Ruixuan Li

Public spaces are encountered through changing spatial configurations, yet evidence linking measurable route conditions to in situ emotional valence remains limited. This multi-site observational study examined associations between route-section image-semantic composition, physical spatial attributes, and five-category valence ratings. Twenty participants provided 378 valid ratings across 40 route sections in ten purposively selected public-space sites in Dalian, China, and Nomi and Kanazawa, Japan. Visual composition was derived from 433 quality-screened forward-facing photographs; physical measures included pavement-to-boundary width, element count, and soft-boundary condition and width. Cumulative-logit mixed models included participant and route-section random intercepts and adjusted for sampled setting. We assessed proportional-odds assumptions, 1000 setting-stratified site bootstraps, site-fixed within-site sensitivity, and leave-one-site-out prediction. No image-semantic balance retained an adjusted association. Greater conditional soft-boundary width showed a positive conventional association with more favourable valence in the primary model (β = 0.798; OR = 2.22; BH q < 0.001) and in the within-site analysis (OR = 1.56; BH q = 0.010). Although the conventional Hessian interval excluded the null (95% OR CI 1.62–3.04), the site-bootstrap β interval included zero (−0.003 to 1.404), and the physical-feature model did not improve held-out-site prediction. The finding is therefore a context-bound association requiring replication, not a causal or transferable design rule.

Community parks support everyday leisure, exercise, and social interaction, but how multidimensional microscale spatial and visual features are differently associated with these behavior types continues to warrant further investigation. In particular, semantic composition, spatial form, and low-level visual features have rarely been integrated with video-based behavior recognition and nonlinear modeling at the node level. To address this gap, this study examined behavior-specific nonlinear associations between microscale built-environment features and leisure, exercise, and social behavior in community parks. Using 35 observation nodes in five community parks in Dalian, China, 70 paired video and image samples were collected on weekdays and weekends. Environmental indicators were extracted from static images, while behavioral indicators were derived from video-based behavior recognition and aggregated into behavior proportions. Generalized additive mixed models were used to identify nonlinear associations and key response ranges. Leisure behavior was associated with built vertical interfaces, moderate background depth, and controlled visual stimulation. Recreational equipment proportion showed opposite associations with exercise and social behavior. Low-level visual features captured behavioral differences not fully explained by semantic indicators. These findings provide context-specific quantitative evidence for behavior-oriented assessment and node-level design support in community public spaces.

Parametric simulation is an effective engineering tool for addressing sustainability challenges, yet small-scale thermal comfort assessment remains limited by plugin-hybridizing complexities and workflow inefficiencies. To address these limitations, here we propose a novel comparative workflow that integrates Lands Design and Dragonfly with the assistance of Ladybug-only (LB) and Honeybee (LB&HB) in the Grasshopper model to predict the Universal Thermal Climate Index (UTCI) as the primary indicator. A playground was selected as a sample site to provide a comprehensive training dataset for the extremely hot summer period. Sensitivity analysis was conducted to assess the impact of input uncertainties on model predictions, and the simulation model’s performance was validated against urban–rural microclimate parameters and the calculated UTCI. Among the microclimate results tested, the wind speed and air temperature predictions achieved the highest accuracy (STDE: 0.10 m/s, 0.20 °C). The UTCI simulation of the LB workflow exhibited a strong correlation between calculated UTCI values (R² = 0.90; p = 0.03). Moreover, the agreement between the LB and LB&HB workflows was strong, with simulated UTCI showing good consistency (R² = 0.70–0.80; r = 0.85–0.88). This framework successfully enables real-time UTCI heatmap analysis in simplified cubic neighborhoods. Additionally, it improves the temporal and spatial resolution of thermal predictions, providing designers with critical insights into the algorithms implemented in new workflows to facilitate urban simulation and parametric sustainability.

Crafts are products with both functional and aesthetic properties. Through emotional design, we can enhance not only the functionality of craft products, but also their aesthetic appeal. This study focused on ceramic teapots as a case study, selecting 20 samples from top-selling Chinese and Japanese ceramic teapots on JD.com. Employing machine learning methods, this study explored the relationship between the design features of ceramic teapots and the emotional preferences of young consumers. A classification model was developed and new teapots were designed for validation. The main findings are as follows: 1) The shape of the teapot lid, spout, handle, and body, as well as the color, decoration, and usability of the teapot, significantly influence young people’s emotional preferences. 2) Model evaluation revealed that the accuracies of the binary and ternary classification models established through random forest reached 91.0% and 81.3%, respectively. 3) The proportion of newly designed teapots that aligned with young people’s emotional preferences reached 91.1% (binary classification) and 64.5% (ternary classification), which is higher than the results of the original 20 teapots. In conclusion, this study demonstrates that the relationship between the perceived image and design features of top-selling Chinese and Japanese ceramic teapots can effectively guide the design of ceramic teapot forms and successfully convey the intended image. The established model can be used to evaluate the emotional quality of newly designed teapots, providing data-driven support for designers to create ceramic teapots that resonate with market preferences.

