Fawad Salam Khan
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
Fawad Salam Khan has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Mohd Norzali Haji Mohd
Universiti Tun Hussein Onn Malaysia
4 shared publications - M. Danial Khan
CONVSYS (Pvt) Ltd
2 shared publications Muhammad Danial Khan
Dept. of Machine Learning Automation & Innovation, CONVSYS (Pvt) Ltd, Islamabad, Pakistan
2 shared publicationsRaja Masood Larik
Department of Electrical Engineering, NED Univesrity of Engg. & Tech. (NEDUET), Karachi, Pakistan
2 shared publicationsSusama Bagchi
Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Malaysia
2 shared publications- Arif Ullah
Multimedia University
1 shared publication
Latest Publications
- Open Access
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 33 (2) , 1140-1149
Proposed algorithm base optimisation plan for feature selection-based intrusion detection in cloud computing
A crucial element in detecting unusual network system behavior is the network intrusion detection system (NIDS), which also helps to stop network attacks from happening. Despite the fact that a great deal of machine learning techniques has been used in intrusion detection, current solutions still struggle to provide accurate classification results. Furthermore, when dealing with imbalanced multi-category traffic data, a single classifier may not be able to produce a superior. Particularly, internet of things (IoT) gadgets is now a commonplace aspect of life. On the other hand, some problems are becoming worse and lack clear remedies. Convergence, communication speed, and security between various IoT devices are among the primary concerns. In order to achieve this goal, an enhanced artificial bee colony technique utilizing binary search equations and neural networks—known as the (BABCN) algorithm for intrusion detection in terms of convergence and communication speed—is presented in this study. The artificial bee is improved by the depth-first search framework and binary search equations upon which the BABCN method is based. The suggested approach has a good ability to detect intrusions in the network and enhances categorization, according to the findings obtained by using the NSL-KDD dataset.
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 33 (2) , 1140-1149
Open AccessProposed algorithm base optimisation plan for feature selection-based intrusion detection in cloud computing
A crucial element in detecting unusual network system behavior is the network intrusion detection system (NIDS), which also helps to stop network attacks from happening. Despite the fact that a great deal of machine learning techniques has been used in intrusion detection, current solutions still struggle to provide accurate classification results. Furthermore, when dealing with imbalanced multi-category traffic data, a single classifier may not be able to produce a superior. Particularly, internet of things (IoT) gadgets is now a commonplace aspect of life. On the other hand, some problems are becoming worse and lack clear remedies. Convergence, communication speed, and security between various IoT devices are among the primary concerns. In order to achieve this goal, an enhanced artificial bee colony technique utilizing binary search equations and neural networks—known as the (BABCN) algorithm for intrusion detection in terms of convergence and communication speed—is presented in this study. The artificial bee is improved by the depth-first search framework and binary search equations upon which the BABCN method is based. The suggested approach has a good ability to detect intrusions in the network and enhances categorization, according to the findings obtained by using the NSL-KDD dataset.
- 27 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Federated learning-based UAVs for the diagnosis of Plant Diseases
The technological revolution for farmers, especially for the safety of their crops from pests, plays an evident change and convenience for the agriculture industry. The current research presented the classification of different pests using federated learning-based UAVs. The designed scenarios comprise four different sites connected with a global model where different parameters for these sites are received from the local model. State-of-the-art EfficientNet deep model with B03 configurations provides the best accuracy for classifying nine types of pests. The system can achieve an accuracy of 99.55% with the augmentation of images into different angles. The federated learning designed UAVs are the most reliable connection with very less computation power during the classification of pests for the agricultural environment.
- 27 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Federated learning-based UAVs for the diagnosis of Plant Diseases
The technological revolution for farmers, especially for the safety of their crops from pests, plays an evident change and convenience for the agriculture industry. The current research presented the classification of different pests using federated learning-based UAVs. The designed scenarios comprise four different sites connected with a global model where different parameters for these sites are received from the local model. State-of-the-art EfficientNet deep model with B03 configurations provides the best accuracy for classifying nine types of pests. The system can achieve an accuracy of 99.55% with the augmentation of images into different angles. The federated learning designed UAVs are the most reliable connection with very less computation power during the classification of pests for the agricultural environment.
