Skip to main content

Hamza Aldabbas

Al-Balqa Applied University, Computer Science, Faculty Member

Followers

759

Following

107

Co-authors

3

Public Views

PhD Degree in Computer Science and Software Engineering, De Montfort University, Leicester-United Kingdom (2009-2012).Previously M.Sc, Computer Science (2009) and B.Sc Computer Information Systems (2006) from Al-Balqa Applied University, Al-Salt, Hashemite Kingdom of Jordan.I am currently an Associate Professor at Al-Balqa Applied University /Prince Abdullah bin Ghazi Faculty of Information and Communication Technology-Jordan (3/2/2013— until now). Previously a lecturer at De Montfort University/UK (2010-2012) with responsibility for teaching and project supervision at B.Sc
Supervisors: Dr. Helge Janicke

less

InterestsView All (6)

Uploads

Papers by Hamza Aldabbas

Cloud-based email phishing attack using machine and deep learning algorithm

Complex & Intelligent Systems

Cloud computing refers to the on-demand availability of personal computer system assets, specific... more Cloud computing refers to the on-demand availability of personal computer system assets, specifically data storage and processing power, without the client's input. Emails are commonly used to send and receive data for individuals or groups. Financial data, credit reports, and other sensitive data are often sent via the Internet. Phishing is a fraudster's technique used to get sensitive data from users by seeming to come from trusted sources. The sender can persuade you to give secret data by misdirecting in a phished email. The main problem is email phishing attacks while sending and receiving the email. The attacker sends spam data using email and receives your data when you open and read the email. In recent years, it has been a big problem for everyone. This paper uses different legitimate and phishing data sizes, detects new emails, and uses different features and algorithms for classification. A modified dataset is created after measuring the existing approaches. We cr...

Machine Learning Techniques for Spam Detection in Email and IoT Platforms: Analysis and Research Challenges

Security and Communication Networks

Nowaday, emails are used in almost every field, from business to education. Emails have two subca... more Nowaday, emails are used in almost every field, from business to education. Emails have two subcategories, i.e., ham and spam. Email spam, also called junk emails or unwanted emails, is a type of email that can be used to harm any user by wasting his/her time, computing resources, and stealing valuable information. The ratio of spam emails is increasing rapidly day by day. Spam detection and filtration are significant and enormous problems for email and IoT service providers nowadays. Among all the techniques developed for detecting and preventing spam, filtering email is one of the most essential and prominent approaches. Several machine learning and deep learning techniques have been used for this purpose, i.e., Naïve Bayes, decision trees, neural networks, and random forest. This paper surveys the machine learning techniques used for spam filtering techniques used in email and IoT platforms by classifying them into suitable categories. A comprehensive comparison of these techniqu...

Lightweight Challenge-Response Authentication in SDN-Based UAVs Using Elliptic Curve Cryptography

Electronics, Mar 25, 2022

Machine learning for Autopsy reports Forensic using Text Classification Techniques

2022 2nd International Conference on Computing and Information Technology (ICCIT)

A forensic autopsy is a surgical process in which experts collect a deceased body's internal ... more A forensic autopsy is a surgical process in which experts collect a deceased body's internal and external information. These death certificates are the source of timely warnings of an increase in disease activity. It's only helpful if accurate and quantitative data is available. Therefore, the Classification of plain text medical autopsy reports reduces the time consumption and irregularities. The motive is to design an automatic text classification system that classifies plain text autopsy reports. Therefore, a methodology proposes using different Automatic Text Classification Techniques (ATC). This technique has embedded Feature Extraction, Feature Representation, and Feature Reduction techniques. These techniques use for the construction of classification models that classify the text of autopsy reports. Data sets collected from these types will be helpful in future experiments. Finally, the performance of the classifier measures by using different Evaluation parameters. These Evaluation Measures are Precision, Recall, Accuracy, and F-measure.

Radio Network Forensic with mmWave Using the Dominant Path Algorithm

Secur. Commun. Networks, 2022

For the last two decades, cybercrimes are growing on a daily basis. To track down cybercrimes and... more For the last two decades, cybercrimes are growing on a daily basis. To track down cybercrimes and radio network crimes, digital forensic for radio networks provides foundations. The data transfer rate for the next-generation wireless networks would be much greater than today’s network in the coming years. The fifth-generation wireless systems are considering bands beyond 6 GHz. The network design of the next-generation wireless systems depends on propagation characteristics, frequency reuse, and bandwidth variation. This article declares the channel’s propagation characteristics of both line of sight (LoS) and non-LOS (NLoS) to construct and detect the path of rays coming from anomalies. The simulations were carried out to investigate the diffraction loss (DL) and frequency drop (FD). Indoor and outdoor measurements were taken with the omnidirectional circular dipole antenna with a transmitting frequency of 28 GHz and 60 GHz to compare the two bands of the 5th generation. Millimeter...

