利用柔性神经树的实时肌电信号手势识别模型

传统的手势识别通常采用数字信号处理(Digital Signal Processing,DSP)芯片或者集合方法(Ensem-ble Methods)研究实时识别问题。这些方法易导致数学模型参数繁多、硬件连接复杂和实时识别率较低。提出一种基于表面肌电信号与柔性神经树(Flexible Neural Trees,FNT)模型的实时手势识别模型。表面肌电信号(surface Electromyography,sEMG)具有非入侵式、易于采集特点,故被广泛应用于行为识别和诊断等领域。柔性神经树模型通过简单的预定义来构建,能够解决人工神经网络(Artificial Neural Network,ANN)的结构依赖性高的问题。柔性神经树模型不仅能够避免复杂的计算和电路连接,还具有较高的实时识别率和较低的方均根误差(Root Mean Square Error,RMSE)。实验针对六名参与者的六种手势进行测试,结果表明该模型实时识别率较高,实际应用也证明该算法可行。

Estimating van Genuchten Model Parameters of Undisturbed Soils Using an Integral Method

The van Genuchten model is the most widely used soil water retention curve （SWRC） model. Two undisturbed soils （clay and loam） were used to evaluate the accuracy of the integral method to estimate van Genuchten model parameters and to determine SWRCs of undisturbed soils. SWRCs calculated by the integral method were compared with those measured by a high speed centrifuge technique. The accuracy of the calculated results was evaluated graphically, as well as by root mean square error （RMSE）, normalized root mean square error （NRMSE） and Willmott＇s index of agreement （1）. The results obtained from the integral method were quite similar to those by the centrifuge technique. The RMSEs （4.61 ×10^-5 for Eum-Orthic Anthrosol and 2.74 × 10^-4 for Los-Orthic Entisol） and NRMSEs （1.56 × 10^-4 for Eum- Orthic Anthrosol and 1.45 ×10^-3 for Los-Orthic Entisol） were relatively small. The 1 values were 0.973 and 0.943 for Eum-Orthic Anthrosol and Los-Orthic Entisol, respectively, indicating a good agreement between the integral method values and the centrifuge values. Therefore, the integral method could be used to estimate SWRCs of undisturbed clay and loam soils.

A Model for Estimating Total Forest Coverage with Ground-Based Digital Photography

Vegetation fractional coverage (VFC) is one of the key indicators of vegetation distribution. In the work a measurement-based model was developed to derive total forest VFC (TG) as well as the VFC of trees (T) and shrub-grasses (G) separately in a subtropical forest area in Nanjing, China. Both upward and downward photographs were taken with a digital camera in 72 quadrats (10 m × 10 m each). Fifteen models were established and validated. Models jointly using both T and G performed better than those using the T and G separately. The best model, TG = T + G- 1.134 × T × G- 0.025 (R2 = 0.9115, P < 0.01, root mean squared error = 0.0789), is recommended for application. This model provides a good way to obtain total forest VFC values through taking tree and shrub-grass photos on ground below tree canopy rather than above tree canopy.

Validation and intercomparison of HY-2A/MetOp-A/Oceansat-2 scatterometer wind products

Sea surface winds are of great significance in scientific research. In the last few years,three series of scatterometers were launched to measure these winds,including the Advanced Scatterometer(ASCAT) aboard Meteorological Operational Satellite A(Met Op-A) and Met Op-B,Oceansat-2 Scatterometer(OSCAT),and HY-2A Scatterometer(HY-2A SCAT). Based on buoy wind data,validation and intercomparison of these scatterometers were performed. Scatterometer-derived wind and buoy wind data were collected only if the spatial difference was less than 0.1 degree and temporal difference less than 5 min. After discarding wind direction data outside five times the standard deviation,ASCAT wind products showed high accuracy in both wind speed and direction,with root-mean-square error(RMSE) 0.86 m/s and 17.97 degrees,respectively. HY-2A SCAT nearly meets the mission requirement,with RMSE for wind speed 1.23 m/s and 22.85 degrees for wind direction. OSCAT had poor performance when compared with the others. RMSE for wind speed was 1.54 m/s and 39.86 degrees for wind direction,which greatly exceeds the mission requirement of 20 degrees. In addition,the RMSE for wind direction shows a high-low pattern on buoy wind speed. However,a wind speed range from 14 to 15 m/s was found to be abnormal,and the reason remains unclear. There was no systematic dependency of both wind speed and direction residuals on buoy wind speed and cross-track location of the wind vector cells across the entire range. No seasonal variation was found for any scatterometer.

