摘要 : The 2023 SDGs report underscores the prolonged disruption of COVID-19 on community living spaces, infrastructure, education, and income equality, exacerbating social and spatial inequality. Against the backdrop of the dual impact of significant events and the emergence of digital technologies, a coherent research trajectory is essential for characterizing social–spatial equity and understanding its influential factors within the urban planning discipline. While prior research emphasized spatial dimensions and mitigated spatial differentiation to ensure urban equity, the complexity of these interconnections necessitates a more comprehensive approach. This study adopts a holistic perspective, focusing on the "social–spatial" dynamics, utilizing social perception (sentiment maps) and spatial differentiation (housing prices index) pre- and post-pandemic to elucidate the interconnected and interactive nature of uneven development at the urban scale. It employs a multi-dimensional methodological framework integrating morphology analysis of housing conditions, GIS analysis of urban amenities, sentiment semantic analysis of public opinion, and multiscale geographically weighted regression (MGWR) analysis of correlation influential factors. Using Suzhou, China, as a pilot study, this research demonstrates how these integrated methods complement each other, exploring how community conditions and resource distribution collectively bolster resilience, thereby maintaining social–spatial equity amidst pandemic disruptions. The findings reveal that uneven resource distribution exacerbates post-pandemic social stratification and spatial differentiation. The proximity of well-maintained ecological environments, such as parks or scenic landmarks, generally exhibits consistency and positive effects on "social–spatial" measurement. Simultaneously, various spatial elements influencing housing prices and social perception show geographic heterogeneity, particularly in areas farther from the central regions of Xiangcheng and Wujiang districts. This study uncovers a bilateral mechanism between social perception and spatial differentiation, aiming to delve into the interdependent relationship between social–spatial equity and built environmental factors. Furthermore, it aspires to provide meaningful references and recommendations for urban planning and regeneration policy formulation in the digital era to sustain social–spatial equity.

摘要 : This study primarily focuses on investigating whether virtual reality scenarios can authentically replicate real-life audio-visual environments. The authenticity of audio-visual environments plays a crucial role in both the design and VR fields today. Only when the authenticity of audio-visual interactive experiences is validated as feasible can virtual reality technology demonstrate positive impacts. We assessed the annoyance levels subjectively under different audio-visual conditions: a real cafeteria environment and a simulated cafeteria environment. Participants were tasked with the same activities in both environments. After each experiment, they indicated their levels of annoyance by completing a questionnaire. The results indicated a significant positive correlation between the overall subjective annoyance levels in both experiments and the subjective annoyance levels associated with different behaviors. This suggests that under identical audio conditions, virtual reality scenarios more effectively replicate the real noise environment. Furthermore, we have uncovered that certain objective factors influence the expression of authenticity. Optimizing these factors may potentially further enhance the feasibility of virtual reality technology in audio-visual environments.

摘要 : Historic dwellings in cities are considered to be an important resource on the way to carbon neutrality because of their great potential for low-carbon renewal. However, in addition to obligatory heritage conservation requirements, there is no uniformity in historic dwellings' operation mode and conditioning equipment, which means detailed carbon emissions accounting is critical but challenging. To estimate the spatio-temporal distribution of carbon emissions from historic dwellings and thus support the development of decarbonization retrofit strategies, this research proposed a low-interventional carbon footprint accounting system based on a digital twin management platform. Multiple digital technologies are applied to monitor and evaluate the occupants' lifestyles, indoor environment, user location, and equipment energy consumption. Based on backend algorithms, the spatio-temporal distribution of carbon emissions is inserted into the building plan to graphically present the evaluation results. Compared with traditional simulation methods, the proposed system enables the automatic updating of energy accounting parameters by fusing multi-source data into one platform, improving accounting efficiency and accuracy simultaneously. A case study in China proves the outstanding performance of the accuracy of accounting results, with an approximate daily spatial error of 20 % and a total accounting error of less than 15 %.

摘要 : As an inevitable part of construction and demolition (C&D) waste, muck has a dreadful environmental impact due its inadequate management by the traditional governance process. This paper therefore focuses on the management of muck generated from C&D waste by utilizing platform governance as an alternative process, which should more effectively contribute to China's circular economy. The study explores the feasibility of providing such a platform governance mode by using Petri net to compare the traditional governance process and platform governance process for the management of muck trucks, and by using Nanjing's muck smart supervision platform as a case study to assess the effectiveness of the platform governance mode. Results from Petri net simulation modeling reveal that the platform governance mode is more effective than the traditional mode, and from the case study it is found that the success of Nanjing's muck waste management can be attributed to the platform governance mode. The platform management approach can therefore contribute to the sustainability of muck waste governance, and is suitable as an integrated and effective management mode for current practices of muck waste management and resource recovery in China. The main finding from the study is that the platform governance mode significantly improves the efficiency of muck waste management as compared with the traditional governance mode and can therefore provide greater economic and environmental benefits as part of a circular economy.

