Business leaders increasingly rely on mobile devices to examine environmental, social, and governance data when making urgent investment decisions. However, dense sustainability metrics on small screens often overwhelm decision-makers, impairing rapid and confident judgment. This study investigates how touchscreen interaction gestures shape investment intuition. The authors conducted a randomized controlled experiment with 120 experienced executives browsing a mobile dashboard. By isolating gesture continuity as the sole manipulated variable within an otherwise identical interface, they identify a specific interaction-design mechanism that shapes professional cognition. Continuous swiping significantly boosted cognitive fluency and enhanced investment confidence compared with discrete clicking, reducing average reaction time from 51.76 seconds to 45.28 seconds and raising confidence ratings from 69.12 to 78.45 points, without increasing judgment errors.
When learning a second language, individuals often struggle to understand culturally nuanced phrases, leading to significant communication breakdowns in everyday conversations. Existing mobile educational tools focus almost exclusively on surface pronunciation, leaving users helpless when interpreting cultural metaphors literally. To address this practical challenge, the authors developed a mobile application driven by artificial intelligence that delivers real-time multimodal feedback during interactive voice learning. A randomized controlled trial involving 120 language learners evaluated this innovative intervention. The proposed system diagnosed metaphoric misinterpretations with 91.83% accuracy. Thus, the experimental group recorded a significantly higher delayed retention score of 86.1, while the control group scored 64.3. This interactive approach helps reduce cognitive load while bridging deep cultural divides in mobile language education.
Digital art is primarily consumed through two-dimensional screens, engaging only vision and hearing. This unimodal sensory stimulation not only induces perceptual fatigue but also eliminates the tangible, textured qualities of physical art, leaving viewers emotionally detached. To address this sensory overload and lack of embodied connection, the authors present a wearable tactile feedback framework that captures dynamic color, motion, and sound from digital artworks and translates them into synchronized vibrotactile patterns on the skin. In a controlled experiment with sixty participants, this synchronized tactile stimulation significantly distributed the cognitive processing load. Compared with the visual-only condition, the wearable haptic system reduced perceived mental demand by 27.5% and user frustration by 30.9%, while increasing aesthetic immersion by 42.5%. The framework also achieved a low end-to-end system latency of 7.2 ms, enabling responsive, real-time multisensory interaction with digital artworks.
At present, China's cultural and creative design has many problems, such as the superficial use of symbols, the homogenization of visual expression, etc., and falls into the dilemma of the semantic hollowing out of the tangible and godless. In response to the above limitations, this article proposes a data-driven paradigm that integrates image theory and digital technology, focusing on how human-machine collaboration mechanisms can achieve systematic optimization of the intelligent translation and design process of cultural symbols. The study uses Panofsky's three-level theory of image science as the decoding framework, combined with web crawling, computer vision, and natural language processing technologies, to decode the aesthetic consensus of contemporary youth; by fine-tuning the diffusion model through Low-Rank Adaptation, one can train generative artificial intelligence with specific cultural styles and embed them into brand visual projects. This study validates the practical effectiveness of data-driven human-machine collaboration in cultural and creative design.
Individuals dedicate extensive time to interacting with smartphone screens for digital media consumption. Although manipulating devices via spatial hand gestures offers innovative possibilities, executing these gestures on constrained displays frequently induces mental fatigue and distraction. To address this cognitive overload, this study investigates the effect of spatial gesture interaction on cognitive load. The authors propose a three-layer interaction model and evaluate it through experiments involving 60 participants, utilizing eye tracking to compare traditional touch interaction against spatial gestures. The findings indicate that the gesture-based model significantly reduced users' mental workload. Specifically, the initial visual fixation time decreased from 354 ms to 285 ms, while visual search efficiency improved from 2.9 to 3.8 bits/s. Additionally, task completion time was reduced by 22.4%, and subjective immersion increased by 23.1 points.
The rapid proliferation of intelligent devices and mobile applications underscores the need to move beyond static design toward dynamic visual systems that support personalized, context-aware user interactions. Traditional interface design methods are fundamentally insufficient for meeting high user demands for real-time adaptability across multiple scenarios. To address this challenge, an Artificial Intelligence (AI)-driven dynamic visual interface design method is proposed. This mechanism achieves autonomous perception and real-time judgment of complex user behavior, enabling the real-time generation and layout optimization of visual elements. Experimental results confirm that the AI-driven method significantly enhances User Experience (UX) and interaction efficiency within mobile computing environments. This research provides a solid foundational framework for the development of future Human-AI Interaction and adaptive intelligent interfaces.
Visitors exploring a traditional craft workshop often fail to grasp the rich stories embedded in different areas of the physical space, reducing intangible cultural heritage to isolated facts. This study tackles the problem of narrative fragmentation and context detachment in mobile augmented reality heritage experiences. This study investigates the design, evaluation, and use of an innovative handheld augmented reality approach driven by place awareness that couple's mobile visual perception with semantic narrative mapping. A knowledge-graph-driven narrative engine dynamically selects story segments according to the user's real-time location and behavior. A lightweight gesture interface further lowers cognitive load. In a user study with 40 participants at a heritage workshop, the system significantly improved narrative coherence and knowledge acquisition while reducing cognitive load compared to a GPS-based guide, with large effect sizes across all measured outcomes.
