MUHAMMAD NOOR UL ISLAM - Academia.edu (original) (raw)

Uploads

Papers by MUHAMMAD NOOR UL ISLAM

Research paper thumbnail of A Privacy Preserved, Trust Relationship (PTR) Model for Internet of Vehicles

Electronics

The Internet of vehicles (IoV) depicts a reality where ordinary things are connected to vehicular... more The Internet of vehicles (IoV) depicts a reality where ordinary things are connected to vehicular ad-hoc networks (VANETs), allowing them to transmit and collaborate. By placing these regular objects in VANETs and making them available at any time, this network and data sharing may raise real privacy and security issues. Thus, group-based communication is mostly preferred in the literature. However, in heavy network scenarios, cluster-based communication mostly leads to additional overload in the form of the group leader that causes delay and disrupts the performance of a network. Due to the interaction of VANETs with applications that are not stable for life, privacy and security mechanism for detecting many malicious nodes is in great demand. Therefore, a multi-phantom node selection has been proposed in this paper to select trustworthy, normal, and malicious nodes. The multi-phantom node scheme is proposed to reduce the phantom node load, where the multi-lateral nodes in a cluste...

Research paper thumbnail of Evaluation of Preprocessing Techniques for U-Net Based Automated Liver Segmentation

2021 International Conference on Artificial Intelligence (ICAI), 2021

To extract liver from medical images is a challenging task due to similar intensity values of liv... more To extract liver from medical images is a challenging task due to similar intensity values of liver with adjacent organs, various contrast levels, various noise associated with medical images and irregular shape of liver. To address these issues, it is important to preprocess the medical images, i.e., computerized tomography (CT) and magnetic resonance imaging (MRI) data prior to liver analysis and quantification. This paper investigates the impact of permutation of various preprocessing techniques for CT images, on the automated liver segmentation using deep learning, i.e., U-Net architecture. The study focuses on Hounsfield Unit (HU) windowing, contrast limited adaptive histogram equalization (CLAHE), z-score normalization, median filtering and Block-Matching and 3D (BM3D) filtering. The segmented results show that combination of three techniques; HU-windowing, median filtering and z-score normalization achieve optimal performance with Dice coefficient of 96.93%, 90.77% and 90.84% for training, validation and testing respectively.

Research paper thumbnail of Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network

Sensors (Basel, Switzerland), 2021

Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the... more Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. Method: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim’s data...

Research paper thumbnail of A Privacy Preserved, Trust Relationship (PTR) Model for Internet of Vehicles

Electronics

The Internet of vehicles (IoV) depicts a reality where ordinary things are connected to vehicular... more The Internet of vehicles (IoV) depicts a reality where ordinary things are connected to vehicular ad-hoc networks (VANETs), allowing them to transmit and collaborate. By placing these regular objects in VANETs and making them available at any time, this network and data sharing may raise real privacy and security issues. Thus, group-based communication is mostly preferred in the literature. However, in heavy network scenarios, cluster-based communication mostly leads to additional overload in the form of the group leader that causes delay and disrupts the performance of a network. Due to the interaction of VANETs with applications that are not stable for life, privacy and security mechanism for detecting many malicious nodes is in great demand. Therefore, a multi-phantom node selection has been proposed in this paper to select trustworthy, normal, and malicious nodes. The multi-phantom node scheme is proposed to reduce the phantom node load, where the multi-lateral nodes in a cluste...

Research paper thumbnail of Evaluation of Preprocessing Techniques for U-Net Based Automated Liver Segmentation

2021 International Conference on Artificial Intelligence (ICAI), 2021

To extract liver from medical images is a challenging task due to similar intensity values of liv... more To extract liver from medical images is a challenging task due to similar intensity values of liver with adjacent organs, various contrast levels, various noise associated with medical images and irregular shape of liver. To address these issues, it is important to preprocess the medical images, i.e., computerized tomography (CT) and magnetic resonance imaging (MRI) data prior to liver analysis and quantification. This paper investigates the impact of permutation of various preprocessing techniques for CT images, on the automated liver segmentation using deep learning, i.e., U-Net architecture. The study focuses on Hounsfield Unit (HU) windowing, contrast limited adaptive histogram equalization (CLAHE), z-score normalization, median filtering and Block-Matching and 3D (BM3D) filtering. The segmented results show that combination of three techniques; HU-windowing, median filtering and z-score normalization achieve optimal performance with Dice coefficient of 96.93%, 90.77% and 90.84% for training, validation and testing respectively.

Research paper thumbnail of Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network

Sensors (Basel, Switzerland), 2021

Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the... more Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. Method: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim’s data...