Refine
Departments, institutes and facilities
- Institut für Verbraucherinformatik (IVI) (166) (remove)
Document Type
- Conference Object (104)
- Article (44)
- Part of a Book (9)
- Doctoral Thesis (5)
- Report (3)
- Book (monograph, edited volume) (1)
Year of publication
Language
- English (166) (remove)
Keywords
- ICT (8)
- Sustainability (7)
- Dementia (5)
- Exergame (5)
- Shared autonomous vehicles (5)
- Design (4)
- Eco-Feedback (4)
- GDPR (4)
- Global Software Engineering (4)
- Public Transport (4)
- Qualitative research (4)
- User Experience (4)
- Autonomous Driving (3)
- Consumer Informatics (3)
- Exergames (3)
- Fall prevention (3)
- HCI (3)
- Mobility (3)
- Offshoring (3)
- Older adults (3)
- Privacy (3)
- Smart Home (3)
- Sustainable Interaction Design (3)
- Trust (3)
- Wizard of Oz (3)
- Workplace (3)
- software engineering (3)
- usability (3)
- usable privacy (3)
- Adoption (2)
- Appropriation (2)
- Artificial Intelligence (2)
- Augmented Reality (2)
- Business Ethnography (2)
- Claim personal data (2)
- Data literacy (2)
- Data takeout (2)
- Digital Sovereignty (2)
- Empirical Study (2)
- Food (2)
- Global Software Development (2)
- Human Factors In Software Design (2)
- Information Systems (2)
- IoT (2)
- Living Lab (2)
- Machine Learning (2)
- Management (2)
- Methodology (2)
- Modal Shift (2)
- Nachhaltigkeit (2)
- Organizational Culture (2)
- Peer-to-Peer (2)
- Practice Theory (2)
- Qualitative Study (2)
- Qualitative study (2)
- Risk Perception (2)
- Self-Driving Cars (2)
- Service Design (2)
- Shared Autonomous Vehicles (2)
- Social sustainability (2)
- Software (2)
- Taste (2)
- Usable Privacy (2)
- User Acceptance (2)
- User-Centered Design (2)
- Videogame (2)
- Virtual Reality (2)
- Voice Assistants (2)
- autonomous driving (2)
- caregivers (2)
- co-design (2)
- end user development (2)
- feature selection (2)
- interaction design (2)
- machine learning (2)
- participatory design (2)
- prototyping (2)
- rebound effects (2)
- recommender systems (2)
- sustainability (2)
- sustainable mobility (2)
- travel mode choice (2)
- 3D Printer (1)
- AI-Systems (1)
- AR design (1)
- AR development (1)
- AR/VR (1)
- Accessibility (1)
- Accounting practices (1)
- Active and Healthy Aging Technologies (1)
- Active healthy ageing (1)
- Administrative work (1)
- Adoption Factors (1)
- Advances in Design Science Research (1)
- Agile software development (1)
- Alexa (1)
- Appropriation Infras-tructure (1)
- Articulation Work (1)
- Attention mechanism (1)
- Augmented reality en (1)
- Automated taxis (1)
- Automotive UI (1)
- Autonomes Fahren (1)
- Autonomous vehicles (1)
- Backorder prediction (1)
- Balance (1)
- Bayesian Hierarchical Model (1)
- Biometric data (1)
- Black-box models (1)
- Blockchain (1)
- Business Models (1)
- CNN (1)
- Car Interior Design (1)
- Car Management (1)
- Car Telematics (1)
- Care (1)
- Caregiver (1)
- Carsharing (1)
- Case study (1)
- Case-Study (1)
- Co-Design (1)
- Co-performance (1)
- Cognitive processing (1)
- Collaboration and e-Services (1)
- Collaborative design (1)
- Communication breakdown (1)
- Community (1)
- Computer Aided Software Engineering (1)
- Computer Support (1)
- Computing Milieux (1)
- Conceptual model (1)
- Connected Car (1)
- Connected Car Services (1)
- Constructionism (1)
- Consumer protection (1)
- Consumption (1)
- Consumption feedback (1)
- Context (1)
- Context-awareness (1)
- Conversational user interfaces (1)
- Cooperative Work (1)
- Country Risks (1)
- Crisis management (1)
- Curse of dimensionality (1)
- DSGVO (1)
- Data Integration (1)
- Data collection (1)
- Data protection by design (1)
- Data visualization (1)
- Demands of Older Adults (1)
- Deployment (1)
- Design Case Study (1)
- Design Probe (1)
- Design Recommendations (1)
- Design Theory and Practice (1)
- Design-Fiction (1)
- Digital Energy Management (1)
- Digital Plumbing (1)
