Al-Balqa Applied University

The current SMAC (Social, Mobile, Analytic, Cloud) technology trend paves the way to a future in which intelligent machines, networked processes and big data are brought together. This virtual world has generated vast amount of data which is accelerating the adoption of machine learning solutions & practices. Machine Learning enables computers to imitate and adapt human-like behaviour. Using machine learning, each interaction, each action performed, becomes something the system can learn and use as experience for the next time. This work is an overview of this data analytics method which enables computers to learn and do what comes naturally to humans, i.e. learn from experience. It includes the preliminaries of machine learning, the definition, nomenclature and applications' describing it's what, how and why. The technology roadmap of machine learning is discussed to understand and verify its potential as a market & industry practice. The primary intent of this work is to give insight into why machine learning is the future.

Abstract Background As COVID-19 has been declared as a pandemic disease by the WHO on March 11th, 2020, the global incidence of COVID-19 disease increased dramatically. In response to the COVID-19 situation, Jordan announced the emergency state on the 19th of March, followed by the curfew on 21 March. All educational institutions have been closed as well as educational activities including clinical medical education have been suspended on the 15th of March. As a result, Distance E-learning emerged as a new method of teaching to maintain the continuity of medical education during the COVID-19 pandemic related closure of educational institutions. Distance E-Learning is defined as using computer technology to deliver training, including technology-supported learning either online, offline, or both. Before this period, distance learning was not considered in Jordanian universities as a modality for education. This study aims to explore the situation of distance E-learning among medical students during their clinical years and to identify possible challenges, limitations, satisfaction as well as perspectives for this approach to learning. Methods This cross-sectional study is based on a questionnaire that was designed and delivered to medical students in their clinical years. For this study, the estimated sample size ( n = 588) is derived from the online Raosoft sample size calculator. Results A total of 652 students have completed the questionnaire, among them, 538 students (82.5%) have participated in distance learning in their medical schools amid COVID-19 pandemic. The overall satisfaction rate in medical distance learning was 26.8%, and it was significantly higher in students with previous experience in distance learning in their medical schools as well as when instructors were actively participating in learning sessions, using multimedia and devoting adequate time for their sessions. The delivery of educational material using synchronous live streaming sessions represented the major modality of teaching and Internet streaming quality and coverage was the main challenge that was reported by 69.1% of students. Conclusion With advances in technologies and social media, distance learning is a new and rapidly growing approach for undergraduate, postgraduate, and health care providers. It may represent an optimal solution to maintain learning processes in exceptional and emergency situations such as COVID-19 pandemic. Technical and infrastructural resources reported as a major challenge for implementing distance learning, so understanding technological, financial, institutional, educators, and student barriers are essential for the successful implementation of distance learning in medical education.

We propose and experimentally evaluate a software solution for automatic detection and classification of plant leaf diseases. The proposed solution is an improvement to the solution proposed in The developed processing scheme consists of four main phases as in The following two steps are added successively after the segmentation phase. In the first step we identify the mostlygreen colored pixels. Next, these pixels are masked based on specific threshold values that are computed using Otsu's method, then those mostly green pixels are masked. The other additional step is that the pixels with zeros red, green and blue values and the pixels on the boundaries of the infected cluster (object) were completely removed. The experimental results demonstrate that the proposed technique is a robust technique for the detection of plant leaves diseases. The developed algorithm"s efficiency can successfully detect and classify the examined diseases with a precision between 83% and 94%, and can achieve 20% speedup over the approach proposed in [1].

Administrative and medical processes of the healthcare organizations are rapidly changing because of the use of artificial intelligence (AI) systems. This change demonstrates the critical impact of AI at multiple activities, particularly in medical processes related to early detection and diagnosis. Previous studies suggest that AI can raise the quality of services in the healthcare industry. AI-based technologies have reported to improve human life quality, making life easier, safer and more productive. This study presents a systematic review of academic articles on the application of AI in the healthcare sector. The review initially considered 1,988 academic articles from major scholarly databases. After a careful review, the list was filtered down to 180 articles for full analysis to present a classification framework based on four dimensions: AI-enabled healthcare benefits, challenges, methodologies, and functionalities. It was identified that AI continues to significantly outperform humans in terms of accuracy, efficiency and timely execution of medical and related administrative processes. Benefits for patients’ map directly to the relevant AI functionalities in the categories of diagnosis, treatment, consultation and health monitoring for self-management of chronic conditions. Implications for future research directions are identified in the areas of value-added healthcare services for medical decision-making, security and privacy for patient data, health monitoring features, and creative IT service delivery models using AI.

