Introduction: Real-time evaluations of the severity of depressive symptoms are of great significance for the diagnosis and treatment of patients with major depressive disorder (MDD). In clinical practice, the evaluation approaches are mainly based on psychological scales and doctor-patient interviews, which are time-consuming and labor-intensive. Also, the accuracy of results mainly depends on the subjective judgment of the clinician. With the development of artificial intelligence (AI) technology, more and more machine learning methods are used to diagnose depression by appearance characteristics. Most of the previous research focused on the study of single-modal data; however, in recent years, many studies have shown that multi-modal data has better prediction performance than single-modal data. This study aimed to develop a measurement of depression severity from expression and action features and to assess its validity among the patients with MDD.Methods: We proposed a multi-modal deep convolutional neural network (CNN) to evaluate the severity of depressive symptoms in real-time, which was based on the detection of patients’ facial expression and body movement from videos captured by ordinary cameras. We established behavioral depression degree (BDD) metrics, which combines expression entropy and action entropy to measure the depression severity of MDD patients.Results: We found that the information extracted from different modes, when integrated in appropriate proportions, can significantly improve the accuracy of the evaluation, which has not been reported in previous studies. This method presented an over 74% Pearson similarity between BDD and self-rating depression scale (SDS), self-rating anxiety scale (SAS), and Hamilton depression scale (HAMD). In addition, we tracked and evaluated the changes of BDD in patients at different stages of a course of treatment and the results obtained were in agreement with the evaluation from the scales.Discussion: The BDD can effectively measure the current state of patients’ depression and its changing trend according to the patient’s expression and action features. Our model may provide an automatic auxiliary tool for the diagnosis and treatment of MDD.

Recent policy initiatives for urban development have changed the relationships among stakeholders in China’s urban consolidation processes. Building upon Giddens’ (Giddens A (1984) The Constitution of Society: Outline of the Theory of Structuration. Berkeley, CA: University of California Press.) structuration theory and Ostrom’s (Ostrom E (2005) Understanding Institutional Diversity. Princeton, NJ: Princeton University Press) institutional analysis and development thesis, this paper develops a power arena analytic framework, and uses it to examine the new power relations among the stakeholders in a dilapidated residential redevelopment project in Shenzhen. Our findings reveal that Shenzhen’s new approach incentivised the developer to frame a local decision-making structure which aligned the property owners into two broad groups: those who supported the developer, or cooperative, and those who disputed with the developer, or un-cooperative. Shenzhen’s new attempt was unable to balance power distribution between the main stakeholders and caused intense conflicts and poor project outcomes. A range of factors, including passive participation of residents in project preparation, weak mechanisms to curb speculation, and policy inconsistency associated with tiers of governments, were responsible for the poor performance. These findings contribute to the understanding of the complexity in power relations underlying urban development influenced by planning policy.

The walkability of a neighborhood is important for alleviating transport problems and improving the social and physical wellbeing of residents. However, it is unclear to what extent high walkability contributes to positive attitudes about walking and walking experiences on university campuses. In addition, little is known about the extent and mechanism by which walking attitude influences the affective walking experiences of students. Therefore, this study aimed to analyze the relationship between campus walkability and students’ affective walking experience, as well as to explain the role of walking attitude as a mediator of this relationship. To address these issues, data were collected via questionnaires at a Chinese university and analyzed by using the structural equation model. After controlling for personal characteristics, the results indicated that campus walkability had a positive direct and indirect (through walking attitude) association with affective walking experiences. Our findings have proved that walkable campuses are important because they promote positive walking attitudes and walking emotions, which are beneficial to students’ mental health and subjective wellbeing.

Continuous reform efforts in urban China have scaled back direct government intervention by introducing freer land market trials. Anecdotal evidence reveals, however, that the liberal approach has yielded little advantageous result in Shenzhen, where such experiments are pioneered. By building on new institutionalist concepts and analyzing primary and secondary data, this paper demonstrates that deficiencies of formal rules created a policy vacuum, while informal constraints increased project uncertainty. Understanding the interwoven formal and informal institutional deficiencies adds new insights to the literature in explaining project outcomes and urban policy innovations in China’s urban transformation.