A machine learning approach for non-invasive fall detection using Kinect

Multimedia Tools and Applications, 2022

Securing data dissemination in vehicular ad hoc networks

Vehicular ad hoc networks (VANETs) are a subclass of mobile ad hoc networks (MANETs) in which the... more Vehicular ad hoc networks (VANETs) are a subclass of mobile ad hoc networks (MANETs) in which the mobile nodes are vehicles; these vehicles are autonomous systems connected by wireless communication on a peer-to-peer basis. They are self-organized, self-configured and self-controlled infrastructure-less networks. This kind of network has the advantage of being able to be set-up and deployed anywhere and anytime because it has no infrastructure set-up and no central administration. Distributing information between these vehicles over long ranges in such networks, however, is a very challenging task, since sharing information always has a risk attached to it especially when the information is confidential. The disclosure of such information to anyone else other than the intended parties could be extremely damaging, particularly in military applications where controlling the dissemination of messages is essential. This thesis therefore provides a review of the issue of security in VANE...

Facial Emotion Recognition Using Transfer Learning

2020 International Conference on Computing and Information Technology (ICCIT-1441), 2020

Facial Emotion Recognition is considered very significant for Human Computer Interaction (HCI) an... more Facial Emotion Recognition is considered very significant for Human Computer Interaction (HCI) and they play a vital role in everyday human life. In recent years Convolutional Neural Network (CNNs) has become very popular among researcher for image analysis, because CNNs have generated remarkable results. However, CNNs needs a lot of data to train from scratch. This problem has been addressed by several researchers who have trained CNNs with millions of images, this training knowledge can also be used in a different task which is known as Transfer Learning. AlexNet is one of the best pre-trained CNNs. Our work reflects a brief comparison between modern pre-trained CNNs and using transfer learning with classification approach like Support Vector Machine (SVM), generally known as hybrid classifier. The testing has been done on two very popular expression database Cohn-Kanade+ (CK+) database and Natural Visible and Infrared Expression (NVIE) database. Results clearly depicts that pre-trained CNNs produces better result than handcrafted approaches.

A Two-Level Authentication Protocol for Vehicular Adhoc Networks

The technology growth nowadays has made its way into the world of transportation by establishing ... more The technology growth nowadays has made its way into the world of transportation by establishing smart vehicles and smarter vehicular transportation named Vehicular Ad-hoc networks (VANET). VANET gains its fame day by day by the way how it facilitates the efficient and safe transportation to the voyagers. However, the prime requirement of VANET is authentication. The main aim of the proposed work is to develop a practical and efficient pseudonymous authentication protocol which augments the conditional privacy preservation. Two-Way authentication is provided using local alias and global alias name. The alias name has offered to all the vehicles who register with the certification authority. The simulation result shows that the Two-Way protocol provides authentication with optimal packet delivery ratio (PDR), end-to-end delay and propagation delay.

A study on modeling vehicles mobility with MLC for enhancing vehicle-to-vehicle connectivity in VANET

Journal of Ambient Intelligence and Humanized Computing, 2020

Smart City Based Autonomous Water Quality Monitoring System Using WSN

Wireless Personal Communications, 2020

Deep Learning-Based Sentimental Analysis for Large-Scale Imbalanced Twitter Data

Future Internet, 2019

Emotions detection in social media is very effective to measure the mood of people about a specif... more Emotions detection in social media is very effective to measure the mood of people about a specific topic, news, or product. It has a wide range of applications, including identifying psychological conditions such as anxiety or depression in users. However, it is a challenging task to distinguish useful emotions’ features from a large corpus of text because emotions are subjective, with limited fuzzy boundaries that may be expressed in different terminologies and perceptions. To tackle this issue, this paper presents a hybrid approach of deep learning based on TensorFlow with Keras for emotions detection on a large scale of imbalanced tweets’ data. First, preprocessing steps are used to get useful features from raw tweets without noisy data. Second, the entropy weighting method is used to compute the importance of each feature. Third, class balancer is applied to balance each class. Fourth, Principal Component Analysis (PCA) is applied to transform high correlated features into norm...

