Deep learning-based recognition of stained tongue coating images

Objective To build a dataset encompassing a large number of stained tongue coating images and process it using deep learning to automatically recognize stained tongue coating images.Methods A total of 1001 images of stained tongue coating from healthy students at Hunan University of Chinese Medicine and 1007 images of pathological(non-stained)tongue coat-ing from hospitalized patients at The First Hospital of Hunan University of Chinese Medicine withlungcancer;diabetes;andhypertensionwerecollected.Thetongueimageswererandomi-zed into the training;validation;and testing datasets in a 7:2:1 ratio.A deep learning model was constructed using the ResNet50 for recognizing stained tongue coating in the training and validation datasets.The training period was 90 epochs.The model’s performance was evaluated by its accuracy;loss curve;recall;F1 score;confusion matrix;receiver operating characteristic(ROC)curve;and precision-recall(PR)curve in the tasks of predicting stained tongue coating images in the testing dataset.The accuracy of the deep learning model was compared with that of attending physicians of traditional Chinese medicine(TCM).Results The training results showed that after 90 epochs;the model presented an excellent classification performance.The loss curve and accuracy were stable;showing no signs of overfitting.The model achieved an accuracy;recall;and F1 score of 92%;91%;and 92%;re-spectively.The confusion matrix revealed an accuracy of 92%for the model and 69%for TCM practitioners.The areas under the ROC and PR curves were 0.97 and 0.95;respectively.Conclusion The deep learning model constructed using ResNet50 can effectively recognize stained coating images with greater accuracy than visual inspection of TCM practitioners.This model has the potential to assist doctors in identifying false tongue coating and prevent-ing misdiagnosis.

Depression recognition using functional connectivity based on dynamic causal model

Dynamic casual modeling of functional magnetic resonance imaging（fMRI） signals is employed to explore critical emotional neurocircuitry under sad stimuli. The intrinsic model of emotional loops is built on the basis of Papez＇s circuit and related prior knowledge, and then three modulatory connection models are established. In these models, stimuli are placed at different points, which represents they affect the neural activities between brain regions, and these activities are modulated in different ways. Then, the optimal model is selected by Bayesian model comparison. From group analysis, patients＇ intrinsic and modulatory connections from the anterior cingulate cortex （ACC） to the right inferior frontal gyrus （rlFG） are significantly higher than those of the control group. Then the functional connection parameters of the model are selected as classifier features. The classification accuracy rate from the support vector machine（SVM） classifier is 80.73%, which, to some extent, validates the effectiveness of the regional connectivity parameters for depression recognition and provides a new approach for the clinical diagnosis of depression.

A Study of ISA in Chinese Cultural Communication

The paper tentatively studies the function of the indirect speech act in Chinese cultural communication, namely, domestic communication. Two aspects are shown in this paper： communication between people of different social status, genders and casual relationships, and communication between people of same social status, genders and close relationships. Therefore, the study result can be concluded like this： whether the use of indirect speech act is successful or not always influences people＇s communication significantly.

IMAGE-BASED SCALING FOR SHIP TOP VIEW ISAR IMAGES

A high quality top view or side view ship ISAR image with proper cross-range scale is very useful for target recognition. A technique aiming at solving the ship top view image scaling is developed, in which the cross-range scale information is obtained by measuring the slopes of the two feature lines of the ship, the centerline and the stern line. Neither the prior knowledge about the ship nor the tracking data is required. The proposed technique is fully based on the image. It is used with ease and high efficiency. Examples are provided to demonstrate its effectiveness with both simulated and real data. The scaled results are in accordance with the real shape of the ship.

