World is now considered as global village because of interconnected networks. Smart phones and la... more World is now considered as global village because of interconnected networks. Smart phones and large computing devices exchange millions of information each day. Information or data privacy is first priority for any tech company. Information security get attention both from academia and industry sectors for the purpose of data prevention, integrity and data modification. Traditional and mathematical security models are implemented to address information related issues but does not provide full proof data privacy. Computational Intelligence is power technique inspired from biological development and act as intelligent agent which detects treats in real and complex environments. Computational Intelligence is further sub divided in to Fuzzy Logic, Evaluation Computation, Artificial Neural Networks and hybrid approach. In this research study each branch of Computational Intelligence is studied from cybersecurity point of view with its merits and demerits.
Recent innovations and advanced technology encourage users to implement solutions against harmful... more Recent innovations and advanced technology encourage users to implement solutions against harmful attacks. This is provided new capabilities of dynamic provisioning, monitoring, and management to reduce the IT barriers.IDS is one of the challenging tasks where attackers always change their tools and techniques. Several techniques have been implemented to secure the IoT network, but a few problems are expanding, and their results are not well defined. According to this study, machine learning techniques have been used to detect and classify the problem into the anomaly and normal from the Network Intrusion Detection dataset. First, the data is preprocessed and make it standardize by standard scaler function. The random forest technique has been used to extract the significant features from the dataset. Furthermore, five different classification technique has been used based on the performance measure and compared. The outcome represents that the Decision tree model accomplished the highest accuracy of 100% among other classifiers.
AI and IoT for Sustainable Development in Emerging Countries, 2022
The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 2... more The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 223 billion deaths worldwide. It is believed that the world will need to take preventive measures against the COVID-19 pandemic until a vaccine is developed. Early detection of COVID19 infections is a major challenge for healthcare professionals, governments, and organizations to combat against the virus. Therefore, its need an intelligent monitoring system that detects COVID19 and tracks the infected person may improve clinical decision-making and stop spreading the virus among people. The Internet of things (IoT), machine learning, and the Deep learning approach changed our lives in the healthcare sector. This survey presents how IoT, machine learning, and deep learning are incorporated into the pandemic prevention and control system by detection, diagnosis, monitoring, tracing, and social distance finding. We examine and review the most recent literature and present the role of IoT, machine learning, and deep learning in combating the current COVID-19 pandemic. Further, we have also identified a few issues and research directions while using IoT during the COVID-19 pandemic.
Indonesian Journal of Electrical Engineering and Computer Science, 2021
Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small... more Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small unmanned aerial vehicles (UAVs) are used in FANETs applications and these small UAVs have limited resources while efficiently utilization of these resources is most critical task in real time monitoring of FANETs application. Network consumes its resources in path selection process and data routing from source to destination. Selecting of efficient routing protocol to utilize all available resources played vital role in extending network life time. In this article fisheye state routing (FSR) protocol is implemented in FANET and compare networks performance in term of channel utilization, link utilization vs throughput and packet delivery ratio (PDR) with distance sequence distance vector (DSDV), optimized link state routing (OLSR), adhoc on demand distance vector (AODV), dynamic source routing (DSR) and temperary ordered routing protocol (TORA). Experimental analysis slows that FSR is g...
A visually impaired person faces many difficulties in their daily life, such as having trouble fi... more A visually impaired person faces many difficulties in their daily life, such as having trouble finding their ways, recognize the person and objects. One of the crucial problems is to recognize the currencies for a blind or visually impaired person. In this research article, we have proposed a system to recognize a Pakistani currency for a blind or visually impaired person based on Convolutional Neural Network (CNN) and Support Vector Machine (SVM). In the proposed system, seven different Pakistani paper currency notes (Rs.10, 20, 50, 100,500, 1000 and 5000) are used for training and testing. Experimental results show that the proposed system can recognize seven notes of Pakistan's Currency (Rs. 10, 20, 50, 100, 500, 1000, 5000) successfully with an accuracy of 96.85%.
