A Knowledge-based Expert System for Supporting Security in Software Engineering Projects
Authors : Ahmad Azzazi,Mohammad Shkoukani
Abstract : Building secure software systems requires the intersection between two engineering disciplines, software engineering and security engineering. There is a lack of a defined security mechanism for each of the software development phases, which affects the quality of the software system intensively. In this paper, the authors are proposing a framework to consider the security aspects in all the phases of the software development process from the requirements until the deployment of the software product, with three additional phases that are important to automatically produce a secure system. The framework is developed after analyzing the existing models for secure system development. The key elements of the framework are the addition of the phases like physical, training, and auditing, where they improve the level of security in software engineering projects. The authors found so a solution for the replacement of the knowledge of the security engineer through the construction of an intelligent knowledge-based system, which provides the software developer with the security rules needed in each phase of the software development lifecycle and it improves the awareness of the software developer about the security-related issues in each phase of the software development lifecycle. The framework and the expert system are tested on a variety of software projects, where a significant improvement of security in each phase of the software development process is achieved.
Keywords : Knowledge-based systems; security engineering; software development process; expert systems
Visit
Comparison of Multiple Machine Learning Algorithms for Urban Air Quality Forecasting
Authors :
Abstract : Environmental air pollution has become one of the major threats to human lives nowadays in developed and developing countries. Due to its importance, there exist various air pollution forecasting models, however, machine learning models proved one of the most efficient methods for prediction. In this paper, we assessed the ability of machine learning techniques to forecast NO2, SO2, and PM10 in Amman, Jordan. We compared multiple machine learning methods like artificial neural networks, support vector regression, decision tree regression, and extreme gradient boosting. We also investigated the effect of the pollution station and the meteorological station distance on the prediction result as well as explored the most relevant seasonal variables and the most important minimal set of features required for prediction to improve the prediction time. The experiments showed promising results for predicting air pollution in Amman with artificial neural network outperforming the other algorithms and scoring RMSE of 0.949 ppb, 0.451 ppb, and 5.570 µg/m3 for NO2, SO2, and PM10 respectively. Our results indicated that when the meteorological variables were obtained from the same pollution station the results were better. We were also able to reduce the time by reducing the set of variables required for prediction from 11 down to 3 and achieved major time improvement by about 80% for NO2, 92% for SO2, and 90% for PM10. The most important variables required for predicting NO2 were the previous day values of NO2, humidity and wind direction. While for SO2 they were the previous day values of SO2, temperature, and wind direction values of the previous day. Finally, for PM10 they were the previous day values of PM10, humidity, and day of the year.
Keywords :
Visit
Graph Database Security: Blockchain Solution and Open Challenges
Authors : Mohammad Shkoukani and Ahmad Altamimi
Abstract : NoSQL graph-oriented databases are developed to handle a massive amount of data; some of this data is sensitive and need to be protected. However, graph databases were initially designed by not considering security as an important feature. Therefore, they provide poor privacy and security protection, which can raise security breaches. In this paper, we survey the major security issues for graph databases and outline open challenges. The popular security issues were reviewed and categorized along with the existing attacks, threats, and state-of-the-art solutions. Furthermore, we gap the graph security requirements by proposing a security model based on Blockchain technology. The goal of the model is to support the development of graph-based applications that preserve the security and the integrity of the stored data. The model can be adapted as a stand-alone system or equipped to make integration with multiple systems easier. This enables applications to harness secured graph databases for many modern-day use applications and eliminates restrictions imposed by data models and database vendors for better security and privacy. As proof of concept, the proposed model can be implemented using Ethereum, an open-source distributed platform that facilitates the creation of Blockchain and its smart contract/rules. We believe that this research forms a basis for broader future studies of using Blockchain technology to facilitate the development of different applications with perceiving data security.
Keywords :
Visit
Ground-level Ozone Prediction Using Machine Learning Techniques: A Case Study in Amman, Jordan
Authors : Maryam Aljanabi, Mohammad Shkoukani & Mohammad Hijjawi
Abstract : Air pollution is one of the most serious hazards to humans' health nowadays, it is an invisible killer that takes many human lives every year. There are many pollutants existing in the atmosphere today, ozone being one of the most threatening pollutants. It can cause serious health damage such as wheezing, asthma, inflammation, and early mortality rates. Although air pollution could be forecasted using chemical and physical models, machine learning techniques showed promising results in this area, especially artificial neural networks. Despite its importance, there has not been any research on predicting ground-level ozone in Jordan. In this paper, we build a model for predicting ozone concentration for the next day in Amman, Jordan using a mixture of meteorological and seasonal variables of the previous day. We compare a multi-layer perceptron neural network (MLP), support vector regression (SVR), decision tree regression (DTR), and extreme gradient boosting (XGBoost) algorithms. We also explore the effect of applying various smoothing filters on the time-series data such as moving average, Holt-Winters smoothing and Savitzky-Golay filters. We find that MLP outperformed the other algorithms and that using Savitzky-Golay improved the results by 50% for coefficient of determination (R2) and 80% for root mean square error (RMSE) and mean absolute error (MAE). Another point we focus on is the variables required to predict ozone concentration. In order to reduce the time required for prediction, we perform feature selection which greatly reduces the time by 91% as well as shrinking the number of features required for prediction to the previous day values of ozone, humidity, and temperature. The final model scored 98.653% for R2, 1.016 ppb for RMSE and 0.800 ppb for MAE.
