Recently, there has been a significant increase in the number of Artificial Intelligence (AI) systems, software, and components. As a result, it is crucial to evaluate their quality. Quality models for AI have in fact been proposed, but there is a lack of Systematic Mapping Studies (SMS) for quality models in AI systems, software, and components. The goal of this paper is to understand, classify, and critically evaluate existing quality models for AI systems, software, and components. This study conducts an SMS to investigate quality models proposed by various authors in the past. The study only found quality models for AI systems and software. So far, the SMS has revealed no work on AI software component quality models. Finally, the limitations of the quality models and the implications for future research and development efforts are discussed.

This study aims to identify telecom customer segments by utilizing machine learning and subsequently develop a web-based dashboard. The dashboard visualizes the cluster analysis based on demographics, behavior, and region features. The study applied analytic pipeline that involved five stages i.e. data generation, data pre-processing, data clustering, clusters analysis, and data visualization. Firstly, the customer’s dataset was generated using Faker Python package. Secondly was the pre-processing which includes the dimensionality reduction of the dataset using the PCA technique and finding the optimal number of clusters using the Elbow method. Unsupervised machine learning algorithm K-means was used to cluster the data, and these results were analyzed and labeled with labels and descriptions. Lastly, a dashboard was developed using Microsoft Power BI to visualize the clustering results in meaningful analysis. According to the results, four customer clusters were obtained. An interactive web-based dashboard called INSIGHT was developed to provide analysis of customer segments based on demographic, behavioral, and regional traits; and to devise customized query for deeper analysis. The correctness of the clustering results was evaluated and achieved a satisfactory Silhouette Score of 0.3853. Hence, the telecom could target their customers accurately based on their needs and preferences to increase service satisfaction.

Background: Mobile health apps, for example, the Tät, have been shown to be potentially effective in improving pelvic floor muscle training (PFMT) among women, but they have not yet been studied among pregnant women. Adherence to daily PFMT will improve pelvic floor muscle strength leading to urinary incontinence (UI) improvement during the pregnancy. Objective: This study aims to document the validation process in developing the Kegel Exercise Pregnancy Training app, which was designed to improve the PFMT adherence among pregnant women. Methods: We utilized an intervention mapping approach incorporated within the mobile health development and evaluation framework. The framework involved the following steps: (1) conceptualization, (2) formative research, (3) pretesting, (4) pilot testing, (5) randomized controlled trial, and (6) qualitative research. The user-centered design-11 checklist was used to evaluate the user-centeredness properties of the app. Results: A cross-sectional study was conducted to better understand PFMT and UI among 440 pregnant women. The study reported a UI prevalence of 40.9% (180/440), with less than half having good PFMT practice despite their good knowledge. Five focus group discussions were conducted to understand the app design preferred by pregnant women. They agreed a more straightforward design should be used for better app usability. From these findings, a prototype was designed and developed accordingly, and the process conformed to the user-centered design–11 (UCD-11) checklist. A PFMT app was developed based on the mHealth development and evaluation framework model, emphasizing higher user involvement in the application design and development. The application was expected to improve its usability, acceptability, and ease of use. Conclusions: The Kegel Exercise Pregnancy Training app was validated using a thorough design and development process to ensure its effectiveness in evaluating the usability of the final prototype in our future randomized control trial study.

In this research, a new Hybrid Obfuscation Technique was proposed to prevent prohibited Reverse Engineering. The proposed hybrid technique contains three approaches; first approach is string encryption. The string encryption is about adding a mathematical equation with arrays and loops to the strings in the code to hide the meaning. Second approach is renaming system keywords to Unicode to increase the difficulty and complexity of the code. Third approach is transforming identifiers to junk code to hide the meaning and increase the complexity of the code. An experiment was conducted to evaluate the proposed Hybrid Obfuscation Technique. The experiment contains two phases; the first phase was conducting reverse engineering against java applications that do not use any protection to determine the ability of reversing tools to read the compiled code. The second phase was conducting reverse engineering against the proposed technique to evaluate the effectiveness of it. The experiment of the hybrid obfuscation technique was to test output correctness, syntax, reversed code errors, flow test, identifiers names test, methods, and classes correctness test. With these parameters, it was possible to determine the ability of the proposed technique to defend the attack. The experiment has presented good and promising results, where it was nearly impossible for the reversing tool to read the obfuscated code. Even the revealed code did not perform as well as original and obfuscated code.