Research Title: An Object Classification Approach for Autonomous Vehicles Using Machine Learning Techniques

Author: Maram Bani Younes, Published Year: 2023

World Electric Vehicle Journal, 14

Faculty: Information Technology

Abstract: An intelligent, accurate, and powerful object detection system is required for automated driving systems to keep these vehicles aware of their surrounding objects. Thus, vehicles adapt their speed and operations to avoid crashing with the existing objects and follow the driving rules around the existence of emergency vehicles and installed traffic signs. The objects considered in this work are summarized by regular vehicles, big trucks, emergency vehicles, pedestrians, bicycles, traffic lights, and traffic signs on the roadside. Autonomous vehicles are equipped with high-quality sensors and cameras, LiDAR, radars, and GPS tracking systems that help to detect existing objects, identify them, and determine their exact locations. However, these tools are costly and require regular maintenance. This work aims to develop an intelligent object classification mechanism for autonomous vehicles. The proposed mechanism uses machine learning technology to predict the existence of investigated objects over the road network early. We use different datasets to evaluate the performance of the proposed mechanism. Accuracy, Precision, F1-Score, G-Mean, and Recall are the measures considered in the experiments. Moreover, the proposed object classification mechanism is compared to other selected previous techniques in this field. The results show that grouping the dataset based on their mobility nature before applying the classification task improved the results for most of the algorithms, especially for vehicle detection.

Keywords: autonomous vehicle; object detection; object classification; Udacity dataset; BDD100K dataset; machine learning; road network

Research Title: Review of Security Challenges in Mobile Cloud Computing Applications

Author: Maram Bani Younes, Published Year: 2023

2022 International Conference on Emerging Trends in Computing and Engineering Applications (ETCEA, Karak, Jordan

Faculty: Information Technology

Abstract: Mobiles and smartphones recently store huge amounts of valuable information such as personal information, financial transactions, social applications, and call records. These devices allow the transmission of data, by voice, text, or video, at anytime and everywhere. They enable easy access to the required information. The huge development of mobile devices has introduced the ability to use new and advanced applications. In several scenarios, the advanced applications require a connection to the cloud services. This affects the general environment, infrastructure, and security challenges of mobile applications. In this paper, we mainly aim to investigate the security challenges and issues of Mobile Cloud Computing (MCC) applications. First, we discuss the most popular applications of MCC. Then, we present an adversary and threat model that determines the main security challenges and issues in these applications. We summarize some security techniques, that have been used to tackle these challenges and determine their main requirements. Finally, clear recommendations regarding the directions and required research in this field are given in the paper.

Keywords: Wireless communication , Threat modeling , Cloud computing , Market research , Mobile handsets , Malware , Mobile applications

Research Title: Machine learning based prediction with parameters tuning of multi-label real road vehicles characteristics

Author: Maram Bani Younes, Published Year: 2022

ACM International Symposium on Performance Evaluation of Wireless Ad Hoc, Sensor, & Ubiquitous Networks, canada

Faculty: Information Technology

Abstract: The real-time traffic characteristics on the road network highly affect the safety conditions and the driving behaviors there. Early detection of crowded areas or hazardous conditions on the road network should affect the drivers' decisions and behavior to guarantee smooth and comfortable trips. Machine learning mechanisms have been mainly used for general prediction after extensive training processes. Over the road networks, trained machines could be really helpful to obtain instant predictions that assist drivers and autonomous vehicles there. However, the quality and efficiency of these machines are affected by several criteria including the quality of the used dataset and the tuning of the parameters of the regression algorithm. In this work, we investigate the performance of the most popular regression algorithms in terms of temporal prediction of the traffic characteristics in a real road scenario. Moreover, we optimize the regression algorithm by tuning the parameters using the grid search technique. From the experimental results, we can clearly notice the enhancements in predicting the traffic characteristics for different periods of time. We have observed that the number of neighbors, the distance, and the metric parameters' values are best tuned with the values of 4, 'Manhattan', and 'Distance', respectively, for the K-Nearest Neighbor (KNN) regression algorithm.

Keywords: traffic prediction, machine learning

Research Title: Towards green driving: A review of efficient driving techniques

Author: Maram Bani Younes, Published Year: 2022

World Electric Vehicle Journal, 13

Faculty: Information Technology

Abstract: The exponential increase in the number of daily traveling vehicles has exacerbated global warming and environmental pollution issues. These problems directly threaten the continuity and quality of life on the planet. Several techniques and technologies have been used and developed to reduce fuel consumption and gas emissions of traveling vehicles over the road network. Here, we investigate some solutions that assist drivers to follow efficient driving tips during their trips. Advanced technologies of communications or vehicle manufacturing have enhanced traffic efficiency over road networks. In addition, several advisory systems have been proposed to recommend to drivers the most efficient speed, route, or other decisions to follow towards their targeted destinations. These recommendations are selected according to the real-time traffic distribution and the context of the road network. In this paper, different high fuel consumption scenarios are investigated over the road networks. Next, the details of efficient driving techniques that were proposed to tackle each case accordingly are reviewed and categorized for downtown and highway driving. Finally, a set of remarks and existing gaps are reported to researchers in this field.

