In order to evaluate the temporal changes in tree diversity of forest vegetation in Xishuangbanna, Yunnan Province, the study collected tree diversity data from four main forest vegetation in the region through a quadrat survey including tropical rainforest (TRF), tropical coniferous forest (COF), tropical lower mountain evergreen broad-leaved forest (TEBF), tropical seasonal moist forest (TSMF). We extracted the distribution of four forest vegetation in the region in four periods of 1992, 2000, 2009, and 2016 in combination with remote sensing images, using simp son Shannon Wiener and scaling species diversity indexes compare to the differences of tree evenness of four forest vegetation and use the scaling ecological diversity index and grey correlation evaluation model to evaluate the temporal changes of forest tree diversity in the region in four periods. The results show that: (1) The proportion of forest area has a trend of decreasing first and then increasing, which is shown by the reduction from 65.5% in 1992 to 53.42% in 2000, to 52.49% in 2009, and then to 54.73% in 2016. However, the tropical rainforest shows a continuous decreasing trend. (2) There are obvious differences in the contributions of the four kinds of forest vegetation to tree diversity. The order of evenness is tropical rainforest > tropical mountain (low mountain) evergreen broad-leaved forest > warm coniferous forest > tropical seasonal humid forest, and the order of richness is tropical rainforest > tropical mountain (low mountain) evergreen broad-leaved forest > tropical seasonal humid forest > warm coniferous forest, The order of contribution to tree diversity in tropical rainforest > tropical mountain (low mountain) evergreen broad-leaved forest > tropical seasonal humid forest > warm tropical coniferous forest. (3) The tree diversity of tropical rainforests and tropical seasonal humid forests showed a continuous decreasing trend. The tree diversity of forest vegetation in Xishuangbanna in four periods was 1992 > 2009 > 2016 > 2000. The above results show that economic activities are an important factor affecting the biodivesity of Xishuangbanna, and the protection of tropical rainforest is of great significance to maintain the biodiversity of the region.

Intelligent toy design and development talents need to master certain electronic intelligent control, arts and crafts design, product modeling design and other skills. There is a shortage of intelligent toy designers in our country, and toy enterprises are in urgent need of professional and technical personnel engaged in toy product modeling and functional design. Therefore, it is urgent to cultivate intelligent toy design and development talents. This paper explores the necessity of cross-professional training of intelligent toy design and development talents, relies on teachers' scientific research and enterprise projects, etc., takes graduation projects as a breakthrough, pushes back the talent training curriculum system, and proposes an cross-professional collaborative training model. Through cross-professional combination training intelligent toy design talents, so that they have the design thinking of toy designers and a certain degree of electronic engineer design thinking, can better adapt to the rapid development of modern toy design industry, enterprises changing new requirements.

The concept of output-oriented education has been introduced for many years in our country and has been widely used in the process of personnel training in Chinese universities. This paper discusses how the concept of Outcome Based Education can be fully integrated into the process of developing talents in an interdisciplinary and collaborative manner in the context of new engineering. We have made useful explorations in various aspects from curriculum system integration, online teaching resources construction, studio-style course organization mode, rich teaching project library to school-enterprise cooperation project practice, etc., which have improved students' learning effect.

Clustering technics, like k-means and its extended version, fuzzy c-means clustering (FCM) are useful tools for identifying typical behaviours based on various attitudes and responses to well-formulated questionnaires, such as among forensic populations. As more or less standard questionnaires for analyzing aggressive attitudes do exist in the literature, the application of these clustering methods seems to be rather straightforward. Especially, fuzzy clustering may lead to new recognitions, as human behaviour and communication are full of uncertainties, which often do not have a probabilistic nature. In this paper, the cluster analysis of a closed forensic (inmate) population will be presented. The goal of this study was by applying fuzzy c-means clustering to facilitate the wider possibilities of analysis of aggressive behaviour which is treated as a heterogeneous construct resulting in two main phenotypes, premeditated and impulsive aggression. Understanding motives of aggression helps reconstruct possible events, sequences of events and scenarios related to a certain crime, and ultimately, to prevent further crimes from happening.

Vehicle detection stands out as a rapidly developing technology today and is further strengthened by deep learning algorithms. This technology is critical in traffic management, automated driving systems, security, urban planning, environmental impacts, transportation, and emergency response applications. Vehicle detection, which is used in many application areas such as monitoring traffic flow, assessing density, increasing security, and vehicle detection in automatic driving systems, makes an effective contribution to a wide range of areas, from urban planning to security measures. Moreover, the integration of this technology represents an important step for the development of smart cities and sustainable urban life. Deep learning models, especially algorithms such as You Only Look Once version 5 (YOLOv5) and You Only Look Once version 8 (YOLOv8), show effective vehicle detection results with satellite image data. According to the comparisons, the precision and recall values of the YOLOv5 model are 1.63% and 2.49% higher, respectively, than the YOLOv8 model. The reason for this difference is that the YOLOv8 model makes more sensitive vehicle detection than the YOLOv5. In the comparison based on the F1 score, the F1 score of YOLOv5 was measured as 0.958, while the F1 score of YOLOv8 was measured as 0.938. Ignoring sensitivity amounts, the increase in F1 score of YOLOv8 compared to YOLOv5 was found to be 0.06%.

This paper reviews and comments on the evaluation methods of the recreational value of natural landscape resources, pointing out that the current popular TCM method and CVM method both rely too much on the market prediction conclusion and cannot truly reflect the recreational value, and putting forward the idea, specific operation steps and calculation methods of evaluating the recreational value of natural landscape resources with tourism environmental capacity.