Comparison of six statistical approaches in the selection of appropriate fish growth models

The performance of six statistical approaches,which can be used for selection of the best model to describe the growth of individual fish,was analyzed using simulated and real length-at-age data.The six approaches include coefficient of determination(R2),adjusted coefficient of determination(adj.-R2),root mean squared error(RMSE),Akaike's information criterion(AIC),bias correction of AIC(AICc) and Bayesian information criterion(BIC).The simulation data were generated by five growth models with different numbers of parameters.Four sets of real data were taken from the literature.The parameters in each of the five growth models were estimated using the maximum likelihood method under the assumption of the additive error structure for the data.The best supported model by the data was identified using each of the six approaches.The results show that R2 and RMSE have the same properties and perform worst.The sample size has an effect on the performance of adj.-R2,AIC,AICc and BIC.Adj.-R2 does better in small samples than in large samples.AIC is not suitable to use in small samples and tends to select more complex model when the sample size becomes large.AICc and BIC have best performance in small and large sample cases,respectively.Use of AICc or BIC is recommended for selection of fish growth model according to the size of the length-at-age data.

3-D reconstruction of coastal bathymetry from AIRSAR/POLSAR data

This paper introduces a new method for reconstructing three-dimensional （3D） coastal bathymetry changes from Airborne AIRSAR/POLSAR synthetic aperture data. The new method is based on integration between fuzzy B-spline and Volterra algorithm. Volterra algorithm is used to simulate the ocean surface current from AIRSAR/POLSAR data. Then, the ocean surface current information used as input for continuity equation to estimate the water depths from AIRSAR/POLSAR data. This study shows that 3D ocean bathymetry can be reconstructed from AIRSAR/POLSAR data with root mean square error of ±0.03 m.

Slope displacement prediction based on morphological filtering

Combining mathematical morphology (MM),nonparametric and nonlinear model,a novel approach for predicting slope displacement was developed to improve the prediction accuracy.A parallel-composed morphological filter with multiple structure elements was designed to process measured displacement time series with adaptive multi-scale decoupling.Whereafter,functional-coefficient auto regressive (FAR) models were established for the random subsequences.Meanwhile,the trend subsequence was processed by least squares support vector machine (LSSVM) algorithm.Finally,extrapolation results obtained were superposed to get the ultimate prediction result.Case study and comparative analysis demonstrate that the presented method can optimize training samples and show a good nonlinear predicting performance with low risk of choosing wrong algorithms.Mean absolute percentage error (MAPE) and root mean square error (RMSE) of the MM-FAR&LSSVM predicting results are as low as 1.670% and 0.172 mm,respectively,which means that the prediction accuracy are improved significantly.

Comparative Analysis of Four Stem Taper Models for Quercus glauca in Mount Halla,Jeju Island,South Korea

This study was conducted to fit the diameter-height data of Quercusglaucain Jeju Island, South Korea to the four commonly used stem taper equations andto evaluate the performance of the four stem taper models using four statistical criteria： Fit index （FI）, root mean square error （RMSE）, bias （）,and absolute mean difference （AMD）. Results showed that the Kozak02stem taper equation provided the best FI（0.9847）, RMSE（1.5745）,（-0.0030 cm） and AMD （1.0990 cm） whileMax and Burkhart model had the poorest performance among the four stem taper models based on the four evaluation statistics （FI ： 0.9793,RMSE ： 1.8272, ： 0.3040 cm and AMD ： 1.3060 cm）. These stem taper equations can serve as a useful tool for forest managers in estimating the diameter outside bark at any given height, merchantable stem volumes and total stem volumesof the standing trees of Quercusglaucain theGotjawal forests located in Mount Halla, Jeju Island, South Korea.

Prediction of representative deformation modulus of longwall panel roof rock strata using Mamdani fuzzy system

Deformation modulus is the important parameter in stability analysis of tunnels, dams and mining struc- tures. In this paper, two predictive models including Mamdani fuzzy system （MFS） and multivariable regression analysis （MVRA） were developed to predict deformation modulus based on data obtained from dilatometer tests carried out in Bakhtiary dam site and additional data collected from longwall coal mines. Models inputs were considered to be rock quality designation, overburden height, weathering, unconfined compressive strength, bedding inclination to core axis, joint roughness coefficient and fill thickness. To control the models performance, calculating indices such as root mean square error （RMSE）, variance account for （VAF） and determination coefficient （R^2） were used. The MFS results show the significant prediction accuracy along with high performance compared to MVRA results. Finally, the sensitivity analysis of MFS results shows that the most and the least effective parameters on deformation modulus are weatherin~ and overburden height, respectively.

