| Title | Employing Information Theoretic Metrics with Data-Driven Occupancy Detection Approaches: A Comparative Analysis |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Sayed, Aya Nabil, Hamila, Ridha, Himeur, Yassine, Bensaali, Faycal |
| Conference Name | 2022 5th International Conference on Signal Processing and Information Security (ICSPIS) |
| Keywords | Collaboration, composability, compositionality, cross-entropy, Entropy, Gini Impurity Index, Human Behavior, human factors, Information Gain, Information security, information theoretic security, machine learning algorithms, Measurement, Metrics, Occupancy Detection, policy-based governance, pubcrawl, Radio frequency, resilience, Resiliency, Scalability, Signal processing, Signal processing algorithms, Temperature distribution |
| Abstract | Building occupancy data helps increase energy management systems' performance, enabling lower energy use while preserving occupant comfort. The focus of this study is employing environmental data (e.g., including but not limited to temperature, humidity, carbon dioxide (CO2), etc.) to infer occupancy information. This will be achieved by exploring the application of information theory metrics with machine learning (ML) approaches to classify occupancy levels for a given dataset. Three datasets and six distinct ML algorithms were used in a comparative study to determine the best strategy for identifying occupancy patterns. It was determined that both k-nearest neighbors (kNN) and random forest (RF) identify occupancy labels with the highest overall level of accuracy, reaching 97.99% and 98.56%, respectively. |
| DOI | 10.1109/ICSPIS57063.2022.10002508 |
| Citation Key | sayed_employing_2022 |
Employing Information Theoretic Metrics with Data-Driven Occupancy Detection Approaches: A Comparative Analysis