Keywords : Ozone prediction, machine learning, neural networks, supervised learning, regression
Visit
An Experimental Study to Evaluate the Integration of Various Security Approaches to Secure Transferable Data
Authors : Mohammad Shkoukani, Ahmad Altamimi and Hazem Qattous
Abstract : This study investigates the relative ability of combining various security techniques to increase the security level of transmitted data without affecting the cover file. The analysis relies on an empirical study that evaluates the capability of integrating three different but related security measures (encryption, stenography, and compression) in a combined manner. These famed security measures are customized in order to provide adequate security to the data before outsourcing it. To ground our conceptual idea, a security framework is implemented and evaluated using several different text and audio wave files of 16 bits per sample. Results show that hiding data using 4 bits does not show any difference between the original and stego file. In addition, the One-Time-Pad algorithm proved that it allows a larger space to be available to hide data rather than using Pohlig-Hellman algorithm.
Keywords :
Visit
Explore the Major Characteristics of Learning Management Systems and their Impact on e-Learning Success
Authors : Mohammad Shkoukani
Abstract : Today, there are many educational institutions and organizations around the world, especially the universities have adopted the e-learning and learning management system concepts because they want to enhance and support their educational process since the number of students who would like to attend universities and educational institutions is increasing. This paper has many objectives, the first one is comparing between different types of most popular learning management system (LMS) software such as Moodle and Blackboard based on their uniqueness features. The second objective is presenting the learning management systems and their benefits in e-learning. Finally, this research paper presents a proposed model, which consists of six independent variables (application and integration, communication, assessment, content, cost, and security), and one dependent variable which is e-learning success. A questionnaire has been developed and distributed to 450 respondents, and then data was collected from 418 valid questionnaires. The result showed that there is a statistically significant impact of learning management system major characteristics on e-learning success.
Keywords : Learning management system; e-learning; educational process; Moodle; educational institutions
Visit
A proposed model of e-commerce using modern social media and its impact on customer loyalty
Authors :
Abstract : This study aims to find the impact of social media e-commerce on customer loyalty and discover the impact of each characteristic (measure) of the user experience on customer loyalty. These are Usability, Trustability, Relevancy, and Reputation. It also aims to find the difference in customer loyalty when demographic factors change in aspects of gender, age, and education. On the basis of the theoretical framework, hypotheses were proposed to describe the relationship between the independent variables (Usability, Trustability, Relevancy, Reputation), and the dependent variable loyalty, i.e. the demographic factors (gender, age and education). Data was collected from 990 university students and employees of all levels and ages, through a questionnaire instrument. The hypotheses were tested with hierarchal linear and simple regression analyses, which confirmed that the study hypotheses have positive relationships. Finally there is a significant impact of modern social media e-commerce on customer loyalty.
Keywords :
Visit
A proposed dynamic algorithm for association rules mining in big data
Authors :
Abstract : Because of the explosive growth of data that we are suffocating in, while we are starving for knowledge, mining data and information from substantial databases has been perceived as a key research topic. So, Due to the huge size of data that exists in the databases and warehouses and because these data are big, dynamic and change frequently it is difficult and expensive to do mining for frequent patterns and association rule from scratch. In light of such an interest, this paper proposes a Dynamic Algorithm for Association Rules Mining in Big Data that is capable of finding frequent item-sets dynamically and generating association rules from the item-sets by using accumulated knowledge stored in a database table, this table will be modified frequently when the system runs every time and the new value of the table will be the result of processing new inserted data added to the results of previously processed data. The proposed solution is implemented using C#.net and SQL server. The results compared with the Apriori algorithm. It was conclude that Apriori algorithm showed better results than the proposed algorithm in the initial runs, on the other hand the proposed dynamic algorithm provided results near to Apriori algorithm on frequent runs that use small number of transactions but the proposed dynamic algorithm took less processing time than Apriori algorithm by 63.95% on the frequent runs that use big number of transactions
Keywords :
Visit
A New Selection Operator - CSM in Genetic Algorithms for Solving the TSP
Authors : Wael Raef Alkhayri Author,Suhail Sami Owais Author, Mohammad Shkoukani
Abstract : Genetic Algorithms (GAs) is a type of local search that mimics biological evolution by taking a population of string, which encodes possible solutions and combines them based on fitness values to produce individuals that are fitter than others. One of the most important operators in Genetic Algorithm is the selection operator. A new selection operator has been proposed in this paper, which is called Clustering Selection Method (CSM). The proposed method was implemented and tested on the traveling salesman problem. The proposed CSM was tested and compared with other selection methods, such as random selection, roulette wheel selection and tournament selection methods. The results showed that the CSM has the best results since it reached the optimal path with only 8840 iterations and with minimum distance which was 79.7234 when the system has been applied for solving Traveling Salesman Problem (TSP) of 100 cities.