Satellite derived upper ocean thermal structure and its application to tropical cyclone intensity forecasting in the Indian Ocean

Upper ocean heat content is a factor critical to the intensity change of tropical cyclones(TCs). Because of the inhomogeneity of in situ observations in the North Indian Ocean,gridded temperature/salinity(T/S) profiles were derived from satellite data for 1993–2012 using a linear regression method. The satellite derived T/S dataset covered the region of 10°S–32°N,25°–100°E with daily temporal resolution,0.25°×0.25° spatial resolution,and 26 vertical layers from the sea surface to a depth of 1 000 m at standard layers. Independent Global Temperature Salinity Profile Project data were used to validate the satellite derived T/S fields. The analysis confirmed that the satellite derived temperature field represented the characteristics and vertical structure of the temperature field well. The results demonstrated that the vertically averaged root mean square error of the temperature was 0.83 in the upper 1 000 m and the corresponding correlation coefficient was 0.87,which accounted for 76% of the observed variance. After verification of the satellite derived T/S dataset,the TC heat potential(TCHP) was verified. The results show that the satellite derived values were coherent with observed TCHP data with a correlation coefficient of 0.86 and statistical significance at the 99% confidence level. The intensity change of TC Gonu during a period of rapid intensification was studied using satellite derived TCHP data. A delayed effect of the TCHP was found in relation to the intensity change of Gonu,suggesting a lag feature in the response of the inner core of the TC to the ocean.

Establishment and tests of EnOI assimilation module for WAVEWATCH Ⅲ

In this paper, we propose a parallel data assimilation module based on ensemble optimal interpolation （EnOI）. We embedded the method into the full-spectral third-generation wind-wave model, WAVEWATCH III Version 3.14, producing a wave data assimilation system. We present our preliminary experiments assimilating altimeter significant wave heights （SWH） using the EnOI-based wave assimilation system. Waters north of 15°S in the Indian Ocean and South China Sea were chosen as the target computational domain, which was two-way nested into the global implementation of the WAVEWATCH III. The wave model was forced by six-hourly ocean surface wind velocities from the cross-calibrated multi-platform wind vector dataset. The assimilation used along-track SWH data from the Jason-2 altimeter. We evaluated the effect of the assimilation on the analyses and hindcasts, and found that our technique was effective. Although there was a considerable mean bias in the control SWHs, a month-long consecutive assimilation reduced the bias by approximately 84% and the root mean-square error （RMSE） by approximately 65%. Improvements in the SWH RMSE for both the analysis and hindcast periods were more significant in July than January, because of the monsoon climate. The improvement in model skill persisted for up to 48 h in July. Furthermore, the SWH data assimilation had the greatest impact in areas and seasons where and when the sea-states were dominated by swells.

CARRIER FREQUENCY OFFSET ESTIMATION FOR INTERLEAVED OFDMA UPLINK BASED ON SUBSPACE PROCESSING

This paper investigates Carrier Frequency Offset (CFO) estimation in the uplink of the Orthogonal Frequency-Division Multiple Access (OFDMA) systems with the interleaved subcarrier assignment. CFOs between the transmitters and the uplink receiver will destroy orthogonality among different subcarriers, hence resulting in inter-carrier interference and multiuser interference. A two-stage frequency offset estimation algorithm based on subspace processing is proposed. The main advantage of the proposed method is that it can obtain the CFOs of all users simultaneously using only one OFDMA block. Compared with the previously known methods, it not only has a relatively low implementation complexity but is also suitable for random subchannel assignment.

