Interaction Design Research Articles

User emotion recognition and indoor space interaction design: a CNN model optimized by multimodal weighted networks

In interior interaction design, achieving intelligent user-interior interaction is contingent upon understanding the user’s emotional responses. Precise identification of the user’s visual emotions holds paramount importance. Current visual emotion recognition methods rely solely on singular features, predominantly facial expressions, resulting in inadequate coverage of visual characteristics and low recognition rates. This study introduces a deep learning-based multimodal weighting network model to address this challenge. The model initiates with a convolutional attention module, employing a self-attention mechanism within a convolutional neural network (CNN). As a result, the multimodal weighting network model is integrated to optimize weights during training. Finally, a weight network classifier is derived from these optimized weights to facilitate visual emotion recognition. Experimental outcomes reveal a 77.057% correctness rate and a 74.75% accuracy rate in visual emotion recognition. Comparative analysis against existing models demonstrates the superiority of the multimodal weight network model, showcasing its potential to enhance human-centric and intelligent indoor interaction design.

Can AI Robot Teaching Improve Children’s Performance in Housework? A Quasi-Experimental Study

Background: The primary objective of this study is to explore the effects of using Artificial Intelligence (AI) robot-assisted instruction in preschool activities on young children’s performance in housework. Methods: A quasi-experimental design was employed, with an experimental group and two control groups, to observe changes in children’s performance in housework before and after AI robot-assisted teaching. The study sample consisted of preschoolers from metropolitan Taipei, with 65 children in the experimental group, 53 in control group 1, and 75 in control group 2. Children participating in the research project required consent from the school, teachers, and parents. The children in the experimental group received AI robot-assisted instruction on household tasks for two days a week over three consecutive weeks, with each session lasting approximately 20–30 min. Control group 1 did not receive any experimental treatment, while control group 2 underwent the same learning schedule and content as the experimental group but was instructed by teachers instead of AI robots. The data were analyzed based on pre- and post-test surveys of parents observing their children’s performance in household tasks. Results: This study found that both AI robot-assisted teaching and teacher-led instruction enhanced children’s household skills, with the AI robot-assisted method showing slightly better results. These findings suggest that both technological tools and teacher guidance can effectively improve children’s housework performance, while artificial intelligence robots may provide young children with motivation and curiosity to learn due to their appearance and interactive design, which deserves further analysis. Conclusion: As technology rapidly advances, young children are exposed to various technological devices at an early age. Integrating technological media into future preschool teaching is inevitable, and leveraging tools like AI robots to support teaching, reduce teacher burden, and diversify instructional methods could be a direction worth considering.

Interactive teaching design of mobile English based on deep learning

Interactive teaching design of mobile English based on deep learning

AI and Thinkable-Assisted learning media for physical education: a descriptive study on collaborative lecturer education

This research aims to determine the role of Artificial Intelligence (AI) and Thunkable interactive learning media application design in cerebrating practices of lecturer education in the context of physical education (PE) methods integrated training. Questions arise on how lecturers can reinforce PE lessons with technologies such as AI and Thunkable and what challenges they face in doing so. This study utilized descriptive research design and data was collected by means of semi-structured interviews with PE lecturers who were knowledgeable about and had utilized AI or Thunkable in their teaching practice. Analysis of quantitative data was also descriptive but focused on transcribing the qualitative data based on, among others, lecturers' technological competence, benefits and challenges of the implementation, student outcome, and qualitative, lecturers' responses. Results found out that despite 70% of lecturers’ awareness of AI in PE lessons, only 30% of them used the available AI tools for the lessons. Out of the few lecturers who attempted to use the Thunkable application, only 25% were able to generate apps which is the focus of the application. Lecturers suggested that students would benefit a lot from AI especially through active participation rewarded by instant feedback without possibilities of concerns being addressed properly due to insufficient training and technical infrastructures. The implications of this study will focus on educational linguistics considering practical uses of AI tools in the language of education in terms of physical education. The use of AI systems in PE lessons can enhance communication and interaction in a multilingual setting that promotes both language and movement skills. This research aims to determine the role of Artificial Intelligence (AI) and Thunkable interactive learning media application design in cerebrating practices of lecturer education in the context of physical education (PE) methods integrated training. Questions arise on how lecturers can reinforce PE lessons with technologies such as AI and Thunkable and what challenges they face in doing so. This study utilized descriptive research design and data was collected by means of semi-structured interviews with PE lecturers who were knowledgeable about and had utilized AI or Thunkable in their teaching practice. Analysis of quantitative data was also descriptive but focused on transcribing the qualitative data based on, among others, lecturers' technological competence, benefits and challenges of the implementation, student outcome, and qualitative, lecturers' responses. Results found out that despite 70% of lecturers’ awareness of AI in PE lessons, only 30% of them used the available AI tools for the lessons. Out of the few lecturers who attempted to use the Thunkable application, only 25% were able to generate apps which is the focus of the application. Lecturers suggested that students would benefit a lot from AI especially through active participation rewarded by instant feedback without possibilities of concerns being addressed properly due to insufficient training and technical infrastructures. The implications of this study will focus on educational linguistics considering practical uses of AI tools in the language of education in terms of physical education. The use of AI systems in PE lessons can enhance communication and interaction in a multilingual setting that promotes both language and movement skills.

