Computer Vision for Poultry Farms
Monitoring chickens on large poultry farms is labor-intensive, requiring constant attention to environmental conditions and animal well-being, which can hinder staff productivity. Using AI and ML with HPC, a solution was developed to create edge AI devices and computer vision sensors that efficiently monitor parameters like chicken behavior, body temperature, and growth. With IoT-enabled cameras and ML models trained using HPC, the approach achieved over 90% accuracy in chicken detection and segmentation, with a 10-fold reduction in model development time. This innovation supports precision agriculture, providing farmers with advanced tools to enhance productivity and ensure humane food production.
Read more at: [link]
Forecasting Electricity Market Metrics
Forecasting day-ahead electricity prices and loads is essential for decision-making in the energy market, where participants aim to avoid price volatility. By leveraging artificial neural networks (ANN) and time-series prediction models, this research explores efficient methods for predicting electricity metrics using datasets from markets like HUPX and Montenegro. The study finds that ANN architectures combining fully connected layers with recurrent or temporal convolutional layers deliver the most accurate short-term predictions, highlighting the potential of temporal convolutional networks for further exploration. Standardized comparison methods and collaboration with industry experts ensure a robust evaluation of forecasting approaches and their relevance to the energy sector.
Read more at: [link]
Personalized Banking Software Solutions
The project is developing SaaS solutions to enhance personalized banking and payment services through machine learning and data collection. Building on the SKEN expense-tracking app, the new system will integrate with mBanking and eBanking applications, providing users with automatic, detailed transaction categorization and insights. Using NLP-based ML algorithms, the system classifies transactions into predefined categories like food or services, leveraging data from SKEN and research expertise. This innovation aims to offer financial institutions advanced tools for better customer engagement and improved financial insights.
Read more at: [link]