- Digital Receipt (1)
- Disclosive ethics (1)
- Distribute Software Development (1)
- Domestic Technology (1)
- Domestic workplace studies (1)
- Driving Simulator (1)
- E-Business (1)
- E-hailing (1)
- ELSI (1)
- Economics (1)
- Ecosystems (1)
- Effective purpose specification (1)
- Elderly (1)
- Electric micromobility (1)
- Embodied knowledge (1)
- Empfehlungssystem (1)
- Empfehlungssysteme (1)
- Employment (1)
- End-User Development (1)
- Engaging Experience (1)
- Enterprise Engineering (1)
- Enterprise Information Systems (1)
- Erweiterte Realität <Informatik> de (1)
- Ethnographic Research (1)
- Explanatory dialogues (1)
- Extended reality (1)
- Fake review cues (1)
- Fake review detection (1)
- Financial practices (1)
- Folk theories (1)
- Food Practices (1)
- Food Retail (1)
- Food literacy (1)
- Fully Autonomous Driving (1)
- Future Work (1)
- Game design (1)
- Geteilte autonome Fahrzeuge (1)
- Global explanati (1)
- Grassroots (1)
- Grounded Theory (1)
- Guidelines (1)
- HFI (1)
- Health Technology Design (1)
- Hems (1)
- Home energy management system (1)
- Household management (1)
- Human Factors (1)
- Human autonomy (1)
- Human computer interaction (HCI) (1)
- Human review fraud detection (1)
- Human-Food-Interaction (1)
- Human-Robot Collaboration (1)
- Human-centered computing (1)
- Human-food interaction (1)
- Human-robot interaction (1)
- Human–Food Interaction (1)
- ICT Design (1)
- IIoT (1)
- IT-CMF (1)
- Impaired (1)
- Individual Empowerment (1)
- Indoor-positioning (1)
- Infrastructuring (1)
- Innovation (1)
- Integrated Household Information System (1)
- Integration Platform as a Service (1)
- Integration of New Technologies for the Elderly (1)
- Integration of Technologies for Active and Healthy Aging (1)
- Intelligence Amplification (1)
- Intelligence Augmentation (1)
- Intelligent Process Automation (1)
- Interaction design en (1)
- Interactive Artifacts (1)
- Interaktionsdesign de (1)
- Internationalization (1)
- Internet of Things (1)
- Interpretability (1)
- Interview (1)
- Interview study (1)
- Interviews (1)
- Invisible AI (1)
- Jobs (1)
- Kinect (1)
- Konsum (1)
- Last mile problem (1)
- Learning (1)
- Learning Environments (1)
- Legal Aspects (1)
- Living Labs (1)
- Local explanation (1)
- MR (1)
- Marketplaces (1)
- Mental models (1)
- Methods (1)
- Millennials (1)
- Misconception (1)
- Mixed / augmented reality (1)
- Mixed Reality (1)
- Mixed methods (1)
- Mixed-methods (1)
- Mobile technologies (1)
- Mobility behavior (1)
- Model surrogation (1)
- Multimodal Mobility (1)
- NLP (1)
- Nearshoring (1)
- Negotiation of Taste (1)
- Neuroscience (1)
- Nutzerorientierte Methoden (1)
- Observation (1)
- Older people (1)
- Opinion scam (1)
- Organization Theory (1)
- Organizations (1)
- P2P carsharing (1)
- Participatory Design (1)
- Participatory Design (1)
- Participatory design studies (1)
- Partworth Utilities (1)
- Passengers (1)
- Perceived AI (1)
- Performance (1)
- Personal thermal comfort (1)
- Platform economy (1)
- Policy (1)
- Privacy Awareness (1)
- Privatsphäre (1)
- Programmer Workbench (1)
- Qualitative Research (1)
- Recommender Systems (1)
- Relative Added Value (1)
- Remote Work (1)
- Repeat Purchase Recommendations (1)
- Reputation systems (1)
- Research Trajectories (1)
- Research methods (1)
- Research through Design (1)
- Review scam (1)
- Risk Analysis (1)
- Robo-taxi (1)
- Robotic Process Automation (1)
- Robots (1)
- SID (1)
- SME (1)
- SOS calls (1)
- Scan and Go (1)
- Scenarios (1)
- Scoring (1)
- Second Cockpit (1)
- Second Screen (1)
- Self-checkout (1)
- Self-driving (1)
- Self-service (1)
- Semantic representation (1)
- Sensor-based (1)
- Service expansion (1)
- Service robot (1)
- Sharing economies (1)
- Shopping Experience (1)
- Small to medium-sized enterprises (1)
- Smart metering (1)
- Sociable Technologies (1)
- Social Capital (1)