Intelligent detection method for workpiece defect based on industrial CT image

In order to solve the problem of internal defect detection in industry, an intelligent detection method for workpiece defect based on industrial computed tomography (CT) images is proposed. The industrial CT slice image is preprocessed first with the combination of adaptive median filtering and adaptive weighted average filtering by analyzing the characteristics of the industrial CT slice images. Then an image segmentation algorithm based on gray change rate is used to segment low contrast information in industrial CT images, and the feature of workpiece defect is extracted by using Hu invariant moment. On this basis, the radial basis function (RBF) neural network model is established and the firefly algorithm is used for optimization, and the intelligent identification of the internal defects of the workpiece is completed. Simulation results show that this method can effectively improve the accuracy of defect identification and provide a theoretical basis for the detection of internal defects in industry.

Generalization Capabilities of Feedforward Neural Networks for Pattern Recognition

This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.

Intelligence in Clothing Pattern CAD System

It analyzes three recognition methods for five elements,i.e.dot,line,loop,clothing pattern as well as characters,and also applies intelligent points and tangential curve in the CAD system to solve the problem complained by CAD users.It indicates that recognition of five elements is a foundational technique of intelligence in clothing pattern CAD system.Common functions in operation state such as move,rotation,flip,measure,should precede ones in element state as dot,line,and pattern.Moreover,it is realized that the less skill the CAD user needs,the more the CAD software is high-tech.

Direct Synthesis of Monodisperse Hollow Molecularly Imprinted Polymers Based on Unfunctionalized SiO2 for the Recognition of Bisphenol A

A novel and effective approach was developed to synthesize monodisperse hollow molecularly imprinted polymers （MHMIPs） with unfunctionalized SiO2 spheres in a mixture of toluene and CH3CN. The factors that affected the synthesis of MHMIPs were systematically investigated. It was determined that a suitable ratio of toluene to CH3CN and the use of a functional monomer that can generate double H-bonding interactions were the critical factors to obtain MHMIPs with high uniformity and rnonodispersion. The obtained MHMIPs exhibited a fast adsorption rate and high adsorption capacity （270 μmol/g） for bisphenol A. As the shell thickness increased from 90 nm to 130 nm, the binding capacity of the imprinted shells decreased gradually. The relative selectivity coefficients of MHMIPs for tetra-brornobisphenol A （TBBPA）, phenol and p-tert-butylphenol （PTBP） were calculated as 1.53, 1.83 and 1.90, respectively. These findings indicate that MHMIPs have good adsorption performances and suggest applications in the selective removal or sensitive analysis of bisphenol A.

Discriminating ability of molecular markers and morphological characterization in the establishment of genetic relationships in cultivated genotypes of almond and related wild species

A total 23 morphological traits, 19 AFLP-primer combinations, 80 RAPD primers and 32 SSR primer pair were used to compare the informativeness and efficiency of random amplified polymorphic DNA （RAPD）, amplified fragment length polymorphism （AFLP） and simple sequence repeat （SSR） markers in establishing genetic relationships among 29 almond cultivars and three related wild species. SSRs presented a high level of polymorphism and greater information content, as assessed by the expected hetrozygosity, compared to AFLPs and RAPDs. The lowest values of expected hetrozygosity were obtained for AFLPs; however AFLPs showed the highest efficiency, owing to their capacity to reveal large numbers of bands per reaction, which led to high values for various types of indices of diversity. All the three techniques discriminated almond genotypes very effectively, except that SSRs failed to discriminate between ＇Monagha＇ and ＇Sefied＇ almond genotypes. The correlation coefficients of similarity were statistically significant for all the three marker systems, but were lower for the SSR data than for RAPDs and AFLPs. For all the markers, high similarity in dendrogram topologies was obtained, although some differences were observed. All the dendrograms, including that obtained by the combined use of all the marker data, reflect relationships for most of cultivars according to their geographic diffusion. AMOVA detected more variation among cultivated and related wild species of almond within each geographic group. Bootstrap analysis revealed that the number of markers used was sufficient for reliable estimation of genetic similarity and for meaningful comparisons of marker types.