Accurate protein-ligand binding free energy estimation using QM/MM on multi-conformers predicted from classical mining minima

Accurate prediction of binding free energy is crucial for the rational design of drug candidates and understanding protein-ligand interactions. To address this, we have developed four protocols that combine QM/MM calculations and the mining minima (M2) method, tested on 9 targets and 203 ligands. Our protocols carry out free energy processing with or without conformational search on the selected conformers obtained from M2 calculations, where their force field atomic charge parameters are substituted with those obtained from a QM/MM calculation. The method achieved a high Pearson’s correlation coefficient (0.81) with experimental binding free energies across diverse targets, demonstrating its generality. Using a differential evolution algorithm with a universal scaling factor of 0.2, we achieved a low mean absolute error of 0.60 kcal mol-1. This performance surpasses many existing methods and is comparable to popular relative binding free energy techniques but at significantly lower computational cost.

Exploring Architectural Tools for Oculus Quest 2

Virtual Reality (VR) has emerged as a pivotal technology in architectural design and education, offering immersive and interactive experiences that surpass traditional methods. This article delves into the diverse applications of VR in architecture, with a particular emphasis on the various software tools utilized in architectural modeling, visualization, and education. The study conducts a thorough examination of both professional and entry-level VR tools and platforms like Blender, Rhino, Unity, and Enscape, which are increasingly integrated into architectural workflows. By providing real-time rendering, interactive design environments, and enhanced spatial understanding, these tools are transforming the way architects and designers conceive and develop their projects. The article also explores the educational implications of VR software such as Tilt Brush, SketchUp Viewer, and Arkio, which offer accessible platforms for students and educators to engage with complex spatial concepts in an intuitive manner. Through comparative analysis, the study highlights the strengths and limitations of these tools, focusing on their usability, accessibility, and relevance to architectural practice and pedagogy. Furthermore, the integration of VR with Building Information Modeling (BIM) is identified as a significant innovation that enhances collaboration and information synchronization throughout the design and construction process. This article provides a comprehensive overview of the current state of VR software in architecture, offering insights into future trends and potential advancements that could further revolutionize the field. The findings underscore VR’s critical role in fostering creativity, improving design accuracy, and enhancing educational experiences, positioning it as a cornerstone technology in the future of architecture.

The Content-Specific Display: Between Medium and Metaphor

This paper examines the current generation of displays, as found primarily in smartphones, laptops and tablet computers, from an interaction design perspective. Today’s displays are multifunctional, versatile devices with a standardized, rectangular shape and a standardized interaction. We distinguish two pitfalls. First, they facilitate an interaction that is isolated and detached from the physical environment in which they are used. Second, their multi-touch interface provides users with few tangible clues and handles. From our background in embodied interaction, we establish an alternate, hypothetical vision of displays: the content-specific display. The content-specific display is defined as a display designed for one specific function and one type of on-screen content. We explore this concept in three student projects from the First Year Master’s program at Product Development, University of Antwerp, and present two key themes that emerge from it: causality and transformation. Both themes reside in the field of coupling, a concept well-known within the field of embodied interaction, and aim at a more seamless integration of on-screen content within the physical world. Finally, we discuss how the content-specific display influences the design process of digital products, and how it fosters collaboration between product designers and designers of graphical user interfaces.