Keywords: green driving; road context; driving assistance; traffic situation

Research Title: Anti-Müllerian hormone as a biochemical marker of gonadal development and fertility status

Author: Jamal shareef Mulla-Abed , Published Year: 2021

Clinical laboratory International ,

Faculty: Allied Medical Sciences

Abstract: Anti-Müllerian hormone (AMH) plays a critical role in sex differentiation in fetal development and goes on to be important in the regulation of folliculogenesis in women. This article discusses the role of AMH in reproductive physiology and the many different situations where assessment of AMH levels is useful, as well as touching on methods of AMH analysis and reference ranges.

Keywords: hormone

Research Title: Enhanced wide range monotonic piezoresistivity, reliability of Ketjenblack/deproteinized natural rubber nanocomposite, and its biomedical application

Author: Madhanagopal Jagannathan, Published Year: 2017

Journal of Applied Polymer Science,

Faculty: Allied Medical Sciences

Abstract: Piezoresistive behavior of 6 to 9 wt % Ketjenblack reinforced deproteinized natural rubber (KB/DPNR) nanocomposite developed by two-roll mill was studied under compressive pressure (0 to 12.54 MPa). The 6 wt % KB/DPNR exhibited monotonic piezoresistivity, the highest electrical resistance change (485%), remarkable reversibility and minimal hysteresis. Furthermore, a good sensitivity (S) 5 1.1 MPa21 for 0.25 to 2.49 MPa, high test–retest reliability (intraclass correlation co-efficient, ICC 5 0.99) under 0 to 2.49 MPa for three repetitions conducted at an interval of 24 h and excellent repeatability (standard deviation, SD 5 4.8%) to a swing of 6.25 MPa for 50 cyclic compression were achieved. Homogeneous dispersion and high aspect ratio of KB and higher chemical linkage (due to double cross linking agents) between KB and DPNR may be responsible for the enhanced piezoresistivity. For practical application, the KB/DPNR was interfaced with the microcontroller through a bridge rectifier via custom-built Simulink and successfully monitored finger pressure in real time during bone movement on human

Keywords: deproteinized natural rubber; high pressure sensitivity; Ketjenblack; monotonic piezoresistivity

Research Title: New Device for Intrinsic Hand Muscle Strength Measurement: An Alternative to Strain Gauge Handheld Dynamometer

Author: Madhanagopal Jagannathan, Published Year: 2019

Evaluation & the Health professions, 42

Faculty: Allied Medical Sciences

Abstract: An accurate measurement of intrinsic hand muscle strength (IHMS) is required by clinicians for effective clinical decision-making, diagnosis of certain diseases, and evaluation of the outcome of treatment. In practice, the clinicians use Intrins-o-meter and Rotterdam Intrinsic Hand Myometer for IHMS measurement. These are quite bulky, expensive, and possess poor interobserver reliability (37–52%) and sensitivity. The purpose of this study was to develop an alternative lightweight, accurate, cost-effective force measurement device with a simple electronic circuit and test its suitability for IHMS measurement. The device was constructed with ketjenblack/ deproteinized natural rubber sensor, 1-MΩ potential divider, and Arduino Uno through the custom-written software. Then, the device was calibrated and tested for accuracy and repeatability within the force range of finger muscles (100 N). The 95% limit of agreement in accuracy from 1.95 N to 2.06 N for 10 to 100 N applied load and repeatability coefficient of +1.91 N or 6.2% was achieved. Furthermore, the expenditure for the device construction was around US$ 53. For a practical demonstration, the device was tested among 16 participants for isometric strength measurement of the ulnar abductor and dorsal interossei. The results revealed that the performance of the device was suitable for IHMS measurement.

