Amit Wason
Research Subjects
Amit Wason has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
R.S. Kaler
13 shared publications- Deepak Malik
MMEC, MMU, Mullana, India
4 shared publications - Hardeep Singh Saini
Indo Global College of Engineering
4 shared publications Deepak Malik
3 shared publications- Ashok Kumar
Model Institute of Engineering and Technology, Jammu, India
2 shared publications - Bhawna Bhawna
Department of Electronics and Communication Engineering, Punjabi University Patiala, Patiala, India
2 shared publications
Latest Publications
- 28 April 2026
- Published by Springer Nature in Sensing and Imaging
- Vol. 27 (1) , 88
Performance Evaluation of Improved Version of Chernobyl Disaster Optimizer for Classifying Breast Cancer
- 28 April 2026
- Published by Springer Nature in Sensing and Imaging
- Vol. 27 (1) , 88
Performance Evaluation of Improved Version of Chernobyl Disaster Optimizer for Classifying Breast Cancer
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC
- Vol. 25 (2) , 121-137
Grasshopper-Inspired Deep Neural Network for Enhanced Breast Cancer Classification
Early-stage disease diagnosis is critical for effective treatment, and software-aided design can analyze disease architecture for timely detection. Many fail to identify disease severity before it becomes chronic, contributing to global mortality rates. Breast cancer, a prime reason of death among women, can be treated if detected early. Computer-aided diagnosis aids practitioners in accurately assessing disease criticality. This paper introduces an automated diagnosis system utilizing an enhanced Grasshopper Optimization technique and a Deep Neural Network (DNN) classifier. The Grasshopper Algorithm optimally selects features from segmented images, extracted through SIFT and BRISK hybrid techniques. The DNN classifies breast cancer using a partitioned dataset for training and testing. Performance metrics, including accuracy, precision, F-measure, and recall, demonstrate that the proposed system significantly outperforms existing methods, with an F-measure improvement of 5.1% and an accuracy increase of 11.19%.
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC
- Vol. 25 (2) , 121-137
Grasshopper-Inspired Deep Neural Network for Enhanced Breast Cancer Classification
Early-stage disease diagnosis is critical for effective treatment, and software-aided design can analyze disease architecture for timely detection. Many fail to identify disease severity before it becomes chronic, contributing to global mortality rates. Breast cancer, a prime reason of death among women, can be treated if detected early. Computer-aided diagnosis aids practitioners in accurately assessing disease criticality. This paper introduces an automated diagnosis system utilizing an enhanced Grasshopper Optimization technique and a Deep Neural Network (DNN) classifier. The Grasshopper Algorithm optimally selects features from segmented images, extracted through SIFT and BRISK hybrid techniques. The DNN classifies breast cancer using a partitioned dataset for training and testing. Performance metrics, including accuracy, precision, F-measure, and recall, demonstrate that the proposed system significantly outperforms existing methods, with an F-measure improvement of 5.1% and an accuracy increase of 11.19%.
- Retracted
- 3 July 2023
- Published by Springer Nature in Soft Computing
- Vol. 30 (S1) , 335
RETRACTED ARTICLE: Protection technique for performance improvement in GMPLS networks
- 3 July 2023
- Published by Springer Nature in Soft Computing
- Vol. 30 (S1) , 335
RetractedRETRACTED ARTICLE: Protection technique for performance improvement in GMPLS networks
- 17 May 2022
- Published by Taylor & Francis
- p. 199-212
A Deep Learning and Multilayer Neural Network Approach for Coronary Heart Disease Detection
Every year, we see that the expiry percentage increases as an outcome of heart syndrome. There are many factors that lead to this increase. Diagnosis of this disease should be perfect to reduce this increase; a misdiagnosis by the doctors or lack of knowledge in the patient may lead to an increase in expiry percentage. The blood coagulates in the veins; the heart muscle becomes ravenous for oxygen. Within a short amount of time, heart muscle cells decrease, triggering lasting injury. A smart system that can diagnose coronary heart disease in its early stage is required. It needs a data set of patients with some influential parameters, such as age, high blood pressure, high cholesterol, obesity, gender, smoking, diabetes etc. This system is used to avoid wrong judgment, which is the most common mistake physicians make. To implement this smart system, we can use the data of stat log for heart disease. The database consists of characteristics of persons being spotted for cardiac problems. The finding is used to identify if a patient has a cardiac disorder. We can use various techniques, such as the feed forward, back propagation, cascade forward and layer recurrent models for this test. The collected data can be used for three activities, first for the training of the network, second was validation followed by testing of network with data for which it was trained. Machine learning and deep learning techniques are may be used for higher accuracy.