Purpose – The purpose of this paper is to propose and examine a conceptual model that best explains the key factors influencing Jordanian customers' intention to adopt mobile banking (MB). Design/methodology/approach – The proposed conceptual model was based on the Technology Acceptance Model (TAM). This was extended by adding perceived risk and self-efficacy as an external factors. Structural equation modelling (SEM) was conducted to analyse the data collected from the field survey questionnaires administered to a convenience sample of Jordanian banking customers. Findings – The results showed that behavioural intention is significantly influenced by perceived usefulness, perceived ease of use, and perceived risk. Research limitations/implications – Practical and theoretical implications for both Jordanian banks and researchers in the MB context are also discussed in the concluding section. Originality/value – MB-related issues are yet to be examined empirically in the Jordanian context. This submission has attempted to fill this gap by empirically examining some of the important factors influencing the adoption of MB from the Jordanian customers’ perspective.

Biochar is gaining significant attention due to its potential for carbon (C) sequestration, improvement of soil health, fertility enhancement, and crop productivity and quality. In this review, we discuss the most common available techniques for biochar production, the main physiochemical properties of biochar, and its effects on soil health, including physical, chemical, and biological parameters of soil quality and fertility, nutrient leaching, salt stress, and crop productivity and quality. In addition, the impacts of biochar addition on salt-affected and heavy metal contaminated soils were also reviewed. An ample body of literature supports the idea that soil amended with biochar has a high potential to increase crop productivity due to the concomitant improvement in soil structure, high nutrient use efficiency (NUE), aeration, porosity, and water-holding capacity (WHC), among other soil amendments. However, the increases in crop productivity in biochar-amended soils are most frequently reported in the coarse-textured and sandy soils compared with the fine-textured and fertile soils. Biochar has a significant effect on soil microbial community composition and abundance. The negative impacts that salt-affected and heavy metal polluted soils have on plant growth and yield and on components of soil quality such as soil aggregation and stability can be ameliorated by the application of biochar. Moreover, most of the positive impacts of biochar application have been observed when biochar was applied with other organic and inorganic amendments and fertilizers. Biochar addition to the soil can decrease the nitrogen (N) leaching and volatilization as well as increase NUE. However, some potential negative effects of biochar on microbial biomass and activity have been reported. There is also evidence that biochar addition can sorb and retain pesticides for long periods of time, which may result in a high weed infestation and control cost.

These molecules or classes of natural substances are characterized by two phenyl rings at least and one or more hydroxyl substituents. This description comprehends a large number of heterogeneous compounds with reference to their complexity. Therefore, polyphenols can be simply classified into flavonoids and non-flavonoids, or be subdivided in many sub-classes depending on the number of phenol units within their molecular structure, substituent groups, and/or the linkage type between phenol units. Polyphenols are widely distributed in plant tissues where they mainly exist in form of glycosides or aglycones. The structural diversity of flavonoid molecules arises from variations in hydroxylation pattern and oxidation state resulting in a wide range of compounds: flavanols, anthocyanidins, anthocyanins, isoflavones, flavones, flavonols, flavanones, and flavanonols.

: The architecture of a learning system implies a heavy task for e-learning to be integrated into a complicated system that is flexible, time scalable, and capable of lasting, even though there are many diverse tools. Currently, higher education in United Arab Emirates is experiencing a major transformation, considering increased accessibility. Therefore, the study aims to identify the advantages and disadvantages of e-learning in university education in United Arab Emirates. A descriptive study design was used to randomly select students from Ajman university, who were enrolled in 2018/2019 academic year. A close-ended structured questionnaire was constructed to collect data from students. Frequencies and percentages were used to analyse the data collected. 81% students stated that e-learning provides scientific material in an interesting way. Similarly, 80% students have responded that e-learning increases the possibility of contact between students among themselves and between the students and the teacher. 73% students indicated that due to increasing social isolation, they spend more time in front of the technical means of social interaction account and face-to-face with others. 70% students have indicated that there is a presence of electronic illiteracy among parents, which reduces their ability to follow their children electronically. It is essential for potential e-learners to understand the differences between an e-learning classroom setting and a conventional classroom setting as there are both advantages and disadvantages of e-learning to both environments that can probably influence their overall performance as a student.