- Social Media (1)
- Social learning (1)
- Social practice theory en (1)
- Social practices (1)
- Socio Informatics (1)
- Software Development (1)
- Software as a Service (1)
- Soziale Praktiken (1)
- Strategic Planning (1)
- Strength (1)
- Survey (1)
- Sustainable HCI (1)
- TNC (1)
- Taxi (1)
- Taxi app (1)
- Taxi driver (1)
- Technikfolgenabschätzung (1)
- Technology Assessment (1)
- Technology acceptance (1)
- Teleoperation (1)
- Textual entailment (1)
- Theorie der sozialen Praxis (1)
- Transportation (1)
- Travel Mode Choice (1)
- Travel mode choice (1)
- UXD (1)
- Ubiquity (1)
- Unattended Train Operation (1)
- Usability (1)
- Usage Experience (1)
- User Interface Design (1)
- User Requirements (1)
- User centered design (1)
- User feedback (1)
- User studies (1)
- User-oriented methods (1)
- User-perspective (1)
- Users’ repair strategies (1)
- Verbrauch (1)
- Verbraucherinformatik (1)
- Verification systems (1)
- Virtuelle Realität de (1)
- Voice assistant (1)
- Voight-Kampff test (1)
- Wearables (1)
- Web-Tracking (1)
- Well-being (1)
- Word embedding (1)
- Work (1)
- XR (1)
- accessibility information and communication technology (1)
- adl (1)
- appropriation (1)
- augmented reality (1)
- authoring (1)
- authoring tools (1)
- autonomous systems (1)
- car sharing (1)
- carsharing (1)
- computer system (1)
- connected car (1)
- consumer informatics (1)
- consumption shifting (1)
- critical consumerism (1)
- culture (1)
- culture of participation (1)
- data inadequacy (1)
- data literacy (1)
- data science (1)
- data science canvas (1)
- data visualization (1)
- decision support system (1)
- dementia (1)
- democratization (1)
- demographic transition (1)
- design (1)
- design case study (1)
- design probe (1)
- digital fabrication (1)
- digital receipt (1)
- eXplainable artifcial intelligence (XAI) (1)
- eco-feedback (1)
- emergency response (1)
- empirical studies in interaction design (1)
- ethics (1)
- ethnographically informed studies (1)
- ethnography (1)
- evolutionary development (1)
- exergame (1)
- exergames (1)
- explainable AI (1)
- fall prevention (1)
- fall risk (1)
- field study (1)
- food consumption (1)
- food waste (1)
- generative adversarial network (1)
- hardware engineering (1)
- healthcare (1)
- indirect rebound effects (1)
- interface design (1)
- knowledge management (1)
- knowledge sharing practices (1)
- long-term study (1)
- maker communities (1)
- memories (1)
- mixed reality (1)
- mobile computing (1)
- mobility intelligence (1)
- multi-sensory (1)
- nostalgia (1)
- older adults (1)
- organizational management and coordination (1)
- pervasive computing (1)
- practitioners (1)
- preference migration (1)
- privacy preferences (1)
- privacy settings (1)
- process infrastructure (1)
- project management (1)
- prosumption (1)
- qualitative research (1)
- qualitative research methods (1)
- quality of life (1)
- reCAPTCHA (1)
- relatives (1)
- remembering (1)
- right to access (1)
- shared autonomous vehicles (1)
- shared mobility (1)
- sharing (1)
- small enterprises (1)
- smart heating system (1)
- smart meters (1)
- social interactions (1)
- social robots (1)
- social support (1)
- storytelling (1)
- technological platform (1)
- thermal comfort modelling (1)
- universal design (1)
- user interface (1)
- user journey (1)
- user preferences (1)
- user studies (1)
- user study (1)
- user-centered AI (1)
- validity (1)
- virtual reality, XR (1)
- visibility (1)
- wine (1)
Background
Consumers rely heavily on online user reviews when shopping online and cybercriminals produce fake reviews to manipulate consumer opinion. Much prior research focuses on the automated detection of these fake reviews, which are far from perfect. Therefore, consumers must be able to detect fake reviews on their own. In this study we survey the research examining how consumers detect fake reviews online.