摘要 : Optimizing the operation of chiller plants can reduce energy consumption in heating, ventilation and air conditioning (HVAC) systems and is one of the effective ways to achieve “carbon neutrality” in buildings. Reinforcement learning (RL) demonstrates great potential in this field. However, in real applications, RL continues to face challenges in dealing with extensive state spaces and achieving stable convergence. The main challenge lies in the high coupling and complexity of chiller plant control, making it difficult for RL agents to finely optimize each state during training, resulting in suboptimal control effectiveness. Additionally, as the state space expands, the computation cost and training duration also rise greatly. To address these issues, this paper proposes a clustering-based RL control method. Firstly, the state is divided into more homogeneous subsets by the K-means algorithm. Then, different RL agents are trained based on these subsets, and a public experience pool is established between neighboring agents to enhance the experience exchange. This design makes the training process more context-oriented, enabling agents to learn from similar feature states and reducing the issue of decreased boundary state handling due to state dividing. The experimental results demonstrate that the proposed method achieves 10.1% increase in energy-saving compared to rule-based control, and is close to that of the model-based control. (1.2% difference). Through state clustering, both the learning speed and control effectiveness of the agent are significantly improved. Compared to non-clustered RL, the proposed method reduces the training time by 66.7% and improves the energy saving by 0.9%. © 2023 Elsevier Ltd

摘要 : It is of general concern how poverty concentrates in cities, due to its close association with social equality issues. This research explores this topic at a citywide level. Spatial data of social housing regarding 2008 to 2020 in Shanghai are utilized to examine how the concentration patterns for low-to-moderate-income groups have changed. Multiple methods including spatial autocorrelation analysis, location quotient (LQ), and Mann–Whitney U test were employed to assess the spatial distribution of, and concentration patterns in, social housing, as well as investigating whether the spatial distribution of urban resources was equitable for residents in social housing. We found that the low-to-moderate-income groups were previously concentrated at the boundary of central city and then gradually deconcentrated into a relatively even pattern. However, it is important to note that this process has not effectively facilitated social equality due to the unequitable distribution of urban resources. Consequently, we recommend that policy makers in developing countries pay particular attention to site selection for social housing and the distribution of urban amenities in the future. © 2024 by the authors.

摘要 : The rapid development of urbanization is gradually reducing opportunities for human beings to interact with the natural environment, and environmental pressures have brought about many additional negative emotions for humans. Among them, the mental health problems of college students should be given social attention. Previous research has indicated that natural landscapes exhibit a greater capacity for ameliorating negative emotional states in individuals when compared to urban landscapes. Nevertheless, significant scientific inquiries, such as the uniformity of the rejuvenating effect across distinct categories of natural landscapes and the choice of the optimal plant community for achieving the most potent restorative effect, remain unexplored. This study aimed to address these questions by selecting four plant communities (single-layer grassland, single-layer woodland, tree-grass composite woodland, tree-shrub-grass composite woodland) and using an electroencephalography method to capture the neuroelectric activity of the participants in combination with the Positive and Negative Affect Schedule score to explore the effects of plant community types on emotional recovery. Our results showed that all four plant communities significantly increased positive emotions and significantly reduced negative emotions. Specifically, there was no significant difference in the recovery effect of positive emotions among the four plant community types, but there was a significant difference in the recovery effect of negative emotions. The negative emotion-recovery effect of tree-shrub-grass composite woodland was significantly better than that of tree-grass composite woodland, single-layer grassland, and single-layer woodland, respectively. The electroencephalography findings demonstrated congruence with the behavioral outcomes, revealing a marked elevation in the power of the alpha frequency band within the brain induced by exposure to the tree-shrub-grass composite woodland when compared to exposure to the tree-grass composite woodland, single-layer grassland, and single-layer woodland conditions. The outcomes underscore the superior rejuvenation efficacy of the tree-shrub-grass composite woodland, thereby yielding substantial ramifications for the realms of landscape planning and design.