Detecting event-related driving anger with facial features captured by smartphones

Driving anger is a serious global issue that poses risks to road safety, thus necessitating the development of effective detection and intervention methods. This study investigated the feasibility of using smartphones to capture facial expressions to detect event-related driving anger. Sixty drivers completed the driving tasks in scenarios with and without multi-stage road events and were induced to angry and neutral states, respectively. Their physiological signals, facial expressions, and subjective data were collected. Four feature combinations and six machine learning algorithms were used to construct driving anger detection models. The model combining facial features and the XGBoost algorithm outperformed models using physiological features or other algorithms, achieving an accuracy of 87.04% and an F1-score of 85.06%. Eyes, mouth, and brows were identified as anger-sensitive facial areas. Additionally, incorporating individual characteristics into models further improved classification performance. This study provides a contactless and highly accessible approach for event-related driving anger detection. Practitioner Summary: This study proposed a cost-effective and contactless approach for event-related and real-time driving anger detection and could potentially provide insights into the design of emotional interactions in intelligent vehicles.

Examining the factors affecting sustained use in smart interactive cabinet design: A comparative analysis using SEM and fsQCA

Understanding the factors that contribute to sustained user use is critical to the design and marketing of smart interactive cabinets, which have gained great popularity in recent years. This study investigates the factors that impact users' intentions to continue using smart interactive cabinets and examines how these factors influence product design and marketing strategies. However, existing research has mainly focused on the development and performance evaluation of smart interaction technologies, with less attention paid to users' continued willingness to use smart interaction cabinets and their determinants. To address this gap, 304 valid samples were randomly collected for empirical analysis and hypothesis testing, and a questionnaire survey was administered to 304 young Chinese urban Chinese users born in the 1980s and 1990s. By synthesizing and analyzing the usage patterns and influencing factors among young consumers, the study employs a combination of covariance-based structural equation modeling (CB-SEM) and fuzzy-set qualitative comparative analysis (fsQCA) to evaluate the data.The analysis highlights the significance of perceived usefulness, ease of use, and innovation in predicting users' intentions to continue using smart interactive cabinets. This study offers insights into the factors influencing continued use and provides valuable guidance for manufacturers and marketers in designing and marketing smart interactive products to enhance user experience and satisfaction.

Thoughts on the Rational Design of MOF-Guest Interactions for Future Intelligent Materials.

The MOF-guest relationship is broken down in elementary phases, descriptors, and parameters. These descriptors and parameters allow precise descriptions of processes, whether they occur at the point when the guest enters the MOF, during the stay, or at the point of exiting. Description of these three phases is possible according to the location of the guest inside the MOF, the activity between MOF and guest, whether stimuli can be used, and whether a selective action can be exercised. The vocabulary provided herein can be useful to better formulate requirements when designing host-guest interactions in, and building new classes of, intelligent materials.

Art design interventions as a catalyst for sustainable development and infrastructure enhancement in intangible cultural heritage

This study explores the transformative role of art design interventions in the sustainable development and infrastructure enhancement of intangible cultural heritage, with a particular focus on honored brands. The research develops a framework that positions aesthetic and interactive art design interventions as pivotal components in revitalizing these brands. Aesthetic interventions translate the brand’s core philosophy, spirit, and values into compelling visual symbols, harmonizing cultural heritage with modern image design to elevate brand reputation and consumer preference. Interactive interventions enhance user experience, particularly among younger demographics, by integrating technological and entertainment-based engagement, thereby strengthening consumer loyalty and brand influence. The study further investigates how these art design interventions serve as catalysts for broader social development, contributing to the modern relevance and societal impact of time-honored brands. Additionally, it examines the impact of these interventions on sustainable development, societal support, and policy alignment. By weaving together these elements, the research underscores the critical importance of aligning brand strategies with societal goals, fostering environments where brands actively contribute to social welfare and sustainable growth. The findings offer valuable theoretical insights and practical strategies for the sustainable development of time-honored brands, providing clear directions for future research and practice.