Assessing the visual quality of rural landscapes is pivotal for quantifying ecological services and preserving cultural heritage; however, conventional ecological indicators neglect emotional and cognitive dimensions. To address this gap, the present study proposes a novel visual quality assessment method for rural landscapes that integrates multimodal sentiment classification models to strengthen sustainability metrics. Four landscape types were selected from three representative villages in Dalian City, China, and the physiological signals (EEG, EOG) and subjective evaluations (Beauty Assessment and SAM Scales) of students and teachers were recorded. Binary, ternary, and five-category emotion classification models were then developed. Results indicate that the binary and ternary models achieve superior accuracy in emotional valence and arousal, whereas the five-category model performs least effectively. Furthermore, an ensemble learning approach outperforms individual classifiers in both binary and ternary tasks, yielding a 16.54% increase in mean accuracy. Integrating subjective and objective data further enhances ternary classification accuracy by 7.7% compared to existing studies, confirming the value of multi-source features. These findings demonstrate that a multi-source sentiment computing framework can serve as a robust quantitative tool for evaluating emotional quality in rural landscapes and promoting their sustainable development.

The visual quality assessment of rural landscapes is vital for quantifying ecological ser-vice functions and cultural heritage, yet traditional ecological indicators fail to capture emotional and cognitive experiences. Therefore, this study introduces a meth-od for assessing rural landscape visual quality that integrates a multi-modal emotion classification model to enhance the quantitative drive towards sustainability. The experiment selected four types of landscapes from three representative villages in Dalian, China, collecting physiological data (EOG, EEG) and subjective evaluations (beauty assessment and SAM scale) from participants. Binary, ternary, and five-element classification models were constructed. The results indicate that the bi-nary and ternary classification models yielded the highest accuracy in emotion valence and arousal, while the five-element model demonstrated the lowest performance. Additionally, ensemble learning models outperformed single classifiers in binary and ternary tasks, with an average accuracy improvement of 7.59%. Moreover, the collaborative fusion of subjective and objective data enhanced the accuracy of the ternary classification by 7.7% compared to existing research, confirming the efficacy of multisource features. The findings suggest that the framework based on multi-source affective computing can serve as a quantitative tool for assessing the emotional quality of rural landscapes and promoting the sustainable development of rural areas.

An effective community landscape design consistently impacts thermally comfortable outdoor conditions and climate adaptation. Therefore, constructing sustainable communities requires a resilience assessment of existing built environments for optimal design mechanisms, especially the renewal of thermally resilient communities in densely populated cities. However, the current community only involves green space design and lacks synergistic landscape design for renewing the central community. The main contribution of this study is that it reveals a three-level optimization method to validate the Synergistic Landscape Design Strategies (SLDS) (i.e., planting, green building envelope, water body, and urban trees) for renewing urban communities. A typical Japanese community in central Komatsu City was selected to illustrate the simulation-based design strategies. The microclimate model ENVI-met reproduces communities involving 38 case implementations to evaluate the physiologically equivalent temperature (PET) and microclimate condition as a measure of the thermal environments in humid subtropical climates. The simulation results indicated that the single-family buildings and real estate flats were adapted to the summer thermal mitigation strategy of water bodies and green roofs (W). In small-scale and large-scale models, the mean PET was lowered by 1.4–5.0 °C (0.9–2.3 °C), and the cooling effect reduced mean air temperature by 0.4–2.3 °C (0.5–0.8 °C) and improved humidification by 3.7–15.2% (3.7–5.3%). The successful SLDS provides precise alternatives for realizing Sustainable Development Goals (SDGs) in the renewal of urban communities.

The quality of urban public spaces affects the emotional response of users; therefore, the emotional data of users can be used as indices to evaluate the quality of a space. Emotional response can be evaluated to effectively measure public space quality through affective computing and obtain evidence-based support for urban space renewal. We proposed a feasible evaluation method for multi-type urban public spaces based on multiple physiological signals and ensemble learning. We built binary, ternary, and quinary classification models based on participants’ physiological signals and self-reported emotional responses through experiments in eight public spaces of five types. Furthermore, we verified the effectiveness of the model by inputting data collected from two other public spaces. Three observations were made based on the results. First, the highest accuracies of the binary and ternary classification models were 92.59% and 91.07%, respectively. After external validation, the highest accuracies were 80.90% and 65.30%, respectively, which satisfied the preliminary requirements for evaluating the quality of actual urban spaces. However, the quinary classification model could not satisfy the preliminary requirements. Second, the average accuracy of ensemble learning was 7.59% higher than that of single classifiers. Third, reducing the number of physiological signal features and applying the synthetic minority oversampling technique to solve unbalanced data improved the evaluation ability.