Office workers increasingly manage their own lighting environments using mobile devices, yet existing control interfaces—typically slider-based panels—impose high cognitive load and fail to support divided attention in dynamic work settings. This research investigates how a mobile, context-aware recommendation interface can reduce this burden while preserving user agency. This study designed a tablet-based prototype that presents a single task-specific lighting recommendation with three symmetrically weighted actions—accept, adjust, and dismiss—accompanied by a real-time illuminance preview. A mixed-design user study with 36 office workers compared the adaptive interface against a manual control baseline. The adaptive interface reduced perceived workload by 28.6% on the NASA-TLX, improved visual comfort by 41.2%, and achieved significantly higher System Usability Scale (SUS) scores. Interaction logs revealed a 70.4% acceptance rate alongside frequent fine-grained adjustments. The findings offer design implications for mobile interfaces that balance system proactivity with user agency.
With the globalization of mobile advertising, cross-cultural misinterpretation of visual symbols has become a critical bottleneck in mobile human-computer interaction (MHCI), undermining communication effectiveness across diverse audiences. Existing static methods feature superficial cultural encoding and no real-time feedback, failing to meet mobile scenarios' dynamic and low-latency demands. This study proposes an MHCI-oriented intelligent closed-loop framework with three core modules (Encoder-DiagnosticNet-Generator) and a dual-loop architecture: an outer loop for real-time monitoring via the Gap Index and an inner loop for deep adaptation. Using eye-tracking and emotional feedback, it quantifies audience attention and affective responses to optimize alignment. Specifically, an edge-cloud scheme reduces latency by 45ms in weak networks. Validated across three cultural groups (N=180), the framework outperforms traditional models by 12%- 23% and cuts cultural bias by 63%. This study provides a practical, low-latency solution for global brands to realize effective visual communication in mobile scenarios.
Motion capture technologies have expanded opportunities for both digital dance creation and the scientific analysis of contemporary movement. However, significant challenges remain, including limited technical adaptability, tensions between artistic expression and data-driven quantification, and inadequate semantic modeling of complex movement patterns. Traditional dance creation also struggles to accurately restore and analyze complex movements. This study uses embodied cognition and motion morphology quantification to explore motion capture in mobile interactive systems. It establishes standards and a quantitative framework, then validates the approach through an empirical study of the dance work Folding Shadow. Statistical methods verify its effectiveness in creation optimization, style recognition, and emotional modeling. Addressing the rationality of artistic quantification and the necessity of technical application, this paper proposes an integrated framework that balances technical logic and artistic expression. It offers a new interdisciplinary perspective for dance research and mobile human-computer interaction applications in the arts.
Traditional diet and exercise interventions are increasingly constrained by persistent challenges, including low user adherence, delayed or lagging health feedback, and a lack of sufficiently personalized guidance. This study examines artificial intelligence in health behavior intervention and constructs a closed-loop model of "perception-cognition-decision." The perceptual layer realizes the accurate quantification of multimodal health data with the help of computer vision technology. The cognitive layer integrates the digital nudge theory and optimizes the user selection environment through visual presentation and anthropomorphic interaction. The decision-making layer introduces the big language model to upgrade the traditional imperative intervention into a generative dialogue with contextual understanding. The dynamic threshold model of just-in-time adaptive intervention solves the problem of inaccurate intervention timing. The results show that the intervention model can delay the exponential decline of user compliance, which provides a reference for realizing high-precision personalized health management.
As mobile and social media technologies become central to cultural production and dissemination, intangible cultural heritage (ICH) brand logos are increasingly designed, evaluated, and shared within mobile interaction contexts. This study proposes a mobile-oriented multimodal framework for ICH logo generation, integrating visual, textual, and user behavioral data to support human-computer collaborative design. Users interact with multiple logo alternatives through mobile interfaces, while real-time feedback on recognition, aesthetics, and interaction behaviors is collected for iterative optimization. Results from a mobile-based user study show that the proposed approach improves recognition consistency, aesthetic acceptance, and engagement compared to conventional methods. The findings demonstrate the value of multimodal interaction for culturally sensitive brand visualization and contribute empirical insights to mobile human-computer interaction research.
This study first addresses the practical challenges faced by intelligent teaching platforms in supporting clinical teachers' integration of teaching and practice-such as mismatched task recommendations, fragile feedback loops, and the phenomenon of "high activity but low improvement"-and then proposes a multi-loop, closed-loop integration framework grounded in context-aware mobile human-computer interaction (HCI). A comparative study was conducted on 125 clinical teachers (traditional, hybrid, and AI-enhanced groups) using platform logs, questionnaires, and case analyses. Results indicate that the framework significantly shortens feedback cycles, enhances teachers' behavioral activity and competency improvement, with the AI-enhanced path achieving the optimal effect. By integrating clinical context, individual adaptation, and real-time feedback, the mechanism effectively bridges the gap between platform intervention and practical teaching, providing empirical support for the innovation of clinical teachers' intelligent training mechanisms.