2020 IEEE 23rd International Multitopic Conference (INMIC), 2020
In recent years, the rate of skin diseases is increasing worldwide, skin cancer is defined as the... more In recent years, the rate of skin diseases is increasing worldwide, skin cancer is defined as the rapid growth of skin cells due to DNA damage which cannot be repaired. It can be harmful and can lead to death if not diagnosed at early stages. The rapid growth of technology, makes it possible to detect different skin diseases at early stages. The impact of rapid technological change on sustainable development in the areas of image processing and machine learning gives an ability to detect early, which increases the probability of survival in the cancer patients. This research primarily focuses on segmentation and classification of the skin lesions from the MRI scan images. Segmentation is carried out in three stages which are pre-processing, segmentation and postprocessing. In the second section, classification is performed using feature extractor and different classifiers. The features are firstly extracted using color, shape, texture component of the skin lesion, and then concatena...
Artificial Intelligence Systems and the Internet of Things in the Digital Era, 2021
COVID-19 is an infectious disease caused by SARS-Cov2 that has spread rapidly worldwide. Accordin... more COVID-19 is an infectious disease caused by SARS-Cov2 that has spread rapidly worldwide. According to the World Health Organization (WHO), the total cases of 4374783839 are reported from different countries. In this consequence, it is necessary to diagnose automatically COVID-19, which helps in prevention during spreading among people. In this study, we have used machine learning techniques to diagnose and classify the COVID-19 and normal patients from chest X-ray images using a machine learning technique. The proposed system involves pre-processing, feature extraction, and classification. In the pre-processing, the image is to enhance and improve the contrast. In the feature extraction, the Histogram of Oriented Gradients has been applied to extract the image's feature. Finally, in classification two different machine learning techniques (Support Vector Machine and Logistic Regression) have been used to classify COVID-19 and normal patients. The result analysis shows that the SVM achieved the highest accuracy of 96% and provide a better result than logistic regression (92% accuracy).
Conventional network architectures are not appropriate for the needs of current businesses, carri... more Conventional network architectures are not appropriate for the needs of current businesses, carriers, and end-users. Consequently, new evolving network architecture, Software Defined Network can be used to solve a problem as it is more adaptive, dynamic, manageable, and programmable. The SDN architecture control and data planes are isolated, network information and the state are legalized, and the essential network infrastructure is excluded from the applications. However, a network may achieve a point where the computer or network resources restrict the data flow that is controlled according to the bandwidth. In this paper, the custom network topology is created. To observe the performance of Dijkstra's shortest route algorithm in the SDN open-source controllers: RYU and POX to find out the shortest route between source and the destination nodes. The controller's performance is calculated based on the quality-of-service measures, containing throughput and packet delivery ra...
Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed ... more Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed to enhance road traffic protection by making drivers become more mindful of the road and its potential hazards, as well as other vehicles around them. The design of traffic sign, traffic light, traffic cone, car, road lane, pedestrian and road blocker detection and Recognition, a significant ADAS subsystem, has been a problem for many years and thus becomes an essential and successful research topic in the field of smart transport systems. This paper present different approaches Devised over the last 3 years for the diverse modalities. We present a survey of each challenge in form of table in terms of “algorithm, parameter, result, advantage, and disadvantage. For each survey, we describe the possible implementations suggested and analyze their underlying assumptions, while impressive advancements were demonstrated at limited scenarios, inspection into the needs of next generation system...
The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 2... more The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 223 billion deaths worldwide. It is believed that the world will need to take preventive measures against the COVID-19 pandemic until a vaccine is developed. Early detection of COVID19 infections is a major challenge for healthcare professionals, governments, and organizations to combat against the virus. Therefore, its need an intelligent monitoring system that detects COVID19 and tracks the infected person may improve clinical decision-making and stop spreading the virus among people. The Internet of things (IoT), machine learning, and the Deep learning approach changed our lives in the healthcare sector. This survey presents how IoT, machine learning, and deep learning are incorporated into the pandemic prevention and control system by detection, diagnosis, monitoring, tracing, and social distance finding. We examine and review the most recent literature and present the role of IoT, machine learning, and deep learning in combating the current COVID-19 pandemic. Further, we have also identified a few issues and research directions while using IoT during the COVID-19 pandemic.