Keywords: force sensor, intrinsic muscles, muscle strength evaluation, cost effective, device

Research Title: Toward Creating Software Architects Using Mobile Project-Based Learning Model (Mobile-PBL) for Teaching Software Architecture

Author: Lamis Al-Qoran, Published Year: 2023

Faculty: Information Technology

Abstract: Project-based learning (PBL) promotes increased levels of learning, deepens student understanding of acquired knowledge, and improves learning motivation. Students develop their ability to think and learn independently through depending on themselves in searching for knowledge, planning, exploration, and looking for solutions to practical problems. Information availability, student engagement, and motivation to learn all increase with mobile learning. The teaching process may be enhanced by combining the two styles. This paper proposes and evaluates a teaching model called Mobile Project-Based Learning (Mobile-PBL) that combines the two learning styles. The paper investigates how significantly Mobile-PBL can benefit students. The traditional lecture method used to teach the software architecture module in the classroom is not sufficient to provide students with the necessary practical experience to earn a career as software architects in the future. Therefore, the first author tested the use of the model for teaching the software architecture module at Philadelphia University’s Software Engineering Department on 62 students who registered for a software architecture course over three semesters. She compared the results of using the model for teaching with those results that were obtained when using the project-based learning (PBL) approach alone. The students’ opinions regarding the approach, any problems they had, and any recommendations for improvement were collected through a focus group session after finishing each semester and by distributing a survey to students to evaluate the effectiveness of the used model. Comments from the students were positive, according to the findings. The projects were well-received by the students, who agreed that it gave them a good understanding of several course ideas and concepts, as well as providing them with the required practical experience. The students also mentioned a few difficulties encountered while working on the projects, including student distraction from social media and the skills that educators and learners in higher education institutions are expected to have.

Keywords: software architecture education; Jordanian higher education; project-based learning; mobile learning

Research Title: State of the Art of Mobile Learning in Jordanian Higher Education: An Empirical Study

Author: Lamis Al-Qoran, Published Year: 2023

Multimodal Technologies and Interaction, 7

Faculty: Information Technology

Abstract: A new approach to learning is mobile learning (m-learning), which makes use of special features of mobile devices in the education sector. M-learning is becoming increasingly common in higher education institutions all around the world. The use of mobile devices for education and learning has also gained popularity in Jordan. Unlike studies about Jordan, there are many studies that thoroughly analyze the situation of m-learning in other countries. Thus, it is important to understand the current situation of m-learning at Jordanian universities, especially in light of the COVID-19 pandemic. While there have been some studies conducted prior to COVID-19 and a few studies after COVID-19, there is a need for a comprehensive study that provides an in-depth exploration of the current situation, student adoption, benefits, disadvantages, and challenges, particularly following COVID-19. Therefore, this study utilizes a sequential exploratory mixed research method to investigate the current state of the art of m-learning in Jordanian higher education with a particular focus on student adoption, benefits, disadvantages, and challenges. Firstly, the study explores the existing literature on m-learning and conducts 15 interviews with educators and learners in three Jordanian universities to gain insights into their experiences with m-learning. The study then distributes a survey to students at four Jordanian universities, representing both public and private universities, to generalize the results from the qualitative study. Additionally, the study investigates the relationship between student enrollment in public/private universities and the adoption of m-learning. The study came to the conclusion that students have a positive opinion of m-learning and are also willing to use it. However, there are a number of disadvantages and challenges to its adoption. Additionally, there is a relationship between student enrolment in public/private universities and the adoption of m-learning. These findings have important implications for institutions that want to incorporate m-learning into their undergraduate and graduate degree programs, as they aid decision-makers in these universities in creating frameworks that may be able to meet the needs of m-learning.

Keywords: educational mobile applications; mobile learning; Jordanian higher education; perceptions; adoption

Research Title: 5-Fluorouracil Delivery Using Smart Carriers

Author: Mohammad Bayan, Published Year: 2023

Global E-Conference on Chemistry and Chemical Engineering, E-Conference

Faculty: Pharmacy

Abstract: This study focused on creating a novel, one-pot delivery system for FU to treat colorectal cancer using methacrylate derivatives. Increasing patient compliance, lowering dosage requirements, and reducing undesired side effects can all improve the therapeutic outcome of the regimen. Six polymer-based pellets containing FU as a model drug were successfully created utilizing a thermal bulk polymerization process based on the HA and MA monomers. The drug-loaded formulations had a good drug entrapment efficiency of around 90%. The EA concentration greatly enhanced the Young's modulus, glass transition temperature, and tensile strength, but it significantly lowered the tensile elongation at the break value. By raising the crosslinker concentration, the pellets' in vitro swelling behavior was dramatically reduced. Less than 30% cumulative drug release was attained for all formulations after 5 hours of starting the release study. After 24 hours, 70% of a drug's total cumulative release was achieved. The created drug delivery system showed the ability to delay the release of 5-fluorouracil under conditions that mimicked the upper gastrointestinal tract while allowing its release in a regulated manner afterwards, which makes it promising for the prospective administration of 5-fluorouracil to the colon.

Keywords: Sustainability; Smart Carriers; Triggered Delivery; Colorectal Carcinoma