Khalid Mahmood Awan

Bio: Khalid Mahmood Awan is an academic researcher from COMSATS Institute of Information Technology. The author has contributed to research in topics: Routing protocol & Wireless sensor network. The author has an hindex of 11, co-authored 36 publications receiving 417 citations. Previous affiliations of Khalid Mahmood Awan include Universiti Teknologi Malaysia.

Underwater Wireless Sensor Networks: A Review of Recent Issues and Challenges

Abstract: Underwater Wireless Sensor Networks (UWSNs) contain several components such as vehicles and sensors that are deployed in a specific acoustic area to perform collaborative monitoring and data collection tasks. These networks are used interactively between different nodes and ground-based stations. Presently, UWSNs face issues and challenges regarding limited bandwidth, high propagation delay, 3D topology, media access control, routing, resource utilization, and power constraints. In the last few decades, research community provided different methodologies to overcome these issues and challenges; however, some of them are still open for research due to variable characteristics of underwater environment. In this paper, a survey of UWSN regarding underwater communication channel, environmental factors, localization, media access control, routing protocols, and effect of packet size on communication is conducted. We compared presently available methodologies and discussed their pros and cons to highlight new directions of research for further improvement in underwater sensor networks.

A Data Augmentation-Based Framework to Handle Class Imbalance Problem for Alzheimer’s Stage Detection

Abstract: Alzheimer's Disease (AD) is the most common form of dementia. It gradually increases from mild stage to severe, affecting the ability to perform common daily tasks without assistance. It is a neurodegenerative illness, presently having no specified cure. Computer-Aided Diagnostic Systems have played an important role to help physicians to identify AD. However, the diagnosis of AD into its four stages; No Dementia, Very Mild Dementia, Mild Dementia, and Moderate Dementia remains an open research area. Deep learning assisted computer-aided solutions are proved to be more useful because of their high accuracy. However, the most common problem with deep learning architecture is that large training data is required. Furthermore, the samples should be evenly distributed among the classes to avoid the class imbalance problem. The publicly available dataset (OASIS) has serious class imbalance problem. In this research, we employed a transfer learning-based technique using data augmentation for 3D Magnetic Resonance Imaging (MRI) views from OASIS dataset. The accuracy of the proposed model utilizing a single view of the brain MRI is 98.41% while using 3D-views is 95.11%. The proposed system outperformed the existing techniques for Alzheimer disease stages.

A Heterogeneous IoV Architecture for Data Forwarding in Vehicle to Infrastructure Communication

Abstract: The Internet of vehicles (IoV) is a newly emerged wave that converges Internet of things (IoT) into vehicular networks to benefit from ubiquitous Internet connectivity. Despite various research efforts, vehicular networks are still striving to achieve higher data rate, seamless connectivity, scalability, security, and improved quality of service, which are the key enablers for IoV. It becomes even more critical to investigate novel design architectures to accomplish efficient and reliable data forwarding when it comes to handling the emergency communication infrastructure in the presence of natural epidemics. The article proposes a heterogeneous network architecture incorporating multiple wireless interfaces (e.g., wireless access in vehicular environment (WAVE), long-range wireless fidelity (WiFi), and fourth generation/long-term evolution (4G/LTE)) installed on the on-board units, exploiting the radio over fiber approach to establish a context-aware network connectivity. This heterogeneous network architecture attempts to meet the requirements of pervasive connectivity for vehicular ad hoc networks (VANETs) to make them scalable and adaptable for IoV supporting a range of emergency services. The architecture employs the Best Interface Selection (BIS) algorithm to always ensure reliable communication through the best available wireless interface to support seamless connectivity required for efficient data forwarding in vehicle to infrastructure (V2I) communication successfully avoiding the single point of failure. Moreover, the simulation results clearly argue about the suitability of the proposed architecture in IoV environment coping with different types of applications against individual wireless technologies.

A priority-based congestion-avoidance routing protocol using IoT-based heterogeneous medical sensors for energy efficiency in healthcare wireless body area networks:

Abstract: A wireless body area network is a collection of Internet of Things–based wearable heterogeneous computing devices primarily used in healthcare monitoring applications. A lot of research is in proce...

A state-of-the-art survey of malware detection approaches using data mining techniques

Abstract: Data mining techniques have been concentrated for malware detection in the recent decade. The battle between security analyzers and malware scholars is everlasting as innovation grows. The proposed methodologies are not adequate while evolutionary and complex nature of malware is changing quickly and therefore turn out to be harder to recognize. This paper presents a systematic and detailed survey of the malware detection mechanisms using data mining techniques. In addition, it classifies the malware detection approaches in two main categories including signature-based methods and behavior-based detection. The main contributions of this paper are: (1) providing a summary of the current challenges related to the malware detection approaches in data mining, (2) presenting a systematic and categorized overview of the current approaches to machine learning mechanisms, (3) exploring the structure of the significant methods in the malware detection approach and (4) discussing the important factors of classification malware approaches in the data mining. The detection approaches have been compared with each other according to their importance factors. The advantages and disadvantages of them were discussed in terms of data mining models, their evaluation method and their proficiency. This survey helps researchers to have a general comprehension of the malware detection field and for specialists to do consequent examinations.

A review of medical image data augmentation techniques for deep learning applications.

Abstract: Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state-of-the-art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.