During the global urgency, experts from all over the world searching for a new technology that su... more During the global urgency, experts from all over the world searching for a new technology that supports the COVID19 pandemic. The deep learning and artificial intelligence application used the researchers on the previous epidemic, which encouraged a new angle to fight against the COVID19 outbreak. The limited number of COVID19 kits available in hospitals is due to the increasingly high number of cases. Therefore, it is necessary to implement an alternative system that detects and diagnoses the COVID19 and stops spreading among people. This chapter aims to detect and classify COVID19 infected, normal, and pneumonia patients from X-ray images using deep learning techniques (proposed CNN, AlexNet, and VGG16 models). The experiment was performed by combining two datasets, which are available on the Kaggle repository. The result analysis shows that the proposed CNN model achieved the highest accuracy of 95% from other deep learning models (AlexNet 90% of accuracy, and VGG16 94% of accuracy).
The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 2... more The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 223 billion deaths worldwide. It is believed that the world will need to take preventive measures against the COVID-19 pandemic until a vaccine is developed. Early detection of COVID19 infections is a major challenge for healthcare professionals, governments, and organizations to combat against the virus. Therefore, its need an intelligent monitoring system that detects COVID19 and tracks the infected person may improve clinical decision-making and stop spreading the virus among people. The Internet of things (IoT), machine learning, and the Deep learning approach changed our lives in the healthcare sector. This survey presents how IoT, machine learning, and deep learning are incorporated into the pandemic prevention and control system by detection, diagnosis, monitoring, tracing, and social distance finding. We examine and review the most recent literature and present the role of IoT, machine learning, and deep learning in combating the current COVID-19 pandemic. Further, we have also identified a few issues and research directions while using IoT during the COVID-19 pandemic.
During the global urgency, experts from all over the world searching for a new technology that su... more During the global urgency, experts from all over the world searching for a new technology that supports the COVID19 pandemic. The deep learning and artificial intelligence application used the researchers on the previous epidemic, which encouraged a new angle to fight against the COVID19 outbreak. The limited number of COVID19 kits available in hospitals is due to the increasingly high number of cases. Therefore, it is necessary to implement an alternative system that detects and diagnoses the COVID19 and stops spreading among people. This chapter aims to detect and classify COVID19 infected, normal, and pneumonia patients from X-ray images using deep learning techniques (proposed CNN, AlexNet, and VGG16 models). The experiment was performed by combining two datasets, which are available on the Kaggle repository. The result analysis shows that the proposed CNN model achieved the highest accuracy of 95% from other deep learning models (AlexNet 90% of accuracy, and VGG16 94% of accuracy).
The coronavirus (COVID-19) pandemic rapidly spread from the infected person who has a severe heal... more The coronavirus (COVID-19) pandemic rapidly spread from the infected person who has a severe health problem around the world. World Health Organization (WHO) has identified the coronavirus as a global pandemic issue. The infected person has a severe respiratory issue that needs to be treated in an intensive health care unit. The detection of COVID-19 using machine learning techniques will help in healthcare system about fast recovery of patients worldwide. One of the crucial steps is to detect these pandemic diseases by predicting whether COVID19 infects the human body or not. The investigation is carried out by analyzing Chest X-ray images to diagnose the patients. In this study, we have presented a method to efficiently classify the COVID-19 infected patients and normally based on chest X-ray radiography using Machine Learning techniques. The proposed system involves pre-processing, feature extraction, and classification. The image is pre-processed to improve the contrast enhanc...
