MQMais Haj Qasem

Mais Haj Qasem

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mais Haj Qasem has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-Agent System Combined With Distributed Data Mining for Mutual Collaboration Classification

    by Mais Haj Qasem, Nadim Obeid, Amjad Hudaib, Mohammed Amin Almaiah, Ali Al-Zahrani, Ahmad Al-Khasawneh

    Distributed Data Mining (DDM) has been proposed as a means to deal with the analysis of distributed data, where DDM discovers patterns and implements prediction based on multiple distributed data sources. However, DDM faces several problems in terms of autonomy, privacy, performance and implementation. DDM requires homogeneity regarding environment, control, administration and the classification algorithm(s), and such that requirements are too strict and inflexible in many applications. In this paper, we propose the employment of a Multi-Agent System (MAS) to be combined with DDM (MAS-DDM). MAS is a mechanism for creating goal-oriented autonomous agents within shared environments with communication and coordination facilities. We shall show that MAS-DDM is both desirable and beneficial. In MAS-DDM, agents could communicate their beliefs (calculated classification) by covering private and non-sharable data, and other agents decide whether the use of such beliefs in classifying instances and adjusting their prior assumptions about each class of data. In MAS-DDM, we will develop and use a modified Naive Bayesian algorithm because (1) Naive Bayesian has been shown to be the most used algorithm to deal with uncertain data, and (2) to show that even if all agents in MAS-DDM use the same algorithm, MAS-DDM preforms better than DDM approaches with non-communicating processes. Point (2) provide an evidence that the exchange of information between agents helps in increasing the accuracy of the classification task significantly.


  • Open Access

    Fog Computing Framework for Smart City Design

    by Mais Haj Qasem, Alaa Abu-Srhan, Hutaf Natoureah, Esra Alzaghoul

    Fog-computing is a new network architecture and computing paradigm that uses user or near-users devices (network edge) to carry out some processing tasks. Accordingly, it extends the cloud computing with more flexibility the one found in the ubiquitous networks. A smart city based on the concept of fog-computing with flexible hierarchy is proposed in this paper. The aim of the proposed design is to overcome the limitations of the previous approaches, which depends on using various network architectures, such as cloud-computing, autonomic network architecture and ubiquitous network architecture. Accordingly, the proposed approach achieves a reduction of the latency of data processing and transmission with enabled real-time applications, distribute the processing tasks over edge devices in order to reduce the cost of data processing and allow collaborative data exchange among the applications of the smart city. The design is made up of five major layers, which can be increased or merged according to the amount of data processing and transmission in each application. The involved layers are connection layer, real-time processing layer, neighborhood linking layer, main-processing layer, data server layer. A case study of a novel smart public car parking, traveling and direction advisor is implemented using IFogSim and the results showed that reduce the delay of real-time application significantly, reduce the cost and network usage compared to the cloud-computing paradigm. Moreover, the proposed approach, although, it increases the scalability and reliability of the users’ access, it does not sacrifice much time, nor cost and network usage compared to fixed fog-computing design.


  • Open Access

    Heterogeneity in IoT-based Smart Cities Designs

    by Mais Haj Qasem, Wesam AlMobaideen

    Smart city is a strategy of supporting new way of living using data that are collected from different types of electronic devices, analyzed and utilized to enable efficient resource usability and service optimization. Applications of various nature are elaborated in the smart cities, such as traffic planning applications, crowd monitoring, public health care, security, economy and urban planning. Thus, various requirements are needed to incorporate and facilitate efficient development of these applications in the smart city design. Accordingly, smart city can be distinguished via the requirements that support these applications. In this study, the requirements of smart city in relations to the involved applications and its influence on the smart city design are discussed. A list of smart city requirements is concluded and the potentials of various network architecture to facilitate such requirements are discussed. Based on the requirements and the architectures, the existing smart city designs are evaluated and compared.