Keywords : Genetic Algorithm; Traveling Salesman Problem; Genetic Algorithm Operators; Clustering; Selection Operator
Visit
A New Technique to Manage Big Bioinformatics Data Using Genetic Algorithms
Authors : Huda Jalil Dikhil Author 2: Mohammad Shkoukani Author 3: Suhail Sami Owais
Abstract : The continuous growth of data, mainly the medical data at laboratories becomes very complex to use and to manage by using traditional ways. So, the researchers start studying genetic information field which increased in the past thirty years in bioinformatics domain (the computer science field, genetic biology field, and DNA). This growth of data becomes known as big bioinformatics data. Thus, efficient algorithms such as Genetic Algorithms are needed to deal with this big and vast amount of bioinformatics data in genetic laboratories. So the researchers proposed two models to manage the big bioinformatics data in addition to the traditional model. The first model by applying Genetic Algorithms before MapReduce, the second model by applying Genetic Algorithms after the MapReduce, and the original or the traditional model by applying only MapReduce without using Genetic Algorithms. The three models were implemented and evaluated using big bioinformatics data collected from the Duchenne Muscular Dystrophy (DMD) disorder. The researchers conclude that the second model is the best one among the three models in reducing the size of the data, in execution time, and in addition to the ability to manage and summarize big bioinformatics data. Finally by comparing the percentage errors of the second model with the first model and the traditional model, the researchers obtained the following results 1.136%, 10.227%, and 11.363% respectively. So the second model is the most accurate model with the less percentage error.
Keywords : Bioinformatics; Big Data; Genetic Algorithms; Hadoop MapReduce
Visit
Real-time transit tracking system to evolve and facilitate the transportation process at the Applied Science University
Authors : Mohammad Shkoukani1* , Fadi Ajjam2 , Hamza Ali2 and Hisham Salah3
Abstract : Travel and transportation are important for most people and play a major role in the human life; therefore this paper describes a prototype system called eBus which is a tracking system for campus buses at the Applied Science University. This system consists of two parts an Android application that is used by both the driver and the student which provides the ability for the students to track the buses’ movements on a specific route and show their information on the map and it also enables the bus driver to see the students’ locations on the map. The second part of the system is a windows application that is used by the transportation manager, the application allows the transportation manager to control & monitor the transportation system, enables him to monitor the buses’ movements, modify users, and notify him about the bus status. So, the main objective of our developed system is to facilitate the way of interactivity among the three actors (transportation manager, student, and bus driver) which make the transportation system convenient to use, more effective and efficient.
Keywords : Transportation, Tracking system, Global positioning system.
Visit
Balancing the Network Clusters for the Lifetime Enhancement in Dense Wireless Sensor Networks
Authors : Hesham Abusaimeh, Mohammad Shkoukani & Faiz Alshrouf
Abstract : The Wireless Sensor Networks consist of large number of low cost, long battery life sensor nodes. Clustering sensors into groups is improving the network lifetime and saving energy. Many Approaches have been designed to cluster the networks into groups. However, few of these clustering algorithms, have studied the numbers of the nodes of each cluster and the way of balancing them. None of these clustering algorithms considers the energy level of the wireless sensor nodes in balancing the clusters. In this paper, we have applied a new technique to balance the number of nodes in the clusters based on the energy level of the wireless sensor nodes. This technique is compared with the default ZigBee clustering protocol in order to measure its performance.