- 17 May 2022
- Published by Taylor & Francis
- p. 199-212
A Deep Learning and Multilayer Neural Network Approach for Coronary Heart Disease Detection
Every year, we see that the expiry percentage increases as an outcome of heart syndrome. There are many factors that lead to this increase. Diagnosis of this disease should be perfect to reduce this increase; a misdiagnosis by the doctors or lack of knowledge in the patient may lead to an increase in expiry percentage. The blood coagulates in the veins; the heart muscle becomes ravenous for oxygen. Within a short amount of time, heart muscle cells decrease, triggering lasting injury. A smart system that can diagnose coronary heart disease in its early stage is required. It needs a data set of patients with some influential parameters, such as age, high blood pressure, high cholesterol, obesity, gender, smoking, diabetes etc. This system is used to avoid wrong judgment, which is the most common mistake physicians make. To implement this smart system, we can use the data of stat log for heart disease. The database consists of characteristics of persons being spotted for cardiac problems. The finding is used to identify if a patient has a cardiac disorder. We can use various techniques, such as the feed forward, back propagation, cascade forward and layer recurrent models for this test. The collected data can be used for three activities, first for the training of the network, second was validation followed by testing of network with data for which it was trained. Machine learning and deep learning techniques are may be used for higher accuracy.
- 28 July 2020
- Published by Springer Nature in Journal of Optics
- Vol. 49 (3) , 298-304
Performance investigation of hybrid optical amplifiers for high-speed optical networks
- 28 July 2020
- Published by Springer Nature in Journal of Optics
- Vol. 49 (3) , 298-304
Performance investigation of hybrid optical amplifiers for high-speed optical networks
- 7 July 2020
- Published by Walter de Gruyter GmbH in Journal of Optical Communications
- Vol. 44 (s1) , s909-s914
Performance analysis of hybrid optical amplifiers for multichannel wavelength division multiplexed (WDM) optical networks
Hybrid Optical Amplifier (HOA) has made a significant change in Wavelength Division Multiplexed (WDM) optical networks. We have proposed diverse hybrid optical amplifier configurations for the better performance of WDM optical networks. These configurations are SOA-EDFA, EDFA-EDFA and EDFA-Raman amplifier for 24 channels WDM optical networks at 10 Gbps with channel spacing of 0.8 nm. The performance of the systems is evaluated on the behalf of different parameters such as, quality factor, eye diagram, bit error rate and output power. The efforts are made to optimize these parameters. From the results, it is assessed that EDFA-Raman configuration gives superior results as compared to EDFA-EDFA configuration and SOA-EDFA hybrid optical amplifier configuration for long distance. Further it is also observed that EDFA-Raman hybrid optical amplifier configuration is suitable for high data rates up to 20 Gbps.
- 7 July 2020
- Published by Walter de Gruyter GmbH in Journal of Optical Communications
- Vol. 44 (s1) , s909-s914
Performance analysis of hybrid optical amplifiers for multichannel wavelength division multiplexed (WDM) optical networks
Hybrid Optical Amplifier (HOA) has made a significant change in Wavelength Division Multiplexed (WDM) optical networks. We have proposed diverse hybrid optical amplifier configurations for the better performance of WDM optical networks. These configurations are SOA-EDFA, EDFA-EDFA and EDFA-Raman amplifier for 24 channels WDM optical networks at 10 Gbps with channel spacing of 0.8 nm. The performance of the systems is evaluated on the behalf of different parameters such as, quality factor, eye diagram, bit error rate and output power. The efforts are made to optimize these parameters. From the results, it is assessed that EDFA-Raman configuration gives superior results as compared to EDFA-EDFA configuration and SOA-EDFA hybrid optical amplifier configuration for long distance. Further it is also observed that EDFA-Raman hybrid optical amplifier configuration is suitable for high data rates up to 20 Gbps.
