Credit card usage has surged, heightening concerns about fraud. To address this, advanced credit card fraud detection (CCFD) technology employs machine learning algorithms to analyze transaction behavior. Credit card data's complexity and imbalance can cause overfitting in conventional models. We propose a Bayesian-optimized Extremely Randomized Trees via Tree-structured Parzen Estimator (TP-ERT) to detect fraudulent transactions. TP-ERT uses higher randomness in split points and feature selection to capture diverse transaction patterns, improving model generalization. The performance of the model is assessed using real-world credit card transaction data. Experimental results demonstrate the superiority of TP-ERT over the other CCFD systems. Furthermore, our validation exhibits the effectiveness of TPE compared to other optimization techniques with higher F1 score.•The optimized Extremely Randomized Trees model is a viable artificial intelligence tool for detecting credit card fraud.•Model hyperparameter tuning is conducted using Tree-structured Parzen Estimator, a Bayesian optimization strategy, to efficiently explore the hyperparameter space and identify the best combination of hyperparameters. This facilitates the model to capture intricate patterns in the transactions, resulting in enhanced model performance.•The empirical findings exhibit that the proposed approach is superior to the other machine learning models on a real-world credit card transaction dataset.
Mental health is a state of mind influences one thinking, feeling and acting from inside and outside that are vital for children's normal growth and development. Psychological distress may results in serious mental health problem if left untreated. Hence, early diagnosis can largely improve the condition from being deteriorating. This study determined the prevalence of psychological distress and its associated risk factors among children in Penang, Malaysia. The study applied stratified multistage cluster sampling for the recruitment of children, and their socio-demographics background, health and lifestyle practices, and the prevalence and risk factors of psychological distress were succinctly studied. The study provides a fundamental platform for informing parents and policy makers about psychological distress, and the need to strategize potential health intervention for achieving optimum human well-being.•Stratified multistage cluster sampling was useful to study the prevalence and risk factors of psychological distress in a children population.•DASS-Y is robust for brief dimensional measure of depression, anxiety and stress among children.
Slope instability represents a substantial secondary hazard post-earthquake, leading to considerable socio-economic losses from the destruction of structures, infrastructure, and human lives. This study addresses the urgent need for precise evaluation of seismic slope stability, a subject that has gained significant attention in earthquake engineering over the past decade. A theoretical framework is proposed that utilizes an improved Sarma method, estimating seismic forces and safety factors based on limit equilibrium theory. A Python-based implementation enhances both computational efficiency and reliability. The enhanced method is validated against the pseudo-static approach, exhibiting strong performance. Moreover, critical elements affecting slope stability, such as slope characteristics and seismic motion parameters, are examined. Although the findings predominantly concentrate on rocky slopes, next research intends to broaden the method's application to multiple slope types, hence facilitating more thorough and effective stability evaluations across different geological contexts.•Deriving seismic slope safety factors based on improved Sarma and Pseudo static methods.•Developing Python programs based on the improved Sarma safety factor method.•Assessing seismic rock slope stability based on calculated Safety Factors.
The Asian Arowana, Scleropages formosus (Müller and Schlegel, 1844) is a large majestic freshwater teleost, crowned as the king of aquariums with its bright charismatic appearance and magnificent swimming performance. The most expensive Asian arowana is the Golden Blue-based Malayan Arowana which is endemic to the Bukit Merah Lake and Kerian River Basin, Perak, Malaysia. S. formosus has been listed as endangered by the IUCN (International Union for Conservation of Nature), regulated under Appendix 1 of the Convention of International Trade on Endangered Species (CITES) for commercial trade. Environmental DNA (eDNA) analysis has become widely accepted in biodiversity monitoring for the detection of rare and endangered species without harming any ecosystem or threatened species. Hence, the application of eDNA as wild population monitoring of S. formosus is possible for conservation and CITES enforcement program.•The species-specific primer of S. formosus was designed based on selected sequences obtained from GenBank•This report presents the potential application of eDNA in the management of the Malaysian 686 CITES Act for conservation monitoring of the Asian Arowana•The detection and wild population monitoring is possible through the eDNA method as complementary tools.
PM2.5 air pollution poses significant health risks, particularly in urban areas such as Jakarta, where concentrations frequently surpass acceptable levels due to rapid urbanization. This study addresses autocorrelation in air quality data and evaluates the monitoring performance of XGBoost and Support Vector Regression (SVR) models using Individual and Exponentially Weighted Moving Average (EWMA) Charts. PM2.5 levels were obtained from Jakarta's Air Quality Index. The findings reveal that the SVR model effectively manages autocorrelation, while the combination of XGBoost and the EWMA chart yielded superior monitoring performance. Specifically, this approach detected only one out-of-control (OOC) point in Phase II and none in Phase I, with identified shifts ranging from moderate to large. Overall, the XGBoost and EWMA chart integration offers a robust solution for precise air quality monitoring and minimizes false alarms. The identification of OOC points provides actionable insights by highlighting significant deviations in air quality data that may require immediate intervention. Key points:•SVR and XGBoost model regression was introduced to enhance forecasting accuracy.•EWMA chart based on XGBoost residuals has better monitoring results.