Methods
We conducted a systematic literature review over the research on fake review detection from the consumer-perspective. We included academic literature giving new empirical data. We provide a narrative synthesis comparing the theories, methods and outcomes used across studies to identify how consumers detect fake reviews online.
Results
We found only 15 articles that met our inclusion criteria. We classify the most often used cues identified into five categories which were (1) review characteristics (2) textual characteristics (3) reviewer characteristics (4) seller characteristics and (5) characteristics of the platform where the review is displayed.
Discussion
We find that theory is applied inconsistently across studies and that cues to deception are often identified in isolation without any unifying theoretical framework. Consequently, we discuss how such a theoretical framework could be developed.
Exploring Future Work - Co-Designing a Human-robot Collaboration Environment for Service Domains
(2020)
There has been increasing interest in the application of humanoid robots in service domains like retail or care homes in recent years. Here, most use cases focus on serving customer needs autonomously. Frequently, human intervention becomes necessary to support the robot in exceptional situations. However, direct intervention of service operators is often not possible and requires specialized personnel. In a co-design process with 13 service operators from a pharmacy, we designed a remote working environment for human-robot collaboration that enables first-time experiences and collaboration with robots. Five participants took part in an assessment study and reported on their experiences about the utility, usability and user experience. Results show that participants were able to control and train the robot through the remote control environment. We discuss implications of our results for future work in service domains and emphasize a shift of focus from full robot automatization to human-robot collaboration forms.
This article concerns the design and development of Information- and Communication Technology, in particular computer systems in regard to the demographic transition which will influence user capabilities. It is questionable if current applied computer systems are able to meet the requirements of altered user groups with diversified capabilities. Such an enquiry is necessary based on actual forecasts leading to the assumption that the average age of employees in enterprises will increase significantly within the next 50-60 years, while the percentage of computer aided business tasks, operated by human individuals, rises from year to year. This progress will precipitate specific consequences for enterprises regarding the design and application of computer systems. If computer systems are not adapted to altered user requirements, efficient and productive utilisation could be negatively influenced. These consequences constitute the motivation to extend traditional design methodologies and thereby ensure the application of computer systems that are usable, independent of user capabilities.
This article concerns with the accessibility of Business process modelling tools (BPMo tools) and business process modelling languages (BPMo languages). Therefore the reader will be introduced to business process management and the authors' motivation behind this inquiry. Afterwards, the paper will reflect problems when applying inaccessible BPMo tools. To illustrate these problems the authors distinguish between two different categories of issues and provide practical examples. Finally the article will present three approaches to improve the accessibility of BPMo tools and BPMo languages.