- 1 November 2018
- Published by Elsevier in Optical Fiber Technology
- Vol. 45, 345-351
Bandwidth reusability by handoff management for new ONUs in passive optical networks
- 1 November 2018
- Published by Elsevier in Optical Fiber Technology
- Vol. 45, 345-351
Bandwidth reusability by handoff management for new ONUs in passive optical networks
- 7 August 2018
- Published by Walter de Gruyter GmbH in Journal of Optical Communications
- Vol. 42 (2) , 365-373
Neurofuzzy and Biogeography-Based Optimization of Bandwidth Granularity for PON Based on Optical Path Fragmentation
Passive optical network (PON) supported orthogonal frequency division multiplexing is a network that is designed for subsequent generation of optical networks. During this work, the proposed algorithm consists of neurofuzzy rules which update and control the minimum bandwidth allocation granularity g \left( g \right) . In order to improve the quality of service, a biogeography-based optimization algorithm is introduced and a new fitness function is proposed which reduces the round trip time by enhancing the distribution scaling factor. Hence, the proposed work reduces the jitter and increases the throughput of the PON for fixed g = 1 g = 1 which enhances the network performance by 3.4 % and 1.23 %, respectively.
- 7 August 2018
- Published by Walter de Gruyter GmbH in Journal of Optical Communications
- Vol. 42 (2) , 365-373
Neurofuzzy and Biogeography-Based Optimization of Bandwidth Granularity for PON Based on Optical Path Fragmentation
Passive optical network (PON) supported orthogonal frequency division multiplexing is a network that is designed for subsequent generation of optical networks. During this work, the proposed algorithm consists of neurofuzzy rules which update and control the minimum bandwidth allocation granularity g \left( g \right) . In order to improve the quality of service, a biogeography-based optimization algorithm is introduced and a new fitness function is proposed which reduces the round trip time by enhancing the distribution scaling factor. Hence, the proposed work reduces the jitter and increases the throughput of the PON for fixed g = 1 g = 1 which enhances the network performance by 3.4 % and 1.23 %, respectively.
- 7 July 2018
- Published by Walter de Gruyter GmbH in Journal of Optical Communications
- Vol. 42 (2) , 259-264
Link Fault Tolerant Algorithms to Optimize the Blocking in Optical Burst Switching Networks
In this paper, link fault tolerant algorithms (LFTAs) are employed for optimization of blocking performance in optical burst switching (OBS) networks for dynamic establishment of wavelength-routed lightpaths. This paper presents two algorithms: link fault tolerance algorithm for least congestion (LFTALC) and link fault tolerance algorithm for optimized blocking (LFTAOB). In former algorithm, the path with least congestion is selected and in the latter algorithm the path with least blocking probability is selected and then both the algorithms check for the availability of fault on the links present in the selected path. The findings indicate that methods of developing link based fault tolerant algorithms keep good performance and fairness among all the connections. The key advantage of these proposed algorithms as compared to routing and wavelength assignment algorithm is that these are very simple in nature and require less service disruption time.
- 7 July 2018
- Published by Walter de Gruyter GmbH in Journal of Optical Communications
- Vol. 42 (2) , 259-264
Link Fault Tolerant Algorithms to Optimize the Blocking in Optical Burst Switching Networks
In this paper, link fault tolerant algorithms (LFTAs) are employed for optimization of blocking performance in optical burst switching (OBS) networks for dynamic establishment of wavelength-routed lightpaths. This paper presents two algorithms: link fault tolerance algorithm for least congestion (LFTALC) and link fault tolerance algorithm for optimized blocking (LFTAOB). In former algorithm, the path with least congestion is selected and in the latter algorithm the path with least blocking probability is selected and then both the algorithms check for the availability of fault on the links present in the selected path. The findings indicate that methods of developing link based fault tolerant algorithms keep good performance and fairness among all the connections. The key advantage of these proposed algorithms as compared to routing and wavelength assignment algorithm is that these are very simple in nature and require less service disruption time.
- 22 June 2018
- Published by Springer Nature in Journal of Optics
- Vol. 47 (3) , 396-404
Performance evaluation of hybrid optical amplifiers in WDM system
- 22 June 2018
- Published by Springer Nature in Journal of Optics
- Vol. 47 (3) , 396-404
Performance evaluation of hybrid optical amplifiers in WDM system