A decision hyper plane heuristic based artificial immune network classification algorithm

Most of the developed immune based classifiers generate antibodies randomly, which has negative effect on the classification performance. In order to guide the antibody generation effectively, a decision hyper plane heuristic based artificial immune network classification algorithm （DHPA1NC） is proposed. DHPAINC taboos the inner regions of the class domain, thus, the antibody generation is limited near the class domain boundary. Then, the antibodies are evaluated by their recognition abilities, and the antibodies of low recognition abilities are removed to avoid over-fitting. Finally, the high quality antibodies tend to be stable in the immune network. The algorithm was applied to two simulated datasets classification, and the results show that the decision hyper planes determined by the antibodies fit the class domain boundaries well. Moreover, the algorithm was applied to UCI datasets classification and emotional speech recognition, and the results show that the algorithm has good performance, which means that DHPAINC is a promising classifier.

Separate Dimming Controlling and Data Transmission for an Indoor Visible Light Communication System

Simultaneous dimming controlling and data transmission are usually required in a white LED based indoor visible light communication system.However,the diming controlling of LED normally interferes the data transmission due to the modulation nonlinearity of LED.In order to solve this problem,a scheme by separating the LEDs for the functions of dimming control and data transmission respectively is proposed in this paper.In the scheme,the LEDs used for dimming control function are driven by a dc amplified circuit,and the LEDs for data transmission are driven by a digital modulation circuit respectively.In this way,the modulation distortion to the data signal caused by the modulation nonlinearity can be avoided even if the dimming is at high level dc driven current.The proof-of-concept experiment of a 2.5Mbit/s visible light communication system demonstrates that the dimming controlling and data transmission can be realized simultaneously in a simple way,and the data transmission is not affected by the dimming controlling function.Compared to previous methods,the scheme in this paper is simpler and cost effective,and makes sense when high rate data is transmitted in a visible light communication system.

Region Pair Grey Difference Classifier for Face Detection

A new kind of region pair grey difference classifier was proposed. The regions in pairs associated to form a feature were not necessarily directly-connected, but were selected dedicatedly to the grey transition between regions coinciding with the face pattern structure. Fifteen brighter and darker region pairs were chosen to form the region pair grey difference features with high discriminant capabilities. Instead of using both false acceptance rate and false rejection rate, the mutual information was used as a unified metric for evaluating the classifying performance. The parameters of specified positions, areas and grey difference bias for each single region pair feature were selected by an optimization processing aiming at maximizing the mutual information between the region pair feature and classifying distribution, respectively. An additional region-based feature depicting the correlation between global region grey intensity patterns was also proposed. Compared with the result of Viola-like approach using over 2 000 features, the proposed approach can achieve similar error rates with only 16 features and 1/6 implementation time on controlled illumination images.

Identification of Rhodiola species by using RP-HPLC

An approach was established using RP-HPLC (reversed-phase high-performance liquid chromatography) to identify ten species of Rhodiola, R. coccinea A. Bor, R. junggarica C.Y. Yang et N.R. Cui spn., R. heterodonta A. Bor, R. linearifolia A. Bor, R. pamiro alaiucm A. Bor, R. kaschgarica A. Bor, R. litwinowii A. Bor, R. gelida schrenk, R. rosea L. and R. quadrifide Fisch et Mey collected from the Tianshan Mountains areas of China. Chromatograms of alcohol-soluble proteins, generated from these ten Rhodiola spp. were compared. Each chromatogram of alcohol-soluble proteins came from a single seed of one wild species only. The results showed that when using a Waters Delta Pak. C18, 5 μm particle size reversed phase column (150 mm×3.9 mm), a linear gradient of 22%?55% solvent B with a flow rate of 1 ml/min and a run time of 67 min, the chromatography gave optimum separation of Rhodiola alcohol-soluble proteins. Chromatogram of each species was different and could be used to identify those species. Cluster analysis of genetic similarity coefficients of 37% to 60% showed a medium degree of genetic diversity among the species in these eco-areas. Cluster analysis showed that the ten species of Rhodiola can be divided into four clusters and yielded the general and unique biochemical markers of these species. RP-HPLC was shown to be a rapid, repeatable and reliable method for Rhodiola species identification and analysis of genetic diversity.

