Software Defect Prediction (SDP) models are built using software metrics derived from software systems. The quality of SDP models depends largely on the quality of software metrics (dataset) used to build the SDP models. High dimensionality is one of the data quality problems that affect the performance of SDP models. Feature selection (FS) is a proven method for addressing the dimensionality problem. However, the choice of FS method for SDP is still a problem, as most of the empirical studies on FS methods for SDP produce contradictory and inconsistent quality outcomes. Those FS methods behave differently due to different underlining computational characteristics. This could be due to the choices of search methods used in FS because the impact of FS depends on the choice of search method. It is hence imperative to comparatively analyze the FS methods performance based on different search methods in SDP. In this paper, four filter feature ranking (FFR) and fourteen filter feature subset selection (FSS) methods were evaluated using four different classifiers over five software defect datasets obtained from the National Aeronautics and Space Administration (NASA) repository. The experimental analysis showed that the application of FS improves the predictive performance of classifiers and the performance of FS methods can vary across datasets and classifiers. In the FFR methods, Information Gain demonstrated the greatest improvements in the performance of the prediction models. In FSS methods, Consistency Feature Subset Selection based on Best First Search had the best influence on the prediction models. However, prediction models based on FFR proved to be more stable than those based on FSS methods. Hence, we conclude that FS methods improve the performance of SDP models, and that there is no single best FS method, as their performance varied according to datasets and the choice of the prediction model. However, we recommend the use of FFR methods as the prediction models based on FFR are more stable in terms of predictive performance.

Artificial intelligence (AI) and wearable sensors are gradually transforming healthcare service delivery from the traditional hospital-centred model to the personal-portable-device-centred model. Studies have revealed that this transformation can provide an intelligent framework with automated solutions for clinicians to assess patients’ general health. Often, electronic systems are used to record numerous clinical records from patients. Vital sign data, which are critical clinical records are important traditional bioindicators for assessing a patient’s general physical health status and the degree of derangement happening from the baseline of the patient. The vital signs include blood pressure, body temperature, respiratory rate, and heart pulse rate. Knowing vital signs is the first critical step for any clinical evaluation, they also give clues to possible diseases and show progress towards illness recovery or deterioration. Techniques in machine learning (ML), a subfield of artificial intelligence (AI), have recently demonstrated an ability to improve analytical procedures when applied to clinical records and provide better evidence supporting clinical decisions. This literature review focuses on how researchers are exploring several benefits of embracing AI techniques and wearable sensors in tasks related to modernizing and optimizing healthcare data analyses. Likewise, challenges concerning issues associated with the use of ML and sensors in healthcare data analyses are also discussed. This review consequently highlights open research gaps and opportunities found in the literature for future studies.

This study examines the efficacy of robots as assistive technology (AT) learning tools for children with autism spectrum disorder (ASD). The study attempts to find answers to whether robots as assistive tools can (i) profoundly improve achievement in learning and (ii) provide valuable learning experiences among this group of children. Using LEGO Mindstorms EV3, a robot was built and programmed to teach the basic concept of place value in mathematics. Eight children with ASD, specifically, four females and four males, participated in the single case study, and six special education teachers took part in the interviews. The children participated in both traditional and robotic intervention lessons and were assessed at the end of each session. The results indicate a positive increase in content knowledge and an improved disposition toward learning, thus demonstrating the potential utilization of robots as AT tools for harnessing classroom learning. Data from the interviews with teachers highlighted four valuable learning experiences that occurred in the classrooms as a result of the robotic interventions; namely, with respect to young children with ASD, the AT (1) promoted interest and engagement, (2) increased attention and focus, (3) triggered interactions and communication, and (4) created a happy and fun learning environment.

The metaheuristic algorithm is a very important area of research that continuously improves in solving optimization problems. Nature-inspired is one of the metaheuristic algorithm classifications that has grown in popularity among researchers over the last few decades. Nature-inspired metaheuristic algorithms contribute significantly to tackling many standing complex problems (such as the combinatorial t-way testing problem) and achieving optimal results. One challenge in this area is the combinatorial explosion problem, which is always intended to find the most optimal final test suite that will cover all combinations of a given interaction strength. As such, test case generation has been selected as the most active research area in combinatorial t-way testing as Non-deterministic Polynomial-Time Hardness (NP-hard). However, not all metaheuristics are effectively adopted in combinatorial t-way testing, some proved to be effective and thus have been popular tools selected for optimization, whilst others were not. This research paper outlines a hundred and ten (110) outstanding nature-inspired metaheuristic algorithms for the last decades (2001 and 2021), such as the Coronavirus Optimization Algorithm, Ebola Optimization Algorithm, Harmony Search, Tiki-Taka Algorithm, and so on. The purpose of this review is to revisit and carry out an up-to-date review of these distinguished algorithms with their respective current states of use. This is to inspire future research in the field of combinatorial t-way testing for better optimization. Thus, we found that all metaheuristics have a simple structure that can be adopted in different areas to become more efficient in optimization. Finally, we suggested some future paths of investigation for researchers who are interested in the combinatorial t-way testing field to employ more of these algorithms by tuning their parameters settings to achieve an optimal solution.

Recent years we have witnessed major advancements in technologies that support the children that have been diagnosed with the autism by the increasing number of the application to enhance their ability in communication, understanding and interface with others. There are increasing numbers of a new mobile application that can be found on the market today, unfortunately, many of them are difficult to use and learn by the autistic children. This is due to the lack of usability guidelines for mobile application and relatively unexplored and unproven. This research will propose usability guidelines for interface design of mobile application for autism. The objectives of this research are to identify existing usability factors that have been currently used to design the interface of mobile application for autism and to review the usability guideline to design the interface of mobile application for autism. This project will be conducted in three phases and mixed method involving observation and interview will be applied. The finding of this study is to identify compatible usability elements for designing mobile application user interface for autistic children.