A Framework for Integrating Usability Practices into Small-Sized Software Development Organizations

International Journal of Software Engineering & Applications, 2016

Preferences of Saudi Users on Arabic Website Usability

International journal of Web & Semantic Technology, 2016

Evolution of Software Reliability Growth Models: A Comparison of Auto-Regression and Genetic Programming Models

International Journal of Computer Applications, 2015

Evaluating the Adoption and Acceptance of e-Government in the Developing Countries: A Case Study of Jordan

Citizens of developing countries have been observed to have a low level of trust in their e Gover... more Citizens of developing countries have been observed to have a low level of trust in their e Government services, because of the limited user involvement in the entire development life cycle of the e Government portal. Hence, we are looking for means to improve this emerging concern with a special focus on the Jordanian Government Portal (JGP). This paper aims to contribute to the advancement of e Government services provided in developing countries. We proposed a conceptual model on eGovernment adoption and acceptance by integrating and augmenting key notions from the Technology Acceptance Model (TAM3), Information System Success Model (ISSM) and other relevant literature in the field of Management Information Systems (MIS). Based on the model, we have designed empirical studies to investigate how citizens perceive the quality of the JGP, which was used as a case study. A questionnaire survey has been conducted to identify important factors influencing the adoption and acceptance of...

An Overview of an Advanced Vehicle Security System

In the past few decades wireless networks have become increasingly popular, due to the wide avail... more In the past few decades wireless networks have become increasingly popular, due to the wide availability and rapid introduction of wireless transceivers into a variety of computing devices such as PDAs, laptop and desktop computers. Global Positioning System (GPS) is used to determine position and speed of objects by using the satellite technology. Furthermore, Radio Frequency is another technology which is used to determine the objects' locations. In this paper we have presented an overview for using the previous technologies to track a stolen vehicle by using a system that is resulted from mixing all of those technologies in addition to proposed an enhancement idea that could help the resulted system to determine the cars' thieves by sending their photos to the security agency base to be recognized.

The Use of E-government Among Citizens

Challenges of Computer Crime Investigation In North Africa's Countries

Computer crime is the use of information technology in any suspicious criminal activities. Recent... more Computer crime is the use of information technology in any suspicious criminal activities. Recently, our life becomes increasingly depending on modern information technology; however, it becomes very important to improve the computer crime investigation procedure especially in cases of processing very important and sensitive information such as government and military intelligence, banking information or personal private information. Cybercrime investigation helps detecting unauthorized access to any digital source information with the intent of modifying, destroying or stealing that digital data or information. Such suspicious actions can cause financial damages or important information loss; moreover, it might distribute or destroy high secret and private or confidential information. Therefore, this paper focuses mainly on highlighting the main challenges of the North Africa's countries (Libya, Tunis, Algeria, and Morocco) in computer crime investigation system by taking a loo...

Mobile Grid System: Policy and Privacy

Cloud-based email phishing attack using machine and deep learning algorithm

Complex & Intelligent Systems

Cloud computing refers to the on-demand availability of personal computer system assets, specific... more Cloud computing refers to the on-demand availability of personal computer system assets, specifically data storage and processing power, without the client's input. Emails are commonly used to send and receive data for individuals or groups. Financial data, credit reports, and other sensitive data are often sent via the Internet. Phishing is a fraudster's technique used to get sensitive data from users by seeming to come from trusted sources. The sender can persuade you to give secret data by misdirecting in a phished email. The main problem is email phishing attacks while sending and receiving the email. The attacker sends spam data using email and receives your data when you open and read the email. In recent years, it has been a big problem for everyone. This paper uses different legitimate and phishing data sizes, detects new emails, and uses different features and algorithms for classification. A modified dataset is created after measuring the existing approaches. We cr...

Machine Learning Techniques for Spam Detection in Email and IoT Platforms: Analysis and Research Challenges

Security and Communication Networks

Nowaday, emails are used in almost every field, from business to education. Emails have two subca... more Nowaday, emails are used in almost every field, from business to education. Emails have two subcategories, i.e., ham and spam. Email spam, also called junk emails or unwanted emails, is a type of email that can be used to harm any user by wasting his/her time, computing resources, and stealing valuable information. The ratio of spam emails is increasing rapidly day by day. Spam detection and filtration are significant and enormous problems for email and IoT service providers nowadays. Among all the techniques developed for detecting and preventing spam, filtering email is one of the most essential and prominent approaches. Several machine learning and deep learning techniques have been used for this purpose, i.e., Naïve Bayes, decision trees, neural networks, and random forest. This paper surveys the machine learning techniques used for spam filtering techniques used in email and IoT platforms by classifying them into suitable categories. A comprehensive comparison of these techniqu...

