Refine
H-BRS Bibliography
- yes (90) (remove)
Departments, institutes and facilities
Document Type
- Conference Object (54)
- Article (20)
- Part of a Book (8)
- Report (4)
- Contribution to a Periodical (3)
- Working Paper (1)
Year of publication
Keywords
- User Experience (7)
- Eco-Feedback (4)
- Sustainable Interaction Design (4)
- Verbraucherinformatik (4)
- Kompetenz (3)
- Mobility (3)
- Organisation (3)
- Public Transport (3)
- Self-Driving Cars (3)
- Shared Autonomous Vehicles (3)
Intelligentes Carsharing zur Förderung der urbanen Mobilität - Einfach Teilen : Schlussbericht
(2019)
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.
Durch die Digitalisierung befindet sich die Mobilitätsbranche im starken Umbruch. So wird man bei der Verkehrsmittelwahl zukünftig wohl auch auf selbstfahrende Autos zurückgreifen können. Die Studie erweitert die Verkehrs- und Nutzerakzeptanzforschung, indem unter Berücksichtigung relativer Teilmehrwerte tiefergehend analysiert wird, wie sich die neuen Verkehrsmodi autonomer Privat-PKW, autonomes Carsharing und autonomes Taxi aus heutiger Sicht in den bestehenden Verkehrsmix einsortieren. Hierzu wurde auf Basis der Nutzerpräferenztheorie eine Onlineumfrage (n=172) zu den relativen Mehrwerten der neuen autonomen Verkehrsmodi durchgeführt. Es zeigt sich, dass Nutzer im Vergleich zum PKW bei den autonomen Modi Verbesserungen im Fahrkomfort und in der Zeitnutzung sehen, in vielen anderen Bereichen – insbesondere bei Fahrspaß und Kontrolle – hingegen keine Vorteile oder sogar relative Nachteile sehen. Gegenüber dem ÖPNV bieten die autonomen Modi in fast allen Eigenschaften Mehrwerte. Diese Betrachtung auf Teilnutzenebene liefert eine genauere Erklärung für Nutzerakzeptanz des automatisierten Fahrens.
Digitisation has brought a major upheaval to the mobility sector, and in the future, self-driving cars will probably be one of the transport modes. This study extends transport and user acceptance research by analysing in greater depth how the new modes of autonomous private cars, autonomous carsharing and autonomous taxis fit into the existing traffic mix from today's perspective. It focuses on accounting for relative added value. For this purpose, user preference theory was used as a base for an online survey (n=172) on the relative added value of the new autonomous traffic modes. Results show that users see advantages in the autonomous modes for driving comfort and time utilization whereas, in comparison to conventional cars, in many other areas – especially in terms of driving pleasure and control – they see no advantages or even relative disadvantages. Compared to public transport, the autonomous modes offer added values in almost all characteristics. This analysis at the partwor th level provides a more detailed explanation for user acceptance of automated driving.
Shared Autonomous Vehicles: Potentials for a Sustainable Mobility and Risks of Unintended Effects
(2018)
Automated and connected cars could significantly reduce congestion and emissions through a more efficient flow of traffic and a reduction in the number of vehicles. An increase in demand for driving with autonomous vehicles is also conceivable due to higher comfort and improved quality of time using driverless cars. So far, empirical evidence supporting this hypothesis is missing. To analyze the influence of autonomous driving on mobility behavior and to uncover user preferences, which serve as an indicator for future travel mode choices, we conducted an online survey with a paired comparison of current and future travel modes with 302 German participants. The results do not confirm the hypothesis that ownership will become an outdated model in the future. Instead they suggest that private cars, whether traditional or fully automated, will remain the preferred travel mode. At the same time, carsharing will benefit from full automation more than private cars. However, findings indicate that the growth of carsharing will mainly be at the expense of public transport, showing that more effort should be placed in making public transportation more attractive if sustainable mobility is to be developed.
Innovations in the mobility industry such as automated and connected cars could significantly reduce congestion and emissions by allowing the traffic to flow more freely and reducing the number of vehicles according to some researchers. However, the effectiveness of these sustainable product and service innovations is often limited by unexpected changes in consumption: some researchers thus hypothesize that the higher comfort and improved quality of time in driverless cars could lead to an increase in demand for driving with autonomous vehicles. So far, there is a lack of empirical evidence supporting either one or other of these hypotheses. To analyze the influence of autonomous driving on mobility behavior and to uncover user preferences, which serve as indicators for future travel mode choices, we conducted an online survey with a paired comparison of current and future travel modes with 302 participants in Germany. The results do not confirm the hypothesis that ownership will become an outdated model in the future. Instead they suggest that private cars, whether conventional or fully automated, will remain the preferred travel mode. At the same time, carsharing will benefit from full automation more than private cars. However, the findings indicate that the growth of carsharing will mainly be at the expense of public transport, showing that more emphasis should be placed in making public transport more attractive if sustainable mobility is to be developed.