摘要 : Minority Cultural Heritage (MCH) plays a crucial role in preserving human cultural and historical diversity. In Southwest China, there is a disparity between the abundance of ethnic minority cultural heritage resources and their inadequate protection and development. However, limited by interdisciplinary barriers, research into the distribution patterns of varied MCH in this area remains unexplored, making an initial step towards comprehensive preservation. The study investigates the relationship between MCH distribution and its association with factors of geography, climate, transportation, economics, and demographics, utilizing spatial geographic analysis, Geodetector methods, and social network analysis. The results indicate the following: (1) The distribution of 483 national-level MCH in Southwest China exhibits clustering, with a higher concentration in the southern regions. Honghe Prefecture, Dali Prefecture, and Qiandongnan Prefecture serve as the core areas with high MCH density, accounting for 47.2% of the total concentration. (2) All three categories of MCH show cohesive distribution patterns. cultural heritage clusters in the northern to southeastern regions of Yunnan Province, intangible cultural heritage clusters in the southeastern to southern regions of Guizhou Province, and agricultural cultural heritage clusters in the northern region of Yunnan Province. (3) The distribution of MCH among different ethnic minorities demonstrates polarization. The Yi and Tibetan ethnic groups have a higher quantity and diversity of MCH, while the Qiang, Lisu, and Jingpo ethnic groups have relatively fewer resources. (4) Single-factor analysis reveals that natural factors like the proportion of mountainous areas, river density, and annual average sunshine, as well as human factors like the proportion of minority population, urbanization rate, and road mileage, have the strongest explanatory power for the distribution of MCH. Furthermore, the interaction between these factors and others enhances the explanatory power for the distribution of MCH in Southwest China. This study provides scientific evidence for the assessment, protection, and sustainable development of MCH.

摘要 : In the biomedical literature, entities are often distributed within multiple sentences and exhibit complex interactions. As the volume of literature has increased dramatically, it has become impractical to manually extract and maintain biomedical knowledge, which would entail enormous costs. Fortunately, document-level relation extraction can capture associations between entities from complex text, helping researchers efficiently mine structured knowledge from the vast medical literature. However, how to effectively synthesize rich global information from context and accurately capture local dependencies between entities is still a great challenge. In this paper, we propose a Local to Global Graphical Reasoning framework (LoGo-GR) based on a novel Biased Graph Attention mechanism (B-GAT). It learns global context feature and information of local relation path dependencies from mention-level interaction graph and entity-level path graph respectively, and collaborates with global and local reasoning to capture complex interactions between entities from document-level text. In particular, B-GAT integrates structural dependencies into the standard graph attention mechanism (GAT) as attention biases to adaptively guide information aggregation in graphical reasoning. We evaluate our method on three publicly biomedical document-level datasets: Drug-Mutation Interaction (DV), Chemical-induced Disease (CDR), and Gene-Disease Association (GDA). LoGo-GR has advanced and stable performance compared to other state-of-the-art methods (it achieves state-of-the-art performance with 96.14&#x0025;-97.39&#x0025; F1 on DV dataset, advanced performance with 68.89&#x0025; F1 and 84.22&#x0025; F1 on CDR and GDA datasets, respectively). In addition, LoGo-GR also shows advanced performance on general-domain document-level relation extraction dataset, DocRED, which proves that it is an effective and robust document-level relation extraction framework. Our codes are publicly available at: <uri>https://github.com/Zxy-MLlab/LoGo-GR</uri>. IEEE

摘要 : As China’s urbanization rate continues to rise, new cities are constantly being built, and the popularity of sustainable concepts has led to the development of numerous green infrastructure projects. The increase in green resources has improved the overall urban environment, but this environmental improvement can lead to local stratification and give rise to a phenomenon known as “green gentrification”. Green gentrification can enhance neighborhood vitality but may also lead to negative consequences, such as the displacement of indigenous populations. This study primarily focuses on whether there is residential segregation and social differentiation between indigenous residents and newcomers due to green gentrification and whether they hold different views on green infrastructure. To address these issues and advance the cause of urban fairness and justice, break down neighborhood segregation, and promote community integration, we conducted satisfaction surveys and in-depth personal interviews with indigenous residents and newcomers regarding the Julong Lake facility, their individual circumstances, and the neighborhood relationships. The survey results revealed the following: (1) Both the indigenous residents and the newcomers expressed a relatively high satisfaction with the sports facilities at Julong Lake, but both groups reported a lower satisfaction with the neighborhood relationships. (2) The indigenous residents exhibited a lower satisfaction compared to the newcomers regarding the commercial facilities, social attributes, and green infrastructure surrounding Julong Lake. Additionally, the overall satisfaction with Julong Lake was lower for the indigenous residents compared to the newcomers. We synthesized the survey results and personal interviews with the indigenous residents and the newcomers and arrived at the following conclusions: (1) In the context of urbanization and uneven distribution of green resources in urban areas, the integration of suburban green resources with real estate development has given rise to the new phenomenon of an emerging green middle class, primarily driven by green resources. (2) The new residents exhibited higher satisfaction levels with Julong Lake park attributes and their personal circumstances compared to the long-term residents. This suggests a “green preference” among the new residents, leading to social stratification among the long-term residents driven by cultural aesthetics and value pursuits. The result of this is a stratification and adjacent residential segregation between the long-term residents and the newcomers. (3) The emerging green middle class areas have, on the one hand, promoted the migration of capital, middle-class populations, and green resources to the suburbs, to some extent favoring suburban green development. In conclusion, we hope that this research can help facilitate more equitable allocation of green resources in cities, formulate more optimal green policies, and promote harmonious coexistence and the sharing of the benefits of green development among residents of different income levels in urban areas. © 2023 by the authors.