In recent years, the population growth rate has been gradually declining in China. As the population problem becomes increasingly significant, the accurate prediction of population development trends has become a top priority, used to facilitate national scientific planning and effective decision making. Based on historical data spanning a period of 20 years (1999–2018), this article presents predictions of the populations of 210 prefecture-level cities using the Malthusian model, Unary linear regression model, Logistic model, and Gray prediction model. Furthermore, because the gray prediction model exhibited the highest degree of accuracy in formulating predictions, this study uses the model to predict and analyze future population development trends. The results reveal that the population gap between cities is gradually widening, and the total urban population shows a pattern of rising in middle-tier cities (second-tier cities and third-tier cities) and declining in high-tier cities (first-tier cities and new first-tier cities) and low-tier cities (fourth-tier cities and fifth-tier cities). From the viewpoint of geographical distribution, the population growth rate is basically balanced between the northern part and the southern part of China. In addition, the population growth of the high-tier cities is gradually slowing while the low-tier cities are experiencing a negative growth of population, but middle-tier cities are experiencing skyrocketing population growth. From the viewpoint of regional development, although the development of regional integration has been strengthened over the years, the radiative driving effect of large urban agglomerations and metropolitan areas is relatively limited.

No abstract

The ashy-throated parrotbill ( Paradoxornis alphonsianus) is a sexually monomorphic species with high abundance in Southwest China, which has been widely used as a fighting bird across Guizhou Province, leading it to become one of the most coveted and heavily hunted wild birds in the region at present. Information on the sexes is a fundamental requirement for a wide variety of avian studies. From a conservation perspective, knowledge necessary for quick sexing of this species should be important, as the determination of sex contributes to the understanding of which sexes are used for fighting. Our goal was to develop a quick method that can be used to identify sex of the ashy-throated parrotbill in the field. Seven body traits were measured and compared between the sexes among 124 individual ashy-throated parrotbills, with sex determined by molecular techniques. Data revealed that the male is the larger sex, with significantly greater measurements than the female in bill length, wing length, and middle claw length. The univariate discriminant function based on bill length featured the highest identification accuracy (67.7%). The larger body size of males may have evolved by sexual selection, but additional data are needed to test this hypothesis. This study found that male and female ashy-throated parrotbills are divergent in size, although further efforts are required for a discriminant function with more robust accuracy.

No abstract

In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems. Choosing the algorithm and hyperparameter setting correctly can promote the overall performance greatly, but users often fail to do so due to the absence of knowledge. How to help users to effectively and quickly select the suitable algorithm and hyperparameter settings for the given task instance is an important research topic nowadays, which is known as the CASH problem. In this paper, we design the Auto-Model approach, which makes full use of known information in the related research paper and introduces hyperparameter optimization techniques, to solve the CASH problem effectively. Auto-Model tremendously reduces the cost of algorithm implementations and hyperparameter configuration space, and thus capable of dealing with the CASH problem efficiently and easily. To demonstrate the benefit of Auto-Model, we compare it with classical Auto-Weka approach. The experimental results show that our proposed approach can provide superior results and achieves better performance in a short time.