  • Open Access

    Multiagent System for Mutual Collaboration Classification for Cancer Detection

    by Mais Haj Qasem, Amjad Hudaib, Nadim Obeid

    A multiagent system (MAS) is a mechanism for creating goal‐oriented autonomous agents in shared environments with communication and coordination facilities. Distributed data mining benefits from this goal‐oriented mechanism by implementing various distributed clustering, classification, and prediction techniques. Hence, this study developed a novel multiagent model for distributed classification tasks in cancer detection with the collaboration of several hospitals worldwide using different classifier algorithms. A hospital agent requests help from other agents for instances that are difficult to classify locally. The agents communicate their beliefs (calculated classification), and others decide on the benefit of using such beliefs in classifying instances and adjusting their prior assumptions on each class of data. A MAS model state and behavior and communication are then developed to facilitate information sharing among agents. Regarding accuracy, implementing the proposed approach in comparison with typically different noncommunicated distributed classifications shows that sharable information considerably increases the classification task accuracy by 25.77%.


  • Open Access

    Extreme Learning Machine for Credit Risk Analysis

    by Mais Haj Qasem, Loai Nemer

    Credit risk analysis is important for financial institutions that provide loans to businesses and individuals. Banks and other financial institutions generally face risks that are mostly of financial nature; hence, such institutions must balance risks and returns. Analyzing or determining risk levels involved in credits, finances, and loans can be performed through predictive analytic techniques, such as an extreme learning machine (ELM). In this work, we empirically evaluated the performance of an ELM for credit risk problems and compared it to naive Bayes, decision tree, and multi-layer perceptron (MLP). The comparison was conducted on the basis of a German credit risk dataset. The simulation results of statistical measures of performance corroborated that the ELM outperforms naive Bayes, decision tree, and MLP classifiers by 1.8248%, 16.6346%, and 5.8934%, respectively.


  • Open Access

    Requirements Prioritization Techniques Comparison

    by Amjad Hudaib, Raja Masadeh, Mais Haj Qasem, Abdullah Alzaqebah

    Requirements prioritization is considered as one of the most important approaches in the requirement engineering process. Requirements prioritization is used to define the ordering or schedule for executing requirement based on their priority or importance with respect to stakeholders’ viewpoints. Many prioritization techniques for requirement have been proposed by researchers, and there is no single technique can be used for all projects types. In this paper we give an overview of the requirement process and requirement prioritization concept. We also present the most popular techniques used to prioritize the software project requirements and a compression between these techniques. On the other hand, we spot the light on the importance of involving the non-functional requirements prioritization because of the great effects of non-functional on project success and quality; some approaches that used in prioritize non-functional requirements are discussed in this paper, in addition a general model is proposed based on reviewing the prioritization techniques in order to suggests a best suited technique for specific projects according to decision makers parameters.


  • Matrix multiplication of big data using MapReduce: A review

    by Mais Haj Qasem, Alaa Abu Sarhan, Raneem Qaddoura, Basel A. Mahafzah

    One popular application for big data is matrix multiplication, which has been solved using many approaches. Recently, researchers have applied MapReduce as a new approach to solve this problem. In this paper, we provide a review for matrix multiplication of big data using MapReduce. This review includes the techniques for solving matrix multiplication using MapReduce, the time-complexity and the number of mappers needed for each technique. Moreover, this review provides the number of articles published between the year 2010 and 2016 for each of the following three topics: Big Data, Matrix Multiplication, and MapReduce.


  • Requirements Prioritization Techniques Review and Analysis

    by Raneem Qaddoura, Alaa Abu-Srhan, Mais Haj Qasem, Amjad Hudaib

    Requirements prioritization is considered as one of the most important activities in the requirement engineering process. This paper gives an overview of the requirements prioritization activities and techniques. It also presents how data mining and machine learning techniques have been used to prioritize the software project requirements. A comparison between these techniques is also presented.


  • FIPA-Based Semi-centralized Protocol for Negotiation

    by Amjad Hudaib, Mais Haj Qasem, Nadim Obeid