The use of anthropometric measurements in machine learning algorithms for hypertension prediction enables the development of simple, non-invasive prediction models. However, different machine learning algorithms were utilized in conjunction with various anthropometric data, either alone or in combination with other biophysical and lifestyle variables. It is essential to assess the impacts of the chosen machine learning models using simple anthropometric measurements. We developed and tested 13 machine learning methods of neural network, ensemble, and classical categories to predict hypertension in adolescents using only simple anthropometric measurements. The imbalanced dataset of 2461 samples with 30.1% hypertension subjects was first partitioned into 90% for training and 10% for validation. The training dataset was reduced to eight simple anthropometric measurements: age, C index, ethnicity, gender, height, location, parental hypertension, and waist circumference using correlation coefficient. The Synthetic Minority Oversampling Technique (SMOTE) combined with random under-sampling was used to balance the dataset. The models with optimal hyperparameters were assessed using accuracy, precision, sensitivity, specificity, F1-score, misclassification rate, and AUC on the testing dataset. Across all seven performance measures, no model consistently outperformed the others. LightGBM was the best model for all six performance metrics, except sensitivity, whereas Decision Tree was the worst. We proposed using Bayes’ Theorem to assess the models’ applicability in the Sarawak adolescent population, resulting in the top four models being LightGBM, Random Forest, XGBoost, and CatBoost, and the bottom four models being Logistic Regression, LogitBoost, SVM, and Decision Tree. This study demonstrates that the choice of machine learning models has an effect on the prediction outcomes.

This study outlines and developed a multilayer perceptron (MLP) neural network model for adolescent hypertension classification focusing on the use of simple anthropometric and sociodemographic data collected from a cross-sectional research study in Sarawak, Malaysia. Among the 2,461 data collected, 741 were hypertensive (30.1%) and 1720 were normal (69.9%). During the data gathering process, eleven anthropometric measurements and sociodemographic data were collected. The variable selection procedure in the methodology proposed selected five parameters: weight, weight-to-height ratio (WHtR), age, sex, and ethnicity, as the input of the network model. The developed MLP model with a single hidden layer of 50 hidden neurons managed to achieve a sensitivity of 0.41, specificity of 0.91, precision of 0.65, -score of 0.50, accuracy of 0.76, and Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.75 using the imbalanced data set. Analyzing the performance metrics obtained from the training, validation and testing data sets show that the developed network model is well-generalized. Using Bayes’ Theorem, an adolescent classified as hypertensive using this created model has a 66.2% likelihood of having hypertension in the Sarawak adolescent population, which has a hypertension prevalence of 30.1%. When the prevalence of hypertension in the Sarawak population was increased to 50%, the developed model could predict an adolescent having hypertension with an 82.0% chance, whereas when the prevalence of hypertension was reduced to 10%, the developed model could only predict true positive hypertension with a 33.6% chance. With the sensitivity of the model increasing to 65% and 90% while retaining a specificity of 91%, the true positivity of an adolescent being hypertension would be 75.7% and 81.2%, respectively, according to Bayes’ Theorem. The findings show that simple anthropometric measurements paired with sociodemographic data are feasible to be used to classify hypertension in adolescents using the developed MLP model in Sarawak adolescent population with modest hypertension prevalence. However, a model with higher sensitivity and specificity is required for better positive hypertension predictive value when the prevalence is low. We conclude that the developed classification model could serve as a quick and easy preliminary warning tool for screening high-risk adolescents of developing hypertension.

Mean daily rainfall of more than 30mm could result in flood hazard. Accurate prediction of rainfall intensity could help in forecasting of flash flood and help to save lives and properties. One of the common machine learning techniques in rainfall prediction is Radial Basis Function (RBF) neural network. Rainfall intensity is classified into four categories, i.e. light (50mm) in this study. The rainfall intensity categories is forecasted using the RBF network model utilizing the daily meteorology data for Kuching, Sarawak, Malaysia. The input vectors being considered for the RBF network model are minimum, maximum and mean temperature (°C), mean relative humidity (%), mean wind speed (m/s), mean sea level pressure (hPa) and mean precipitation (mm) for the year 2009 to 2013. The prime focus in this paper is to analyse the ramification of the training data size, number of hidden neurons, and different input variables (i.e. combination of meteorology data) in influencing the performance of the RBF network model. From this study, it could be concluded that, the factor that would influence the performance of the RBF model is only the input variables used, if and only if the network model is equipped with sufficient number of hidden neurons and trained with adequate number of training data. Another interesting observation from this study is that, the RBF network model produced consistent result throughout the testing using a specific hidden neuron number when the RBF network is retrained and tested.

