Fusion of Region Extraction and Cross-Entropy SVM Models for Wheat Rust Diseases Classification

Wheat rust diseases are one of the major types of fungal diseases that cause substantial yield quality losses of 15%–20%every year.The wheat rust diseases are identified either through experienced evaluators or computerassisted techniques.The experienced evaluators take time to identify the disease which is highly laborious and too costly.If wheat rust diseases are predicted at the development stages,then fungicides are sprayed earlier which helps to increase wheat yield quality.To solve the experienced evaluator issues,a combined region extraction and cross-entropy support vector machine(CE-SVM)model is proposed for wheat rust disease identification.In the proposed system,a total of 2300 secondary source images were augmented through flipping,cropping,and rotation techniques.The augmented images are preprocessed by histogram equalization.As a result,preprocessed images have been applied to region extraction convolutional neural networks(RCNN);Fast-RCNN,Faster-RCNN,and Mask-RCNN models for wheat plant patch extraction.Different layers of region extraction models construct a feature vector that is later passed to the CE-SVM model.As a result,the Gaussian kernel function in CE-SVM achieves high F1-score(88.43%)and accuracy(93.60%)for wheat stripe rust disease classification.

Equilibrium of liquid-liquid extraction of 2-phenylbutyric acid enantiomers: Experiment and model

The utilization of liquid–liquid extraction for the separation of 2-phenylbutyric acid（2-PBA） enantiomers was proposed. Factors affecting the extract process were investigated, including organic solvents, β-cyclodextrin derivatives, cyclodextrin concentration, p H and temperature. A model was proposed to describe the separation process based on the homogeneous phase reaction mechanism. Important parameters of this model were determined experimentally. The physical distribution coefficients for molecular and ionic 2-PBA were0.129 and 7.455, respectively. The equilibrium constants of the complexation reactions were 89.36 and36.78 L·mol^-1 for（＋）-and（-）-2-PBA, respectively. The model was verified by experiments and proved to be an excellent means to optimize the separation system. Through modeling prediction and experiment, the best conditions（e.g., pH value of 3.00, extractant concentration of 0.1 mol·L^-1, temperature of 5.0 ℃） were acquired. Under this condition, the maximum enantioselectivity（2.096） was obtained.

Development and Test of Hydrostatic Extraction Scheme in Spectral Model

The introduction of 'hydrostatic extraction' scheme, or 'standard stratification approximation', into spectral model gained some advantages compared with commonly used schemes. However, computational instability may occur for high vertical resolution versions if the stratification parameter C0 taken as a constant. In this paper, the possible cause leading to the instability is discussed and an improved scheme presented where C0 is generalized to be a function of both height and latitudes. Hence the reference atmosphere gets closer to the real atmosphere and the temperature deviation field to be expanded becomes smoother everywhere. Test by real case forecasts shows good computational stability of the new scheme and better prediction performance than-usual schemes of spectral model.

2D-HIDDEN MARKOV MODEL FEATURE EXTRACTION STRATEGY OF ROTATING MACHINERY FAULT DIAGNOSIS

A new feature extraction method based on 2D-hidden Markov model（HMM） is proposed. Meanwhile the time index and frequency index are introduced to represent the new features. The new feature extraction strategy is tested by the experimental data that collected from Bently rotor experiment system. The results show that this methodology is very effective to extract the feature of vibration signals in the rotor speed-up course and can be extended to other non-stationary signal analysis fields in the future.

THE EXTRACTION EQUILIBRIUM MODEL AND SIMULATION OF COUNTERCURRENT SOLVENT EXTRACTION OF Gd-Tb-Dy-HCl-HEH(EHP)-KEROSENE SYSTEM

The extraction equilibrium mathematic models for gadolinium,terbium and dysprosium in HCl-1.5 mol/L HEH(EHP)system covering a relatively wide range of lanthanide concentration and acidity,have been developed.There are four independent variables and nine parameters.The average relative error is 4.56%.A computer program for the simulation of the counter current solvent extraetion process has also been written.Thus,the Gd,Tb and Dy concentrations in both aqueous and organic phase in eaeh stage as well as the aqueous acidity may be calculated.Product purities,distribution ratio and extraction factors may also be obtained thereby.The simulation results so obtained may serve as the referenee data for designing solvent ex- traction processes including those processes providing apart from the conventional outgoing organic stream, outgoing raffinate and an extra outgoing third exit stream either organic or aqueous.

Selective ensemble modeling based on nonlinear frequency spectral feature extraction for predicting load parameter in ball mills

Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.