Chaos Particle Swarm Optimization Combined with Circular Median Filtering for Geophysical Parameters Retrieval from WindSat

This paper established a geophysical retrieval algorithm for sea surface wind vector, sea surface temperature, columnar atmospheric water vapor, and columnar cloud liquid water from WindSat, using the measured brightness temperatures and a matchup database. To retrieve the wind vector, a chaotic particle swarm approach was used to determine a set of possible wind vector solutions which minimize the difference between the forward model and the WindSat observations. An adjusted circular median filtering function was adopted to remove wind direction ambiguity. The validation of the wind speed, wind direction, sea surface temperature, columnar atmospheric water vapor, and columnar liquid cloud water indicates that this algorithm is feasible and reasonable and can be used to retrieve these atmospheric and oceanic parameters. Compared with moored buoy data, the RMS errors for wind speed and sea surface temperature were 0.92 m s^(-1) and 0.88℃, respectively. The RMS errors for columnar atmospheric water vapor and columnar liquid cloud water were 0.62 mm and 0.01 mm, respectively, compared with F17 SSMIS results. In addition, monthly average results indicated that these parameters are in good agreement with AMSR-E results. Wind direction retrieval was studied under various wind speed conditions and validated by comparing to the Quik SCAT measurements, and the RMS error was 13.3?. This paper offers a new approach to the study of ocean wind vector retrieval using a polarimetric microwave radiometer.

Extreme air pollution events:Modeling and prediction

In order to get prepared for the coming extreme pollution events and minimize their harmful impacts, the first and most important step is to predict their possible intensity in the future. Firstly, the generalized Pareto distribution （GPD） in extreme value theory was used to fit the extreme pollution concentrations of three main pollutants： PM10, NO2 and SO：, from 2005 to 2010 in Changsha, China. Secondly, the prediction results were compared with actual data by a scatter plot. Four statistical indicators： EMA （mean absolute error）, ERMS （root mean square error）, IA （index of agreement） and R2 （coefficient of determination） were used to evaluate the goodness-of-fit as well. Thirdly, the return levels corresponding to different return periods were calculated by the fitted distributions. The fitting results show that the distribution of PM10 and SO2 belongs to exponential distribution with a short tail while that of the NOe belongs to beta distribution with a bounded tail. The scatter plot and four statistical indicators suggest that GPD agrees well with the actual data. Therefore, the fitted distribution is reliable to predict the return levels corresponding to different return periods. The predicted return levels suggest that the intensity of coming pollution events for PM10 and SO2 will be even worse in the future, which means people have to get enough preparation for them.

Optimal sensor placement for structural response estimation

A methodology, termed estimation error minimization(EEM) method, was proposed to determine the optimal number and locations of sensors so as to better estimate the vibration response of the entire structure. Utilizing the limited sensor measurements, the entire structure response can be estimated based on the system equivalent reduction-expansion process(SEREP) method. In order to compare the capability of capturing the structural vibration response with other optimal sensor placement(OSP) methods, the effective independence(EI) method, modal kinetic energy(MKE) method and modal assurance criterion(MAC) method, were also investigated. A statistical criterion, root mean square error(RMSE), was employed to assess the magnitude of the estimation error between the real response and the estimated response. For investigating the effectiveness and accuracy of the above OSP methods, a 31-bar truss structure is introduced as a simulation example. The analysis results show that both the maximum and mean of the RMSE value obtained from the EEM method are smaller than those from other OSP methods, which indicates that the optimal sensor configuration obtained from the EEM method can provide a more accurate estimation of the entire structure response compared with the EI, MKE and MAC methods.

Three-Step Difference Scheme for Solving Nonlinear Time-Evolution Partial Differential Equations

In this paper, a special three-step difference scheme is applied to the solution of nonlinear time-evolution equations, whose coefficients are determined according to accuracy constraints, necessary conditions of square conservation, and historical observation information under the linear supposition. As in the linear case, the schemes also have obvious superiority in overall performance in the nonlinear case compared with traditional finite difference schemes, e.g., the leapfrog(LF) scheme and the complete square conservation difference(CSCD) scheme that do not use historical observations in determining their coefficients, and the retrospective time integration(RTI) scheme that does not consider compatibility and square conservation. Ideal numerical experiments using the one-dimensional nonlinear advection equation with an exact solution show that this three-step scheme minimizes its root mean square error(RMSE) during the first 2500 integration steps when no shock waves occur in the exact solution, while the RTI scheme outperforms the LF scheme and CSCD scheme only in the first 1000 steps and then becomes the worst in terms of RMSE up to the 2500th step. It is concluded that reasonable consideration of accuracy, square conservation, and historical observations is also critical for good performance of a finite difference scheme for solving nonlinear equations.

