Malware is one of the most frequent cyberattacks, with its prevalence growing daily across the network. Malware traffic is always asymmetrical compared to benign traffic, which is always symmetrical. Fortunately, there are many artificial intelligence techniques that can be used to detect malware and distinguish it from normal activities. However, the problem of dealing with large and high-dimensional data has not been addressed enough. In this paper, a high-performance malware detection system using deep learning and feature selection methodologies is introduced. Two different malware datasets are used to detect malware and differentiate it from benign activities. The datasets are preprocessed, and then correlation-based feature selection is applied to produce different feature-selected datasets. The dense and LSTM-based deep learning models are then trained using these different versions of feature-selected datasets. The trained models are then evaluated using many performance metrics (accuracy, precision, recall, and F1-score). The results indicate that some feature-selected scenarios preserve almost the same original dataset performance. The different nature of the used datasets shows different levels of performance changes. For the first dataset, the feature reduction ratios range from 18.18% to 42.42%, with performance degradation of 0.07% to 5.84%, respectively. The second dataset reduction rate is between 81.77% and 93.5%, with performance degradation of 3.79% and 9.44%, respectively.

Skin cancer is one of the major types of cancer with an increasing incidence in recent decades. The source of skin cancer arises in various dermatologic disorders. Skin cancer is classified into various types based on texture, color, morphological features, and structure. The conventional approach for skin cancer identification needs time and money for the predicted results. Currently, medical science is utilizing various tools based on digital technology for the classification of skin cancer. The machine learning-based classification approach is the robust and dominant approach for automatic methods of classifying skin cancer. The various existing and proposed methods of deep neural network, support vector machine (SVM), neural network (NN), random forest (RF), and K-nearest neighbor are used for malignant and benign skin cancer identification. In this study, a method was proposed based on the stacking of classifiers with three folds towards the classification of melanoma and benign skin cancers. The system was trained with 1000 skin images with the categories of melanoma and benign. The training and testing were performed using 70 and 30 percent of the overall data set, respectively. The primary feature extraction was conducted using the Resnet50, Xception, and VGG16 methods. The accuracy, F1 scores, AUC, and sensitivity metrics were used for the overall performance evaluation. In the proposed Stacked CV method, the system was trained in three levels by deep learning, SVM, RF, NN, KNN, and logistic regression methods. The proposed method for Xception techniques of feature extraction achieved 90.9% accuracy and was stronger compared to ResNet50 and VGG 16 methods. The improvement and optimization of the proposed method with a large training dataset could provide a reliable and robust skin cancer classification system.

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.

The number of online documents has rapidly grown, and with the expansion of the Web, document analysis, or text analysis, has become an essential task for preparing, storing, visualizing and mining documents. The texts generated daily on social media platforms such as Twitter, Instagram and Facebook are vast and unstructured. Most of these generated texts come in the form of short text and need special analysis because short text suffers from lack of information and sparsity. Thus, this topic has attracted growing attention from researchers in the data storing and processing community for knowledge discovery. Short text clustering (STC) has become a critical task for automatically grouping various unlabelled texts into meaningful clusters. STC is a necessary step in many applications, including Twitter personalization, sentiment analysis, spam filtering, customer reviews and many other social network-related applications. In the last few years, the natural-language-processing research community has concentrated on STC and attempted to overcome the problems of sparseness, dimensionality, and lack of information. We comprehensively review various STC approaches proposed in the literature. Providing insights into the technological component should assist researchers in identifying the possibilities and challenges facing STC. To gain such insights, we review various literature, journals, and academic papers focusing on STC techniques. The contents of this study are prepared by reviewing, analysing and summarizing diverse types of journals and scholarly articles with a focus on the STC techniques from five authoritative databases: IEEE Xplore, Web of Science, Science Direct, Scopus and Google Scholar. This study focuses on STC techniques: text clustering, challenges to short texts, pre-processing, document representation, dimensionality reduction, similarity measurement of short text and evaluation.

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.

Traditionally, water quality is evaluated using expensive laboratory and statistical procedures, making real-time monitoring ineffective. Poor water quality requires a more practical and cost-effective solution. Water pollution has been a severe issue, hurting water quality in recent years. Therefore, it is crucial to create a model that forecasts water quality to control water pollution and inform consumers in the event of the detection of poor water quality. For effective water quality management, it is essential to accurately estimate the water quality class. Motivated by these considerations, we utilize the benefits of machine learning methods to construct a model capable of predicting the water quality index and water quality class. This study aims to investigate the performance of machine learning models for multiclass classification in the Langat River Basin water quality assessment. Three machine learning models were developed using Artificial Neural Networks (ANN), Decision Trees (DT), and Support Vector Machines (SVM) to classify river water quality. Comparative performance analysis between the three models indicates that the SVM is the best model for predicting river water quality in this study. In addition, there is a statistically significant difference in performance between the SVM, DT, and ANN models at the 0.05 level of confidence. The use of the kernel function, the grid search method, and the multiclass classification technique used in this study significantly impacts the effectiveness of the SVM model. The findings bolster the idea that machine learning models, particularly SVM, can be used to forecast WQI with a high degree of accuracy, hence enhancing water quality management. Consequently, the model based on machine learning lowered the cost and complexity of calculating sub-indices of six water quality parameters and classifying water quality compared to the standard IKA-JAS formula.