An Impact of Hydrostatic Extraction Scheme on BMRC's Global Spectral Model

There are two important features in geophysical fluid dynamics. One is that the atmospheric and oceanic equations of motion include the Coriolis force; another is that they describe a stratified fluid. The hydrostatic extraction scheme, or standard stratification approximation, posed by Zeng (1979), reflects the second aspect of geophysical fluid dynamics. There exist two major advantages in this scheme; accurate computation of the pressure gradient force can be obtained over steep mountain slopes, and the accumulation error in vertical finite differencing can be reduced, especially near the tropopause.Chen et al (1987) introduced the hydrostatic extraction scheme into a global spectral model, which attained preliminary success at low resolution. Zhang and Sheng et al (1990) developed and improved the hydrostatic extraction scheme in a global spectral model, in which C0, the parameter that represents the stratification of the reference atmosphere, changes not only with height, but also with latitude. The scheme has been incorporated BMRC's global spectral model (IAPB). Four 5-day forecasts have been performed to test the IAPB with the hydrostatic extraction scheme. Objective verifications demonstrate a positive effect of the hydrostatic extration scheme on BMRC's model, particularly at upper levels, over the tropics and the Antartic region.

Solvent extraction kinetics of Sm(Ⅲ),Eu(Ⅲ) and Gd(Ⅲ) with 2-ethylhexyl phosphoric acid-2-ethylhexyl ester

Solvent extraction kinetics of Sm（Ⅲ）, Eu（Ⅲ） and Gd（Ⅲ） from hydrochloric acid have been focused on using 2-ethylhexyl phosphoric acid-2-ethylhexyl ester （P507） with Anordning for Kontinuerlig Undersokning av Fordelningsfaktore rid Vatske Extraction （AKUFVE）. Compared with the conventional set-up, some advantages emerge obviously, for example, fast phase separation, easy operation and convenience of kinetic data acquisition. First of all, the extraction mechanism was discussed based on the dimeric model of P507. Secondly, the effects of stirring speed were investigated and 420 r-min-1 was determined of the following experiments. The effects of pH, concentration of rare earth elements （REEs） and P507 on the extraction rate were analyzed. The results indicated that the extraction mechanism changed with the increasing concentration of P507. Then, the experiments with different temperature were carried out. It turned out that the values of apparent activation energy （Ea） for Sm（Ⅲ）, Eu（Ⅲ） and Gd（Ⅲ） extracted by P507 were 26.80 kJ-mol-1, 13.40 kJ.mol-1 and 1.10 kJ- mol- 1 respectively, the resistance of the entire process was limited by diffusion or both of diffusion and reaction. Finally, the correlation equations were obtained, and the theoretical results fit with the experimental data well, most relative error was within ± 30%.

Solvent extraction of lanthanum and cerium ions from hydrochloric acidic aqueous solutions using partly saponified 2-ethylhexyl phosphonic acid mono-2-ethylhexyl ester

In order to clarify the extraction process with saponified extractant, the solvent extraction experiments of rare earth elements(REEs), lanthanum and cerium, by using partly saponified 2-ethylhexyl phosphoric acid mono-2-ethylhexyl ester(EHEHPA, HL) from hydrochloric acidic solutions have been performed. The concentration of initial aqueous rare earth ion was in a range of 0.0010–0.1000 mol·L^(-1); EHEHPA in a range of 0.2877–0.8631 mol·L^(-1) with saponification rate of 0.3(mole fraction), and the initial aqueous p H in a range of 1.00–4.00. Firstly, the extracted species were determined by the saturation extraction capacity method. Secondly, according to the equilibrium aqueous pH values, the extraction processes were divided into three different categories: extraction with saponified EHEHPA, extraction with un-saponified EHEHPA, and hydrolysis process. Finally, for the first two processes, in order to predict the distribution ratio, two semi-empirical calculation models were developed with.The calculation results are in good agreement well with the experimental data.

Analysis of Response Surface in the Study of RE(NO_3)_3-HNO_3-P507-Kerosene Extraction System

RE(NO_3)_3-HNO_3-P507-kerosene extraction system(RE=La,Ce,Pr,Nd,Sm,Eu,Gd,Tb,Dy,Ho,Er, Tm,Yb,Lu,Y)was studied by the response surface technique.14 models for extracting single rare earth ele- ment in a broad range of acidity and initial rare earth concentration were obtained by using the stepwise regression method.Three-dimensional display of the response surface of the model of extracting Er^(3+)was showed as an example,which reveals clearly the dependence of distribution ratio upon both initial acidity and ini- tial rare earth concentration.