An Extension of the Dimension-Reduced Projection 4DVar

This paper extends the dimension-reduced projection four-dimensional variational assimilation method(DRP-4DVar) by adding a nonlinear correction process,thereby forming the DRP-4DVar with a nonlinear correction, which shall hereafter be referred to as the NC-DRP-4DVar. A preliminary test is conducted using the Lorenz-96 model in one single-window experiment and several multiple-window experiments. The results of the single-window experiment show that compared with the adjoint-based traditional 4DVar, the final convergence of the cost function for the NC-DRP-4DVar is almost the same as that using the traditional 4DVar, but with much less computation. Furthermore, the 30-window assimilation experiments demonstrate that the NC-DRP-4DVar can alleviate the linearity approximation error and reduce the root mean square error significantly.

Evaluation of Some Stem Taper Models for Camellia japonica in Mount Halla, Korea

This study was conducted to evaluate the performance of the four stem taper models on Camellia japonica in Jeju Island, Korea using fit statistics and lack-of-fit statistics. The five statistical criteria that were used in this study were standard error of estimate(SEE), mean bias( E), absolute mean difference(AMD), coefficient of determination(R2), and root mean square error(RMSE). Results showed that the Kozak model 02 stem taper had the best performance in all fit statistics(SEE: 3.4708, E : 0.0040 cm, AMD : 0.9060 cm, R2 : 0.9870, and RMSE : 1.2545). On the other hand, Max and Burkhart stem taper model had the poorest performance in each statistical criterion(SEE: 4.2121, E : 0.2520 cm, AMD : 1.1300 cm, R2 : 0.9805, and RMSE: 1.5317). For the lack-of-fit statistics, the Kozak model 02 also provided the best performance having the best AMD in most of the relative height classes for diameter outside bark prediction and in most of the DBH classes for total volume prediction while Max and Burkhart had the poorest performance. These stem taper equations could help forest managers to better estimate the diameter outside bark at any given height, merchantable stem volumes and total stem volumes of the standing trees of Camellia japonica in the forests of Jeju Island, Korea.

Long-range precipitation forecasts using paleoclimate reconstructions in the western United States

Long-range precipitation forecasts are useful when managing water supplies.Oceanicatmospheric oscillations have been shown to influence precipitation.Due to a longer cycle of some of the oscillations,a short instrumental record is a limitation in using them for long-range precipitation forecasts.The influence of oscillations over precipitation is observable within paleoclimate reconstructions;however,there have been no attempts to utilize these reconstructions in precipitation forecasting.A data-driven model,KStar,is used for obtaining long-range precipitation forecasts by extending the period of record through the use of reconstructions of oscillations.KStar is a nearest neighbor algorithm with an entropy-based distance function.Oceanic-atmospheric oscillation reconstructions include the El Nino-Southern Oscillation(ENSO),the Pacific Decadal Oscillation(PDO),the North Atlantic Oscillation(NAO),and the Atlantic Multi-decadal Oscillation(AMO).Precipitation is forecasted for 20 climate divisions in the western United States.A 10-year moving average is applied to aid in the identification of oscillation phases.A lead time approach is used to simulate a one-year forecast,with a 10-fold cross-validation technique to test the models.Reconstructions are used from 1658-1899,while the observed record is used from 1900-2007.The model is evaluated using mean absolute error(MAE),root mean squared error(RMSE),RMSE-observations standard deviation ratio(RSR),Pearson's correlation coefficient(R),NashSutcliffe coefficient of efficiency(NSE),and linear error in probability space(LEPS) skill score(SK).The role of individual and coupled oscillations is evaluated by dropping oscillations in the model.The results indicate 'good' precipitation estimates using the KStar model.This modeling technique is expected to be useful for long-term water resources planning and management.

Estimating Clear Sky Solar Radiation Using Linke and Angstrom Turbidity Coefficients in Romania

The renewable systems design software and building energy simulation software for energy efficient buildings, use as a main input the solar radiation. The implementation of such systems in the urban environment requires accurate meteorological data for the interest area. The existence of a small number of weather stations that to offer data with regard to solar radiation as well as the limited access to these, makes necessary the conceiving of some more accurate estimation mathematical models for all climatological parameters. The present paper proposes a study of the Linke and AngstrOm turbidity coefficients, for Brasov urban area, with the purpose of a more accurate solar radiation simulation. Models performance is analyzed using the root mean square error （RMSE）, the mean bias error （MBE）, the mean percentage error （MPE） and the t-statistic.