In this paper, we provide a participatory design study of a mobile health platform for older adults that provides an integrative perspective on health data collected from different devices and apps. We illustrate the diversity and complexity of older adults’ perspectives in the context of health and technology use, the challenges which follow on for the design of mobile health platforms that support active and healthy ageing (AHA) and our approach to addressing these challenges through a participatory design (PD) process. Interviews were conducted with older adults aged 65+ in a two-month study with the goal of understanding perspectives on health and technologies for AHA support. We identified challenges and derived design ideas for a mobile health platform called “My-AHA”. For researchers in this field, the structured documentation of our procedures and results, as well as the implications derived provide valuable insights for the design of mobile health platforms for older adults.
Daryoush Daniel Vaziri illustrates that the use of mixed methods designs may support the induction of more subtle and complete theories about older adults’ use of technologies for the support of active and healthy aging. The results show that older adults’ social contexts and environments considerably affect their perspectives, practices and attitudes with respect to health, quality of life, well-being and technology use for active and healthy aging support. Results were collected with older adults aged 60+ as well as relevant secondary stakeholders like caregivers, policy makers or health insurance companies.
Background: Falls are common in older adults and can result in serious injuries. Due to demographic changes, falls and related healthcare costs are likely to increase over the next years. Participation and motivation of older adults in fall prevention measures remain a challenge. The iStoppFalls project developed an information and communication technology (ICT)-based system for older adults to use at home in order to reduce common fall risk factors such as impaired balance and muscle weakness. The system aims at increasing older adults’ motivation to participate in ICT-based fall prevention measures. This article reports on usability, user-experience and user-acceptance aspects affecting the use of the iStoppFalls system by older adults.
Methods: In the course of a 16-week international multicenter study, 153 community-dwelling older adults aged 65+ participated in the iStoppFalls randomized controlled trial, of which half used the system in their home to exercise and assess their risk of falling. During the study, 60 participants completed questionnaires regarding the usability, user experience and user acceptance of the iStoppFalls system. Usability was measured with the System Usability Scale (SUS). For user experience the Physical Activity Enjoyment Scale (PACES) was applied. User acceptance was assessed with the Dynamic Acceptance Model for the Re-evaluation of Technologies (DART). To collect more detailed data on usability, user experience and user acceptance, additional qualitative interviews and observations were conducted with participants.
Results: Participants evaluated the usability of the system with an overall score of 62 (Standard Deviation, SD 15.58) out of 100, which suggests good usability. Most users enjoyed the iStoppFalls games and assessments, as shown by the overall PACES score of 31 (SD 8.03). With a score of 0.87 (SD 0.26), user acceptance results showed that participants accepted the iStoppFalls system for use in their own home. Interview data suggested that certain factors such as motivation, complexity or graphical design were different for gender and age.
Conclusions: The results suggest that the iStoppFalls system has good usability, user experience and user acceptance. It will be important to take these along with factors such as motivation, gender and age into consideration when designing and further developing ICT-based fall prevention systems.
IT-accessiblity is often treated as an orphan in companies. Even though the proportion of disabled people is substantial and people become older and more susceptible to disabilities. Besides cost factors, companies often do not have a plan how to implement and control IT-accessibility successfully. However, most companies are familiar with IT-maturity frameworks to evaluate and improve their own IT-infrastructure. It would facilitate dealing with IT-accessibility, if IT-maturity frameworks consider IT-accessibility and provide recommendations and solutions for a successful implementation. Therefore, this article conducts a review of an acknowledged IT-maturity framework with regard to its capability to enable implementation of IT-accessibility in an organization. The first part of this article will illustrate the motivation and background for the authors concern with such a topic. Afterwards the authors will introduce the reader to the reviewed IT-maturity framework and provide basic knowledge on IT-accessibility. The main part of the article will deal with the review of the applied IT-maturity framework and outline examples of critical capabilities for successfully implementing IT-accessibility in an organization. The final section will derive implications and close with planned future research activities in this field.
This paper presents the outcomes of an exploratory field study that examined the social impact of an ICT-based suite of exergames for people with dementia and their caregivers. Qualitative data was collected over a period of 8 months, during which time we studied the daily life of 14 people with dementia and their informal and professional caregivers. We focus on the experiential aspects of the system and examine its social impact when integrated into the daily routines of both people with dementia themselves and their professional and family caregivers. Our findings indicate that relatives were able to regain leisure time, whilst people with dementia were able to recapture certain aspects of their social and daily activities that might otherwise have been lost to them. Results suggest that the system enhanced social-interaction, invigorated relationships, and improved the empowerment of people with dementia and their caregivers to face daily challenges.