The megatrends towards both a digital and a usership economy have changed entire markets in the past and will continue to do so over the next decades. In this work, we outline what this change means for possible futures of the mobility sector, taking the combination of trends in both economies into account. Using a sys-tematic, scenario-based trend analysis, we draft four general future scenarios and adapt the two most relevant scenarios to the automotive sector. Our findings show that combing the trends from both economies provides new insights that have often been neglected in literature because of an isolated view on digital technology only. However, service concepts such as self-driving car sharing or self-driving taxis have a great impact at various levels including microeconomic (e.g., service and product design, business models) and macroeconomic (e.g., with regard to ecological, economical, and social impacts). We give a brief outline of these issues and show which business mo dels could be successful in the most likely future scenarios, before we frame strategic implications for today’s automobile manufacturers.
Mobilitäts- und Nachhaltigkeitsforscher sehen sich bei der Erforschung des Mobilitätsverhaltens von Personen mit einer bunten Palette an Erhebungsmethoden konfrontiert. Erweitert wird diese Vielfalt in der letzten Zeit durch die Möglichkeit, dieses Verhalten direkt über die Smartphones der Probanden zu erfassen. Um die Auswahl geeigneter Methoden zu erleichtern, liefert die vorliegende Literaturstudie einen detaillierten Überblick zu Fragestellungen, Daten und Erhebungsmethoden, die im Bereich der Mobilitätsforschung zur Erfassung von Alltagsmobilität eingesetzt werden.
Advocates of autonomous driving predict that the occupation of taxi driver could be made obsolete by shared autonomous vehicles (SAV) in the long term. Conducting interviews with German taxi drivers, we investigate how they perceive the changes caused by advancing automation for the future of their business. Our study contributes insights into how the work of taxi drivers could change given the advent of autonomous driving: While the task of driving could be taken over by SAVs for standard trips, taxi drivers are certain that other areas of their work such as providing supplementary services and assistance to passengers would constitute a limit to such forms of automation, but probably involving a shifting role for the taxi drivers, one which focuses on the sociality of the work. Our findings illustrate how taxi drivers see the future of their work, suggesting design implications for tools that take various forms of assistance into account, and demonstrating how important it is to consider taxi drivers in the co-design of future taxis and SAV services.
Das Konzept des Living Lab ist eine in der Wissenschaft anerkannte Innovations- und Forschungsmethodik. Im betrieblichen Kontext - insbesondere in kleinen und mittleren Unternehmen (KMU) – wird sie bislang jedoch kaum genutzt. Um die Nutzung im kommerziellen Kontext von Smart Home zu erforschen, wird im Forschungsprojekt SmartLive aktuell ein Living Lab zum Thema aufgebaut, bei dem Unternehmen, Forscher sowie ca. 30 teilnehmenden Haushalte die alltägliche Nutzung von kommerziellen, sowie experimentell entwickelten Lösungen untersuchen und neue Interaktionskonzepte gemeinsam erarbeiten. Ferner wurden mit den teilnehmenden Unternehmen Interviews zu deren Entwicklungsprozessen, deren Einstellung zu Usability und User Experience (UUX), sowie den Potenzialen und Möglichkeiten eines Living Labs für KMU geführt. Ziel der Interviews ist es, darauf aufbauend UUX-Dienstleistungen zu identifizieren, die rund um ein kommerziell betriebenes Living Lab angeboten werden können. Hierbei wurde zunächst das Kompetenz-Netzwerk als ein wichtiges Asset eines Living Lab hervorgehoben, da es eine projektförmige Kooperation fördert. Zudem wurde der Bedarf nach flexiblen Dienstleistungen ähnlich einem Baukastensystem deutlich, mit dessen Hilfe relativ kurzfristig als auch nachhaltige innovative Konzepte erprobt, Marketingstrategien entwickelt sowie prototypische Entwicklungen hinsichtlich UUX und technischer Qualität evaluiert werden können.