Statistics indicate that most road accidents occur due to a lack of time to react to instant traf... more Statistics indicate that most road accidents occur due to a lack of time to react to instant traffic. This problem can be addressed with self-driving vehicles with the application of automated systems to detect such traffic events. The Autonomous Vehicle Navigation System (ATS) has been a standard in the Intelligent Transport System (ITS) and many Driver Assistance Systems (DAS) have been adopted to support these Advanced Autonomous Vehicles (IAVs). To develop these recognition systems for automated self-driving cars, it's important to monitor and operate in real-time traffic events. It requires the correct detection and response of traffic event an automated vehicle. In this paper proposed to develop such a system by applying image recognition to detect and respond to a road blocker by means of real-time distance measurement. To study the performance by measuring accuracy and precision of road blocker detection system and distance calculation, various experiments were conducted by using Shalom frame dataset and detection accuracy, precision of 99%, 100%, while distance calculation 97%, 99% has been achieved by this approach.
Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small... more Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small unmanned aerial vehicles (UAVs) are used in FANETs applications and these small UAVs have limited resources while efficiently utilization of these resources is most critical task in real time monitoring of FANETs application. Network consumes its resources in path selection process and data routing from source to destination. Selecting of efficient routing protocol to utilize all available resources played vital role in extending network life time. In this Article Fisheye State Routing (FSR) protocol is implemented in FANET and compare networks performance in term of Channel Utilization, Link Utilization vs Throughput and packet delivery ratio (PDR) with distance sequence distance vector (DSDV), optimized link state routing (OLSR), adhoc on demand distance vector (AODV), dynamic source routing (DSR) and temperary ordered routing protocol (TORA). Experimental Analysis slows that FSR is good in term of PDR (16438 packets delivered), Channel Utilization (89%) and Link vs Throughput from the rest of routing protocols after addressing of these problems UAVs resources are efficiently utilized (energy).
Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed ... more Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed to enhance road traffic protection by making drivers become more mindful of the road and its potential hazards, as well as other vehicles around them. The design of traffic sign, traffic light, traffic cone, car, road lane, pedestrian and road blocker detection and Recognition, a significant ADAS subsystem, has been a problem for many years and thus becomes an essential and successful research topic in the field of smart transport systems. This paper present different approaches Devised over the last 3 years for the diverse modalities. We present a survey of each challenge in form of table in terms of
According to statistics, most road accidents take place due slow response time to instant traffic... more According to statistics, most road accidents take place due slow response time to instant traffic events. Accidents can be reduced by implementing automated detect systems. The Autonomous Vehicle Navigation System (ATS) has been a standard in the Intelligent Transport System (ITS) and many Driver Assistance Systems (DAS) have been adopted in Advanced Autonomous Vehicles (IAVs). This research article presents a novel navigation approach for the autonomous system to detect road blockers based on a color probability model. This work mainly focused on the detection and classification of road blocker in images. The detection technique is mainly based on four major phases namely pre-processing, segmentation and post-processing, Distance calculation. In pre-processing phase images are resized and segment road blocker from the image via color segmentation in the end post-processing technique is applied to merge the candidate region. Edge labeling algorithm is applied to remove the extraneous objects in the image. Mean value is calculated to detect candidate bounding box region to find the distance between road blocker and vehicle. Subsequently machine learning techniques which involved various steps like feature extraction and classification. In feature extraction, the combination of shape and texture using histogram-oriented gradient (HOG) and local binary pattern (LBP) for object labeling. In classification, four different machine algorithms (i)Support vector machine (SVM), (ii)K-Nearest Neighbor (KNN), (iii) Decision Tree (DT), and (iv) Naïve Bayes (NB) algorithms are used to efficiently classify road blockers. The conducted experimental analysis shows that the SVM and NB algorithms achieved the highest accuracy of 97% among the proposed classifiers (77% accuracy for Decision Tree, 93% accuracy for K-Nearest Neighbors, and 96% of Color segmentation).