Dementia not only affects the cognitive capabilities, especially memory and orientation, but also physical capabilities, which are associated with a decrease of physical activities. Here, ICT can play a major role to improve health, quality of life and wellbeing in older adults suffering from dementia and related stakeholders, such as relatives, professional and informal caregivers. The aim of the presented system is to increase physical and cognitive capabilities of people with dementia and their caregivers to support them in daily life activities, reduce the strain of the caregivers and improve both their wellbeing.
As a result of ageing societies, the prevalence of dementia, and accordingly the need of care is increasing rapidly. Here, the use of ICT-based technologies may facilitate and promote a self-sustaining life-style for people with dementia and their caregivers. The presented poster describes early findings from the project MobiAssist and outlines the ICT-based training system. The system aims to increase the physical and cognitive capabilities of people with dementia, relief the caregivers and improve wellbeing of involved parties.
Insights from an Exergame-Based Training System for People with Dementia and Their Caregivers
(2020)
There has been increasing interest in designing for dementia in recent years. Empirical investigation is now needed of the long-term role of caregivers in appropriating ICTs into the complex daily life of people with dementia (PwD). We present here the outcomes of a 4-month evaluation of the individual, social and institutional impact of a videogame-based training system. The everyday behavior and interactions of 52 PwD and 25 caregivers was studied qualitatively, focusing on the role played by caregivers in integrating the system into daily routines. Our results indicate that the successful appropriation of ICT for PwD depends partly on the physical, cognitive and social benefits for PwD, but especially on the added value perceived by their social care-network. We discuss the need for design in dementia to develop more socially embedded innovations that can address the social actors involved and thus contribute to practical solutions for professional and private care.
Within qualitative interviews we examine attitudes towards driverless cars in order to investigate new mobility services and explore the impact of such services on everyday mobility. We identified three main issues that we would like to discuss in the workshop: (I) Designing beyond a driver-centric approach; (II) Developing mobility services for cars which drive themselves; and (III) Exploring self-driving practices.
The design of self-driving cars is one of the most exciting and ambitious challenges of our days and every day, new research work is published. In order to give an orientation, this article will present an overview of various methods used to study the human side of autonomous driving. Simplifying roughly, you can distinguish between design science-oriented methods (such as Research through Design, Wizard of Oz or driving simulator ) and behavioral science methods (such as survey, interview, and observation). We show how these methods are adopted in the context of autonomous driving research and dis-cuss their strengths and weaknesses. Due to the complexity of the topic, we will show that mixed method approaches will be suitable to explore the impact of autonomous driving on different levels: the individual, the social interaction and society.
The alternative use of travel time is one of the widely discussed benefits of driverless cars. We therefore conducted 14 co-design sessions to examine how people manage their time, to determine how they perceive the value of time in driverless cars and to derive design implications. Our findings suggest that driverless mobility will affect both people’s use of travel time as well as their time management in general. The participants repeatedly stated the desire of completing tasks while traveling to save time for activities that are normally neglected in their everyday life. Using travel time efficiently requires using car space efficiently, too. We found out that the design concept of tiny houses could serve as common design pattern to deal with the limited space within cars and support diverse needs.
Traditionally automotive UI focusses on the ergonomic design of controls and the user experience in the car. Bringing networked sensors into the car, connected cars can provide additional information to car drivers and owners, for and beyond the driving task. While there already are technological solutions, such as mobile applications commercially available, research on users’ information demands in such applications is scarce. We conducted four focus groups to uncover what kind of information users might be interested in to see on a second dashboard. Our findings show that besides control screens of todays’ dashboards, people are also interested in connected car services providing context information for a current driving situation and allowing strategic planning of driving safety or supporting car management when not driving. Our use cases inform the design of content for secondary dashboards for and especially beyond the driving context with a user perspective.