Informations- und Kommunikationstechnologie (IKT) in den Bereichen Smart Home und Smart Living ist durch die zunehmende Vernetzung des häuslichen Anwendungsfelds mit der Digitalisierung des Stromnetzes, alternativen Möglichkeiten der Energiegewinnung und -speicherung und neuer Mobilitätskonzepte geprägt und zu einem unverzichtbaren Bestandteil privaten wie unternehmerischen Handelns geworden.
In the course of growing online retailing, recommendation systems have become established that derive recommendations from customers’ purchase histories. Recommending suitable food products can represent a lucrative added value for food retailers, but at the same time challenges them to make good predictions for repeated food purchases. Repeat purchase recommendations have been little explored in the literature. These predict when a product will be purchased again by a customer. This is especially important for food recommendations, since it is not the frequency of the same item in the shopping basket that is relevant for determining repeat purchase intervals, but rather their difference over time. In this paper, in addition to critically reflecting classical recommendation systems on the underlying repeat purchase context, two models for online product recommendations are derived from the literature, validated and discussed for the food context using real transaction data of a German stationary food retailer.
Autonomous driving enables new mobility concepts such as shared-autonomous services. Although significant re-search has been done on passenger-car interaction, work on passenger interaction with robo-taxis is still rare. In this paper, we tackle the question of how passengers experience robo-taxis as a service in real-life settings to inform the interaction design. We conducted a Wizard of Oz study with an electric vehicle where the driver was hidden from the passenger to simulate the service experience of a robo-taxi. 10 participants had the opportunity to use the simulated shared-autonomous service in real-life situations for one week. By the week's end, 33 rides were completed and recorded on video. Also, we flanked the study conducting interviews before and after with all participants. The findings provided insights into four design themes that could inform the service design of robo-taxis along the different stages including hailing, pick-up, travel, and drop-off.
Nachhaltiges Innovationsmanagement in KMU: Eine empirische Untersuchung zu Living Labs as a Service
(2016)
Die neue europäische Umweltstrategie der Integrierten Produktpolitik fordert von produzierenden kleinen und mittleren Unternehmen (KMU) eine eigenverantwortliche und produktbezogene Nachhaltigkeitsstrategie. Obgleich die Gestaltung von IKT-Services in nachhaltigkeitsrelevanten Bereichen ein großes Marktpotential verspricht, birgt das Innovationsmanagement für KMU einige Risiken. Um diese Herausforderungen zu adressieren motiviert diese Arbeit Living Labs, als Innovationsinfrastruktur, um den spezifischen Bedarfen von KMU für ein nachhaltiges Innovationsmanagement gerecht zu werden. Auf der Basis von 15 semi-strukturierten Interviews mit 7 KMU, die IKT-Lösungen in den Bereichen Wohnen und Mobilität entwickeln, wurden Herausforderungen sowie etablierte Strategien für ein nachhaltiges Innovationsmanagement erhoben sowie Potenziale und mögliche Risiken von Living Labs exploriert. Die Studie zeigt KMU spezifische Bedarfe auf, die eine Anpassung des Living Lab Ansatzes als Service-Dienstleistungen erforderlich machen.
Critical consumerism is complex as ethical values are difficult to negotiate, appropriate products are hard to find, and product information is overwhelming. Although recommender systems offer solutions to reduce such complexity, current designs are not appropriate for niche practices and use non-personalized intransparent ethics. To support critical consumption, we conducted a design case study on a personalized food recommender system. Therefore, we first conducted an empirical pre-study with 24 consumers to understand value negotiations and current practices, co-designed the recommender system, and finally evaluated it in a real-world trial with ten consumers. Our findings show how recommender systems can support the negotiation of ethical values within the context of consumption practices, reduce the complexity of finding products and stores, and strengthen consumers. In addition to providing implications for the design to support critical consumption practices, we critically reflect on the scope of such recommender systems and its appropriation.
Since stationary self-checkout is widely introduced and well understood, previous research barely examined newer generations of smartphone-based Scan&Go. Especially from a design perspective, we know little about the factors contributing to the adoption of Scan&Go solutions and how design enables consumers to take full advantage of this development rather than being burdened with using complex and unenjoyable systems. To understand the influencing factors and the design from a consumer perspective, we conducted a mixed-methods study where we triangulated data of an online survey with 103 participants and a qualitative study with 20 participants. Based on the results, our study presents a refined and nuanced understanding of technology as well as infrastructure-related factors that influence adoption. Moreover, we present several implications for designing and implementing of Scan&Go in retail environments.