Mohammad Fraiwan

Classification of Sleep Stages Using Multi-wavelet Time Frequency Entropy and LDA

BACKGROUND The process of automatic sleep stage scoring consists of two major parts: feature extraction and classification. Features are normally extracted from the polysomnographic recordings, mainly electroencephalograph (EEG) signals. The EEG is considered a non-stationary signal which increases the complexity of the detection of different waves in it. OBJECTIVES This work presents a new technique for automatic sleep stage scoring based on employing continuous wavelet transform (CWT) and linear discriminant analysis (LDA) using different mother wavelets to detect different waves embedded in the EEG signal. METHODS The use of different mother wavelets increases the ability to detect waves in the EEG signal. The extracted features were formed based on CWT time frequency entropy using three mother wavelets, and the classification was performed using the linear discriminant analysis. Thirty-two data sets from the MIT-BIH database were used to evaluate the performance of the proposed method. RESULTS Features of a single EEG signal were extracted successfully based on the time frequency entropy using the continuous wavelet transform with three mother wavelets. The proposed method has shown to outperform the classification based on a CWT using a single mother wavelet. The accuracy was found to be 0.84, while the kappa coefficient was 0.78. CONCLUSIONS This work has shown that wavelet time frequency entropy provides a powerful tool for feature extraction for the non-stationary EEG signal; the accuracy of the classification procedure improved when using multiple wavelets compared to the use of single wavelet time frequency entropy.

Analysis and Identification of Malicious JavaScript Code

ABSTRACT Malicious JavaScript code has been actively and recently utilized as a vehicle for Web-based security attacks. By exploiting vulnerabilities such as cross-site scripting (XSS), attackers are able to spread worms, conduct Phishing attacks, and do Web page redirection to “typically” porn Web sites. These attacks can be preemptively prevented if the malicious code is detected before executing. Based on the fact that a malignant code will exhibit certain features, we propose a novel classification-based detection approach that will identify Web pages containing infected code. Using datasets of trusted and malicious Web sites, we analyze the behavior and properties of JavaScript code to point out its key features. These features form the basis of our identification system and are used to properly train the various classifiers on malicious and benign data. Performance evaluation results show that our approach achieves a 95% or higher detection accuracy, with very small (less than 3%) false positive and false negative ratios. Our solution surpasses the performance of the comparable literature.

On Using Classification Techniques for Corpus Reduction in Arabic Text-To-Speech Systems

Abstract Text-to-speech tools are gaining an increasing momentum with the pervasiveness of today’s computer applications. These tools are typically implemented using diphones and syllables, with a body of knowledge (i.e., corpus) comprised of pre-recorded sounds. Although pre-recording achieves high intelligibility and a more natural experience, it requires a large memory size to store the sounds, which in turn leads to slowness in the conversion process. In this paper, we tackle the problem of reducing the size of memory required to store the pre-recordings of an Arabic text-to-speech system. We take a different approach and explore building a classification model based on predefined types of news documents, and propose a scheme for constructing an Arabic corpus based on this model. Performance evaluation results show that, using our scheme, a 29% reduction of the database size will only incur a 0.57% loss of recognition correctness, while a massive 89% reduction will lower the correctness by a mere 1.29%.

Empowering PlanetLab: A Method for TCP Evaluation Over the Planetary-scale Testbed

PlanetLab, the planetary-scale overlay network, has become the de facto platform for conducting network experiments under real-life realistic conditions, scale, and geographic distribution. Many tools have been developed to manage the PlanetLab resources. However, they do not provide extra experimental capabilities to this network. Currently, PlanetLab only allows experiments at the application level, as lower levels (e.g., TCP level) are shared among all users and modifications to, for example, the TCP stack will affect all users’ experiments. In this paper, we present the design of a methodology that allows researchers to implement their new TCP stack, transport algorithms, and protocols on top of PlanetLab. The approach works much like a plug-in that interacts with the PlanetLab nodes without interfering with the operating system or any other running processes. We present a research case study as an example that can make use of such a method to allow for evaluation over PlanetLab. The case study is about testing a new TCP stack, and comparing it to an existing TCP implementation under specific deployment scenarios.