Examinations are among the most widely used and effective methods for assessing knowledge mastery, both domestically and internationally, and are extensively used in various talent-selection processes. Currently, offline exam venues usually rely on on-site manual invigilation combined with exam-monitoring videos to further strengthen invigilation efforts. However, this invigilation method not only utilizes large amounts of human and material costs but also cannot comprehensively detect cheating behavior during exam processes and thus fairness cannot be guaranteed. To improve the efficiency of video reviews during invigilation, save labor costs, and strengthen invigilation efforts, this study proposes the use of target detection algorithms to achieve automatic detection of cheating actions in the exam room. To improve the speed of video detection, a student's abnormal-behavior detection method was proposed based on improved YOLOv8 and attention mechanism to achieve real-time detection of cheating actions in an exam room on a regular performance computer. The results showed that the detection accuracy of the improved YOLOv8 model reached 82.71%, thus meeting the application requirements.

A common practice to capture the non-stationary characteristics of the time series data in Artificial Neural Network (ANN) is by randomly dividing the whole set of available data into training, validation and testing, i.e. the data in validation and testing are represented in the training data. Consequently, the usability of the developed model on data not represented by the training data used during the network model development process is always doubtful. In this work, we present a back-propagation neural network (BNN) model trained using one-day history data to predict soil moisture data at 1 km resolution for two future dates. Specifically, high soil moisture values were observed in the training data while the testing data were characterized by drier conditions due to minimal or no rainfall. Our model uses separate mean and standard deviation statistics values from the training and testing data, respectively, to the z-normalized data. With data pre-processed using this method, the BNN model next uses a moving window of size 4 km × 4 km to capture the spatial variability of the soil moisture throughout the 40 km × 40 km study area. The coupling of the normalization and moving window method managed to achieve average soil moisture with Root Mean Square (RMSE) of 3.67% and correlation coefficient,R²of 0.89. By only using the suggested normalization without the moving window method, the BNN model managed to achieve an average RMSE of barely 5.82% withR² = 0.83. When comparing with the normal practice of using the same mean and standard deviation statistics of the training data in the testing data, the retrieval accuracy of the BNN model deteriorates to 8.86% withR² = 0.32. The experiment results demonstrated that the proposed coupling method performed better in terms of both RMSE and R²for soil moisture retrieval.

In the realm of landslide susceptibility prediction, the challenge of overfitting and overestimation has persisted despite various modeling attempts. This study aims to elevate the predictive capabilities of the Extreme Gradient Boosting (XGBoost) and Random Forest (RF) models for landslide susceptibility assessment through the innovative application of Bayesian Optimization (BO). Using data from Penang Island in Malaysia, we comprehensively incorporated topographical, hydrological, human, and environmental factors influencing landslides. Leveraging Geographic Information System (GIS) tools, we meticulously constructed spatial databases encompassing all pertinent landslide conditioning elements. Our findings unveil the remarkable performance of the optimized XGBoost model, achieving an astounding 100.0% Success Rate (SR) and an impressive 97.1% Prediction Rate (PR). In comparison, the optimized RF model achieved an SR of 99.7% and a PR of 96.3%, while the stacked models followed closely with an SR of 96.8% and a PR of 95.6%. These conclusive results underscore the transformative potential of addressing overfitting and overestimation challenges through the strategic combination of stacking and hyperparameter optimization. The improved accuracy of these algorithms bears immense significance, extending to applications in site selection, engineering structure health monitoring, and disaster mitigation, thus elevating the importance of Landslide Susceptibility Maps (LSMs) in safeguarding communities and infrastructure.