This study evaluated the performance of several machine learning classifiers—Decision Tree, Random Forest, Logistic Regression, Gradient Boosting, SVM, KNN, and Naive Bayes—for adaptability classification in online and onsite learning environments. Decision Tree and Random Forest models achieved the highest accuracy of 0.833, with balanced precision, recall, and F1-scores, indicating strong, overall performance. In contrast, Naive Bayes, while having the lowest accuracy (0.625), exhibited high recall, making it potentially useful for identifying adaptable students despite lower precision. SHAP (SHapley Additive exPlanations) analysis further identified the most influential features on adaptability classification. IT Resources at the University emerged as the primary factor affecting adaptability, followed by Digital Tools Exposure and Class Scheduling Flexibility. Additionally, Psychological Readiness for Change and Technical Support Availability were impactful, underscoring their importance in engaging students in online learning. These findings illustrate the significance of IT infrastructure and flexible scheduling in fostering adaptability, with implications for enhancing online learning experiences.

Goat farming plays an important economic role in numerous developing countries, with Africa being a home to a considerable portion of the global goat population. This study examined the socioeconomic determinants affecting goat herd size among smallholder farmers in Lephalale Local Municipality of the Limpopo Province in South Africa. A simple random sampling technique was used to select 61 participants. The socioeconomic characteristics of smallholder goat farmers in Lephalale Local Municipality were identified and described using descriptive statistics on one hand. On the other hand, a Multiple linear regression model was employed to analyse the socioeconomic determinants affecting smallholder goat farmers’ herd sizes. Findings from the Multiple linear regression model highlighted several key determinants, including the age of the farmer, gender of the farmer, education level, and marital status of farmers, along with determinants like distance to the markets, provision of feed supplements, and access to veterinary services. Understanding these determinants is crucial for policymakers and practitioners to develop targeted strategies aimed at promoting sustainable goat farming practices and improving the livelihoods of smallholder farmers in the region.

Foodborne diseases are a global health problem. Every year, millions of people die worldwide from these diseases. It has been determined that the high prevalence of these diseases is related to unfavorable socioeconomic conditions of the population. In this study, the relationship between foodborne diseases and socioeconomic conditions of the population was determined using principal component analysis as a multivariate statistical analysis technique. In this study, the socioeconomic variables of each Ecuador province and the prevalence of foodborne diseases (hepatitis A, salmonella, shigellosis and typhoid fever) during the years 2018 and 2019 were considered. The results show the relationship between foodborne diseases and the socioeconomic conditions of the population, as well as identifying regions more vulnerable to present high levels of prevalence of foodborne diseases, thus facilitating the implementation of social investment programs to reduce the prevalence of these diseases.

Amidst the COVID-19 pandemic, the imperative of physical distancing has underscored the necessity for telemedicine solutions. Traditionally, telemedicine systems have operated synchronously, requiring scheduled appointments. This study introduces an innovative telemedicine system integrating Artificial Intelligence (AI) to enable asynchronous communication between physicians and patients, eliminating the need for appointments and providing round-the-clock access from any location. The AI-Telemedicine system was developed utilizing Google Sheets and Google Forms. Patients can receive dietary recommendations from the AI acting as the physician and submit self-reports through the system. Physicians have access to patients’ submitted reports and can adjust AI settings to tailor recommendations accordingly. The AI-Telemedicine system for patients requiring daily dietary recommendations has been successfully developed, meeting all nine system requirements. System privacy and security are ensured through user account access controls within Google Sheets. This AI-Telemedicine system facilitates seamless communication between physicians and patients in situations requiring physical distancing, eliminating the need for appointments. Patients have round-the-clock access to the system, with AI serving as a physician surrogate whenever necessary. This system serves as a potential model for future telemedicine solutions.