Lightweight Challenge-Response Authentication in SDN-Based UAVs Using Elliptic Curve Cryptography

Electronics, Mar 25, 2022

Machine learning for Autopsy reports Forensic using Text Classification Techniques

2022 2nd International Conference on Computing and Information Technology (ICCIT)

A forensic autopsy is a surgical process in which experts collect a deceased body's internal ... more A forensic autopsy is a surgical process in which experts collect a deceased body's internal and external information. These death certificates are the source of timely warnings of an increase in disease activity. It's only helpful if accurate and quantitative data is available. Therefore, the Classification of plain text medical autopsy reports reduces the time consumption and irregularities. The motive is to design an automatic text classification system that classifies plain text autopsy reports. Therefore, a methodology proposes using different Automatic Text Classification Techniques (ATC). This technique has embedded Feature Extraction, Feature Representation, and Feature Reduction techniques. These techniques use for the construction of classification models that classify the text of autopsy reports. Data sets collected from these types will be helpful in future experiments. Finally, the performance of the classifier measures by using different Evaluation parameters. These Evaluation Measures are Precision, Recall, Accuracy, and F-measure.

Radio Network Forensic with mmWave Using the Dominant Path Algorithm

Secur. Commun. Networks, 2022

For the last two decades, cybercrimes are growing on a daily basis. To track down cybercrimes and... more For the last two decades, cybercrimes are growing on a daily basis. To track down cybercrimes and radio network crimes, digital forensic for radio networks provides foundations. The data transfer rate for the next-generation wireless networks would be much greater than today’s network in the coming years. The fifth-generation wireless systems are considering bands beyond 6 GHz. The network design of the next-generation wireless systems depends on propagation characteristics, frequency reuse, and bandwidth variation. This article declares the channel’s propagation characteristics of both line of sight (LoS) and non-LOS (NLoS) to construct and detect the path of rays coming from anomalies. The simulations were carried out to investigate the diffraction loss (DL) and frequency drop (FD). Indoor and outdoor measurements were taken with the omnidirectional circular dipole antenna with a transmitting frequency of 28 GHz and 60 GHz to compare the two bands of the 5th generation. Millimeter...

A machine learning approach for non-invasive fall detection using Kinect

Multimedia Tools and Applications, 2022

Securing data dissemination in vehicular ad hoc networks

Vehicular ad hoc networks (VANETs) are a subclass of mobile ad hoc networks (MANETs) in which the... more Vehicular ad hoc networks (VANETs) are a subclass of mobile ad hoc networks (MANETs) in which the mobile nodes are vehicles; these vehicles are autonomous systems connected by wireless communication on a peer-to-peer basis. They are self-organized, self-configured and self-controlled infrastructure-less networks. This kind of network has the advantage of being able to be set-up and deployed anywhere and anytime because it has no infrastructure set-up and no central administration. Distributing information between these vehicles over long ranges in such networks, however, is a very challenging task, since sharing information always has a risk attached to it especially when the information is confidential. The disclosure of such information to anyone else other than the intended parties could be extremely damaging, particularly in military applications where controlling the dissemination of messages is essential. This thesis therefore provides a review of the issue of security in VANE...

Facial Emotion Recognition Using Transfer Learning

2020 International Conference on Computing and Information Technology (ICCIT-1441), 2020

Facial Emotion Recognition is considered very significant for Human Computer Interaction (HCI) an... more Facial Emotion Recognition is considered very significant for Human Computer Interaction (HCI) and they play a vital role in everyday human life. In recent years Convolutional Neural Network (CNNs) has become very popular among researcher for image analysis, because CNNs have generated remarkable results. However, CNNs needs a lot of data to train from scratch. This problem has been addressed by several researchers who have trained CNNs with millions of images, this training knowledge can also be used in a different task which is known as Transfer Learning. AlexNet is one of the best pre-trained CNNs. Our work reflects a brief comparison between modern pre-trained CNNs and using transfer learning with classification approach like Support Vector Machine (SVM), generally known as hybrid classifier. The testing has been done on two very popular expression database Cohn-Kanade+ (CK+) database and Natural Visible and Infrared Expression (NVIE) database. Results clearly depicts that pre-trained CNNs produces better result than handcrafted approaches.

