THE EFFECT OF MISLABELED SAMPLES ON THE PERFORMANCE OF THE LINEAR LEARNING MACHINE

Over the past 15 years the linear learning machine has been applied to a large number of chemicalproblems.The learning machine approach is conceptually simple and does not require knowledge aboutthe statistical distribution of the data.However,there are problems associated with this approach.Oneproblem which has not been investigated is the influence of mislabeled samples on the positioning of thehyerplane in feature space.If a few samples in a data set are incorrectly tagged prior to training(i.e.thesamples are labeled as members of class 2 even though they are actually members of class 1),it is stilIpossible using the linear learning machine to achieve a classification success rate of 100% for the trainingset.However,unfavorable results will be obtained for the prediction set.The magnitude of this effect andits potential implications regarding the proper use of the linear learning machine are discussed.     

STANDARD ERRORS IN THE EIGENVALUES OF A CROSS-PRODUCT MATRIX:THEORY AND APPLICATIONS

New expressions are derived for the standard errors in the eigenvalues of a cross-product matrix by themethod of error propagation.Cross-product matrices frequently arise in multivariate data analysis,especially in principal component analysis (PCA).The derived standard errors account for the variabilityin the data as a result of measurement noise and are therefore essentially different from the standarderrors developed in multivariate statistics.Those standard errors were derived in order to account for thefinite number of observations on a fixed number of variables,the so-called sampling error.They can beused for making inferences about the population eigenvalues.Making inferences about the populationeigenvalues is often not the purposes of PCA in physical sciences,This is particularly true if themeasurements are performed on an analytical instrument that produces two-dimensional arrays for onechemical sample:the rows and columns of such a data matrix cannot be identified with observations onvariables at all.However,PCA can still be used as a general data reduction technique,but now the effectof measurement noise on the standard errors in the eigenvalues has to be considered.The consequencesfor significance testing of the eigenvalues as well as the usefulness for error estimates for scores andloadings of PCA,multiple linear regression (MLR) and the generalized rank annihilation method(GRAM) are discussed.The adequacy of the derived expressions is tested by Monte Carlo simulations.     

美丽中国与国土空间规划关系的地理学思考

The concept of‘Beautiful China'is a new goal of ecological construction in the new era of socialism and aims to meet the needs of people as they strive for a better life.National land spatial planning is one major component of the Chinese state's overall planning for various spatial types.The concept of‘Beautiful China'is thus a leading goal of Chinese development in the second centenary.The background of this concept aims for‘ecological beauty'as well as the combined beauty of‘economy-politics-culture-society-ecology.'The construction of‘Beautiful China'therefore necessitates a differentiated evaluation index system that is built on the basis of local conditions.This concept is intimately related to land spatial planning and the idea of Beautiful China guides an important direction for this planning which itself provides an important mechanism and spatial guarantee for construction.The establishment of land spatial planning nevertheless needs to strengthen further discussion of the regional system of human-land relationship,point axis system,main functional division,sustainable development,resources and environmental carrying capacity as well as new urbanization,and the rural multi-system.The aim of this paper is to summarize current thinking in land spatial planning,scientifically analyze the natural geographical conditions,the socioeconomic development,the interrelationship of the land space,plan the goal,vision and path of land space,encourage the public to participate in and carry out dynamic evaluation,build an intelligent system platform for land and spatial planning to realize the goal of‘Beautiful China'from a geographical perspective.And they can also present key ideas relating to the compilation and implementation of land spatial planning.     