- Open Access
- 1 August 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 12 (4) , 4099-4110
Breast cancer histological images nuclei segmentation and optimized classification with deep learning
Breast cancer incidences have grown worldwide during the previous few years. The histological images obtained from a biopsy of breast tissues are regarded as being the highest accurate approach to determine whether any cells exhibit symptoms of cancer. The visible position of nuclei inside the image is achieved through the use of instance segmentation, nevertheless, this work involves nucleus segmentation and features classification of the predicted nucleus for the achievement of best accuracy. The extracted features map using the feature pyramid network has been modified using segmenting objects by locations (SOLO) convolution with grasshopper optimization for multiclass classification. A breast cancer multiclassification technique based on a suggested deep learning algorithm was examined to achieve the accuracy of 99.2% using a huge database of ICIAR 2018, demonstrating the method’s efficacy in offering an important weapon for breast cancer multi-classification in a medical setting. The segmentation accuracy achieved is 88.46%.
- 1 August 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 12 (4) , 4099-4110
Open AccessBreast cancer histological images nuclei segmentation and optimized classification with deep learning
Breast cancer incidences have grown worldwide during the previous few years. The histological images obtained from a biopsy of breast tissues are regarded as being the highest accurate approach to determine whether any cells exhibit symptoms of cancer. The visible position of nuclei inside the image is achieved through the use of instance segmentation, nevertheless, this work involves nucleus segmentation and features classification of the predicted nucleus for the achievement of best accuracy. The extracted features map using the feature pyramid network has been modified using segmenting objects by locations (SOLO) convolution with grasshopper optimization for multiclass classification. A breast cancer multiclassification technique based on a suggested deep learning algorithm was examined to achieve the accuracy of 99.2% using a huge database of ICIAR 2018, demonstrating the method’s efficacy in offering an important weapon for breast cancer multi-classification in a medical setting. The segmentation accuracy achieved is 88.46%.
- Open Access
- 1 January 2022
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 72 (3) , 5741-5759
Deep Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Control Using 3D Hand Gestures
The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades. Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle (UAV) required maximum accuracy. In this paper, we designed a hybrid framework, which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures. The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient (DDPG) to receive the best reward and take actions according to 3D hand gestures input. The UAV consist of a Jetson Nano embedded testbed, Global Positioning System (GPS) sensor module, and Intel depth camera. The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function. The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives (PID) flight controller. There are six reward functions estimated for 2500, 5000, 7500, and 10000 episodes of training, which have been normalized between 0 to −4000. The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value. The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.
- 1 January 2022
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 72 (3) , 5741-5759
Open AccessDeep Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Control Using 3D Hand Gestures
The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades. Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle (UAV) required maximum accuracy. In this paper, we designed a hybrid framework, which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures. The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient (DDPG) to receive the best reward and take actions according to 3D hand gestures input. The UAV consist of a Jetson Nano embedded testbed, Global Positioning System (GPS) sensor module, and Intel depth camera. The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function. The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives (PID) flight controller. There are six reward functions estimated for 2500, 5000, 7500, and 10000 episodes of training, which have been normalized between 0 to −4000. The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value. The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.
