从社区到街景：大流行时代建筑环境对行人流动性影响的变化

该研究以墨尔本中央商务区为研究区域，聚焦疫情前、疫情中、疫情后三个阶段，构建整合社区尺度、街道尺度及时间 - 天气维度的多源高分辨率数据集，通过采集多平台多源数据并经异常值剔除、数据分布调整等预处理后，测试 7 种机器学习模型并借助 SHAP 算法分析特征影响，最终发现深度学习模型（尤其是 MLP）预测精度最高，且步行流动对建成环境的依赖从疫情前社区尺度特征主导转向疫情中及疫情后街道尺度特征主导，跨尺度特征交互作用增强，同时疫情引发的步行者对公共交通依赖降低、对绿色开放可步行空间偏好提升等行为变化具有持久性，可为城市韧性提升与规划更新提供实证支撑。
This study takes the Melbourne Central Business District as the research area, focusing on the three stages before the epidemic, during the epidemic, and after the epidemic, and constructs a multi-source high-resolution data set that integrates the community scale, street scale, and time-weather dimensions. By collecting multi-platform multi-source data and preprocessing such as outlier removal and data distribution adjustment, 7 machine learning models were tested and the influence of features was analyzed with the help of the SHAP algorithm. Finally, the deep learning model (especially MLP) has the highest prediction accuracy, and the dependence of pedestrian flow on the built environment has shifted from being dominated by community-scale features before the epidemic to being dominated by street-scale features during and after the epidemic. The interaction of cross-scale features has been enhanced. At the same time, behavioral changes caused by the epidemic such as reduced reliance on public transportation and increased preference for green, open and walkable spaces are durable, which can provide empirical support for improving urban resilience and planning updates.

基于虚拟现实技术的城市建成环境中的行人情感感知：中英文文献比较研究

该文章围绕虚拟现实（VR）技术在城市建成环境行人情绪感知研究中的应用，对 2015-2024 年中国知网（CNKI）和 Web of Science（WOS）数据库中 37 篇中文文献与 113 篇英文文献展开对比综述。研究采用文献计量分析（借助 CiteSpace 工具）与定性分析相结合的方法，梳理了两类文献的发表趋势、研究热点、学科网络及合作模式等：中文文献更侧重具身认知与脑电图（EEG）监测，英文文献则聚焦 VR 在压力恢复和健康评估中的应用；同时发现中文研究虽近年增长迅速但国际合作不足，英文研究起步早且地理分布更广。在此基础上，文章提出 “感官 - 认知 - 情感” 框架及空间干预策略，揭示了城市规划从工程导向向以人为本模式的转变，还探讨了 VR 技术在神经科学、公共卫生等领域的应用潜力与局限（如生态效度、硬件兼容性问题），并为未来跨平台数据标准化、跨文化研究及伦理规范建立等提供了方向，为沉浸式技术、建成环境研究与城市情感福祉交叉领域的后续研究奠定了理论与方法基础。
This article focuses on the application of virtual reality (VR) technology in the study of pedestrian emotion perception in urban built environments, and conducts a comparative review of 37 Chinese documents and 113 English documents in the China National Knowledge Infrastructure (CNKI) and Web of Science (WOS) databases from 2015 to 2024. The study used a combination of bibliometric analysis (with the help of CiteSpace tools) and qualitative analysis to sort out the publication trends, research hotspots, disciplinary networks and cooperation models of the two types of literature: Chinese literature focused more on embodied cognition and electroencephalography (EEG) monitoring, while English literature focused on the application of VR in stress recovery and health assessment. It was also found that although Chinese research has grown rapidly in recent years, international cooperation is insufficient, and English research started earlier and was more geographically distributed. On this basis, the article proposes a "sensory-cognitive-emotion" framework and spatial intervention strategies, reveals the transformation of urban planning from an engineering orientation to a people-centered model, and also discusses the application potential and limitations of VR technology in neuroscience, public health and other fields (such as ecological validity, hardware compatibility issues), and provides directions for future cross-platform data standardization, cross-cultural research and the establishment of ethical norms, laying a theoretical and methodological foundation for subsequent research in the intersection of immersive technology, built environment research and urban emotional well-being.

