Search

Purpose This paper aims to propose a novel way of using textual clustering as a feature selection method. It is applied to identify the most important keywords in the profile classification. The method is demonstrated through the problem of sick-leave promoters on Twitter. Design/methodology/approach Four machine learning classifiers were used on a total of 35,578 tweets posted on Twitter. The data were manually labeled into two categories: promoter and nonpromoter. Classification performance was compared when the proposed clustering feature selection approach and the standard feature selection were applied. Findings Radom forest achieved the highest accuracy of 95.91% higher than similar work compared. Furthermore, using clustering as a feature selection method improved the Sensitivity of the model from 73.83% to 98.79%. Sensitivity (recall) is the most important measure of classifier performance when detecting promoters’ accounts that have spam-like behavior. Research limitations/implications The method applied is novel, more testing is needed in other datasets before generalizing its results. Practical implications The model applied can be used by Saudi authorities to report on the accounts that sell sick-leaves online. Originality/value The research is proposing a new way textual clustering can be used in feature selection.

The decrease in rainfall and the decrease in rainy days are also accompanied by a poor distribution of rainfall especially during the period of growth of the rain crops which usually extends from October to May. The Cheliff is under the influence of a semi-arid climate with precipitation that ranges from about 600 mm year(-1) to the northeast and 300 mm year(-1) to the west and south of the basin. The daily rainfall data used in this study concern eleven stations covering varying periods representative of different rainfall regimes in the Cheliff basin. The results obtained showed that the monthly dry sequences encountered during the rainy season decrease when the number of dry days increases, and the maximum values have been observed for the number of 1 to 7 consecutive dry days and the values were observed for a number greater than or equal to 21 consecutive dry days. It is important to say that the month of February recorded the lowest value of consecutive dry days for all stations. Also, the western stations of the study area display the largest values of the lengths of the dry sequences. Most of the stations are more correlated with the MO and AMO climatic indices than the other indices. These are the stations located west of the study area that are strongly correlated with AMO. It also appears that the total number of dry days of the stations located west of the study area is negatively correlated with SOI.

With the increasing number of mobile phones and mobile applications, there is a noticeable rise in cybercrimes. Hence, an urgent need for mobile forensics. Before starting investigation, the investigator should choose one of the acquisition types; physical acquisition, logical acquisition or manual acquisition. The current mobile acquisition tools use these methods to produce an image of the entire mobile content, files of specific datatypes, or data of a certain application. Unfortunately, the resultant output does not facilitate investigating cases related to specific mobile application, since the tool might acquire more than what is needed which requires investigators to filter data manually, or acquire all the application’s data without sufficient analysis. Both cases are effort and time consuming. This study analyzes and compares currently available forensics tools that are designed to extract WhatsApp data only. The comparative study is based on two aspects; National Institute of Standards and Technology (NIST) Mobile Device Tool Test Assertions and researchers’ requirements. The results of the comparative study showed a shortage in the current WhatsApp forensics tools as they do not satisfy all NIST Test Assertions. Additionally, several researchers’ requirements such as: creating projects, comprehensive analysis, applying filters and validating the extracted files, were not met in the studied tools.

Productive families suffer from attracting customers to buy their products, since their lack of knowledge in marketing and modern technologies. The proposed online application “Made with Passion Mobile Application” embedded with a mobile-based dashboard to support productive families visually track, analyze and display key performance indicators (KPI) that measures how the business doing. Furthermore, it eases extracting important information from the data and to know its behavior at a sooner time. The proposed application supports both Android and iOS operating systems and developed using React Native framework. And Tableau software used to provide the dashboard for the application.

Nowadays, technology and mobile applications have become involved in various areas of life. Therefore, the need for applications in areas such as healthcare is significant. A survey was conducted at the College of Dentistry in Imam Abdulrahman bin Faisal University. Survey results of this academic environment show a need for a system to link dental students with supervisors. Current commercially available off-the-shelf applications do not cater for all requirements. This paper proposes a solution that supports the interaction between the supervisor, and the student at the College. However, such a system can be extended to work in other dental colleges within the Kingdom of Saudi Arabia and beyond.

In order to improve the quality of decisions, companies are trying to find solutions for better supervision during the progress of the projects. Dolf Technologies is a business located in Saudi Arabia with their headquarters in Khobar. The company has several challenges concerning project management. These challenges are influencing the quality and the punctuality of the delivered tasks. One effective way to deal with such a problem is to monitor all these tasks in an effective way. This paper reports on the case of employing performance dashboards by DOLF Technologies. The suggested solution consists of two dashboards, one is destined to operational control level employees and the second is dedicated to strategic level management. Both dashboards are designed using Tableau software connected to online excel sheet where the company data is stored. The first solution is the operational dashboard displays the progress of each task in each subproject, colored by if the task is on time or overdue. Moreover, working hours left compared with the deadline. As well as, the overall progress of each subproject displayed by how much it is finished in percentage out of 100. The second solution is the managerial dashboard an abstraction of the operational dashboard. It shows vertical progress bars; each visualizes the frequency of delays in tasks that each sub-project has. In addition, pie charts show the percentage of completed tasks for each subproject. The dashboards have been deployed and the initial feedback is positive.

