This study introduces an innovative real-time AI posture correction service for three major powerlifting exercises: bench press, squat, and deadlift, utilizing YOLOv5 and MediaPipe. Due to the rising popularity of online fitness apps post-pandemic, there is a need for accurate posture correction tools to prevent injuries associated with incorrect exercise forms. The proposed method involves a comprehensive MultiPose Exercise Dataset (MPED), which collects 3D joint coordinate data from multiple angles using a smartphone camera. This data is used to train machine learning and deep learning models for detailed posture classification and real-time feedback. The AI service offers specific corrective feedback for both concentric and eccentric contractions, improving exercise efficiency and safety. The study’s results show that models built with machine learning algorithms generally outperform deep learning models for posture classification, and the proposed detailed feedback system is effective in preventing injuries and enhancing performance. This comprehensive approach ensures that users receive tailored feedback to correct their form in real-time, significantly reducing the risk of injury and promoting better overall fitness outcomes.

The supply of livestock products depends on many internal and external factors. Omitting any one factor can make it difficult to describe the market patterns. So, forecasting livestock indexes such as prices and supplies is challenging due to the effect of unknown factors. This paper proposes a Stacking Forest Ensemble method (SFE-NET) to forecast pork supply by considering both internal and external factors, thereby contributing to sustainable pork production. We first analyze the internal factors to explore features related to pork supply. External factors such as weather conditions, gas prices, and disease information are also collected from different sources. The combined dataset is from 2016 to 2022. Our SFE-NET method utilizes Random Forest, Gradient Boosting, and XGBoost as members and a neural network as the meta-method. We conducted seven experiments for daily, weekly, and monthly pork supply using different sets of factors, such as internal, internal and external, and selected. The results showed the following findings: (a) The proposed method achieved Coefficient of Determination scores between 84% and 91% in short and long periods, (b) the external factors increased the performance of forecasting methods by about 2% to 12%, and (c) the proposed stacking ensemble method outperformed other comparative methods by 1% to 18%. These improvements in forecasting accuracy can help promote more sustainable pork production by enhancing market stability and resilience.