Organizations in various industries have widely developed the artificial intelligence (AI) maturity model as a systematic approach. This study aims to review state-of-the-art studies related to AI maturity models systematically. It allows a deeper understanding of the methodological issues relevant to maturity models, especially in terms of the objectives, methods employed to develop and validate the models, and the scope and characteristics of maturity model development. Our analysis reveals that most works concentrate on developing maturity models with or without their empirical validation. It shows that the most significant proportion of models were designed for specific domains and purposes. Maturity model development typically uses a bottom-up design approach, and most of the models have a descriptive characteristic. Besides that, maturity grid and continuous representation with five levels are currently trending in maturity model development. Six out of 13 studies (46%) on AI maturity pertain to assess the technology aspect, even in specific domains. It confirms that organizations still require an improvement in their AI capability and in strengthening AI maturity. This review provides an essential contribution to the evolution of organizations using AI to explain the concepts, approaches, and elements of maturity models.

There are three income categories for Malaysians: the top 20% (T20), the middle 40% (M40), and the bottom 40% (B40). The government has extended B40′s access to higher education to eliminate socioeconomic disparities and improve their lives. The number of students enrolled in bachelor’s degree programmes at universities has risen annually. However, not all students who enrolled graduated. Machine learning approaches have been widely used and improved in education. However, research studies related to unsupervised learning in education are generally lacking. Therefore, this study proposes a clustering-based approach for classifying B40 students based on their performance in higher education institutions (HEIs). This study developed three unsupervised models (k-means, BIRCH, and DBSCAN) based on the data of B40 students. Several data pre-processing tasks and feature selection have been conducted on the raw dataset to ensure the quality of the training data. Each model is optimized using different tuning parameters. The observational results have shown that the optimized k-means on Model B (KMoB) achieved the highest performance among all the models. KMoB produced five clusters of B40 students based on their performance. With KMoB, this study may assist the government in reducing HEI drop-out rates, increasing graduation rates, and eventually boosting students’ socioeconomic status.

Background: Mobile health (mHealth) apps play an important role in delivering education, providing advice on treatment, and monitoring patients’ health. Good usability of mHealth apps is essential to achieve the objectives of mHealth apps efficiently. To date, there are questionnaires available to assess the general system usability but not explicitly tailored to precisely assess the usability of mHealth apps. Hence, the mHealth App Usability Questionnaire (MAUQ) was developed with 4 versions according to the type of app (interactive or standalone) and according to the target user (patient or provider). Standalone MAUQ for patients comprises 3 subscales, which are ease of use, interface and satisfaction, and usefulness. Objective: This study aimed to translate and validate the English version of MAUQ (standalone for patients) into a Malay version of MAUQ (M-MAUQ) for mHealth app research and usage in future in Malaysia. Methods: Forward and backward translation and harmonization of M-MAUQ were conducted by Malay native speakers who also spoke English as their second language. The process began with a forward translation by 2 independent translators followed by harmonization to produce an initial translated version of M-MAUQ. Next, the forward translation was continued by another 2 translators who had never seen the original MAUQ. Lastly, harmonization was conducted among the committee members to resolve any ambiguity and inconsistency in the words and sentences of the items derived with the prefinal adapted questionnaire. Subsequently, content and face validations were performed with 10 experts and 10 target users, respectively. Modified kappa statistic was used to determine the interrater agreement among the raters. The reliability of the M-MAUQ was assessed by 51 healthy young adult mobile phone users. Participants needed to install the MyFitnessPal app and use it for 2 days for familiarization before completing the designated task and answer the M-MAUQ. The MyFitnessPal app was selected because it is one among the most popular installed mHealth apps globally available for iPhone and Android users and represents a standalone mHealth app. Results: The content validity index for the relevancy and clarity of M-MAUQ were determined to be 0.983 and 0.944, respectively, which indicated good relevancy and clarity. The face validity index for understandability was 0.961, which indicated that users understood the M-MAUQ. The kappa statistic for every item in M-MAUQ indicated excellent agreement between the raters (κ ranging from 0.76 to 1.09). The Cronbach α for 18 items was .946, which also indicated good reliability in assessing the usability of the mHealth app. Conclusions: The M-MAUQ fulfilled the validation criteria as it revealed good reliability and validity similar to the original version. M-MAUQ can be used to assess the usability of mHealth apps in Malay in the future.

An exploration task can be performed by a team of mobile robots more efficiently than human counterparts. They can access and give live updates for hard-to-reach areas such as a disaster site or a sewer. However, they face some issues hindering them from optimal path planning due to the symmetrical shape of the environments. Multiple robots are expected to explore more areas in less time while solving robot localization and collision-avoidance issues. When deploying a multi-robot system, it is ensured that the hardware parts do not collide with each other or the surroundings, especially in symmetric environments. Two types of methods are used for collision avoidance: centralized and decentralized. The decentralized approach has mainly been used in recent times, as it is computationally less expensive. This article aims to conduct a systematic literature review of different collision-avoidance strategies and analyze the performance of innovative collision-avoidance techniques. Different methods such as Reinforcement Learning (RL), Model Predictive Control (MPC), Altruistic Coordination, and other approaches followed by selected studies are also discussed. A total of 17 studies are included in this review, extracted from seven databases. Two experimental designs are studied: empty/open space and confined indoor space. Our analysis observed that most of the studies focused on empty/open space scenarios and verified the proposed model only through simulation. ORCA is the primary method, against which all the state-of-the-art techniques are evaluated. This article provides a comparison between different methods used for multi-robot collision avoidance. It discusses if the methods used are focused on safety or path planning. It also sheds light on the limitations of the studies included and possible future directions.

The exponential growth of todays technologies has resulted in the growth of high-throughput data with respect to both dimensionality and sample size. Therefore, efficient and effective supervision of these data becomes increasing challenging and machine learning techniques were developed with regards to knowledge discovery and recognizing patterns from these data. This paper presents machine learning tool for preprocessing tasks and a comparative study of different classification techniques in which a machine learning tasks have been employed in an experimental set up using a dataset archived from the UCI Machine Learning Repository website. The objective of this paper is to analyse the impact of refined feature selection on different classification algorithms to improve the prediction of classification accuracy for room occupancy. Subsets of the original features constructed by filter or information gain and wrapper techniques are compared in terms of the classification performance achieved with selected machine learning algorithms. Three feature selection algorithms are tested, specifically the Information Gain Attribute Evaluation (IGAE), Correlation Attribute Evaluation (CAE) and Wrapper Subset Evaluation (WSE) algorithms. Following a refined feature selection stage, three machine learning algorithms are then compared, consisting the Multi-Layer Perceptron (MLP), Logistic Model Trees (LMT) and Instance Based k (IBk). Based on the feature analysis, the WSE was found to be optimal in identifying relevant features. The application of feature selection is certainly intended to obtain a higher accuracy performance. The experimental results also demonstrate the effectiveness of Instance Based k compared to other ML classifiers in providing the highest performance rate of room occupancy prediction.