A Two-Level Authentication Protocol for Vehicular Adhoc Networks

The technology growth nowadays has made its way into the world of transportation by establishing ... more The technology growth nowadays has made its way into the world of transportation by establishing smart vehicles and smarter vehicular transportation named Vehicular Ad-hoc networks (VANET). VANET gains its fame day by day by the way how it facilitates the efficient and safe transportation to the voyagers. However, the prime requirement of VANET is authentication. The main aim of the proposed work is to develop a practical and efficient pseudonymous authentication protocol which augments the conditional privacy preservation. Two-Way authentication is provided using local alias and global alias name. The alias name has offered to all the vehicles who register with the certification authority. The simulation result shows that the Two-Way protocol provides authentication with optimal packet delivery ratio (PDR), end-to-end delay and propagation delay.

A study on modeling vehicles mobility with MLC for enhancing vehicle-to-vehicle connectivity in VANET

Journal of Ambient Intelligence and Humanized Computing, 2020

Smart City Based Autonomous Water Quality Monitoring System Using WSN

Wireless Personal Communications, 2020

Deep Learning-Based Sentimental Analysis for Large-Scale Imbalanced Twitter Data

Future Internet, 2019

Emotions detection in social media is very effective to measure the mood of people about a specif... more Emotions detection in social media is very effective to measure the mood of people about a specific topic, news, or product. It has a wide range of applications, including identifying psychological conditions such as anxiety or depression in users. However, it is a challenging task to distinguish useful emotions’ features from a large corpus of text because emotions are subjective, with limited fuzzy boundaries that may be expressed in different terminologies and perceptions. To tackle this issue, this paper presents a hybrid approach of deep learning based on TensorFlow with Keras for emotions detection on a large scale of imbalanced tweets’ data. First, preprocessing steps are used to get useful features from raw tweets without noisy data. Second, the entropy weighting method is used to compute the importance of each feature. Third, class balancer is applied to balance each class. Fourth, Principal Component Analysis (PCA) is applied to transform high correlated features into norm...

A Framework for Integrating Usability Practices into Small-Sized Software Development Organizations

International Journal of Software Engineering & Applications, 2016

Preferences of Saudi Users on Arabic Website Usability

International journal of Web & Semantic Technology, 2016

Evolution of Software Reliability Growth Models: A Comparison of Auto-Regression and Genetic Programming Models

International Journal of Computer Applications, 2015

Evaluating the Adoption and Acceptance of e-Government in the Developing Countries: A Case Study of Jordan

Citizens of developing countries have been observed to have a low level of trust in their e Gover... more Citizens of developing countries have been observed to have a low level of trust in their e Government services, because of the limited user involvement in the entire development life cycle of the e Government portal. Hence, we are looking for means to improve this emerging concern with a special focus on the Jordanian Government Portal (JGP). This paper aims to contribute to the advancement of e Government services provided in developing countries. We proposed a conceptual model on eGovernment adoption and acceptance by integrating and augmenting key notions from the Technology Acceptance Model (TAM3), Information System Success Model (ISSM) and other relevant literature in the field of Management Information Systems (MIS). Based on the model, we have designed empirical studies to investigate how citizens perceive the quality of the JGP, which was used as a case study. A questionnaire survey has been conducted to identify important factors influencing the adoption and acceptance of...

An Overview of an Advanced Vehicle Security System

In the past few decades wireless networks have become increasingly popular, due to the wide avail... more In the past few decades wireless networks have become increasingly popular, due to the wide availability and rapid introduction of wireless transceivers into a variety of computing devices such as PDAs, laptop and desktop computers. Global Positioning System (GPS) is used to determine position and speed of objects by using the satellite technology. Furthermore, Radio Frequency is another technology which is used to determine the objects' locations. In this paper we have presented an overview for using the previous technologies to track a stolen vehicle by using a system that is resulted from mixing all of those technologies in addition to proposed an enhancement idea that could help the resulted system to determine the cars' thieves by sending their photos to the security agency base to be recognized.

The Use of E-government Among Citizens

Challenges of Computer Crime Investigation In North Africa's Countries

Computer crime is the use of information technology in any suspicious criminal activities. Recent... more Computer crime is the use of information technology in any suspicious criminal activities. Recently, our life becomes increasingly depending on modern information technology; however, it becomes very important to improve the computer crime investigation procedure especially in cases of processing very important and sensitive information such as government and military intelligence, banking information or personal private information. Cybercrime investigation helps detecting unauthorized access to any digital source information with the intent of modifying, destroying or stealing that digital data or information. Such suspicious actions can cause financial damages or important information loss; moreover, it might distribute or destroy high secret and private or confidential information. Therefore, this paper focuses mainly on highlighting the main challenges of the North Africa's countries (Libya, Tunis, Algeria, and Morocco) in computer crime investigation system by taking a loo...

Mobile Grid System: Policy and Privacy