A5006731938- Building Energy and Comfort Optimization
- Data Stream Mining Techniques
- Traffic Prediction and Management Techniques
- Energy Load and Power Forecasting
- Smart Grid Energy Management
- Anomaly Detection Techniques and Applications
- BIM and Construction Integration
- Atmospheric and Environmental Gas Dynamics
- Advanced Chemical Sensor Technologies
- Housing Market and Economics
- Infrastructure Maintenance and Monitoring
- Explainable Artificial Intelligence (XAI)
- Air Quality Monitoring and Forecasting
- Recommender Systems and Techniques
- Facilities and Workplace Management
- Urban Planning and Valuation
- Time Series Analysis and Forecasting
Aalto University
2020-2024
Granlund (Finland)
2019-2024
An important instrument for achieving smart and high-performance buildings is Machine Learning (ML). A lot of research has been done in exploring the ML models various applications built environment such as occupancy prediction. Nevertheless, focused mostly on analyzing feasibility performance different supervised but rarely practical scalability those models. In this study, a transfer learning method proposed solution to typical problems application buildings. Such are scaling model...
This paper presents an approach integrating explainable artificial intelligence (XAI) techniques with adaptive learning to enhance energy consumption prediction models, a focus on handling data distribution shifts. Leveraging SHAP clustering, our method provides interpretable explanations for model predictions and uses these insights adaptively refine the model, balancing complexity predictive performance. We introduce three-stage process: (1) obtaining values explain predictions, (2)...
This paper investigates the performance of two probabilistic approaches, Ensemble batch Prediction Intervals (EnbPI) a conformal prediction approach and XGBoost Location, Scale Shape (XGBoostLSS), in predicting building energy consumption detecting systemic anomalies with proposed alarm matrix. The research questions focus on effectiveness these models providing both point predictions their utility identifying collective anomalies. Both showed good distribution performance. For example,...
Data drifts pose a critical challenge in the lifecycle of machine learning (ML) models, affecting their performance and reliability. In response to this challenge, we present microbenchmark study, called D3Bench, which evaluates efficacy open-source drift detection tools. D3Bench examines capabilities Evidently AI, NannyML, Alibi-Detect, leveraging real-world data from two smart building use cases.We prioritize assessing functional suitability these tools identify analyze drifts....
Climate change and technological development are pushing buildings to become more sophisticated. The installation of modern building automation systems, smart meters, IoT devices is increasing the amount available operational data. common term for this kind a but producing large amounts raw data does not automatically offer intelligence that would new insights building’s operation. Smart meters mainly used only tracking energy or water consumption in building. On other hand, occupancy...
Abstract Renovating the existing building stock is one of key tools for reaching EU 2020 and 2030 energy goals. The effectiveness retrofitting can be increased significantly through mass renovation stock. However, realization such approach very difficult due to complexity in decision making process lack high-quality data needed conducting a meaningful simulation. This paper presents novel progressive modelling framework coupled with BIM level development support utilization simulation We use...