链接全球视角：中国和国际研究中基于主体的街区级步行性建模的比较回顾

该研究对 2015-2024 年中外基于主体建模（ABM）的街区尺度步行性研究展开对比文献计量分析，借助 VOSviewer 等工具，揭示了两者在研究轨迹、方法路径与制度逻辑上的差异。中国研究呈现政策驱动特征，尤其在 “15 分钟社区生活圈” 政策推动下，聚焦社区更新、适老化设计及公交导向规划；国际研究则由技术创新驱动，整合深度学习、语义分割等方法，关注气候韧性、公平性与流动性复杂性。研究将 ABM 应用划分为五大核心领域，指出两者在数据输入、实施策略等方面的不同，但均认可 ABM 在交通规划、公共卫生及低碳城市建设中的价值。同时，研究明确了数据稀缺、算法局限、伦理担忧等关键挑战，并提出未来研究方向，包括多模态数据融合、与扩展现实结合及制定隐私保护的跨文化建模标准，以此凸显 ABM 作为智能城市模拟工具，在推进适应性、以人为本且可持续的街区规划中的潜力。
This study conducted a comparative bibliometric analysis of block-scale walkability research based on agent modeling (ABM) in China and abroad from 2015 to 2024. With the help of tools such as VOSviewer, it revealed the differences in research trajectories, methodological paths, and institutional logic between the two. Chinese research shows policy-driven characteristics, especially driven by the "15-minute community living circle" policy, focusing on community renewal, aging-friendly design and transit-oriented planning; international research is driven by technological innovation, integrating deep learning, semantic segmentation and other methods, and focusing on climate resilience, equity and mobility complexity. The study divided ABM applications into five core areas and pointed out the differences in data input and implementation strategies between the two, but both recognized the value of ABM in transportation planning, public health and low-carbon city construction. At the same time, the study clarified key challenges such as data scarcity, algorithm limitations, and ethical concerns, and proposed future research directions, including multimodal data fusion, integration with extended reality, and the development of privacy-preserving cross-cultural modeling standards, thereby highlighting the potential of ABM as a smart city simulation tool in promoting adaptive, human-centered, and sustainable neighborhood planning.

评估和优化15分钟后工业化社区生活界的步行性

随着工业转型和15分钟社区生活圈的增长，优化步行性和维护工业遗产是振兴以前工业区的关键。这项研究着重于北京的石景山区，提出了一个综合多源大数据和街头感知的步行性评估框架。使用兴趣点（POI）分类，它是指关键城市设施，行人网络建模和街道视图图像数据的分类，在四个方面开发了步行性友好指数：可访问性，便利性，多样性和安全性。 POI数据提供了有关基本服务的空间分布的见解，而源自openstreetMap的行人网络数据为Wallable Road Network建模。通过语义细分处理的街道视图图像数据用于评估行人途径的质量和安全性。结果表明，由于连通性和土地利用多样性，核心社区表现出较高的步行性友好指数分数，而较旧的和新发达的地区则面临诸如街道不连续性和服务差距之类的挑战。因此，提出了有针对性的优化策略：通过修复零散的小巷并改善网络连接来增强可访问性；通过填充商业和服务设施来促进功能多样性；升级照明，绿化和无障碍基础设施以确保安全；并描述优先区域和平衡的增强区域，以进行差异化改进。这项研究提出了一个可复制的技术框架，其中包括数据采集，模型评估和战略开发，以增强步行性，为全球工业区的振兴提供了宝贵的见解。未来的研究将结合虚拟现实和主观用户反馈，以进一步增强模型对动态时空变化的适应性。
With industrial transformation and the rise in the 15 min community life circle, optimizing walkability and preserving industrial heritage are key to revitalizing former industrial areas. This study, focusing on Shijingshan District in Beijing, proposes a walkability evaluation framework integrating multi-source big data and street-level perception. Using Points of Interest (POI) classification, which refers to the categorization of key urban amenities, pedestrian network modeling, and street view image data, a Walkability Friendliness Index is developed across four dimensions: accessibility, convenience, diversity, and safety. POI data provide insights into the spatial distribution of essential services, while pedestrian network data, derived from OpenStreetMap, model the walkable road network. Street view image data, processed through semantic segmentation, are used to assess the quality and safety of pedestrian pathways. Results indicate that core communities exhibit higher Walkability Friendliness Index scores due to better connectivity and land use diversity, while older and newly developed areas face challenges such as street discontinuity and service gaps. Accordingly, targeted optimization strategies are proposed: enhancing accessibility by repairing fragmented alleys and improving network connectivity; promoting functional diversity through infill commercial and service facilities; upgrading lighting, greenery, and barrier-free infrastructure to ensure safety; and delineating priority zones and balanced enhancement zones for differentiated improvement. This study presents a replicable technical framework encompassing data acquisition, model evaluation, and strategy development for enhancing walkability, providing valuable insights for the revitalization of industrial districts worldwide. Future research will incorporate virtual reality and subjective user feedback to further enhance the adaptability of the model to dynamic spatiotemporal changes.

以接收者为中心的行人噪声烦恼映射：一种使用随机森林、心理声学指标和开源数据的经济高效方法

研究提出了一种以接收者（行人）为中心的交通诱导噪声烦恼映射方法，通过心理声学指标、随机森林建模和开源数据，避免了昂贵的交通流量统计和专有软件的使用，其五步工作流程（数据收集、提取心理声学值、预测建模、测试优化、传播建模）生成了高分辨率的 GIS 噪声烦恼地图，结果显示大都会尺度的烦恼映射在技术上可行且经济实惠，能为步行质量评估、公共空间设计和主动交通政策提供决策支持，同时指出该方法虽未经过主观评估验证，但为城市健康和噪声污染影响研究提供了新工具
A traffic-induced noise annoyance mapping method centered on the recipient (peeder) is proposed. Through psychoacoustic indicators, random forest modeling and open source data, expensive traffic flow statistics and proprietary software are avoided. Its five-step workflow (data collection, psychoacoustic value extraction, prediction modeling, test optimization, and propagation modeling) generates a high-resolution GIS noise annoyance map. The results show that the metropolitan scale annoyance mapping is technically feasible and economical, and can provide decision-making support for walking quality assessment, public space design and active transportation policy. It also points out that although this method has not been subjectively verified, it provides a new tool for urban health and noise pollution impact research.