- Open Access
- 22 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 131614-131624
3D Hand Gestures Segmentation and Optimized Classification Using Deep Learning
Hand gestures recognition system has massive applications which are mainly utilized in robotics and computer vision specially to control Unmanned Aerial Vehicles (UAV). These methods bypass the presence of electronic control to UAVs and provide an ease to the operators. In this paper, we present a method for 3D hand gestures segmentation and classification by combining MASK-RCNN with Grass Hopper Optimization. We created a private 3D and RGB hand gestures dataset using Intel Kinetic and Intel Real sense d435i camera, then proposed a model for RGB hand gestures to estimate the key points using human kinematics, the key points later then utilize to get the best degree of freedom (DoF). The grass hopper optimization besides minimum distance function was applied to achieve the finest deep features from the 3D hand gestures dataset. The ResNet50 network is used as the backbone to calculate the Overlap Coefficient (OC) for segmentation and the ResNet50, ResNet101 networks to calculate the classification for 3D hand gestures. The classification accuracy achieved on the private dataset is 99.05% and 99.29% on public Microsoft Kinect and Leap Motion dataset where the OC are 88.16%. and 88.19% respectively.
- 22 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 131614-131624
Open Access3D Hand Gestures Segmentation and Optimized Classification Using Deep Learning
Hand gestures recognition system has massive applications which are mainly utilized in robotics and computer vision specially to control Unmanned Aerial Vehicles (UAV). These methods bypass the presence of electronic control to UAVs and provide an ease to the operators. In this paper, we present a method for 3D hand gestures segmentation and classification by combining MASK-RCNN with Grass Hopper Optimization. We created a private 3D and RGB hand gestures dataset using Intel Kinetic and Intel Real sense d435i camera, then proposed a model for RGB hand gestures to estimate the key points using human kinematics, the key points later then utilize to get the best degree of freedom (DoF). The grass hopper optimization besides minimum distance function was applied to achieve the finest deep features from the 3D hand gestures dataset. The ResNet50 network is used as the backbone to calculate the Overlap Coefficient (OC) for segmentation and the ResNet50, ResNet101 networks to calculate the classification for 3D hand gestures. The classification accuracy achieved on the private dataset is 99.05% and 99.29% on public Microsoft Kinect and Leap Motion dataset where the OC are 88.16%. and 88.19% respectively.
- 13 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 203-208
A Smart Flight Controller based on Reinforcement Learning for Unmanned Aerial Vehicle (UAV)
Traditional flight controllers consist of Proportional Integral Derivates (PID), that although have dominant stability control but required high human interventions. In this study, a smart flight controller is developed for controlling UAVs which produces operator less mechanisms for flight controllers. It uses a neural network that has been trained using reinforcement learning techniques. Engineered with a variety of actuators (pitch, yaw, roll, and speed), the next-generation flight controller is directly trained to control its own decisions in flight. It also optimizes learning algorithms different from the traditional Actor and Critic networks. The agent gets state information from the environment and calculates the reward function depending on the sensors data from the environment. The agent then receives the observations to identify the state and reward functions and the agent activates the algorithm to perform actions. It shows the performance of a trained neural network consisting of a reward function in both simulation and real-time UAV control. Experimental results show that it can respond with relative precision. Using the same framework shows that UAVs can reliably hover in the air, even under adverse initialization conditions with obstacles. Reward functions computed during the flight for 2500, 5000, 7500 and 10000 episodes between the normalized values 0 and −4000. The computation time observed during each episode is 15 micro sec.
- 13 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 203-208
A Smart Flight Controller based on Reinforcement Learning for Unmanned Aerial Vehicle (UAV)
Traditional flight controllers consist of Proportional Integral Derivates (PID), that although have dominant stability control but required high human interventions. In this study, a smart flight controller is developed for controlling UAVs which produces operator less mechanisms for flight controllers. It uses a neural network that has been trained using reinforcement learning techniques. Engineered with a variety of actuators (pitch, yaw, roll, and speed), the next-generation flight controller is directly trained to control its own decisions in flight. It also optimizes learning algorithms different from the traditional Actor and Critic networks. The agent gets state information from the environment and calculates the reward function depending on the sensors data from the environment. The agent then receives the observations to identify the state and reward functions and the agent activates the algorithm to perform actions. It shows the performance of a trained neural network consisting of a reward function in both simulation and real-time UAV control. Experimental results show that it can respond with relative precision. Using the same framework shows that UAVs can reliably hover in the air, even under adverse initialization conditions with obstacles. Reward functions computed during the flight for 2500, 5000, 7500 and 10000 episodes between the normalized values 0 and −4000. The computation time observed during each episode is 15 micro sec.