Effects of vr-based interactive interior design on the emotional and mental health of office worker

ABSTRACT From the perspective of the evolution of the concept of health, the purpose of mental health is to achieve better living conditions, higher adaptability and development level, and also the best combination of physical and mental well-being and social well-being. According to the literature, the region and privacy of office interior design, the comfort and convenience of office furniture, the charm of office environment and individuation all have an impact on the mental health of office workers. Interactive interior design based on virtual reality can improve the office environment, thus improving the work efficiency and productivity of employees. A comfortable office environment has a positive impact on physical factors for office workers, which is beneficial for improving their mental health. This paper aimed to study how to analyze and study the impact of interactive interior design based on virtual reality (VR) on the emotional and psychological health of office workers. In this paper, the impact of VR interior design was evaluated by fuzzy comprehensive evaluation method, and the analytic hierarchy process (AHP) was used to quantify the weight. In the experiment part of this paper, through the analysis of the questionnaire of the office workers in Chengdu, Sichuan Province, and the comparison of the experimental data, it can be known that before the experiment, the control group and the experimental group were both very healthy, and after the experiment, the psychological health of the two groups was very healthy, which was 0 and 4 people. It can be seen that the psychological health of the workers in the experimental group has changed significantly. This paper studied the influence of VR interaction design on worker’s emotion from the experimental point of view and proved its influence on employee’s emotion from the empirical point of view, which had certain reference significance for future research.

Directed interactive topology optimization design for multi-agent affine formation maneuver control

This paper investigates the directed interactive topology optimization design problem for multi-agent affine formation maneuver control. Firstly, considering the optimization indexes such as information interaction cost and information spreading energy consumption, a directed topology optimization model satisfying affine formation maneuver is established, including two sub-models of topology structure construction and weight allocation. Secondly, aiming at the topological structure construction for affine formation maneuver, a directed k-rooted graph detection method is proposed, which can realize the solution of d +1 -rooted constraint for directed information interaction topology, and then an improved NSGA-II topological structure construction optimization algorithm is designed. Finally, a formation of seven agents in twodimensional space is taken as an example for simulation verification. The results show that the improved topology NSGA -II topology construction optimization The algorithm has better optimization effects, can effectively provide a variety of feasible directed interactive topologies for affine formation maneuver control, and the generated interactive topology can meet the requirements of directed d +1 -rooted graph.

High-throughput magnetic co-doping and design of exchange interactions in topological insulators

High-throughput magnetic co-doping and design of exchange interactions in topological insulators

Intentional or Designed? The Impact of Stance Attribution on Cognitive Processing of Generative AI Service Failures.

With the rapid expansion of the generative AI market, conducting in-depth research on cognitive conflicts in human-computer interaction is crucial for optimizing user experience and improving the quality of interactions with AI systems. However, existing studies insufficiently explore the role of user cognitive conflicts and the explanation of stance attribution in the design of human-computer interactions. This research, grounded in mental models theory and employing an improved version of the oddball paradigm, utilizes Event-Related Spectral Perturbations (ERSP) and functional connectivity analysis to reveal how task types and stance attribution explanations in generative AI influence users' unconscious cognitive processing mechanisms during service failures. The results indicate that under design stance explanations, the ERSP and Phase Locking Value (PLV) in the theta frequency band were significantly lower for emotional task failures than mechanical task failures. In the case of emotional task failures, the ERSP and PLV in the theta frequency band induced by intentional stance explanations were significantly higher than those induced by design stance explanations. This study found that stance attribution explanations profoundly affect users' mental models of AI, which determine their responses to service failure.