Gender differences in ghrelin, nociception genes, psychological factors and quality of life in functional dyspepsia

AIM to evaluate gender differences in the aspect of ghrelin,nociception-related genes and psychological aspects and the quality of life(Qo L) in Korean functional dyspepsia(FD) patients.METHODS Total of 191 persons were prospectively enrolled between March 2013 and May 2016 in Seoul National Bundang Hospital,and classified into control and FD group based on ROME Ⅲ criteria. Questionnaire included assessment for dyspepsia symptoms,Qo L and anxiety or depression. Preproghrelin and nociception genes in the gastric mucosa and plasma acyl/des-acyl ghrelin were measured. RESULTS Lower level of plasma acyl ghrelin in FD patients compared to control was significant only in male(15.9 fmol/m L vs 10.4 fmol/m L,P = 0.017). Significantly higher m RNA expressions of nerve growth factor and transient receptor potential vanilloid receptor 1 were observed in male(P = 0.002 and P = 0.014,respectively) than in female. In contrast,female FD patients had a higher anxiety and depression score than male FD(P = 0.029),and anxiety score was correlated with epigastric pain only in female FD patients(female: Spearman rho = 0.420,P = 0.037). The impairment of overall Qo L was more prominent in female FD patients than male patients(5.4 ± 0.3 vs 6.5 ± 0.3,P = 0.020). CONCLUSION Gender differences of ghrelin and nociception-related genes in male and psychological factors in female underlie FD symptoms. More careful assessment of psychological or emotional status is required particularly for the female FD patients.

Intelligent identifi cation method for near-surface ground fi ssures based on seismic data

Taking a study area in Jinzhong Basin in Qixian County,Shanxi Province,as an example,this work performs an intelligent interpretation of ground fissures.On the basis of a complete analysis of the regional geological background in the study area,dip-steering cube operation and median filtering of seismic data were performed using fast Fourier transform to improve the continuity of seismic events and eliminate random noise.A total of 200 stratigraphic continuous sample training points and 500 discontinuous training points were obtained from the processed seismic data.Thereafter,a variety of attributes(coherence,curvature,amplitude,frequency,etc.)were extracted as the input for the multilayer perceptron neural network training.During the training period,the training results were traced by normalized root mean square error(RMSE)and misclassifi cation.The training results showed a downward trend during the training period.The misclassifi cation curve was stable at 0.3,and the normalized RMSE curve was stable at 0.68.When the value of the normalized RMSE curve reached the minimum,the training was terminated,and the training results were extended to the whole data volume to obtain the attribute cube of intelligent ground fi ssure detection.The characteristics of ground fi ssures were analyzed and identifi ed from the sections and slices.A total of 11 ground fissures were finally interpreted.The interpretation results showed that the dip angles were 60°-85°,the fault throws were 0-43 m,and the extension lengths were 300-1,100 m in the whole area.The strike of 73%of the ground fi ssures was consistent with the direction of the regional tectonic settings.Specifi cally,four ground fi ssures coincided with the surface disclosed,and the verifi cation rate reached 100%.In conclusion,the intelligent ground fi ssure detection attribute based on the dip-steering cube is eff ective in predicting the spatial distribution of ground fi ssures.

Hand Gesture Recognition Based on Improved FRNN

The trained Gaussian mixture model is used to make skincolour segmentation for the input image sequences. The hand gesture region is extracted, and the relative normalization images are obtained by interpolation operation. To solve the proem of hand gesture recognition, Fuzzy-Rough based nearest neighbour（RNN） algorithm is applied for classification. For avoiding the costly compute, an improved nearest neighbour classification algorithm based on fuzzy-rough set theory （FRNNC） is proposed. The algorithm employs the represented cluster points instead of the whole training samples, and takes the hand gesture data＇s fuzziness and the roughness into account, so the campute spending is decreased and the recognition rate is increased. The 30 gestures in Chinese sign language alphabet are used for approving the effectiveness of the proposed algorithm. The recognition rate is 94.96%, which is better than that of KNN （K nearest neighbor）and Fuzzy- KNN （Fuzzy K nearest neighbor）.