- 27 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Breast Cancer Histological Images Nuclei Segmentation using Mask Regional Convolutional Neural Network
the breast cancer cases have increased globally, in the last two decades. Analysis of histological images acquired through biopsy of the breast tissues is thought to be the most reliable way to assess if any cells show signs of malignancy. With the advent of deep neural networks, we are now able to diagnose the disease with near perfect accuracy instead of conventional techniques of mammography for breast cancer detection; however, work done in this area considers nuclei segmentation. This work is focussed on extending the applicability of deep learning technology where network is trained to perform segmentation and classify data as one of the four classes: normal, benign, in-situ and invasive. The classification accuracy achieved is 98.16% and the segmentation accuracy calculated using overlap coefficient from mean intersection over union is 86.39% on the ICIAR2018 Breast Cancer dataset.
- 27 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Breast Cancer Histological Images Nuclei Segmentation using Mask Regional Convolutional Neural Network
the breast cancer cases have increased globally, in the last two decades. Analysis of histological images acquired through biopsy of the breast tissues is thought to be the most reliable way to assess if any cells show signs of malignancy. With the advent of deep neural networks, we are now able to diagnose the disease with near perfect accuracy instead of conventional techniques of mammography for breast cancer detection; however, work done in this area considers nuclei segmentation. This work is focussed on extending the applicability of deep learning technology where network is trained to perform segmentation and classify data as one of the four classes: normal, benign, in-situ and invasive. The classification accuracy achieved is 98.16% and the segmentation accuracy calculated using overlap coefficient from mean intersection over union is 86.39% on the ICIAR2018 Breast Cancer dataset.
- 25 August 2015
- Published by Penerbit UTM Press in Jurnal Teknologi (Sciences & Engineering)
- Vol. 76 (1)
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING LABYRINTHINE AUTHENTICATION FORMULA
Facilities for different sight and sound provisions in remote systems requests extra transmission capacity in the radio frequency range. Effective range administration calculations are important to accomplish massive accomplishment in remote correspondences. Usage of licensed spectrum is increasing day by day so Cognitive Radio is proposed as a solution to meet the demands. CR is a symbolization procedure that distributes the authorized range (the licensed spectrum) despite the fact that facing least obstruction to the authorized clients. In this paper, we investigate the versatile qualities of cognitive radio in secure and dependable correspondence. Anyway the inquiry is the way to make the correspondence dependable such that there happens no spying and data spillage. The conceivable results incorporate coordinating the benefits of spread range balance, utilizing encryption calculations (Encryption keys), and its possibility to switch over different recurrence groups. We concentrate on the different requisitions of CR and the various philosophies which empower a safe Communication system.
- 25 August 2015
- Published by Penerbit UTM Press in Jurnal Teknologi (Sciences & Engineering)
- Vol. 76 (1)
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING LABYRINTHINE AUTHENTICATION FORMULA
Facilities for different sight and sound provisions in remote systems requests extra transmission capacity in the radio frequency range. Effective range administration calculations are important to accomplish massive accomplishment in remote correspondences. Usage of licensed spectrum is increasing day by day so Cognitive Radio is proposed as a solution to meet the demands. CR is a symbolization procedure that distributes the authorized range (the licensed spectrum) despite the fact that facing least obstruction to the authorized clients. In this paper, we investigate the versatile qualities of cognitive radio in secure and dependable correspondence. Anyway the inquiry is the way to make the correspondence dependable such that there happens no spying and data spillage. The conceivable results incorporate coordinating the benefits of spread range balance, utilizing encryption calculations (Encryption keys), and its possibility to switch over different recurrence groups. We concentrate on the different requisitions of CR and the various philosophies which empower a safe Communication system.