Accurate, label-free, and rapid methods for measuring phosphorus concentrations are essential in a hydroponic system, as excessive or insufficient phosphorus levels can adversely affect plant growth, human health, and environmental sustainability. In this study, we demonstrate the advantages of hybrid machine learning models compared to single machine learning models in predicting phosphorus concentration based on the absorbance dataset. Three machine learning classifiers- Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)- were employed as bases for single and hybrid machine learning models. Three ensemble techniques (voting, bagging, and stacking) were used to hybridize the classifiers. Among the single models, KNN demonstrated the fastest computational time of 18.07 s, while SVM achieved the highest accuracy of 99.6%. The hybrid SVM/KNN model using a voting classifier showed a significant increase in accuracy for KNN with only a slight increase in computational time. Bagging techniques increased the accuracy but at a longer computational time. The stacking technique, which combined SVM, KNN, and RF, achieved the highest accuracy of 99.73% with a short computational time of 36.18 s compared to the bagging and voting technique. This study demonstrates that the machine learning method can effectively distinguish phosphorus concentrations. In contrast, hybrid machine learning techniques can improve accuracy for predicting phosphorus without using labels, despite requiring longer computational time.
Objectives. The prevalence rate of work-related musculoskeletal disorders (WMSDs) globally is notably high. There are a limited number of studies investigating WMSDs and their associated risk factors. However, there are currently no data available for WMSDs among industrial workers in Peninsular Malaysia. This study aimed to identify the prevalence of WMSDs and associated risk factors among industrial workers experiencing WMSDs through their daily working tasks. Methods. A quantitative study using a questionnaire was conducted among industrial workers from rehabilitation centres and factories in Peninsular Malaysia. The analysis of 232 participant narratives aimed to identify the correlation between job tasks and musculoskeletal pain, especially in case of repetitive and heavy handling tasks. Results. The prevalence of WMSDs among industrial workers stands at 93.1%. The results also indicate that the most affected part of the body was the lower back, with 62.1% for 7 days or more in the last year, caused by industrial workers' job tasks. The prominent risk factors associated with body parts include gender, age, working hours and most difficult tasks with MSDs, especially in the lower back. Conclusion. This survey helps us to understand whether the workers are experiencing any discomfort, pain or disability related to workplace activities.
Wastewater monitoring for SARS-CoV-2 has attracted considerable attention worldwide to complement the existing clinical-based surveillance system. In this study, we report our first successful attempt to prove the circulation of SARS-CoV-2 genes in Malaysian urban wastewater. A total of 18 wastewater samples were obtained from a regional sewage treatment plant that received municipal sewage between February 2021 and May 2021. Using the quantitative PCR assay targeting the E and RdRp genes of SARS-CoV-2, we confirmed that both genes were detected in the raw sewage, while no viral RNA was found in the treated sewage. We were also able to show that the trend of COVID-19 cases in Kuala Lumpur and Selangor was related to the changes in SARS-CoV-2 RNA levels in the wastewater samples. Overall, our study highlights that monitoring wastewater for SARS-CoV-2 should help local health professionals to obtain additional information on the rapid and silent circulation of infectious agents in communities at the regional level.
Glycemic control among patients with prediabetes and type 2 diabetes mellitus (T2D) in Malaysia is suboptimal, especially after the continuous worsening over the past decade. Improved glycemic control may be achieved through a comprehensive management strategy that includes medical nutrition therapy (MNT). Evidence-based recommendations for diabetes-specific therapeutic diets are available internationally. However, Asian patients with T2D, including Malaysians, have unique disease characteristics and risk factors, as well as cultural and lifestyle dissimilarities, which may render international guidelines and recommendations less applicable and/or difficult to implement. With these thoughts in mind, a transcultural Diabetes Nutrition Algorithm (tDNA) was developed by an international task force of diabetes and nutrition experts through the restructuring of international guidelines for the nutritional management of prediabetes and T2D to account for cultural differences in lifestyle, diet, and genetic factors. The initial evidence-based global tDNA template was designed for simplicity, flexibility, and cultural modification. This paper reports the Malaysian adaptation of the tDNA, which takes into account the epidemiologic, physiologic, cultural, and lifestyle factors unique to Malaysia, as well as the local guidelines recommendations.