社会生态补偿标准测算方法(英文)

Ecological compensation is a hot subject in academic studies, and the determina-tion of the spatial allocation of compensation payments is a key point in the research of eco-logical compensation. There are two kinds of thoughts in the determination of regional spatial allocation at present: "evaluation of ecological construction cost" and "evaluation of ecosystem services value". This paper analyzes the relationships between social ecological compensation and regional socio-economic development, and establishes two econometric models with the data of 2007 from various provinces in China. Through these models, the impacts of geographical endowments on the regional socio-economic development in various provinces are analyzed from the social justice viewpoint and the concept of "equivalent value of geographical endowments" (EGE for short) is proposed. This paper analyzes the application prospect of EGE in the policy making of regional ecological compensation. The results showed that: (1) the implementation of social ecological compensation is not only an effective guarantee for each region to obtain the equal rights of survival, development and decent environment, but also an essential assurance to the coordinated, balanced and sustainable development among various regions; (2) the regional difference in geographical endowments is an important factor affecting the regional spatial variation of socio-economic development. Therefore, geographical endowments are important bases for the determination of the spatial allocation of compensation payments in social ecological compensation; (3) based on the EGE, the government can determine the spatial allocation of social ecological compensation scientifically, and avoid the "sweeping approach" phenomenon in the policy making process of ecological compensation.     

发展地理学视角下中国区域均衡发展

Large regional differences and uneven regional development are fundamental challenges for China. Balanced regional development is an important issue in research on development geography. This study reviews the course of balanced regional development in China and summarizes its characteristics in each period. The results show that inter-regional development in China has undergone successive periods of balanced and unbalanced development. Each period has enhanced social development and contributed to a more balanced regional development. This paper discusses the scientific connotation of balanced regional development, and invokes sustainable development theory to argue that we should pay attention to the differences in resource endowments among regions, and solves the imbalance among the economy, humans, and nature to promote the spatial balance of regional development and green development for better coordination between economy and ecology. The balanced promotion of the well-being of people in each region is the ultimate goal of balanced regional development. We then use concepts from development geography to examine China’s path of balanced regional development from the three perspectives of society, the economy, and ecology. Suggestions are also provided for the balanced development of China’s regions and the improvement of public well-being.     

SIMPLE VALIDATORY TOOLS FOR JUDGING THE PREDICTIVE PERFORMANCE OF PARAFAC AND THREE-WAY PLS

The methods PARAFAC and three-way PLS are compared with respect to their ability to predictreversed-phase retention values.Special attention is paid to simple validatory tools,the meaning and useof which are explained.The simple validatory tools consist of percentages of explained variation in the training set and thosethat can be calculated with the use of markers.These markers are special(reference)solutes,the retentionvalues of which are used to gain information about a new object for which predictions are wanted.Different validatory tools can be calculated with the use of these marker retention values:percentagesof used variation and mean sum of squared residuals after applying the model to these marker retentionvalues.The validatory tools are evaluated on their power to estimate their test set counterparts:thepercentages of explained variation in the test set and mean sum of squared prediction errors in the test set.Two different data sets from reversed-phase chromatography are used to evaluate the validatory tools.The first data set has a high signal-to-noise ratio and is measured under the same measurementconditions.The second data set has a low signal-to-noise ratio and is measured under differentmeasurement conditions.Some of the simple validatory tools seem to have relevance to their test setcounterparts,even in the case of the second data set.     

THREE-WAY METHODS FOR THE CALIBRATION OF CHROMATOGRAPHIC SYSTEMS:COMPARING PARAFAC AND THREE-WAY PLS

For the calibration of chromatographic systems,different methods can be used.One class of methodsutilizes three-way approaches.The calibration problem is stated in such a way that the decompositionof a three-way array can serve for the prediction of retention on new stationary phases.Two three-way approaches are presented:the Unfold-PCA and PARAFAC models.The theory ofboth methods is presented and the differences are highlighted,the main difference being that PARAFACis a trilinear decomposition whereas Unfold-PCA is not.Both three-way methods are evaluated on asmall data set consisting of retention measurements of eight solutes at six mobile phase compositions onsix stationary phases.The differences in performance of the two models are minor,For calibration purposes,two variants of the methods are discussed:three-way PLS and an extensionof PARAFAC.Again the theory and differences between the two methods are explained.The predictiveperformance of the two methods is compared using the same data set as earlier.The differences inpredictive performance,however,are minor.Both methods are capable of predicting 98% of thevariation in the test sets.Yet,there are other considerations when comparing methods than predictiveperformance,e.g.the quality of the predictions.     