Determination of the Bioaccessibility of Cadmium in Golden Thread by Physiologically Based Extraction Test Digestion Using the in vitro/Caco2 Cell Model and Subsequent Risk Assessment

Background:The ingestion of golden thread contaminated with heavy metals through the food chain leads to detrimental effects to human health.During digestion,not all of the heavy metals could be released to the gastrointestinal tract and readily to be absorbed by human body.Thus,bioaccessibility is an important issue in health risk assessments.Aims and Objectives:The aims and objectives of this study were to investigate the bioaccessibility of Cd in golden thread and assess the associated health risks based on the exposure to bioaccessible Cd.Materials and Methods:Inductively coupled plasma mass spectrometry(ICP-MS)has been applied to determine the Cd content in golden thread.Physiologically based extraction test(PBET)digestion was performed in the in vitro/Caco2 cell model to investigate the bioaccessibility of Cd in golden thread.Furthermore,the target hazard quotient(THQ)was used to assess the risks of the total and the bioaccessible content of Cd in golden thread.Results:The results revealed that the total Cd content in six batches of golden thread ranged from 3.203 to 5.723 mg/kg.After uptake by Caco2 cells,the bioaccessibility of Cd ranged from 42.36%to 59.73%.The results of the risk assessment indicated that prior to uptake by Caco2 cells,the THQ values of Cd for all batches of golden thread were greater than 1.However,after uptake by Caco2 cells,the THQ values of Cd in all samples were less than 1,thus suggesting that the risks were at a safe level.Conclusion:This study was the first to perform health risk assessment with bioaccessible heavy metals present in traditional Chinese medicine by PBET digestion using an in vitro/Caco2 cell model,thus enabling us to obtain more accurate and objective results while allowing us to avoid unnecessary government intervention and to establish more reasonable limit standards for heavy metals.

Small-signal model parameter extraction for AlGaN/GaN HEMT

A new 22-element small signal equivalent circuit model for the AlGaN/G N high electron mobility transistor（HEMT） is presented. Compared with the traditional equivalent circuit model, the gate forward and breakdown conductions（G_（gsf） and G_（gdf）） are introduced into the new model to characterize the gate leakage current. Additionally, for the new gate-connected field plate and the source-connected field plate of the device, an improved method for extracting the parasitic capacitances is proposed, which can be applied to the small-signal extraction for an asymmetric device. To verify the model, S-parameters are obtained from the modeling and measurements. The good agreement between the measured and the simulated results indicate that this model is accurate,stable and comparatively clear in physical significance.

Temperature-variable high-frequency dynamic modeling of PIN diode

The PIN diode model for high frequency dynamic transient characteristic simulation is important in conducted EMI analysis. The model should take junction temperature into consideration since equipment usually works at a wide range of temperature. In this paper, a temperature-variable high frequency dynamic model for the PIN diode is built, which is based on the Laplace-transform analytical model at constant temperature. The relationship between model parameters and temperature is expressed as temperature functions by analyzing the physical principle of these parameters. A fast recovery power diode MUR1560 is chosen as the test sample and its dynamic performance is tested under inductive load by a temperature chamber experiment, which is used for model parameter extraction and model verification. Results show that the model proposed in this paper is accurate for reverse recovery simulation with relatively small errors at the temperature range from 25 to 120 ℃.

An Intelligent Heuristic Manta-Ray Foraging Optimization and Adaptive Extreme Learning Machine for Hand Gesture Image Recognition

The development of hand gesture recognition systems has gained more attention in recent days,due to its support of modern human-computer interfaces.Moreover,sign language recognition is mainly developed for enabling communication between deaf and dumb people.In conventional works,various image processing techniques like segmentation,optimization,and classification are deployed for hand gesture recognition.Still,it limits the major problems of inefficient handling of large dimensional datasets and requires more time consumption,increased false positives,error rate,and misclassification outputs.Hence,this research work intends to develop an efficient hand gesture image recognition system by using advanced image processing techniques.During image segmentation,skin color detection and morphological operations are performed for accurately segmenting the hand gesture portion.Then,the Heuristic Manta-ray Foraging Optimization(HMFO)technique is employed for optimally selecting the features by computing the best fitness value.Moreover,the reduced dimensionality of features helps to increase the accuracy of classification with a reduced error rate.Finally,an Adaptive Extreme Learning Machine(AELM)based classification technique is employed for predicting the recognition output.During results validation,various evaluation measures have been used to compare the proposed model’s performance with other classification approaches.

Accuracy Improvement of ASTER Stereo Satellite Generated DEM Using Texture Filter

The grid DEM(digital elevation model) generation can be from any of a number of sources:for instance,analogue to digital conversion of contour maps followed by application of the TIN model,or direct elevation point modelling via digital photogrammetry applied to airborne images or satellite images.Currently,apart from the deployment of point-clouds from LiDAR data acquisition,the generally favoured approach refers to applications of digital photogrammetry.One of the most important steps in such deployment is the stereo matching process for conjugation point(pixel) establishment:very difficult in modelling any homogenous areas like water cover or forest canopied areas due to the lack of distinct spatial features.As a result,application of automated procedures is sure to generate erroneous elevation values.In this paper,we present and apply a method for improving the quality of stereo DEMs generated via utilization of an entropy texture filter.The filter was applied for extraction of homogenous areas before stereo matching so that a statistical texture filter could then be applied for removing anomalous evaluation values prior to interpolation and accuracy assessment via deployment of a spatial correlation technique.For exemplification,we used a stereo pair of ASTER 1B images.