World is now considered as global village because of interconnected networks. Smart phones and la... more World is now considered as global village because of interconnected networks. Smart phones and large computing devices exchange millions of information each day. Information or data privacy is first priority for any tech company. Information security get attention both from academia and industry sectors for the purpose of data prevention, integrity and data modification. Traditional and mathematical security models are implemented to address information related issues but does not provide full proof data privacy. Computational Intelligence is power technique inspired from biological development and act as intelligent agent which detects treats in real and complex environments. Computational Intelligence is further sub divided in to Fuzzy Logic, Evaluation Computation, Artificial Neural Networks and hybrid approach. In this research study each branch of Computational Intelligence is studied from cybersecurity point of view with its merits and demerits.
Recent innovations and advanced technology encourage users to implement solutions against harmful... more Recent innovations and advanced technology encourage users to implement solutions against harmful attacks. This is provided new capabilities of dynamic provisioning, monitoring, and management to reduce the IT barriers.IDS is one of the challenging tasks where attackers always change their tools and techniques. Several techniques have been implemented to secure the IoT network, but a few problems are expanding, and their results are not well defined. According to this study, machine learning techniques have been used to detect and classify the problem into the anomaly and normal from the Network Intrusion Detection dataset. First, the data is preprocessed and make it standardize by standard scaler function. The random forest technique has been used to extract the significant features from the dataset. Furthermore, five different classification technique has been used based on the performance measure and compared. The outcome represents that the Decision tree model accomplished the highest accuracy of 100% among other classifiers.
AI and IoT for Sustainable Development in Emerging Countries, 2022
The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 2... more The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 223 billion deaths worldwide. It is believed that the world will need to take preventive measures against the COVID-19 pandemic until a vaccine is developed. Early detection of COVID19 infections is a major challenge for healthcare professionals, governments, and organizations to combat against the virus. Therefore, its need an intelligent monitoring system that detects COVID19 and tracks the infected person may improve clinical decision-making and stop spreading the virus among people. The Internet of things (IoT), machine learning, and the Deep learning approach changed our lives in the healthcare sector. This survey presents how IoT, machine learning, and deep learning are incorporated into the pandemic prevention and control system by detection, diagnosis, monitoring, tracing, and social distance finding. We examine and review the most recent literature and present the role of IoT, machine learning, and deep learning in combating the current COVID-19 pandemic. Further, we have also identified a few issues and research directions while using IoT during the COVID-19 pandemic.
Indonesian Journal of Electrical Engineering and Computer Science, 2021
Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small... more Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small unmanned aerial vehicles (UAVs) are used in FANETs applications and these small UAVs have limited resources while efficiently utilization of these resources is most critical task in real time monitoring of FANETs application. Network consumes its resources in path selection process and data routing from source to destination. Selecting of efficient routing protocol to utilize all available resources played vital role in extending network life time. In this article fisheye state routing (FSR) protocol is implemented in FANET and compare networks performance in term of channel utilization, link utilization vs throughput and packet delivery ratio (PDR) with distance sequence distance vector (DSDV), optimized link state routing (OLSR), adhoc on demand distance vector (AODV), dynamic source routing (DSR) and temperary ordered routing protocol (TORA). Experimental analysis slows that FSR is g...
A visually impaired person faces many difficulties in their daily life, such as having trouble fi... more A visually impaired person faces many difficulties in their daily life, such as having trouble finding their ways, recognize the person and objects. One of the crucial problems is to recognize the currencies for a blind or visually impaired person. In this research article, we have proposed a system to recognize a Pakistani currency for a blind or visually impaired person based on Convolutional Neural Network (CNN) and Support Vector Machine (SVM). In the proposed system, seven different Pakistani paper currency notes (Rs.10, 20, 50, 100,500, 1000 and 5000) are used for training and testing. Experimental results show that the proposed system can recognize seven notes of Pakistan's Currency (Rs. 10, 20, 50, 100, 500, 1000, 5000) successfully with an accuracy of 96.85%.