Exam scheduling: A case study

Academic institutions are moving toward automated management of the educational process. One aspect of this process is the exam scheduling. The large number of students, classes, professors, and venues renders the manual scheduling process tedious and useless. In this paper, we describe the efforts of the Arab East College for High Education in Saudi Arabia in scheduling exams in the least number of conflicts, among other constraints. We give the details for a two-stage solution approach; the first stage is a greedy algorithm and the second one is a genetic algorithm. The two algorithms work in tandem to generate the best exam timetable. Automation of this process has greatly reduced the number of conflicts, exam days, and the required venues.

Analysis and classification of Arabic crowd-sourced news reports: A case study of the Syrian crisis

The prevalence of social media, in the whole world and the Arab region in particular, has fueled the active engagement and participation of large swaths of the Arabic society in current events. Social media has been used to rally public opinion, increase awareness, spread information/misinformation, and organize large events. Data analysis is necessary to drive decision making, advertisement, political campaigning, counter-intelligence, etc. The sheer volume of data and number of users calls for automated methods for analysis and classification of Arabic text. In this paper, the problem of analysis and classification of Arabic news reports was studied. Innovative methods, based on lexical analysis and machine learning, were employed to tame the complexity of the Arabic language. Different classification algorithms were compared and the classification accuracy results are promising. This research presents seminal steps toward specialized analysis of Arabic crowd-sourced data and social media.

A gaming approach to behavioural rehabilitation: concept exploration

The awareness of behavioural disabilities like autism has increased dramatically in the past few years, revealing staggering numbers of affected individuals, mainly children. The pervasiveness of mobile and gaming technologies presents an excellent opportunity to educate children with behavioural difficulties. In this paper, gaming technology was used to present real-life scenarios to children, helping them to behave under those circumstances. Various scenes unconsciously train the children to act in the right manner, which aids their logic, behaviour, and self-confidence. The synergy of advanced fun 2D gaming and animation, attractive graphics, and professional therapy guidance provides an effective and strong learning experience.

A Kinect-based system for Arabic sign language to speech translation

Speech-based smart systems have come to play an increasingly diverse role in todays pervasive technology. Moreover, it is quite common to experience all kinds of innovations on daily basis, ranging from retina identifiers at banks to electronic fingerprints readers. Such proliferation presents an opportunity and a challenge to integrate speech and hearing-challenged individuals into society by designing sign language to speech translation systems. In this paper, we tackle the problem of Arabic Sign Language to Speech transformation. We make use of commercial off-the-shelf components to capture the Sign Language gestures. Graphical gestures were transformed into Arabic text, which in turn can be translated into any spoken language. Web services were used to generate the spoken sounds. The majority of this paper is dedicated to explaining hand and fingers identification. In addition, motion recognition is also detailed. The accuracy in identifying the implemented characters was shown to exceed 80%.

Obstacle avoidance and navigation in robotic systems: A land and aerial robots study

Autonomous airborne systems have generated a lot of interest in civilian and military applications. The operation of such systems involves routing and navigation toward targets and obstacle avoidance. In this paper, these problems were tackled and solutions were applied to land-based robots as well as a quad-rotor aerial system. The quad-rotor flight path navigation and routing was programmed based on GPS and on-board measurement data. Obstacle avoidance was implemented based on an algorithm that relies on the idea of Virtual Potential field. Kalman filters were implemented to improve the accuracy of the measured data. While 3D visualization was used to visually identify obstacles. In the case of in-building reconnaissance, where GPS signals are very weak and largely useless, we rely on laser sensors and data aggregation from proximity feeds to identify obstacles and the shape of the surrounding environment.

Converting web applications into standard XML web services: Two case studies

Internet contains a tremendous amount of valuable web applications that can be used in many systems. To use this kind of applications with other systems, the interaction needs to be in a standard structured format such as XML web service. In this paper, we present a method to convert the current web applications into standard XML web services. The system design and implementation are presented. We applied the proposed system on two test cases: Jordan University of Science and Technology (JUST) course online schedule and Wiley product search engine.