Refine
Departments, institutes and facilities
Document Type
- Article (29) (remove)
Year of publication
Keywords
- Mobility (3)
- GDPR (2)
- Human Factors In Software Design (2)
- Modal Shift (2)
- Public Transport (2)
- Shared autonomous vehicles (2)
- usable privacy (2)
- Accounting practices (1)
- Administrative work (1)
- Alltagsmobilität (1)
- Automated taxis (1)
- Autonomes Fahren (1)
- Autonomous vehicles (1)
- Backorder prediction (1)
- Bonn (1)
- CNN (1)
- Co-performance (1)
- Computer Aided Software Engineering (1)
- Computer-Assisted Mobility Research (1)
- Consumer Informatics (1)
- Context (1)
- Data literacy (1)
- Data protection by design (1)
- Deployment (1)
- Dienstleistung (1)
- Digital Energy Management (1)
- Digital Plumbing (1)
- Digitalisation (1)
- Digitalisierung (1)
- Domestic workplace studies (1)
- Dynamic passenger information (1)
- Dynamische Fahrgastinformationen (1)
- E-hailing (1)
- Ecosystems (1)
- Effective purpose specification (1)
- Embodied knowledge (1)
- Empirical Study (1)
- Employment (1)
- Environmental benefits (1)
- Fahrgastinformation (1)
- Fake review cues (1)
- Fake review detection (1)
- Financial practices (1)
- Food literacy (1)
- Global explanati (1)
- HCI (1)
- Haltestelle (1)
- Household management (1)
- Human review fraud detection (1)
- Human-food interaction (1)
- Human–Food Interaction (1)
- IIoT (1)
- Innerstädtische Bushaltestelle (1)
- Interview study (1)
- Interviews (1)
- IoT (1)
- Local explanation (1)
- Millennials (1)
- Mobility as a Service (1)
- Mobility behavior (1)
- Mobilität (1)
- Mobilitätsdaten (1)
- Mobilitätserhebung (1)
- Opinion scam (1)
- Organizations (1)
- P2P-Carsharing (1)
- Personal thermal comfort (1)
- Personennahverkehr (1)
- Practice Theory (1)
- Programmer Workbench (1)
- Public transport (1)
- Qualitative Interviews (1)
- Qualitative interviews (1)
- Qualitative research (1)
- Quantitative survey (1)
- Review scam (1)
- SID (1)
- Selbstfahrtechnik (1)
- Self-Driving Cars (1)
- Service expansion (1)
- Shared Autonomous Vehicles (1)
- Sharing Economy (1)
- Sharing economies (1)
- Smart metering (1)
- Social sustainability (1)
- Socio Informatics (1)
- Software (1)
- Sustainability (1)
- TNC (1)
- Taste (1)
- Taxi app (1)
- Taxi driver (1)
- Travel mode choice (1)
- UXD (1)
- Urban bus stop (1)
- Usage Experience (1)
- User-perspective (1)
- Verkehrsmittelwahl (1)
- Voice Assistants (1)
- autonomous driving (1)
- consumption shifting (1)
- data inadequacy (1)
- data visualization (1)
- democratization (1)
- design probe (1)
- eXplainable artifcial intelligence (XAI) (1)
- eco-feedback (1)
- empirical studies in interaction design (1)
- ethnography (1)
- feature selection (1)
- food waste (1)
- generative adversarial network (1)
- indirect rebound effects (1)
- machine learning (1)
- multi-sensory (1)
- organizational management and coordination (1)
- pervasive computing (1)
- preference migration (1)
- privacy preferences (1)
- privacy settings (1)
- process infrastructure (1)
- project management (1)
- rebound effects (1)
- right to access (1)
- shared autonomous vehicles (1)
- smart meters (1)
- software engineering (1)
- sustainability (1)
- travel mode choice (1)
- usability (1)
- user journey (1)
- user preferences (1)
- user studies (1)
- wine (1)
- Öffentlicher Personennahverkehr (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.