Unveiling Hidden Energy Anomalies: Harnessing Deep Learning to Optimize Energy Management in Sports Facilities

Anomaly detection in sport facilities has gained significant attention due toits potential to promote energy saving and optimizing operational efficiency.In this research article, we investigate the role of machine learning,particularly deep learning, in anomaly detection for sport facilities. Weexplore the challenges and perspectives of utilizing deep learning methods forthis task, aiming to address the drawbacks and limitations of conventionalapproaches. Our proposed approach involves feature extraction from the datacollected in sport facilities. We present a problem formulation using DeepFeedforward Neural Networks (DFNN) and introduce threshold estimationtechniques to identify anomalies effectively. Furthermore, we propose methodsto reduce false alarms, ensuring the reliability and accuracy of anomalydetection. To evaluate the effectiveness of our approach, we conductexperiments on aquatic center dataset at Qatar University. The resultsdemonstrate the superiority of our deep learning-based method over conventionaltechniques, highlighting its potential in real-world applications. Typically,94.33scheme.