2020 IEEE 23rd International Multitopic Conference (INMIC), 2020
In recent years, the rate of skin diseases is increasing worldwide, skin cancer is defined as the... more In recent years, the rate of skin diseases is increasing worldwide, skin cancer is defined as the rapid growth of skin cells due to DNA damage which cannot be repaired. It can be harmful and can lead to death if not diagnosed at early stages. The rapid growth of technology, makes it possible to detect different skin diseases at early stages. The impact of rapid technological change on sustainable development in the areas of image processing and machine learning gives an ability to detect early, which increases the probability of survival in the cancer patients. This research primarily focuses on segmentation and classification of the skin lesions from the MRI scan images. Segmentation is carried out in three stages which are pre-processing, segmentation and postprocessing. In the second section, classification is performed using feature extractor and different classifiers. The features are firstly extracted using color, shape, texture component of the skin lesion, and then concatena...
Artificial Intelligence Systems and the Internet of Things in the Digital Era, 2021
COVID-19 is an infectious disease caused by SARS-Cov2 that has spread rapidly worldwide. Accordin... more COVID-19 is an infectious disease caused by SARS-Cov2 that has spread rapidly worldwide. According to the World Health Organization (WHO), the total cases of 4374783839 are reported from different countries. In this consequence, it is necessary to diagnose automatically COVID-19, which helps in prevention during spreading among people. In this study, we have used machine learning techniques to diagnose and classify the COVID-19 and normal patients from chest X-ray images using a machine learning technique. The proposed system involves pre-processing, feature extraction, and classification. In the pre-processing, the image is to enhance and improve the contrast. In the feature extraction, the Histogram of Oriented Gradients has been applied to extract the image's feature. Finally, in classification two different machine learning techniques (Support Vector Machine and Logistic Regression) have been used to classify COVID-19 and normal patients. The result analysis shows that the SVM achieved the highest accuracy of 96% and provide a better result than logistic regression (92% accuracy).
Conventional network architectures are not appropriate for the needs of current businesses, carri... more Conventional network architectures are not appropriate for the needs of current businesses, carriers, and end-users. Consequently, new evolving network architecture, Software Defined Network can be used to solve a problem as it is more adaptive, dynamic, manageable, and programmable. The SDN architecture control and data planes are isolated, network information and the state are legalized, and the essential network infrastructure is excluded from the applications. However, a network may achieve a point where the computer or network resources restrict the data flow that is controlled according to the bandwidth. In this paper, the custom network topology is created. To observe the performance of Dijkstra's shortest route algorithm in the SDN open-source controllers: RYU and POX to find out the shortest route between source and the destination nodes. The controller's performance is calculated based on the quality-of-service measures, containing throughput and packet delivery ra...
Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed ... more Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed to enhance road traffic protection by making drivers become more mindful of the road and its potential hazards, as well as other vehicles around them. The design of traffic sign, traffic light, traffic cone, car, road lane, pedestrian and road blocker detection and Recognition, a significant ADAS subsystem, has been a problem for many years and thus becomes an essential and successful research topic in the field of smart transport systems. This paper present different approaches Devised over the last 3 years for the diverse modalities. We present a survey of each challenge in form of table in terms of “algorithm, parameter, result, advantage, and disadvantage. For each survey, we describe the possible implementations suggested and analyze their underlying assumptions, while impressive advancements were demonstrated at limited scenarios, inspection into the needs of next generation system...
The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 2... more The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 223 billion deaths worldwide. It is believed that the world will need to take preventive measures against the COVID-19 pandemic until a vaccine is developed. Early detection of COVID19 infections is a major challenge for healthcare professionals, governments, and organizations to combat against the virus. Therefore, its need an intelligent monitoring system that detects COVID19 and tracks the infected person may improve clinical decision-making and stop spreading the virus among people. The Internet of things (IoT), machine learning, and the Deep learning approach changed our lives in the healthcare sector. This survey presents how IoT, machine learning, and deep learning are incorporated into the pandemic prevention and control system by detection, diagnosis, monitoring, tracing, and social distance finding. We examine and review the most recent literature and present the role of IoT, machine learning, and deep learning in combating the current COVID-19 pandemic. Further, we have also identified a few issues and research directions while using IoT during the COVID-19 pandemic.