This study aims to examine the perspectives of various stakeholders, such as students and educators, on the use of artificial intelligence in teaching mathematics, specifically after the launch of ChatGPT. The study adopts a qualitative case study approach consisting of two stages: content analysis of interviews and investigation of user experience. The first stage of the study shows that ChatGPT is recognized for its improved math capabilities and ability to increase educational success by providing users with basic knowledge of mathematics and various topics. ChatGPT can offer comprehensive instruction and assistance in the study of geometry, and the public discourse on social media is generally positive, with enthusiasm for the use of ChatGPT in teaching mathematics and educational settings. However, there are also voices that approach using ChatGPT in educational settings with caution. In the second stage of the study, the investigation of user experiences through three educational scenarios revealed various issues. ChatGPT lacks a deep understanding of geometry and cannot effectively correct misconceptions. The accuracy and effectiveness of ChatGPT solutions may depend on the complexity of the equation, input data, and the instructions given to ChatGPT. ChatGPT is expected to become more efficient in resolving increasingly complex mathematical problems. The results of this investigation propose a number of avenues for research that ought to be explored in order to guarantee the secure and conscientious integration of chatbots, especially ChatGPT, into mathematics education and learning.

Explainable Artificial Intelligence (XAI) encompasses the strategies and methodologies used in constructing AI systems that enable end-users to comprehend and interpret the outputs and predictions made by AI models. The increasing deployment of opaque AI applications in high-stakes fields, particularly healthcare, has amplified the need for clarity and explainability. This stems from the potential high-impact consequences of erroneous AI predictions in such critical sectors. The effective integration of AI models in healthcare hinges on the capacity of these models to be both explainable and interpretable. Gaining the trust of healthcare professionals necessitates AI applications to be transparent about their decision-making processes and underlying logic. Our paper conducts a systematic review of the various facets and challenges of XAI within the healthcare realm. It aims to dissect a range of XAI methodologies and their applications in healthcare, categorizing them into six distinct groups: feature-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric approaches. Specifically, this study focuses on the significance of XAI in addressing healthcare-related challenges, underscoring its vital role in safety-critical scenarios. Our objective is to provide an exhaustive exploration of XAI's applications in healthcare, alongside an analysis of relevant experimental outcomes, thereby fostering a holistic understanding of XAI's role and potential in this critical domain.

The recent coronavirus disease (COVID-19) pandemic is associated with increasing morbidity and mortality and has impacted the lives of the global populations. Human behavior and knowledge assessment during the crisis are critical in the overall efforts to contain the outbreak. To assess knowledge, attitude, perceptions, and precautionary measures toward COVID-19 among a sample of medical students in Jordan. This is a cross-sectional descriptive study conducted between the 16th and 19th of March 2020. Participants were students enrolled in different levels of study at the six medical schools in Jordan. An online questionnaire which was posted on online platforms was used. The questionnaire consisted of four main sections: socio-demographics, sources of information, knowledge attitudes, and precautionary measures regarding COVID-19. Medical students used mostly social media (83.4%) and online search engines (84.8%) as their preferred source of information on COVID-19 and relied less on medical search engines (64.1%). Most students believed that hand shaking (93.7%), kissing (94.7%), exposure to contaminated surfaces (97.4%), and droplet inhalation (91.0%) are the primary mode of transmission but were indecisive regarding airborne transmission with only 41.8% in support. Participants also reported that elderly with chronic illnesses are the most susceptible group for the coronavirus infection (95.0%). As a response to the COVID-19 pandemic more than 80.0% of study participants adopted social isolation strategies, regular hand washing, and enhanced personal hygiene measures as their first line of defense against the virus. In conclusion, Jordanian medical students showed expected level of knowledge about the COVID-19 virus and implemented proper strategies to prevent its spread.

This study aimed at investigating the factors that mostly affect financial performance of Jordanian Insurance Companies. The study population consisted of all insurance companies' enlisted at Amman stock Exchange during the period (2002-2007) which count (25) insurance company. The data collected was analysed by using a number of basic statistical techniques such as T-test and Multiple- regression. The results showed that the following variables (Leverage, liquidity, Size, Management competence index) have a positive statistical effect on the financial performance of Jordanian Insurance Companies. The researcher recommended that a high consideration of increasing the company assets will lead to a good financial performance and there is a significant need to have highly qualified employees in the top managerial staff.

We propose and evaluate a framework for detection of plant leaf/stem diseases. Studies show that relying on pure naked-eye observation of experts to detect such diseases can be prohibitively expensive, especially in developing countries. Providing fast, automatic, cheap and accurate image-processing-based solutions for that task can be of great realistic significance. The proposed framework is image-processing-based and is composed of the following main steps; in the first step the images at hand are segmented using the K-Means technique, in the second step the segmented images are passed through a pre-trained neural network. As a testbed, we use a set of leaf images taken from Al-Ghor area in Jordan. Our experimental results indicate that the proposed approach can significantly support accurate and automatic detection of leaf diseases. The developed Neural Network classifier that is based on statistical classification perform well and could successfully detect and classify the tested diseases with a precision of around 93%.