This study explores the possibility of integrating and retrieving heterogenous data across platforms by using ontology graph databases to enhance educational insights and enabling advanced data-driven decision-making. Motivated by some of the well-known universities and other Higher Education Institutions ontology, this study improvises the existing entities and introduces new entities in order to tackle a new topic identified from the preliminary interview conducted in the study to cover the study objective. The paper also proposes an innovative ontology, referred to as Student Performance and Course, to enhance resource management and evaluation mechanisms on course, students, and MOOC performance by the faculty. The model solves the issues of data accumulation and their heterogeneity, including the problem of having data in different formats and various semantic similarities, and is suitable for processing large amounts of data in terms of scalability. Thus, it also offers a way to confirm the process of data retrieval that is based on performance assessment with the help of an evaluation matrix.
Non-clinical pharmacokinetic-pharmacodynamic (PKPD) models are crucial in the initial design of drug-dosage regimens and in drug development but has rarely been employed for testing high-risk organisms due to stringent handling procedures. Burkholderia pseudomallei is classified as a Tier 1 select agent with international guidelines recommending this organism to be handled within a biosafety level 3 (BSL3) facility. Unfortunately, BSL3 facilities are not widely available in low-resource settings. This paper describes a detailed guide for setting up an in vitro pharmacodynamic infection model specific for testing B. pseudomallei outside BSL 3 laboratory. Briefly in this study,•All procedures involving active handling of live B. pseudomallei cultures were performed strictly inside a class II BSC in BSL-2 plus negative airflow laboratory.•The model was set to simulate B. pseudomallei-bacteremia treated with ceftazidime, a 1st-line anti-melioidosis drug with an approximate 2-hour half-life. Model validation was performed by simulating ceftazidime half-life.•For the pharmacodynamic study, ceftazidime was given as bolus injections at 8-hour intervals into the central culture chamber containing actively growing B. pseudomallei.
Environmental DNA (eDNA) metabarcoding is a valuable tool for assessing aquatic biodiversity, but the high cost and complexity of DNA extraction pose challenges for widespread adoption, especially in developing countries. This study presents a cost-effective eDNA extraction method using a guanidine hydrochloride (GuHCl) buffer, proteinase-K digestion, and isopropanol precipitation to improve the detection of fish communities. Comparison with the Qiagen DNeasy Blood & Tissue Kit using MiFish universal primers showed that the GuHCl protocol detected more fish species in freshwater samples, with comparable performance in relative read abundance metrics. However, the GuHCl method exhibited higher PCR inhibition in brackish samples, likely due to salinity and natural inhibitors. The results suggest that the GuHCl-based method is a viable alternative, offering enhanced sensitivity for low-abundance species in freshwater samples and cost savings. This protocol facilitates large-scale eDNA metabarcoding for ecological studies and conservation management efforts.•The GuHCl protocol identified a greater diversity of fish species in freshwater samples than the Qiagen kit, but detected fewer species in brackish water samples.•Both extraction methods demonstrated robust positive correlations in metrics of relative read abundance.
Knee osteoarthritis is a prevalent degenerative joint disease leading to pain, stiffness, reduced mobility in the knee, and muscle weakness. Total knee arthroplasty (TKA) is typically the preferred surgical treatment option for moderate to severe osteoarthritis. A deeper understanding of quadriceps and hamstring muscle activation after TKA is needed to monitor patient prognosis postoperatively. This review aims to synthesize and summarize the available evidence on the effects of TKA on quadriceps and hamstring muscle recovery in individuals with knee osteoarthritis. Electronic databases such as PubMed, Scopus, Web of Science, CINAHL, EMBASE, and ProQuest Health & Medical Complete will be searched using relevant keywords related to knee osteoarthritis, total knee arthroplasty, surface electromyography and quadriceps and hamstring muscle recovery. Two reviewers will independently assess the related studies and extract data from the chosen articles. The Cochrane Risk of Bias Tool-1 and the Joanna Briggs critical appraisal checklist will be used to assess the methodological quality of the studies based on study design. Based on the relevance of the data and number of studies, a meta-analysis approach will be used to obtain a unified outcome. This review's findings will support clinical decision-making and offer direction for future researchers studying this patient population. Bullet points that outline the protocol•This proposed systematic review, and meta-analysis will summarize and synthesize literature on the effect of total knee arthroplasty (TKA) on quadriceps and hamstring muscle recovery in individuals with knee osteoarthritis.•This review offers important insights into knee muscle recovery following TKA, assisting orthopedic surgeons and rehabilitation professionals in improving their clinical decision-making.