Toxicity by Game Design: How Players Perceive the Influence of Game Design on Toxicity

Toxicity in online games refers to behaviors where players disrupt the gaming experience of others, leading to adverse outcomes such as depression and low self-esteem. Although scholars have identified various factors contributing to toxicity, ranging from individual motivations to team dynamics to cultural backgrounds, the role of game design has been less frequently discussed. To bridge this gap, we conducted an interview study to explore players' perceptions of how game design influences toxicity. Our research identified four game design elements that participants perceived as contributing factors to the emergency of toxicity in their experiences: team interdependency, fairness, interaction design, and privacy. These findings help us shed light on how game design unintendedly triggers toxic intentions, exposes players to vulnerability, making them potential victims, and affects player interactions which lead to toxicity. We further propose design implications that can mitigate toxicity in online games.

Ironies of Generative AI: Understanding and Mitigating Productivity Loss in Human-AI Interaction

Generative AI (GenAI) systems offer opportunities to increase user productivity in many tasks, such as programming and writing. However, while they boost productivity in some studies, many others show that users are working ineffectively with GenAI systems and losing productivity. Despite the apparent novelty of these usability challenges, these ‘ironies of automation’ have been observed for over three decades in Human Factors research on the introduction of automation in domains such as aviation, automated driving, and intelligence. We draw on this extensive research alongside recent GenAI user studies to outline four key reasons for productivity loss with GenAI systems: a shift in users’ roles from production to evaluation, unhelpful restructuring of workflows, interruptions, and a tendency for automation to make easy tasks easier and hard tasks harder. We then suggest how Human Factors research can also inform GenAI system design to mitigate productivity loss by using approaches such as continuous feedback, system personalization, ecological interface design, task stabilization, and clear task allocation. Thus, we ground developments in GenAI system usability in decades of Human Factors research, ensuring that the design of human-AI interactions in this rapidly moving field learns from history instead of repeating it.

Comparing typing methods for uppercase input in virtual reality: Modifier Key vs. alternative approaches

Typing tasks are basic interactions in a virtual environment (VE). The presence of uppercase letters affects the meanings of words and their readability. By typing uppercase letters on a QWERTY keyboard, the layers can be switched using a modifier key. Considering that VE controllers are typically used in a VE, this input method can result in user fatigue and errors. Thus, this study proposed new alternative interactions for the modifier key input and compared their typing performance and user experience. In an experiment, 30 participants were instructed to type 10 sentences using different typing interaction methods (shift, long press, and double-tap) on a virtual keyboard in a VE. The typing speed, error rate, and number of backspace inputs were measured to compare typing performance. Upon the completion of the typing task, the usability, workload, and sickness associated with each typing method were evaluated. The results showed that the double-tap method exhibited significantly higher typing speed, error rate, ease of use, satisfaction, and workload. This result is consistent with those of previous studies demonstrating that selection tasks were more efficient with fewer hand movements. Thus, this study implies that the double-tap method can be considered as a potential typing interaction for the VEs instead of the traditional method using the shift as a modifier key. Therefore, this study is expected to contribute to the design and development of user-friendly interactions.

Interactive Interface Design for Adaptive and User Behavioural Habits

This study aims to explore adaptive interaction design in relation to user behavior habits, optimizing the user interface (UI) of mobile applications through statistical analysis of user habits. Specifically, the research analyzes user behavior regarding landscape and portrait browsing modes when using mobile applications. The results indicate that adjusting the UI according to different browsing habits can significantly enhance user satisfaction. Therefore, adaptive interaction design strategies play a crucial role in accommodating user behavior habits, contributing to improved user experience and satisfaction.

CockpitGemini: A personalized design framework for smart vehicle cockpits integrating generative model-based multi-agent systems and human digital twins

The evolution of smart vehicle cockpits is transitioning from serving as mere driving tools to becoming intimate partners that significantly enhance user experiences through advanced technologies. This research addresses the growing demand for personalized design in smart vehicle cockpits by proposing a framework, CockpitGemini. This framework integrates generative model-based multi-agent systems and human digital twins, enabling tailored designs and services based on user preferences and real-time status. The capabilities of the proposed framework are illustrated through four dimensions: personalized product design, personalized interactive interface design, user state monitoring and personalized regulation, and personalized driving strategy recommendations. A case study on the design of personalized vehicle seats demonstrates the feasibility and usability of the CockpitGemini framework, highlighting its potential to enhance user satisfaction in smart vehicle cockpits.