Purpose This study aims to investigate the influencers’ credibility dimensions (i.e. attractiveness, trustworthiness, expertise) on purchase intention (PI) through the mediating role of cognitive and affective online engagement among the aesthetic dermatology consumers in Jordan. Design/methodology/approach The population of this study entails all followers of aesthetic dermatology clinics on their Instagram accounts. However, only three influencers from the aesthetic dermatology industry were selected and approved the request of sharing the survey instrument on their official platforms. Overall, 600 surveys were distributed, but only 384 were completed fully, constituting a 64% response rate. Findings The data analysis revealed an excellent fit for the data and indicated an impact of attractiveness and expertise on online engagement and PI. Moreover, a mediating influence was also found for online engagement on the path between influencer credibility and PI. Research limitations/implications This study has a limitation of collecting the data from only three influencers; consequently, collecting data from the followers of more than four influencers would get more generalizable results. Second, considering further, examining the mediating role of other variables such as electronic word-of-mouth (EWOM) and loyalty programs could also provide further insights onto the nature of the factors affecting the PI. In addition, future studies should examine the differences of using more than one social media platform. Practical implications The main findings of this study have a number of managerial implications for marketing management that hint at liking the influencers who are highly trusted owing to their extensive expertise in the area they are marketing rather than only depending on their physical attractiveness. The Jordanian culture does not focus only on the image shared by the social media as the reviews can either support or decline the influence of even the celebrity. Significantly, a set of managerial implications come from the current research. Social implications Two major areas are the most important; these are the trustworthy issue and the EWOM. The marketers should encourage their customers to openly talk about their experiences as they have an imperative role in liking influencers in a way that improves their PI. The second implication is related to social media platforms management that marketing managers should resolve any negative EWOM caused and to enhance followers’ satisfaction levels of the services. The increase in satisfaction positively affects PI, and the service makes the influencer role become more effective. Originality/value This study was able to add a value to the current understanding of the main antecedents of customer engagement by looking at these dimensions of perceived credibility. Another contribution was captured in this study by successfully validating the meditating impact of customer engagement between influencers’ credibility dimensions and PI, especially in the absence of the studies that have addressed such relationship.

BACKGROUND: Healthcare professionals including physicians were subjected to an increased workload during the COVID-19 crisis, leaving them exposed to significant physical and psychological distress. Therefore, our present study aimed to (i) assess the prevalence of burnout and levels of job satisfaction among physicians in Jordan, and (ii) explore physicians' opinions, experiences, and perceptions during the pandemic crisis. METHODS: This was a mixed-method study that utilized a structured web-based questionnaire and semi-structured individual interviews. The 10-Item Burnout Measure-Short version (BMS), and the 5-Item Short Index of Job Satisfaction (SIJS) were adopted to assess occupational burnout and job satisfaction, respectively. Semi-structured interviews were conducted, based on a conceptual framework that was developed from Herzberg's Two-Factor Theory of Motivation and Job Demands-Resources Model. Descriptive statistics and regression models, as well as inductive thematic analysis, were used to analyze quantitative and qualitative data, respectively. RESULTS: A total of 973 survey responses and 11 interviews were included in our analysis. The prevalence of burnout among physicians was (57.7%). Several significant factors were positively associated with burnout, including female gender, working at highly loaded hospitals, working for long hours, doing night shifts, lack of sufficient access to personal protective equipment, and being positively tested for SARS-CoV-2. Regarding job satisfaction, regression analysis revealed that age was positively associated with higher levels of job satisfaction. On contrary, being a general practitioner or specialist, working at highly loaded hospitals, low salaries, and suffering from burnout have predicted lower levels of job satisfaction. Besides, four themes have emerged from the thematic analysis: (i) Work-induced psychological distress during the pandemic, (ii) Decision-driven satisfactory and dissatisfactory experiences, (iii) Impact of the pandemic on doctor-patient communication and professional skills, and (iv) Economic impacts of the pandemic crisis and lockdown. CONCLUSION: A significant physical and psychological burden was associated with the COVID-19 pandemic. Reliable efforts should be implemented aiming at protecting physicians' physical and mental wellbeing, enhancing their working conditions, and raising awareness about burnout. Evidence-based decisions and proper utilization of financial and human resources at institutional and national levels are believed to be crucial for the sustainability of the health workforce, especially in crises.