Keywords : Balance clustering protocol,Wireless sensor network,Energy consumption,Lifetime,Cluster-tree,Cluster-head
Visit
Journal of Emerging Trends in Computing and Information Sciences Understanding the Role of Multimodal Metaphors in E-Government Implementation: An Empirical Investigation
Authors : Mohammad Shkoukani,Yousef Elsheikh,Hesham Abusaimeh
Abstract : Multimodal interaction metaphors have become a way to improve the usability of interactive systems, including e-government platform. This paper presents the experimental results of the inclusion of multimodal metaphors in e-government interfaces in order to enhance usability on the one hand, and trust between users on the other hand to eventually lead to the adoption and use of such interfaces on a large scale in the context under investigation. In this paper, multimodal metaphors that were used: visual and auditory stimuli and avatars. These investigations were evaluated by 40 users as it consisted of two different interfaces in each experiment to demonstrate the role of multimodal metaphors in the successful implementation of e-government interface platform. The results show the positive role of multimodal metaphors in increasing the level of usability in such interactive platforms on the one hand, and on the other hand increase the users trust, and learnability while interacting with those e-government platforms. Also, the results show the validity of the research approach adopted and the way in which users interact with e-government interface platform effectively and efficiently.
Keywords : Multimodal metaphors, e-government, e-services, usability, trust, human computer interaction
Visit
Survey of Web Application and Internet Security Threats
Authors : Hesham Abusaimeh, Mohammad Shkoukani
Abstract : Computer and network security are one of the most challenging topics in the Information Technology research community. Internet security is a significant subject that may affect a wide range of Internet users. People that use Internet to sell, buy and even to communicate needs their communications to be safe and secure. This paper is discussing the different aspects of Internet and networking security and weakness. Main elements of networking security techniques such as the firewalls, passwords, encryption, authentication and integrity are also discussed in this paper. The anatomy of a web applications attack and the attack techniques are also covered in details. The security of high-speed Internet as the growth of its use has stained the limits of existing network security measures. Therefore, other security defense techniques related to securing of high-speed Internet and computer security in the real world are studied as well such as, DNS, One-Time Password and defending the network as a whole. This paper is also surveyed the worm epidemics in the high-speed networks and their unprecedented rates spread.
Keywords : Web application Security, Network Security, Protection tools, SQL Injection, Firewall, and Intrusion Detection System.
Visit
Modified TCP Protocol for Wireless Sensor Networks
Authors : Hesham Abusaimeh, Mohammad Shkoukani
Abstract : The transport layer's protocols have been used in the Wireless Sensor Networks (WSNs) in order to achieve data reliability. However, the limitations of the WSNs did not usually considered when implementing these protocols in the stack of the sensor nodes. In this paper, the TCP protocol has been modified in order to use it with the unique characteristics of the WSNs. The TCP is connection-oriented protocol, which may cause extra overhead, but it will reduce the number of redundant packets. This will also cause increasing the lifetime. In addition, that applying the TCP protocol in the WSN will make it reachable from the traditional wire or wireless network without gateway or connecter. Our proposed stack model has achieved better simulation result that the traditional sensor node stacks in term of throughput, packets loss ratio, and network lifetime.
Keywords : TCP, Wireless Sensor Networks, Transport Layer, ZigBee Stack, Network Lifetime, Network Throughput.
Visit
Proposed Enhanced Object Recognition Approach for Accurate Bionic Eyes
Authors : Mohammad Shkoukani, Hesham Abusaimeh
Abstract : AI has played a huge role in image formation and recognition, but all built on the supervised and unsupervised learning algorithms the learning agents follow. Neural networks have also a role in bionic eyes integration but it is not discussed thoroughly in this paper. The chip to be implanted, which is a robotic device that applies methods developed in machine learning, consists of large scale algorithms for feature learning to construct classifiers for object detection and recognition, to input in the chip system. The challenge however is in identifying a complex image, which may require combined processes of learning features algorithms. In this paper an experimented approaches are stated for individual case of concentration of objects to obtain a high recognition outcome. Each approach may influence one angle, and a suggested non-experimented approach may give a better visual aid for bionic recognition and identification, using more learning and testing methods. The paper discusses the different approached of kernel and convolutional methods to classify objects, in addition to a proposed model to extract a maximized optimization of object formation and recognition. The proposed model combines variety of algorithms that have been experimented in differed related works and uses different learning approaches to handle large datasets in training.
Keywords : Bionic eyes, image recognition, image processing, object recognition, learning machine.
Visit
General and special-purpose methodologies for agent oriented software engineering
Authors : Mohammad Shkoukani, R. Abu Lail
Abstract : This paper provides a summary of software engineering process and its importance in open system industry. It describes the agent oriented software engineering development lifecycle. It also focuses on orientation of multi agent systems and on some representative agent oriented software engineering methodologies such as Gaia, ROADMAP, Tropos, and MaSE which are general purpose methodologies. Then it describes some special purpose methodologies such as ADELFE and SADDE. It also presents the phases for each methodology with its strengths and weaknesses. Finally it proposes the development of a new model that combines the features of two of the existing methodologies which are Gaia and Tropos by concentrating on their strengths and avoiding their weaknesses.
Keywords :
Visit