During the global urgency, experts from all over the world searching for a new technology that su... more During the global urgency, experts from all over the world searching for a new technology that supports the COVID19 pandemic. The deep learning and artificial intelligence application used the researchers on the previous epidemic, which encouraged a new angle to fight against the COVID19 outbreak. The limited number of COVID19 kits available in hospitals is due to the increasingly high number of cases. Therefore, it is necessary to implement an alternative system that detects and diagnoses the COVID19 and stops spreading among people. This chapter aims to detect and classify COVID19 infected, normal, and pneumonia patients from X-ray images using deep learning techniques (proposed CNN, AlexNet, and VGG16 models). The experiment was performed by combining two datasets, which are available on the Kaggle repository. The result analysis shows that the proposed CNN model achieved the highest accuracy of 95% from other deep learning models (AlexNet 90% of accuracy, and VGG16 94% of accuracy).
The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 2... more The world has been facing a challenging issue of COVID-19, which has infected 223 countries and 223 billion deaths worldwide. It is believed that the world will need to take preventive measures against the COVID-19 pandemic until a vaccine is developed. Early detection of COVID19 infections is a major challenge for healthcare professionals, governments, and organizations to combat against the virus. Therefore, its need an intelligent monitoring system that detects COVID19 and tracks the infected person may improve clinical decision-making and stop spreading the virus among people. The Internet of things (IoT), machine learning, and the Deep learning approach changed our lives in the healthcare sector. This survey presents how IoT, machine learning, and deep learning are incorporated into the pandemic prevention and control system by detection, diagnosis, monitoring, tracing, and social distance finding. We examine and review the most recent literature and present the role of IoT, machine learning, and deep learning in combating the current COVID-19 pandemic. Further, we have also identified a few issues and research directions while using IoT during the COVID-19 pandemic.
During the global urgency, experts from all over the world searching for a new technology that su... more During the global urgency, experts from all over the world searching for a new technology that supports the COVID19 pandemic. The deep learning and artificial intelligence application used the researchers on the previous epidemic, which encouraged a new angle to fight against the COVID19 outbreak. The limited number of COVID19 kits available in hospitals is due to the increasingly high number of cases. Therefore, it is necessary to implement an alternative system that detects and diagnoses the COVID19 and stops spreading among people. This chapter aims to detect and classify COVID19 infected, normal, and pneumonia patients from X-ray images using deep learning techniques (proposed CNN, AlexNet, and VGG16 models). The experiment was performed by combining two datasets, which are available on the Kaggle repository. The result analysis shows that the proposed CNN model achieved the highest accuracy of 95% from other deep learning models (AlexNet 90% of accuracy, and VGG16 94% of accuracy).
The coronavirus (COVID-19) pandemic rapidly spread from the infected person who has a severe heal... more The coronavirus (COVID-19) pandemic rapidly spread from the infected person who has a severe health problem around the world. World Health Organization (WHO) has identified the coronavirus as a global pandemic issue. The infected person has a severe respiratory issue that needs to be treated in an intensive health care unit. The detection of COVID-19 using machine learning techniques will help in healthcare system about fast recovery of patients worldwide. One of the crucial steps is to detect these pandemic diseases by predicting whether COVID19 infects the human body or not. The investigation is carried out by analyzing Chest X-ray images to diagnose the patients. In this study, we have presented a method to efficiently classify the COVID-19 infected patients and normally based on chest X-ray radiography using Machine Learning techniques. The proposed system involves pre-processing, feature extraction, and classification. The image is pre-processed to improve the contrast enhanc...