Recent developments of edge computing and content caching in wireless networks enable the Intelligent Transportation System (ITS) to provide high-quality services for vehicles. However, a variety of vehicular applications and time-varying network status make it challenging for ITS to allocate resources efficiently. Artificial intelligence algorithms, owning the cognitive capability for diverse and time-varying features of Internet of Connected Vehicles (IoCVs), enable an intent-based networking for ITS to tackle the above-mentioned challenges. In this paper, we develop an intent-based traffic control system by investigating Deep Reinforcement Learning (DRL) for 5G-envisioned IoCVs, which can dynamically orchestrate edge computing and content caching to improve the profits of Mobile Network Operator (MNO). By jointly analyzing MNO's revenue and users' quality of experience, we define a profit function to calculate the MNO's profits. After that, we formulate a joint optimization problem to maximize MNO's profits, and develop an intelligent traffic control scheme by investigating DRL, which can improve system profits of the MNO and allocate network resources effectively. Experimental results based on real traffic data demonstrate our designed system is efficient and well-performed.

The impressive growth rate of the Internet of Things (IoT) has drawn the attention of cybercriminals more than ever. The growing number of cyber-attacks on IoT devices and intermediate communication media backs the claim. Attacks on IoT, if they remain undetected for an extended period, cause severe service interruption resulting in financial loss. It also imposes the threat of identity protection. Detecting intrusion on IoT devices in real-time is essential to make IoT-enabled services reliable, secure, and profitable. This paper presents a novel Deep Learning (DL)-based intrusion detection system for IoT devices. This intelligent system uses a four-layer deep Fully Connected (FC) network architecture to detect malicious traffic that may initiate attacks on connected IoT devices. The proposed system has been developed as a communication protocol-independent system to reduce deployment complexities. The proposed system demonstrates reliable performance for simulated and real intrusions during the experimental performance analysis. It detects the Blackhole, Distributed Denial of Service, Opportunistic Service, Sinkhole, and Workhole attacks with an average accuracy of 93.74%. The proposed intrusion detection system’s precision, recall, and F1-score are 93.71%, 93.82%, and 93.47%, respectively, on average. This innovative deep learning-based IDS maintains a 93.21% average detection rate which is satisfactory for improving the security of IoT networks.

Although it existed in a few different forms earlier, digital education is essentially a modern invention. It is the digitalization of a segment of the educational system. This article attempts to offer insightful thoughts on the future potential and difficulties of information and communication technology (ICT) and digital education as they relate to adopting the most recent technological advancements in the digital era and extensive online open courses. With the development of internet technology, we have observed a significant shift in how we communicate and collaborate among academics. The digital revolution encouraged unrestricted access to information on a global scale. Today’s classrooms are equipped with a wealth of ICT tools, and almost all instructors have made significant progress in integrating digital technology to improve students’ access to information and cooperative learning opportunities. The higher education system must seek to utilize the power of ICT to be competitive and provide high-quality education as a consequence of digital transformation, disruptive technological innovations, and accelerated change. To accomplish these ambitions, this paper describes some challenges that higher education encounters, as well as technological resources and methodologies they have used in the current scenario to transform higher education to adopt digital transformation. The paper aims to synthesize considerable insights that can be applied to the digitalization of higher education in the current and near future.

Big data (BD) analytics has been increasingly gaining attraction in both practice and theory in light of its opportunities, barriers and expected benefits. In particular, emerging economics view big data analytics as having great importance despite the fact that it has been in a constant struggle with the barriers that prevent its adoption. Thus, this study primarily attempted to determine the drivers of big data analytics in the context of a developing economy, Jordan. The study examined the influence of technological, organizational and environmental factors on big data adoption in the Jordanian SMEs context, using PLS-SEM for the analysis. The empirical results revealed that the relative advantage, complexity, security, top management support, organizational readiness and government support influence the adoption of BD, whilst pressure of competition and compatibility appeared to be of insignificant influence. The findings are expected to contribute to enterprise management and strategic use of data analytics in the present dynamic market environment, for both researcher and practitioner circles concerned with the adoption of big data in developing countries.

In this study we present our initial idea for using genetic algorithms to help a controllable mobile robot to find an optimal path between a starting and ending point in a grid environment. The mobile robot has to find the optimal path which reduces the number of steps to be taken between the starting point and the target ending point. GAs can overcome many problems encountered by traditional search techniques such as the gradient based methods. The proposed controlling algorithm allows four-neighbor movements, so that path-planning can adapt with complicated search spaces with low complexities. The results are promising.