In medical research, mass gathering is considered as one of the intensifying factors for respiratory disease outbreaks. An annual crowding event happens during Muslims’ religious practices of Hajj in Saudi Arabia. Another smaller ritual happens all year round, known as Umrah. While Hajj season is recognized, Umrah seasonality is challenging to identify. This paper uses data from Google Trends to identify Umrah seasons for performers from the Eastern Province in Saudi Arabia. It then investigates the correlation between mass gathering events as it affects the flu spread in the Eastern Province through the use of data. Patient data from a hospital was obtained to find flu seasonality and compared to crowding seasons. Google Trend data was confirmed by a limited dataset of official Umrah data and Flu data was confirmed by official FluNet data from neighboring country, Bahrain. An Exploratory Data Analysis (EDA) approach has been followed to identify the seasonality. Cross-correlation analysis found a strong positive correlation between crowding seasons and flu outbreaks in the Eastern Province with a forward shift of flu data for three months.

In this paper, an efficient and effective decision support solution for online grocery shopping is proposed. The framework focuses on increasing user satisfaction in terms of delivery time and cost. The main idea for time reduction is to give multiple delivery tasks to the same deliverer and then manage his daily schedule in real time manner. This will also influence positively the delivery cost since orders to the same regions will be automatically grouped together. The system is composed of three main subsystems. First, the data generation sub-system,responsible of computing delivery cost estimates and preference deviation. Second, the deliverer selection sub- system, it utilizes skyline and Top-K user preference queries to shortlist the available deliverers according to their schedules and delivery cost, and then select the most suitable one. Finally, once the deliverer is selected, the scheduling sub-system will be responsible of providing the best path to the deliverer by applying genetic algorithm on a modified travelling salesman problem.

A new way of living leads to new and advanced developmental area of innovation. In this paper, an online shopping system design for NEOM megacity project is proposed. The system is based on the use of self-regulating vans and middle stores. Self-regulating vans are employed for delivering the customer orders from different stores passing by the middle stores that appear as common intersecting points. The advantage of doing so is to speed up the delivery process by assigning the customer order to more than one van following the concept of relay race tracking. The relative issues to be addressed here is mainly an initial system design with each of its components being discussed based on the NEOM vision.

This chapter is consecrated to provide background information that encompass the basic concepts of context-aware pervasive computing systems. The major challenges that researchers need to consider when conducting research in context-aware pervasive computing systems and the most interesting approaches that can be used in order to deal with these challenges are reviewed. This chapter describes also the basic design principles of context-aware pervasive systems and depicts different models for representing and reasoning upon contextual information and an overview of the most known development frameworks of context-aware systems and application adaptation is presented too. Moreover, this chapter describes the usefulness of using context-awareness in ubiquitous healthcare domain and the major challenges in using context-awareness in this domain. The well-known works that have been proposed in the field of Ubiquitous healthcare are discussed too.

It is a big pleasure for the user to find the result of its skyline query without waiting for its processing; this can be realized by getting a saved version of this query. This paper focuses on the pre-computation of the skylines of all possible nonempty subsets of a given set of dimensions, what we call the skycube. We develop an efficient top-down approach called TOP-SKY for the skycube computation which derives the skyline objects from one of the subspace's parents adopting some techniques that help to achieve a better performance. In order to evaluate the effectiveness of the approach, TOP-SKY has been compared with the best algorithm in our knowledge Orion and with computing the cuboids of the skycube individually using BNL algorithm.

The materialisation of views has been one of the most successful techniques in optimising OLAP queries. In this context, many works have been conducted aiming either at studying the relationships between the views or at solving the materialised views selection problem. For skyline queries, researchers investigated only the first phase of the materialisation whereas the second phase which is the materialised skyline views selection problem has never been studied because of the difficulty of creating a cost model. In this paper, we propose a genetic method for the materialised skyline views selection problem. In order to reduce the high cost produced by evaluating the skycube all over the selection process, we propose a time reducing heuristic called OnceVisited which avoids the computation of the same query from the same views many times. The conducted experiments have proven the efficiency of the genetic approach since high quality solutions have been found. In addition, the proposed time reducing heuristic OnceVisited has been shown to be very efficient.