Hikmat Khan
Rowan University, Electrical and Computer Engineering, Graduate Student
Research Interests:
The ongoing COVID-19 pandemic has already taken millions of lives and damaged economies across the globe. Most COVID-19 deaths and economic losses are reported from densely crowded cities. It is comprehensible that the effective control... more
The ongoing COVID-19 pandemic has already taken millions of lives and damaged economies across the globe. Most COVID-19 deaths and economic losses are reported from densely crowded cities. It is comprehensible that the effective control and prevention of epidemic/pandemic infectious diseases is vital. According to WHO, testing and diagnosis is the best strategy to control pandemics. Scientists worldwide are attempting to develop various innovative and cost-efficient methods to speed up the testing process. This paper comprehensively evaluates the applicability of the recent top ten state-of-the-art Deep Convolutional Neural Networks (CNNs) for automatically detecting COVID-19 infection using chest X-ray images. Moreover, it provides a comparative analysis of these models in terms of accuracy. This study identifies the effective methodologies to control and prevent infectious respiratory diseases. Our trained models have demonstrated outstanding results in classifying the COVID-19 in...
Research Interests:
Brain tumor segmentation plays an important role in clinical diagnosis for neurologists. Different imaging modalities have been used to diagnose and segment brain tumor. Among all modalities, MRI is preferred because of its non-invasive... more
Brain tumor segmentation plays an important role in clinical diagnosis for neurologists. Different imaging modalities have been used to diagnose and segment brain tumor. Among all modalities, MRI is preferred because of its non-invasive nature and better visualization of internal details of the brain. However, MRI also comes with certain challenges like random noise, various intensity levels, and in-homogeneity that makes detection and segmentation a difficult task. Manual segmentation is extremely laborious and time consuming for the physicians. Manual segmentation is also highly dependent on the physician’s domain knowledge and practical experience. Also, the physician may not be able to see details at the pixel level and may only notice the tumor if it is more prominent and obvious. Therefore, there is a need for brain tumor segmentation techniques that play major role in perfect visualization to assist the physician in identifying different tumor regions. In this paper, we prese...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
We propose ‘VDroid’ a lightweight virtualization architecture based on operating system level virtualization technique for a smartphone. We modify Condroid architecture by addition of a system service called KSMManagerService to the host... more
We propose ‘VDroid’ a lightweight virtualization architecture based on operating system level virtualization technique for a smartphone. We modify Condroid architecture by addition of a system service called KSMManagerService to the host android framework and KSM daemon to kernel. We define the workflow, running criteria and detail integration of both KSMManagerService and KSM daemon. The results show improved memory usage when compared with Condroid and Cell.