Recently, the deep learning technology has been adopted in the study of traditional village landscape. More precisely, it’s usually used to explore the representation of cultural heritage and the diversity of heritage information. In this study, we comprehensively reviewed these deep learning-related literatures for the evaluation of traditional village landscapes. E.g., the landscape image recognition led by the pixel-level semantic segmentation algorithm and image feature extraction technology enable user-centred exploration and make cultural heritage digitally and visually accessible. By suggesting a analytic framework using the pixel-level semantic segmentation algorithm and extracting image features, we attempted to identify the physical attributes and spatial characteristics of traditional village landscapes and further simulate the value perception thinking of experts and the public. Besides, we analysed the impact factors and correlation mechanism of spatial attributes to provide a scientific basis and technical support for the protection and utilization of traditional villages.

Taking the Economic-Society-Environment system as an open system with complex structures, the coordinated relationship of the three subsystems is the prerequisite for regional sustainable development. Based on statistical data from 7 cities of the East China Sea and the established evaluation system, the comprehensive development level and the coupling coordinative degrees were analysed and predicted by R/S analysis. Comprehensive development slightly increased, with a few fluctuations in Jiaxing, and all of the coastal cities were in the run-in and improving stages for basically coordinative development, except Zhoushan, and were undergoing less imbalanced development in 1995, except Jiaxing, Taizhou, Wenzhou and Ningbo. And the comprehensive development of the cities in the eastern region was higher than the other, but the coupling and coordinative degree were both δ convergent, which illustrated the less regional difference in future. However, the trend of the comprehensive and coupling coordinative development of most coastal cities in future will be opposite to that from 1995 to 2015. To realize coupling coordinative development, it is necessary to take advantage of national strategies and their own competitive advantages and then build an eco-environmental collaborative governance alliance for resource saving and establishing an environmentally friendly society.

Eutrophication caused by excessive nitrogen and phosphorus is an important factor affecting water quality in drinking water sources. Convenient monitoring of eutrophication in water bodies can reduce the use of pesticides and reduce energy consumption, helping to promote ecological and economic development. This study examined the relationship between water eutrophication and the oxidation-reduction potential (ORP). The results showed that various parameters related to eutrophication, such as ammonia nitrogen, total nitrogen, total phosphorus, chlorophyll-a, and cyanobacteria, had correlations with ORP. There is a close relationship between eutrophication and the concentration of cyanobacteria. When cyanobacteria blooms occur in the drinking water source, it may contaminate the drinking water. Because the conventional eutrophication index does not include the concentration of cyanobacteria, principal component analysis (PCA) was utilized to comprehensively analyze these eutrophication-related parameters and obtain the eutrophication-related index, with the cumulative contribution of principal components reaching 81.8%. Different mathematical methods such as neural network model and mathematical fitting were used to study the relationship between ORP and the eutrophication-related index. A three-segment relationship between the ORP and the index was established. This three-stage relationship was confirmed in different reservoirs.

This study utilizes data on cyber-fraud crimes from the Public Security Bureau in Xiaoshan District for the year 2021 as its case study. It examines the spatiotemporal distribution of various types of cyber-fraud and investigates the influencing factors from social and built environments. Additionally, quantile regression models are employed to analyze the variation in the number of cases across different quantiles of the influencing factors. The study reveals significant differences in individual characteristics among victims of different types of fraud. Cyber-fraud occurrences exhibit distinct temporal patterns across various temporal scales, with significant differences in the duration of crimes among different fraud types. Cyber-fraud demonstrates significant spatial clustering, mainly concentrated in residential areas. The results of quantile regression indicate that cyber fraud is influenced by both the built environment and social environment, with noticeable variations in the coefficient of influence across different quantiles of the independent variables.

In recent years, video anomaly detection technology , which can intelligently analyze massive video and quickly find abnormal phenomena, has attracted extensive attention with the wide application of video surveillance technology . To address the complex and diverse problem of abnormal human behavior detection in surveillance videos, a surveillance video abnormal behavior detection and localization supervised method based on the deep network model and the traditional method is proposed. Specifically, we combined AGMM and YOLACT methods to obtain more accurate foreground information by fusing the foreground maps extracted by each technique. To further improve the accuracy , we use the PWC-Net technique to extract features of the foreground images and input them into an anomaly classification model for classification. The proposed method effectively detects and locates the abnormal behavior in the monitoring scene. In addition to the aforementioned methods, this paper also employs YOLOV5 and DeepSORT networks for object detection and tracking in the video, which allows us to track the detected objects for better understanding of the scene in the video. Experiments on the UCSD benchmark dataset and the comparison with state-of-the-art schemes prove the advantages of our method.