The risk factors for stunting incidence involve categorical data in both the response and predictor variables. Therefore, we developed a sparse categorical principal component logistic regression model capable of handling data with multicollinearity. The parameters of the sparse categorical principal component logistic regression model were estimated using the maximum likelihood method and the Newton-Raphson iterative approach. The analysis yielded a likelihood ratio value of 144.81 and a chi-square statistic value of 11.07, indicating that all factors included in the model are statistically significant. The results highlight that medical history, inadequate complementary feeding, formula feeding, lack of complementary feeding programs, and lack of iron supplementation for mothers are highly associated with the risk of stunting in toddlers. This emphasizes the need for attention to maternal nutrition from pregnancy through breastfeeding, as well as the nutrition of the toddler. Some important points proposed in this method are:•Stunting data consists of categorical variables containing multicollinearity.•The method applied is sparse logistic regression combined with categorical principal component analysis.•Analysis of risk factors for stunting in toddlers is based on the child's own condition, as well as parental factors, namely age, education, and intake of additional food and supplementary tablets during pregnancy.
In recent days, Internet of Medical Things (IoMT) and Deep Learning (DL) techniques are broadly used in medical data processing in decision-making. A lung tumour, one of the most dangerous medical diseases, requires early diagnosis with a higher precision rate. With that concern, this work aims to develop an Integrated Model (IM- LTS) for Lung Tumor Segmentation using Neural Networks (NN) and the Internet of Medical Things (IoMT). The model integrates two architectures, MobileNetV2 and U-NET, for classifying the input lung data. The input CT lung images are pre-processed using Z-score Normalization. The semantic features of lung images are extracted based on texture, intensity, and shape to provide information to the training network.•In this work, the transfer learning technique is incorporated, and the pre-trained NN was used as an encoder for the U-NET model for segmentation. Furthermore, Support Vector Machine is used here to classify input lung data as benign and malignant.•The results are measured based on the metrics such as, specificity, sensitivity, precision, accuracy and F-Score, using the data from benchmark datasets. Compared to the existing lung tumor segmentation and classification models, the proposed model provides better results and evidence for earlier disease diagnosis.
Maintaining optimal water quality is critical for the success of aquaculture operations, where pH monitoring plays a pivotal role. This study presents a novel approach for pH monitoring in aquaculture ponds by harnessing biomass-based indicators and smartphone-based colorimetric sensing using different setups designs. Three biomass indicators including red cabbage, mango leaf, and used coffee grounds extracts were tested. Standard solutions across a pH range of 1-13 were tested using four setups: black and white polypropylene enclosures, a polyethylene pipe assembly, and a polystyrene tray configuration. The polystyrene tray configuration was determined to be the most effective, as its longer light path (4.5 cm) significantly enhanced color visibility and produced more vibrant color changes, making it ideal for further investigations. The method is as follows:•Water samples were collected from aquaculture ponds. pH were analyzed using this method and standard pH meters.•Mango leaf extract showed strong pH sensitivity and correlation (R² =0.9654).•The mango leaf extract attained a quantification accuracy of 0.5 pH units within a pH range of 3-12.•This smartphone-based approach offers simplicity and ease of implementation empowering aquaculture farmers with a practical tool for monitoring water quality.
With the rapid growth of photovoltaic installed capacity, photovoltaic hydrogen production can effectively solve the problem of electricity mismatch between new energy output and load demand. Photovoltaic electrolysis systems pose unique challenges due to their nonlinear, multivariable, and complex nature. This paper presents a thorough investigation into the control methodologies for such systems, focusing on both Maximum Power Point Tracking (MPPT) and electrolysis cell control strategies. Beginning with a comprehensive review of MPPT techniques, including classical, intelligent, optimization, and hybrid approaches, the study delves into the intricate dynamics of Proton Exchange Membrane Electrolysis Cells (PEMEL). Considering the nonlinear and time-varying characteristics of PEMEL, various control strategies such as Proportional-Integral-Derivative (PID), robust, Model Predictive Control (MPC), and Fault Tolerant Control (FTC) are analyzed. Evaluation metrics encompass stability, accuracy, computational complexity, and response speed. This paper provides a comparative analysis, encapsulating the strengths and limitations of each MPPT and PEM control technique.
In this work, the CT scans images of lung cancer patients are analysed to diagnose the disease at its early stage. The images are pre-processed using a series of steps such as the Gabor filter, contours to label the region of interest (ROI), increasing the sharpening and cropping of the image. Data augmentation is employed on the pre-processed images using two proposed architectures, namely (1) Convolutional Neural Network (CNN) and (2) Enhanced Integrated model for Lung Tumor Identification (EIM-LTI).•In this study, comparisons are made on non-pre-processed data, Haar and Gabor filters in CNN and the EIM-LTI models. The performance of the CNN and EIM-LTI models is evaluated through metrics such as precision, sensitivity, F1-score, specificity, training and validation accuracy.•The EIM-LTI model's training accuracy is 2.67 % higher than CNN, while its validation accuracy is 2.7 % higher. Additionally, the EIM-LTI model's validation loss is 0.0333 higher than CNN's.•In this study, a comparative analysis of model accuracies for lung cancer detection is performed. Cross-validation with 5 folds achieves an accuracy of 98.27 %, and the model was evaluated on unseen data and resulted in 92 % accuracy.