano cyber-physical systems that address the limitations of CPSs.
- 15 September 2023
- Published by Taylor & Francis
- p. 1-9
Nanomaterials for Cyber-Physical Systems
Cyber-physical systems (CPSs) are a new type of engineered system that combines cyber and physical components. The constantly evolving technology trends have enlarged the use of devices day by day, so efforts have been made to link all devices through the internet for better communication and processing. CPSs have been identified as a critical area of research, and they are anticipated to show a significant part in the design and sustainable development of future systems. New nanomaterial discoveries are likely to play a significant role in addressing current and forthcoming challenges in computation and communication. Nanomaterials enable ultra-high-speed short-range and long-range transmission, movable and energy-efficient computing devices, large memory and logic density, ultra-fast interconnects, and self-directed and robust energy-saving devices for retrieving ambient intelligence and desired information. In this chapter, we discuss the importance of nanomaterials in cyber-physical systems for future intelligent communication technology. The goal of this chapter is to provide researchers and system designers with insights into working on the design of nano cyber-physical systems that address the limitations of CPSs.
- 18 August 2023
- Published by Springer Nature
- p. 179-185
Fog-Based Smart Healthcare Architecture in IoT Environment
- 18 August 2023
- Published by Springer Nature
- p. 179-185
Fog-Based Smart Healthcare Architecture in IoT Environment
- 18 August 2023
- Published by Springer Nature
- p. 565-576
Machine Learning Techniques for Human Activity Recognition Using Wearable Sensors
- 18 August 2023
- Published by Springer Nature
- p. 565-576
Machine Learning Techniques for Human Activity Recognition Using Wearable Sensors
- 3 May 2023
- Published by Springer Nature
- p. 621-632
Bidirectional Machine Translation for Punjabi-English, Punjabi-Hindi, and Hindi-English Language Pairs
- 3 May 2023
- Published by Springer Nature
- p. 621-632
Bidirectional Machine Translation for Punjabi-English, Punjabi-Hindi, and Hindi-English Language Pairs
- 15 February 2023
- Published by Springer Nature
- p. 63-69
Effective Communication in NDN via Transient Popular Content Caching at Edge
- 15 February 2023
- Published by Springer Nature
- p. 63-69
Effective Communication in NDN via Transient Popular Content Caching at Edge
- 25 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 468-473
Machine Translation System for Indian Language: Survey
A method known as Machine Translation (MT) is computer software to transform texts from the source language into the target language, with the source language serving as the input and the target language as the output. MT plays an important role in the advancement of communication technologies. After the discovery of the MT, communication technology has been improved. Communication became easy across the world. Early on in the development of the MT, research progressed slowly. Initially, Rule-based and Corpus-based MT technology was employed; however, as time went on, technology transfer took place, and Neural MT's popularity grew. There has been a lot of research in this area, however, most of the models created are for top-level languages, those spoken by many people, whereas research for low-level languages, those spoken by fewer people, is scarce. In this paper, different approaches to MT are discussed. Below is a discussion of various MT models, along with their techniques and limitations, for the future of MT.
- 25 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 468-473
Machine Translation System for Indian Language: Survey
A method known as Machine Translation (MT) is computer software to transform texts from the source language into the target language, with the source language serving as the input and the target language as the output. MT plays an important role in the advancement of communication technologies. After the discovery of the MT, communication technology has been improved. Communication became easy across the world. Early on in the development of the MT, research progressed slowly. Initially, Rule-based and Corpus-based MT technology was employed; however, as time went on, technology transfer took place, and Neural MT's popularity grew. There has been a lot of research in this area, however, most of the models created are for top-level languages, those spoken by many people, whereas research for low-level languages, those spoken by fewer people, is scarce. In this paper, different approaches to MT are discussed. Below is a discussion of various MT models, along with their techniques and limitations, for the future of MT.
- Open Access
- 31 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11038
Framework for Handling Rare Word Problems in Neural Machine Translation System Using Multi-Word Expressions
Machine Translation (MT) systems are now being improved with the use of an ongoing methodology known as Neural Machine Translation (NMT). Natural language processing (NLP) researchers have shown that NMT systems are unable to deal with out-of-vocabulary (OOV) words and multi-word expressions (MWEs) in the text. OOV terms are those that are not currently included in the vocabulary that is used by the NMT system. MWEs are phrases that consist of a minimum of two terms but are treated as a single unit. MWEs have great importance in NLP, linguistic theory, and MT systems. In this article, OOV words and MWEs are handled for the Punjabi to English NMT system. A parallel corpus for Punjabi to English containing MWEs was developed and used to train the different models of NMT. Punjabi is a low-resource language as it lacks the availability of a large parallel corpus for building various NLP tools, and this is an attempt to improve the accuracy of Punjabi in the English NMT system by using named entities and MWEs in the corpus. The developed NMT models were assessed using human evaluation through adequacy, fluency and overall rating as well as automated assessment tools such as the bilingual evaluation study (BLEU) and translation error rate (TER) score. Results show that using word embedding (WE) and MWEs corpus increased the accuracy of translation for the Punjabi to English language pair. The best BLEU score obtained was 15.45 for the small test set, 43.32 for the medium test set, and 34.5 for the large test set, respectively. The best TER rate score obtained was 57.34% for the small test set, 37.29% for the medium test set, and 53.79% for the large test set, repectively.
- 31 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11038
Open AccessFramework for Handling Rare Word Problems in Neural Machine Translation System Using Multi-Word Expressions
Machine Translation (MT) systems are now being improved with the use of an ongoing methodology known as Neural Machine Translation (NMT). Natural language processing (NLP) researchers have shown that NMT systems are unable to deal with out-of-vocabulary (OOV) words and multi-word expressions (MWEs) in the text. OOV terms are those that are not currently included in the vocabulary that is used by the NMT system. MWEs are phrases that consist of a minimum of two terms but are treated as a single unit. MWEs have great importance in NLP, linguistic theory, and MT systems. In this article, OOV words and MWEs are handled for the Punjabi to English NMT system. A parallel corpus for Punjabi to English containing MWEs was developed and used to train the different models of NMT. Punjabi is a low-resource language as it lacks the availability of a large parallel corpus for building various NLP tools, and this is an attempt to improve the accuracy of Punjabi in the English NMT system by using named entities and MWEs in the corpus. The developed NMT models were assessed using human evaluation through adequacy, fluency and overall rating as well as automated assessment tools such as the bilingual evaluation study (BLEU) and translation error rate (TER) score. Results show that using word embedding (WE) and MWEs corpus increased the accuracy of translation for the Punjabi to English language pair. The best BLEU score obtained was 15.45 for the small test set, 43.32 for the medium test set, and 34.5 for the large test set, respectively. The best TER rate score obtained was 57.34% for the small test set, 37.29% for the medium test set, and 53.79% for the large test set, repectively.
- 20 February 2021
- Published by Springer Nature
- p. 865-878
Machine Translation System Using Deep Learning for Punjabi to English
- 20 February 2021
- Published by Springer Nature
- p. 865-878
Machine Translation System Using Deep Learning for Punjabi to English