Statistics indicate that most road accidents occur due to a lack of time to react to instant traf... more Statistics indicate that most road accidents occur due to a lack of time to react to instant traffic. This problem can be addressed with self-driving vehicles with the application of automated systems to detect such traffic events. The Autonomous Vehicle Navigation System (ATS) has been a standard in the Intelligent Transport System (ITS) and many Driver Assistance Systems (DAS) have been adopted to support these Advanced Autonomous Vehicles (IAVs). To develop these recognition systems for automated self-driving cars, it's important to monitor and operate in real-time traffic events. It requires the correct detection and response of traffic event an automated vehicle. In this paper proposed to develop such a system by applying image recognition to detect and respond to a road blocker by means of real-time distance measurement. To study the performance by measuring accuracy and precision of road blocker detection system and distance calculation, various experiments were conducted by using Shalom frame dataset and detection accuracy, precision of 99%, 100%, while distance calculation 97%, 99% has been achieved by this approach.
Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small... more Flying Ad-hoc networks are emergent area in Ad-hoc networks evolved from MANETs and VANETs. Small unmanned aerial vehicles (UAVs) are used in FANETs applications and these small UAVs have limited resources while efficiently utilization of these resources is most critical task in real time monitoring of FANETs application. Network consumes its resources in path selection process and data routing from source to destination. Selecting of efficient routing protocol to utilize all available resources played vital role in extending network life time. In this Article Fisheye State Routing (FSR) protocol is implemented in FANET and compare networks performance in term of Channel Utilization, Link Utilization vs Throughput and packet delivery ratio (PDR) with distance sequence distance vector (DSDV), optimized link state routing (OLSR), adhoc on demand distance vector (AODV), dynamic source routing (DSR) and temperary ordered routing protocol (TORA). Experimental Analysis slows that FSR is good in term of PDR (16438 packets delivered), Channel Utilization (89%) and Link vs Throughput from the rest of routing protocols after addressing of these problems UAVs resources are efficiently utilized (energy).
Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed ... more Advanced Driver Assistance Systems (ADAS) apply to various high-tech in-vehicle systems designed to enhance road traffic protection by making drivers become more mindful of the road and its potential hazards, as well as other vehicles around them. The design of traffic sign, traffic light, traffic cone, car, road lane, pedestrian and road blocker detection and Recognition, a significant ADAS subsystem, has been a problem for many years and thus becomes an essential and successful research topic in the field of smart transport systems. This paper present different approaches Devised over the last 3 years for the diverse modalities. We present a survey of each challenge in form of table in terms of
According to statistics, most road accidents take place due slow response time to instant traffic... more According to statistics, most road accidents take place due slow response time to instant traffic events. Accidents can be reduced by implementing automated detect systems. The Autonomous Vehicle Navigation System (ATS) has been a standard in the Intelligent Transport System (ITS) and many Driver Assistance Systems (DAS) have been adopted in Advanced Autonomous Vehicles (IAVs). This research article presents a novel navigation approach for the autonomous system to detect road blockers based on a color probability model. This work mainly focused on the detection and classification of road blocker in images. The detection technique is mainly based on four major phases namely pre-processing, segmentation and post-processing, Distance calculation. In pre-processing phase images are resized and segment road blocker from the image via color segmentation in the end post-processing technique is applied to merge the candidate region. Edge labeling algorithm is applied to remove the extraneous objects in the image. Mean value is calculated to detect candidate bounding box region to find the distance between road blocker and vehicle. Subsequently machine learning techniques which involved various steps like feature extraction and classification. In feature extraction, the combination of shape and texture using histogram-oriented gradient (HOG) and local binary pattern (LBP) for object labeling. In classification, four different machine algorithms (i)Support vector machine (SVM), (ii)K-Nearest Neighbor (KNN), (iii) Decision Tree (DT), and (iv) Naïve Bayes (NB) algorithms are used to efficiently classify road blockers. The conducted experimental analysis shows that the SVM and NB algorithms achieved the highest accuracy of 97% among the proposed classifiers (77% accuracy for Decision Tree, 93% accuracy for K-Nearest Neighbors, and 96% of Color segmentation).
Uploads
Papers by Muhammad Imad