Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.

Falling is one of the most critical outcomes of loss of consciousness during triage in emergency department (ED). It is an important sign requires an immediate medical intervention. This paper presents a computer vision-based fall detection model in ED. In this study, we hypothesis that the proposed vision-based triage fall detection model provides accuracy equal to traditional triage system (TTS) conducted by the nursing team. Thus, to build the proposed model, we use MoveNet, a pose estimation model that can identify joints related to falls, consisting of 17 key points. To test the hypothesis, we conducted two experiments: In the deep learning (DL) model we used the complete feature consisting of 17 keypoints which was passed to the triage fall detection model and was built using Artificial Neural Network (ANN). In the second model we use dimensionality reduction Feature-Reduction for Fall model (FRF), Random Forest (RF) feature selection analysis to filter the key points triage fall classifier. We tested the performance of the two models using a dataset consisting of many images for real-world scenarios classified into two classes: Fall and Not fall. We split the dataset into 80% for training and 20% for validation. The models in these experiments were trained to obtain the results and compare them with the reference model. To test the effectiveness of the model, a t-test was performed to evaluate the null hypothesis for both experiments. The results show FRF outperforms DL model, and FRF has same accuracy of TTS.

The economy, unemployment, and job creation of South Africa heavily depend on the growth of the agricultural sector. With a growing population of 60 million, there are approximately 4 million small-scale farmers (SSF) number, and about 36,000 commercial farmers which serve South Africa. The agricultural sector in South Africa faces challenges such as climate change, lack of access to infrastructure and training, high labour costs, limited access to modern technology, and resource constraints. Precision agriculture (PA) using AI can address many of these issues for small-scale farmers by improving access to technology, reducing production costs, enhancing skills and training, improving data management, and providing better irrigation infrastructure and transport access. However, there is a dearth of research on the application of precision agriculture using artificial intelligence (AI) by small scale farmers (SSF) in South Africa and Africa at large. The preferred reporting items for systematic reviews and meta-analyses (PRISMA) and Bibliometric analysis guidelines were used to investigate the adoption of precision agriculture and its socio-economic implications for small-scale farmers in South Africa or the systematic literature review (SLR) compared various challenges and the use of PA and AI for small-scale farmers. The incorporation of AI-driven PA offers a significant increase in productivity and efficiency. Through a detailed systematic review of existing literature from inception to date, this study examines 182 articles synthesized from two major databases (Scopus and Web of Science). The systematic review was conducted using the machine learning tool R Studio. The study analyzed the literature review articled identified, challenges, and potential societal impact of AI-driven precision agriculture.

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.

Among contemporary computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are favoured because of their capacity to tackle non-linear modelling and complex stochastic datasets. Nondeterministic models involve some computational intricacies when deciphering real-life problems but always yield better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling power generation/electric power output (EPO) from databases generated in a combined cycle power plant (CCPP). The study presents a comparative study between ANNs and ANFIS to estimate the power output generation of a combined cycle power plant in Turkey. The inputs of the ANN and ANFIS models are ambient temperature (AT), ambient pressure (AP), relative humidity (RH), and exhaust vacuum (V), correlated with electric power output. Several models were developed to achieve the best architecture as the number of hidden neurons varied for the ANNs, while the training process was conducted for the ANFIS model. A comparison of the developed hybrid models was completed using statistical criteria such as the coefficient of determination (R²), mean average error (MAE), and average absolute deviation (AAD). The R² of 0.945, MAE of 3.001%, and AAD of 3.722% for the ANN model were compared to those of R² of 0.9499, MAE of 2.843% and AAD of 2.842% for the ANFIS model. Even though both ANN and ANFIS are relevant in estimating and predicting power production, the ANFIS model exhibits higher superiority compared to the ANN model in accurately estimating the EPO of the CCPP located in Turkey and its environment.

The usage of cybersecurity is growing steadily because it is beneficial to us. When people use cybersecurity, they can easily protect their valuable data. Today, everyone is connected through the internet. It’s much easier for a thief to connect important data through cyber-attacks. Everyone needs cybersecurity to protect their precious personal data and sustainable infrastructure development in data science. However, systems protecting our data using the existing cybersecurity systems is difficult. There are different types of cybersecurity threats. It can be phishing, malware, ransomware, and so on. To prevent these attacks, people need advanced cybersecurity systems. Many software helps to prevent cyber-attacks. However, these are not able to early detect suspicious internet threat exchanges. This research used machine learning models in cybersecurity to enhance threat detection. Reducing cyberattacks internet and enhancing data protection; this system makes it possible to browse anywhere through the internet securely. The Kaggle dataset was collected to build technology to detect untrustworthy online threat exchanges early. To obtain better results and accuracy, a few pre-processing approaches were applied. Feature engineering is applied to the dataset to improve the quality of data. Ultimately, the random forest, gradient boosting, XGBoost, and Light GBM were used to achieve our goal. Random forest obtained 96% accuracy, which is the best and helpful to get a good outcome for the social development in the cybersecurity system.