Enhance Information Flow Tracking with Function Recognition

With the spread use of the computers, a new crime space and method are presented for criminals. Thus computer evidence plays a key part in criminal cases. Traditional computer evidence searches require that the computer specialists know what is stored in the given computer. Binary-based information flow tracking which concerns the changes of control flow is an effective way to analyze the behavior of a program. The existing systems ignore the modifications of the data flow, which may be also a malicious behavior. Thus the function recognition is introduced to improve the information flow tracking. Function recognition is a helpful technique recognizing the function body from the software binary to analyze the binary code. And that no false positive and no false negative in our experiments strongly proves that our approach is effective.

Research of New Concept Sonar—Cognitive Sonar

The performance of a sonar system is closely related to the marine environment and the target characteristics. When dealing with the echoes of a traditional active sonar system, the sonar designers often do not take into account the influence of the environmental information and prior knowledge perceived by sonar receivers, making it difficult to obtain desired processing results. Based on the basic principle and key technology of sonar, this paper proposed a cognition-based intelligent sonar system in theory--cognitive sonar. Cognitive sonar is capable of jointly optimizing the transmission waveform and receiver according to the changes of environment so that its detection and identification performance can be significantly improved.

Using Array Methods to Identify and Process Weak Signals Generated by the Brightlight(Ⅰ) 50t Explosion

Waveforms generated by the 50t explosion of project Brightlight （ I ） were recorded by HILR array. Using array techniques, the author performed identification, f-k analysis, velocity spectrum analysis, etc. of the weak signals. The analysis results show that the signal-to-noise ratio after beamforming was obviously enhanced, and the signal could be clearly shown. The energy from this explosion was mainly concentrated in the 1 -8Hz range from f-k analysis. The velocity spectrum gave clear positions of event phases, which could not be seen in the original weak signals. The maximum energy distribution obtained by the Beaman method is close to the theoretical value in the azimuth-slowness domain.

Possible contribution of artificial neural networks and linear discriminant analysis in recognition of patients with suspected atrophic body gastritis

AIM: To investigate whether ANNs and LDA could recognize patients with ABG in a database, containing only clinical and biochemical variables, of a pool of patients with and without ABG, by selecting the most predictive variables and by reducing input data to the minimum.METHODS: Data was collected from 350 consecutive outpatients (263 with ABG, 87 with non-atrophic gastritis and/or celiac disease [controls]). Structured questionnaires with 22 items (anagraphic, anamnestic, clinical, and biochemical data) were filled out for each patient. All patients underwent gastroscopy with biopsies. ANNs and LDA were applied to recognize patients with ABG.Experiment 1: random selection on 37 variables, experiment 2: optimization process on 30 variables, experiment 3:input data reduction on 8 variables, experiment 4: use of only clinical input data on 5 variables, and experiment 5:use of only serological variables.RESULTS: In experiment 1, overall accuracies of ANNs and LDA were 96.6% and 94.6%, respectively, for predicting patients with ABG. In experiment 2, ANNs and LDA reached an overall accuracy of 98.8% and 96.8%,respectively. In experiment 3, overall accuracy of ANNs was 98.4%. In experiment 4, overall accuracies of ANNs and LDA were, respectively, 91.3% and 88.6%. In experiment 5, overall accuracies of ANNs and LDA were,respectively, 97.7% and 94.5%.CONCLUSION: This preliminary study suggests that advanced statistical methods, not only ANNs, but also LDA,may contribute to better address bioptic sampling during gastroscopy in a subset of patients in whom ABG may be suspected on the basis of aspecific gastrointestinal symptoms or non-digestive disorders.