Providing timely, personalized feedback in creative graphic design courses remains a persistent challenge. Using AI gives a possible way to solve this problem. This study examines how ArtPattern-AI (an AI-based craft pattern design learning system) affects students’ motivation, engagement, and self-efficacy compared with general AIGC tools. ArtPattern-AI is designed as a lightweight, web-based system accessible across mobile and desktop devices, supporting flexible learning beyond classroom settings. The study used both quantitative and qualitative methods, combining a quasi-experiment with follow-up interviews. A total of 73 undergraduate students from two visual communication design classes took part. The experimental group (35 students) used ArtPattern-AI (AAI-CD), while the control group (38 students) used general AIGC tools (GAI-CD). The results showed that the ArtPattern-AI group did better than the AIGC tool group in motivation, engagement, and self-efficacy. These results suggest that AI can support the development of a more active, student-centered learning environment in creative design education.
This study uses a quasi-experimental design to compare the efficiency of intelligent voice technology and traditional teaching in English listening and speaking. Unlike previous summative evaluation-focused studies, it constructs three dynamic models (interactive opportunity density, effective feedback closed loop, emotional filtering correction) to quantitatively analyze technical intervention’s logic from exercise supply, feedback optimization, and psychological resistance alleviation. Results show intelligent voice technology breaks the “dilution effect” of class size on practice time via whole-class concurrent interaction; its millisecond real-time feedback improves error correction; the low-anxiety human-computer dialogue reduces emotional resistance. The experimental class outperforms the control class in fluency, pronunciation accuracy, and expression completeness, highlighting intelligent technology’s advantages in enhancing listening and speaking teaching effectiveness.
Effective human-machine interaction (HMI) relies on intuitive interfaces that align with human perceptual capabilities. As mobile apps and intelligent systems evolve, optimizing these interfaces becomes critical for enhancing user experience. This paper presents a novel approach to improving HMI design through the optimization of visual perception intensity. By analyzing the visual characteristics of human cone cells, the study divides visual perception levels and establishes visual communication indicators as optimization targets. A mathematical model is developed, incorporating Kalman filters for prediction and adjustment. The results demonstrate a 25.11% improvement in the visual communication index, validating the model's ability to optimize interface brightness and better align with human visual perception. This work provides a significant contribution to the design of adaptive interfaces, advancing the field of human-machine interaction with practical applications in mobile and digital technologies.
With the rapid development of generative artificial intelligence, AI-driven content generation tools are deeply integrated into the creative industry. This paper systematically discusses the application status and potential challenges of artificial intelligence in creative industries. It is found that AI has significantly improved the efficiency of content production, but there are still limitations in emotional expression, cultural context understanding, and originality. At the same time, its wide application has also caused ethical and structural problems such as copyright ownership and creative homogenization. This paper further proposes that man-machine collaboration should be the core paradigm of creative production in the future and calls for the establishment of a governance framework that takes into account technological innovation and humanistic values. These insights offer practical guidance for policymakers, industry practitioners, and scholars seeking to navigate the complex integration of AI within the creative industries.
This study reconceptualizes regional cultural IP packaging as a smartphone-mediated, multimodal HCI interface for cultural meaning-making and value co-creation. Using mobile eye-tracking (N=120), an 18-month longitudinal study (n=850), and multi-city field evaluations, the author identifies a three-stage mechanism: narrative-driven visual design reduces cognitive load, emotional resonance increases willingness to pay (beta=0.18, p<0.01) when moderated by cultural identity, and iterative visual updates strengthen long-term loyalty (r=0.86). These effects are attenuated among older adults. Theoretically, the study extends service-dominant logic to hybrid mobile interfaces; practically, it proposes a lean design protocol emphasizing authentic storytelling, multisensory interaction, and user-informed visual evolution.
As mobile and social media technologies become central to cultural production and dissemination, intangible cultural heritage (ICH) brand logos are increasingly designed, evaluated, and shared within mobile interaction contexts. This study proposes a mobile-oriented multimodal framework for ICH logo generation, integrating visual, textual, and user behavioral data to support human–computer collaborative design. Users interact with multiple logo alternatives through mobile interfaces, while real-time feedback on recognition, aesthetics, and interaction behaviors is collected for iterative optimization. Results from a mobile-based user study show that the proposed approach improves recognition consistency, aesthetic acceptance, and engagement compared to conventional methods. The findings demonstrate the value of multimodal interaction for culturally sensitive brand visualization and contribute empirical insights to mobile human–computer interaction research.
Traditional college art appreciation is often constrained by static instructional formats, limited interactivity, and insufficient mobile accessibility, all of which hinder the development of aesthetic mobility. This study proposes an integrated scheme of AIGC-XR synergy and Mobile HCI, constructing a Mobile HCI-based aesthetic immersion model with three teaching modes. Empirical results show the model reduces cognitive load, improves knowledge retention and aesthetic empathy, and enhances aesthetic mobility, verifying the value of Mobile HCI in fostering critical thinking. This study contributes to the digital transformation of art appreciation education and extends the application of Mobile HCI within the domain of aesthetic learning.