CHARACTERIZATION OF FOODS BY INEXACT RULES:THE SEXIA EXPERT SYSTEM

SEXIA is an expert system that uses a new methodological approach to identify foods,particularly oliveoils according to varieties,olive zones and denominations of origin.The methodological approachprovides identification tools,associating a confidence degree or a belief interval to the final hypotheses.The certainty factor and the Dempster-Shaffer theory,with some modifications,have been implementedin SEXIA.The computer can work with 50 chemical parameters whose data have previously beenacquired by the food analyst via a dialogue in the Spanish language.The system has been verified with144 olive oil samples.In this paper some results obtained for distinguishing the Arbequina variety fromother varieties using SEXIA and the BMDP stepwise discriminant analysis program are presented.Finally,promising directions for future research are suggested.     

Exploring the urban-rural development differences and influencing factors in the Huang-Huai-Hai Plain of China

Uneven urban and rural development is one of the main reasons for the decline of the countryside. This imbalance could be measured by the urban-rural difference index(URDI). Existing studies on urban-rural differences have focused on single dimension between urban and rural areas, and lack a systematic multi-dimensional measurement. Based on the construction of an index system and model for measuring urban-rural differences, this study took the Huang-Huai-Hai Plain(HHHP) as the study area, explores the spatial pattern of urban-rural differences in the area, and used geographical weighted regression models to identify the factors affecting urban-rural development differences. Results show that the mean value of URDI in the HHHP was 0.295, and the URDI in its western region was higher than that in the east. The average URDI was relatively high in the western counties along the Beijing–Guangzhou Railway. The low level of urban-rural "population-land-industry" development in the HHHP is an important reason for the small differences between urban and rural areas. Improvements in road transportation infrastructure have led to an increase in the urban-rural development gap. However, the driving force of the road network on urban development is greater than that on rural areas. The role of county economic agglomeration is gaining strength. In the process of rapid economic development, more attention should be paid to the development of the rural economy and the overall revitalization of the countryside. The equivalent allocation of social service facilities is an effective way to solve the problem of urban-rural imbalance. Further analysis demonstrated that terrain factors have relatively little influence on the URDI. This study provides a new perspective and measurement method for understanding the integration of urban and rural development, and provides a useful reference for guiding the urban-rural integration development and the rural revitalization.     

Problem regions and regional problems of socioeconomic development in China: A perspective from the coordinated development of industrialization,informatization, urbanization and agricultural modernization

Identifying the problem regions and regional problems, and thus improving regional policies, are crucial for the sustainable development of various economic entities. The coordinated development of industrialization, informatization, urbanization and agricultural modernization（hereinafter referred to as ＂Sihua＂） is not only a practical need but an important strategic direction of integrating urban-rural development and regional development in recent China, and it also provides a significant perspective for identifying problem regions and regional problems so as to improve the regional policies. This study mainly aims to： firstly, establish a comprehensive evaluation index system so as to explore the spatial pattern of coordinated development of Sihua in China at prefecture level; secondly, to develop an evaluation criteria system to identify the problem regions and regional problems from the perspective of coordinated development of Sihua. This paper comes first in the scientific community to evaluate the coordinated development state of Sihua in China at prefecture level and identify the problem regions and regional problems from the perspective of Sihua development by quantitative analysis. This study may benefit the improvement of regional policies and thus contribute to the sustainable socio-economic development of China.     

