对“密度指数与林分测树因子数学模型”的商榷

从“密度指数与林分测树因子数学模型”所存在的问题出发，对林分密度指数与断面积，平均直径和株数之间的关系模型从数学上进行了推导，提出了正确的参数估计方法，并就拟合数学模型应注意的两个问题，即互为自（因）变量问题与参数一致性估计问题进行了综合讨论。

Quantitative evaluation of urban park cool island factors in mountain city

Evaluating how park characteristics affect the formation of a park cool island(PCI) is the premise of guiding green parks planning in mountain cities.The diurnal variation of PCI intensity was achieved,and correlations between PCI intensity and park characteristics such as park area,landscape shape index(LSI),green ratio and altitude were analyzed,using 3 010 temperature and humidity data from measurements in six parks with typical park characteristics in Chongqing,China.The results indicate that:1) the main factor determining PCI intensity is park area,which leads to obvious cool island effect when it exceeds 14 hm2;2) there is a negative correlation between PCI intensity and LSI,showing that the rounder the park shape is,the better the cool island effect could be achieved;3) regression analysis of humidity and PCI intensity proves that photosynthesis midday depression(PMD) is an important factor causing the low PCI intensity at 13:00;4) the multivariable linear regression model proposed here could effectively well predict the daily PCI intensity in mountain cities.

Comprehensive evaluation of water-inrush risk from coal floors

Lower groups of coal seams are presently being mined from water-inrush from coal floors in order to have safe production in the Yanzhou coal mining area. We need to evaluate the risk in the lower groups of coal seams in mines. Based on a systematic collection of hydrogeological data and some data from mined working faces in these lower groups, we evaluated the factors affecting water-inrush from coal floors of the area by a method of dimensionless analysis. We obtained the order of the factors affecting water-inrush from coal floors and recalculated data on depths of destroyed floors by multiple linear regression analysis and obtained new empirical formulas. We also analyzed the water-inrush coefficient of mined working faces of the lower groups of coal seams and improved the evaluation standard of the water-inrush coefficient method. Finally, we made a comprehensive evaluation of water-inrush risks from coal floors by using the water-inrush coefficient method and a fuzzy clustering method. The evaluation results provide a solid foundation for preventing and controlling the damage caused by water of an Ordovician limestone aquifer in the lower group of coal seams in the mines of Yanzhou. It provides also important guidelines for lower groups of coal seams in other coal mines.

PSYCHOLOGICAL EVALUATION OF COLOR DESIGN

In this paper, a method of predicting psychological values of color design was performed by using random color patterns. The results were analyzed in terms of the Fourier transform of the color patterns, and it was found that the psychological values of the random color patterns depended not only on the zero frequency component but also on the dynamic components of the Fourier transform of the patterns. The application of the estimation method was discussed.

Evaluation of Self Management Behavior of Chronic Kidney Disease Patients

CKD （chronic kidney disease） is a progressive disease. If it is left untreated, it can eventually result in end stage renal failure and necessitate dialysis or kidney transplantation. There is no cure for CKD; instead a great deal of self management over time is essential. The purpose is to evaluate self management behaviour of patients at different stages of CKD. A total of 300 CKD patients were recruited in this cross sectional study from March to July 2015 at nephrology clinic of a tertiary care setting using convenience sampling. Self management behaviour score was determined using in Partners in Health scale and was then compared at different stages of CKD. Demographic and clinical factors contributing to self management behaviour were determined. Results： There was a significant difference in age （p 〈 0.001）, gender （p 〈 0.001）, education level （p 〈 0.001）, marital status （p 〈 0.001）, duration of illness （p 〈 0.001） and number of co-morbidities （p 〈 0.001） among CKD stages. A significant difference in self management behaviour mean score was found among CKD stages （p 〈 0.001）. Post hoc analysis showed self management behaviour mean score for Stage Ⅰ （mean ± SD： 77.81 ± 9.41） was significantly higher than Stage Ⅳ （mean ± SD： 70.53 ± 13.91） and Stage Ⅴ （mean ± SD： 69.54 ± 12.31）. Self management behaviour mean score for Stage Ⅱ （mean ± SD： 78.46 ± 10.01） was significantly higher than Stage Ⅳ and Stage Ⅴ. Multiple linear regression revealed education level （p 〈 0.001） and number of co-morbidities （p = 0.01） as significant predictors of self management behaviour. It can be concluded that special attention should be focused on patients at late stage of CKD, especially those with diabetic nephropathy; low education level and multiple co-morbidities to improve self management behaviour.

Analysis of the Mass Appraisal Model by Using Artificial Neural Network in Kaohsiung City

An accurate assessment of the property value is very important to make a deal, property tax, and mortgage for loan. The mass appraisal system has been developed in some foreign countries, especially in American for a long time. In Taiwan, we still have few experiences in using computer-assisted mass appraisal system, especially using artificial neural network （ANN）. This article has two objectives： （1） to illustrate application of ANN to the Kaohsiung property market by the method of back-propagation. The study is based on the properties data of sales price, we also use multiple regressions in the same data; （2） to evaluate the performance of two models by using the mean absolute percentage error （MAPE） and hit ratio （HR）. This paper finds that using artificial neural network （ANN） is able to overcome multiple regressions＇ methodological problems and also get better performance than multiple regression model （MRA）. These results are useful in helping local government to assess their assessment value.

Man-machine verification of mouse trajectory based on the random forest model

Identifying code has been widely used in man-machine verification to maintain network security.The challenge in engaging man-machine verification involves the correct classification of man and machine tracks.In this study,we propose a random forest(RF)model for man-machine verification based on the mouse movement trajectory dataset.We also compare the RF model with the baseline models(logistic regression and support vector machine)based on performance metrics such as precision,recall,false positive rates,false negative rates,F-measure,and weighted accuracy.The performance metrics of the RF model exceed those of the baseline models.

Comparative evaluation of geological disaster susceptibility using multi-regression methods and spatial accuracy validation

Geological disasters not only cause economic losses and ecological destruction, but also seriously threaten human survival. Selecting an appropriate method to evaluate susceptibility to geological disasters is an important part of geological disaster research. The aims of this study are to explore the accuracy and reliability of multi-regression methods for geological disaster susceptibility evaluation, including Logistic Regression(LR), Spatial Autoregression(SAR), Geographical Weighted Regression(GWR), and Support Vector Regression(SVR), all of which have been widely discussed in the literature. In this study, we selected Yunnan Province of China as the research site and collected data on typical geological disaster events and the associated hazards that occurred within the study area to construct a corresponding index system for geological disaster assessment. Four methods were used to model and evaluate geological disaster susceptibility. The predictive capabilities of the methods were verified using the receiver operating characteristic(ROC) curve and the success rate curve. Lastly, spatial accuracy validation was introduced to improve the results of the evaluation, which was demonstrated by the spatial receiver operating characteristic(SROC) curve and the spatial success rate(SSR) curve. The results suggest that: 1) these methods are all valid with respect to the SROC and SSR curves, and the spatial accuracy validation method improved their modelling results and accuracy, such that the area under the curve(AUC) values of the ROC curves increased by about 3%–13% and the AUC of the success rate curve values increased by 15%–20%; 2) the evaluation accuracies of LR, SAR, GWR, and SVR were 0.8325, 0.8393, 0.8370 and 0.8539, which proved the four statistical regression methods all have good evaluation capability for geological disaster susceptibility evaluation and the evaluation results of SVR are more reasonable than others; 3) according to the evaluation results of SVR, the central-southern Yunnan Province are the highest sus-ceptibility areas and the lowest susceptibility is mainly located in the central and northern parts of the study area.