The technological development of the digital computer and new options to collect, store and transfer mass data have changed the world in the last 40 years. Moreover, due to the ongoing progress of computer power, the establishment of the Internet as critical infrastructure and the options of ubiquitous sensor systems will have a dramatic impact on economies and societies in the future. We give a brief overview about the technological basics especially with regard to the exponential growth of big data and current turn towards sensor-based data collection. From this stance, we reconsider the various dimensions of personal data and and market mechanisms that have an impact of data usage and protection.
Who do you trust: Peers or Technology? A conjoint analysis about computational reputation mechanisms
(2020)
Peer-to-peer sharing platforms are taking over an increasingly important role in the platform economy due to their sustainable business model. By sharing private goods and services, the challenge arises to build trust between peers online mostly without any kind of physical presence. Peer rating has been proven as an important mechanism. In this paper, we explore the concept called Trust Score, a computational rating mechanism adopted from car telematics, which can play a similar role in carsharing. For this purpose, we conducted a conjoint analysis where 77 car owners chose between fictitious user profiles. Our results show that in our experiment the telemetric-based score slightly outperforms the peer rating in the decision process, while the participants perceived the peer rating more helpful in retrospect. Further, we discuss potential benefits with regard to existing shortcomings of user rating, but also various concerns that should be considered in concepts like telemetric-based reputation mechanism that supplements existing trust factors such as user ratings.
Focus on what matters: improved feature selection techniques for personal thermal comfort modelling
(2022)
Occupants' personal thermal comfort (PTC) is indispensable for their well-being, physical and mental health, and work efficiency. Predicting PTC preferences in a smart home can be a prerequisite to adjusting the indoor temperature for providing a comfortable environment. In this research, we focus on identifying relevant features for predicting PTC preferences. We propose a machine learning-based predictive framework by employing supervised feature selection techniques. We apply two feature selection techniques to select the optimal sets of features to improve the thermal preference prediction performance. The experimental results on a public PTC dataset demonstrated the efficiency of the feature selection techniques that we have applied. In turn, our PTC prediction framework with feature selection techniques achieved state-of-the-art performance in terms of accuracy, Cohen's kappa, and area under the curve (AUC), outperforming conventional methods.
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.
Due to expected positive impacts on business, the application of artificial intelligence has been widely increased. The decision-making procedures of those models are often complex and not easily understandable to the company’s stakeholders, i.e. the people having to follow up on recommendations or try to understand automated decisions of a system. This opaqueness and black-box nature might hinder adoption, as users struggle to make sense and trust the predictions of AI models. Recent research on eXplainable Artificial Intelligence (XAI) focused mainly on explaining the models to AI experts with the purpose of debugging and improving the performance of the models. In this article, we explore how such systems could be made explainable to the stakeholders. For doing so, we propose a new convolutional neural network (CNN)-based explainable predictive model for product backorder prediction in inventory management. Backorders are orders that customers place for products that are currently not in stock. The company now takes the risk to produce or acquire the backordered products while in the meantime, customers can cancel their orders if that takes too long, leaving the company with unsold items in their inventory. Hence, for their strategic inventory management, companies need to make decisions based on assumptions. Our argument is that these tasks can be improved by offering explanations for AI recommendations. Hence, our research investigates how such explanations could be provided, employing Shapley additive explanations to explain the overall models’ priority in decision-making. Besides that, we introduce locally interpretable surrogate models that can explain any individual prediction of a model. The experimental results demonstrate effectiveness in predicting backorders in terms of standard evaluation metrics and outperform known related works with AUC 0.9489. Our approach demonstrates how current limitations of predictive technologies can be addressed in the business domain.
AI systems pose unknown challenges for designers, policymakers, and users which aggravates the assessment of potential harms and outcomes. Although understanding risks is a requirement for building trust in technology, users are often excluded from legal assessments and explanations of AI hazards. To address this issue we conducted three focus groups with 18 participants in total and discussed the European proposal for a legal framework for AI. Based on this, we aim to build a (conceptual) model that guides policymakers, designers, and researchers in understanding users’ risk perception of AI systems. In this paper, we provide selected examples based on our preliminary results. Moreover, we argue for the benefits of such a perspective.