BOX-COX TRANSFORMATIONS IN THE ANALYSIS OF COMPOSITIONAL DATA

The statistical analysis of compositional data is of fundamental importance to practitioners in generaland to chemists in particular.The existing methodology is principally due to Aitchison,who effectivelyuses two transformations,a ratio followed by the logarithmic,to create a useful,coherent theory thatin principle allows the plethora of normal-based multivariate techniques to be used on the transformeddata.This paper suggests that the well-known class of Box-Cox transformations can be employed inplace of the logarithmic to significantly improve the existing methodology.This is supported in part byshowing that one of the most basic problems that Aitchison managed to overcome,namely thespecification of an interpretable covariance structure for compositional data,can be resolved,or nearlyresolved,once the ratio transformation has been applied.Hence the resolution is not directly dependenton the logarithmic transformation.It is then verified that access to the general Box-Cox family will allowa more accurate use of the normal-based multivariate techniques,simply because better fits to normalitycan be achieved.Finally,maximum likelihood estimation and some associated asymptotics are employedto construct confidence intervals for ratios of the true,unknown compositional constituents.Heretoforethis had not been done even in the context of the logarithmic transformation.Applications to real dataare presented.     

CHARACTERIZATION OF THE EFFECT OF PEAK SHIFTS ON THE PERFORMANCE OF THE KALMAN FILTER IN MULTICOMPONENT ANALYSES

The effect of peak shifts on the performance of a Kalman filter multicomponent analysis algorithm hasbeen investigated.A series of Gaussian test systems were employed to characterize the concentrationestimation errors and the morphology of the on-line residuals(the innovations sequence).Both forwardand reverse filters were used in the generation of the innovations sequences.It was found that thedifference between the forward and reverse innovations sequences gave an accurate indication of thedirection and magnitude of the peak shift.A series of overlapped two-component systems were alsoinvestigated.Again,a correlation between the difference innovations and the degree of the responseshift was observed.The behavior of the Katman filter in fitting the shifted fluorescence emissionspectrum of benzo[a]pyrene was also examined.The response for henzo[a]pyrene in cyclohexanesolution was compared to that obtained on the surface of a reversed phase thin layer chromatographyplate.A red shift of 4 nm was detected for the surface spectrum by observing the difference innovationssequence.This approach holds promise for correction of response shifts in multicomponent systems.     

The calculation and analysis of ecological footprints,diversity and development capacity of China

The ecological footprint of China’s provinces is calculated in this paper.In general,China’s development is not sustainable because its ecological footprint is beyond its bio-capacity.The sustainability status of each province in China is presented.Ulanowicz’s developmnt capacity formula was introduced to discuss th relation ship of development and ecological footprint’s diversity.The diversity of ecological impacts is related to the efficiency with which an economy uses the source and sink services of the environment and,in this efficiency with which an economy uses the source and sink services of the environment and ,in this view,should be a factor in economic output.Development capacity,calculated from the ecological footprint and its diversity,is used to examine the relationship o economic output with the structure of the ecological footprint.China and its provinces are presented as a case study to investigate this relationship.The analysis shows that footprint capacity is significant in prdicting economic output.Increasing the ecological footprint’s diversity is presented as another way to increase development capacity.     

BIOGEOCHEMISTRY RESEARCH OF FLUORIDE IN ANTARCTIC OCEAN Ⅱ. THE VARIATION CHARACTERISTICS AND CONCENTRATION CAUSE OF FLUORIDE IN THE CUTICLE OF ANTARCTIC KRILL

The cause of the concentration of fluoride in Antaractic krill is studied by the analysis of the characteristics of fluoride change in the cuticle of the krill before and after moulting. Associated with other related information, the source and accumulating mechanism of fluoride in krill are also disscussed. Results show that as an inorganic medium the cuticle of krill has the second concentrating function and action to fluoride after moulting, which has nothing to do with the biological action of the krill. The fluoride is concentrated from seawater, which is prosecuted mainly in the form of ion exchange.     

EXPERT SYSTEM FOR THE CHARACTERIZATION OF LABORATORY SAMPLE INPUT SIGNALS:AUTOCORR

An expert system is presented for automated time series analysis of laboratory sample input signals.Thesystem,AUTOCORR,builds a model of the time series by identifying the processes that are present.These are an uncorrelated random process and,underlying this,possibly one or more of the following:a first-order autoregressive process,a trend and a periodic process.AUTOCORR has a knowledge baseof 44 rules and 41 facts for this purpose.The employed shell,INFER,allows the use of algorithmicprocedures.Elaborate tests with simulated signals show that AUTOCORR has a very low false positivescore and is successful in describing time series for laboratory simulation models.     

