Refine
H-BRS Bibliography
- yes (24)
Departments, institutes and facilities
Document Type
- Article (12)
- Conference Object (10)
- Part of a Book (1)
- Working Paper (1)
Has Fulltext
- yes (24) (remove)
Keywords
- Mobility (3)
- Public Transport (3)
- Consumer Informatics (2)
- Eco-Feedback (2)
- Modal Shift (2)
- Organizational Culture (2)
- Sustainability (2)
- Sustainable Interaction Design (2)
- Workplace (2)
- Accounting practices (1)
- Administrative work (1)
- Adoption (1)
- Appropriation (1)
- Autonomous vehicles (1)
- Backorder prediction (1)
- Beratung (1)
- Bonn (1)
- CNN (1)
- Co-performance (1)
- Data protection by design (1)
- Design Probe (1)
- Dienstleistung (1)
- Digital Receipt (1)
- Digitalisation (1)
- Digitalisierung (1)
- Domestic Technology (1)
- Domestic workplace studies (1)
- Dynamic passenger information (1)
- Dynamische Fahrgastinformationen (1)
- E-hailing (1)
- Effective purpose specification (1)
- Embodied knowledge (1)
- Empirical Study (1)
- Engaging Experience (1)
- Environmental benefits (1)
- Fahrgastinformation (1)
- Fake review cues (1)
- Fake review detection (1)
- Financial practices (1)
- Food Practices (1)
- Food literacy (1)
- GDPR (1)
- Global explanati (1)
- HCI (1)
- Haltestelle (1)
- Household management (1)
- Human review fraud detection (1)
- Human-food interaction (1)
- Innerstädtische Bushaltestelle (1)
- Integrated Household Information System (1)
- Interactive Artifacts (1)
- IoT (1)
- Local explanation (1)
- Ministerium (1)
- Mixed-methods (1)
- Mobilität (1)
- Multimodal Mobility (1)
- Opinion scam (1)
- Personal thermal comfort (1)
- Personennahverkehr (1)
- Politikberatung (1)
- Practice Theory (1)
- Public transport (1)
- Qualitative Interviews (1)
- Qualitative Study (1)
- Qualitative interviews (1)
- Quantitative survey (1)
- Review scam (1)
- Sachverständigenrat (1)
- Scan and Go (1)
- Self-checkout (1)
- Self-service (1)
- Service expansion (1)
- Shared autonomous vehicles (1)
- Shopping Experience (1)
- Smart Home (1)
- TNC (1)
- Taxi app (1)
- Taxi driver (1)
- UXD (1)
- Urban bus stop (1)
- User-perspective (1)
- Voice Assistants (1)
- Wahrnehmung (1)
- Well-being (1)
- Wissenschaftler (1)
- Wissenstransfer (1)
- autonomous driving (1)
- consumption shifting (1)
- data inadequacy (1)
- eXplainable artifcial intelligence (XAI) (1)
- feature selection (1)
- food waste (1)
- generative adversarial network (1)
- indirect rebound effects (1)
- machine learning (1)
- preference migration (1)
- rebound effects (1)
- shared autonomous vehicles (1)
- travel mode choice (1)
- user preferences (1)
- Öffentlicher Personennahverkehr (1)
- Öffentlichkeit (1)
Improved Thermal Comfort Model Leveraging Conditional Tabular GAN Focusing on Feature Selection
(2024)
The indoor thermal comfort in both homes and workplaces significantly influences the health and productivity of inhabitants. The heating system, controlled by Artificial Intelligence (AI), can automatically calibrate the indoor thermal condition by analyzing various physiological and environmental variables. To ensure a comfortable indoor environment, smart home systems can adjust parameters related to thermal comfort based on accurate predictions of inhabitants’ preferences. Modeling personal thermal comfort preferences poses two significant challenges: the inadequacy of data and its high dimensionality. An adequate amount of data is a prerequisite for training efficient machine learning (ML) models. Additionally, high-dimensional data tends to contain multiple irrelevant and noisy features, which might hinder ML models’ performance. To address these challenges, we propose a framework for predicting personal thermal comfort preferences, combining the conditional tabular generative adversarial network (CTGAN) with multiple feature selection techniques. We first address the data inadequacy challenge by applying CTGAN to generate synthetic data samples, incorporating challenges associated with multimodal distributions and categorical features. Then, multiple feature selection techniques are employed to identify the best possible sets of features. Experimental results based on a wide range of settings on a standard dataset demonstrated state-of-the-art performance in predicting personal thermal comfort preferences. The results also indicated that ML models trained on synthetic data achieved significantly better performance than models trained on real data. Overall, our method, combining CTGAN and feature selection techniques, outperformed existing known related work in thermal comfort prediction in terms of multiple evaluation metrics, including area under the curve (AUC), Cohen’s Kappa, and accuracy. Additionally, we presented a global, model-agnostic explanation of the thermal preference prediction system, providing an avenue for thermal comfort experiment designers to consciously select the data to be collected.