STUDIES ON THE BHQ ICE CORE FROM THE LAW DOME, ANTARCTICA

The structure of the ice core varies with depth, Its surface layer is firn, followed by an ice layer with random fabric pattern (beginning at 28m depth), then transformed to a small circle girdle pattern (beginning at 147 m depth) through a transition layer, finally to a single-maximum pattern (beginning at 191 m depth). The stratigraphic profile of the ice core is similar to those of other cores on the Law Dome, For BHQ located in the middle of a flow line from the summit to the coast, the initial depth of every specific layer is less than that in the upstream and larger than that in the downstream. The ice was analyzed for trace elememts using instrumental neutron activation technique. No tendency towards a systematic increase or decrease in the element concentrations in the past 4000 years has been found. The mean concentrations of Na and Al over the past 4000 years are higher than those in the Vostok ice core by factors of 9 and 4, respectively.     

Spatial pattern of knowledge innovation function among Chinese cities and its influencing factors

Knowledge innovation is a key component of urban innovation function and an important basis for modern urban development. Combining the multidisciplinary research of knowledge innovation, this paper constructs a measurement framework of urban knowledge innovation function from the perspective of urban geography and analyzes its spatial pattern and influencing factors. The conclusions are as follows:(1) The function of urban knowledge innovation refers to the tasks and roles it undertakes in the ...     

ON THE INTEGRATION OF KINETIC MODELS USING A HIGH-ORDER TAYLOR SERIES METHOD

A general equation to derive kinetic models up to any order is given. This equation greatly facilitates theapplication of the Taylor series method to the integration of kinetic models up to very high orders. Whendealing with non-stiff models, computing time is always reduced by increasing the integration order, atleast up to the 20th order. When the model is stiff, the integration order should be optimized; however,a twelfth order is recommended to integrate weakly stiff models. The use of an algorithm which permitsthe immediate calculation of the integration step size required to maintain a given accuracy leads tofurther reductions in computing time. When implemented as recommended here, a high-order Taylorseries method is more rapid and accurate than Runge-Kutta and predictor-corrector methods and canbe advantageously used in combination with optimization methods to perform mechanism studies andin multicomponent kinetic determinations.     

DENSIFICATION PROCESS WITHIN THE NEAR-SURFACE LAYER OF THE ANTARCTIC ICE SHEET

The densification process within the near-surface layer of Antarctic Ice Sheet is dominated by the environment and exhibits geographic zonality, In this article, the processes are found to be of three types: warm, cold and alternate, on the basis of the studies on a lot of shallow snow/firm cores from Wilkes Land, Antarctica, and the available data. Warm type densification takes place mainly on the periphery of the Antarctic Ice Sheet, where the mean annual temperature is about --10----15℃. High temperature in summer and consequent melting and infiltration are the main factors influencing the densification process. Cold type densification occurs in the huge central region of the Antarctica, where the mean annual temperature is below --25℃, with the maximum below 0℃ in summer. In this region, ice sintering is a main cause for the densification. The alternate type densification occurs in the transition zone between the above two regions, where the mean annual temperature is --15----25℃ and the highest     

EXPECTATION-MAXIMIZATION ALGORITHM FOR REGRESSION,DECONVOLUTION AND SMOOTHING OF SHOT-NOISE LIMITED DATA

A simple algorithm for deconvolution and regression of shot-noise-limited data is illustrated in this paper.The algorithm is easily adapted to almost any model and converges to the global optimum.Multiple-component spectrum regression,spectrum deconvolution and smoothing examples are used to illustratethe algorithm.The algorithm and a method for determining uncertainties in the parameters based on theFisher information matrix are given and illustrated with three examples.An experimental example ofspectrograph grating order compensation of a diode array solar spectroradiometer is given to illustratethe use of this technique in environmental analysis.The major advantages of the EM algorithm are foundto be its stability,simplicity,conservation of data magnitude and guaranteed convergence.