Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8301971
Xuliang Zhang, Sudi Lou
Due to “semantic gap”, the problem of image emotional semantic annotation has not been solved. In this parper, a method of emotion semantic annotation for cheongsam images based on Fusion Features has been proposed. Multi-features including the color and texture are used to describe the content of the image. Then least squares support vector machine for regression which is optimized by particle swarm optimization is used to build the mapping between the feature space and emotional space. The experiment indicates that this method achieves good effect.
{"title":"Image emotional semantic annotation based on fusion features","authors":"Xuliang Zhang, Sudi Lou","doi":"10.1109/CISP-BMEI.2017.8301971","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8301971","url":null,"abstract":"Due to “semantic gap”, the problem of image emotional semantic annotation has not been solved. In this parper, a method of emotion semantic annotation for cheongsam images based on Fusion Features has been proposed. Multi-features including the color and texture are used to describe the content of the image. Then least squares support vector machine for regression which is optimized by particle swarm optimization is used to build the mapping between the feature space and emotional space. The experiment indicates that this method achieves good effect.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"66 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77922780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8302073
Hongze Xiao, Liqing Li, J. Wang, Shuhuai Huo
This paper proposes an improved threshold segmentation to turn the image of fluffs into binary image, the noises and impurities in the image are eliminated by using Gauss filtering and the method of features statistics of color fluffs, then the centroid coordinate of each color fluff is calculated and the location information of each color fluff is obtained, finally every color fluff is detected and eliminated. The experiment proved that the threshold segmentation has the characteristics of high detection rate and fast calculate speed.
{"title":"The application of improved threshold segmentation on detection of color fluff","authors":"Hongze Xiao, Liqing Li, J. Wang, Shuhuai Huo","doi":"10.1109/CISP-BMEI.2017.8302073","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302073","url":null,"abstract":"This paper proposes an improved threshold segmentation to turn the image of fluffs into binary image, the noises and impurities in the image are eliminated by using Gauss filtering and the method of features statistics of color fluffs, then the centroid coordinate of each color fluff is calculated and the location information of each color fluff is obtained, finally every color fluff is detected and eliminated. The experiment proved that the threshold segmentation has the characteristics of high detection rate and fast calculate speed.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"5 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81464671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8302072
Haowei Zhang, X. Ren, Y. Liu, Qi-Xu Zhou
Magnetic resonance imaging has a long examination time, causing additional pain to glioma patients and causing artifacts in the image. In this paper, a combination of compressed sensing and MRI is used. Base pursuit algorithm, matching pursuit algorithm, orthogonal matching pursuit algorithm, stagewise orthogonal matching pursuit algorithm are used to reconstruct the MRI of glioblastoma, and the subjective and objective evaluation of the reconstructed results is carried out by using gray level co-occurrence matrix, peak signal-to-noise ratio and visual image. In this way, the best expression of the image is selected, thus shortening the time of MRI scanning, reducing the pain of the patient and improving the quality of the image.
{"title":"The application of compressed sensing reconstruction algorithms for MRI of glioblastoma","authors":"Haowei Zhang, X. Ren, Y. Liu, Qi-Xu Zhou","doi":"10.1109/CISP-BMEI.2017.8302072","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302072","url":null,"abstract":"Magnetic resonance imaging has a long examination time, causing additional pain to glioma patients and causing artifacts in the image. In this paper, a combination of compressed sensing and MRI is used. Base pursuit algorithm, matching pursuit algorithm, orthogonal matching pursuit algorithm, stagewise orthogonal matching pursuit algorithm are used to reconstruct the MRI of glioblastoma, and the subjective and objective evaluation of the reconstructed results is carried out by using gray level co-occurrence matrix, peak signal-to-noise ratio and visual image. In this way, the best expression of the image is selected, thus shortening the time of MRI scanning, reducing the pain of the patient and improving the quality of the image.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"26 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76555025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8302194
C. Qiu, Yiheng Cai, X. Gao, Yize Cui
Recent years CNN (Convolutional Neural Network) has performed well in image processing, including image retrieval. However, since the features of CNN extraction are usually high-dimensional, and in the massive data conditions, it is a rather time-consuming process to traverse all the images and calculate the distance between the feature vectors to accurately find the closest Top K images. The proposed paper uses an effective deep learning framework in which Deep Convolution Network is combined with Hash Coding to learn rich medical image representing through CNN. First, a hash layer is added to the network to represent the image information as binary hashing codes; Simultaneously, the dimension of feature vector is effectively reduced by the framework; then, In order to improve the accuracy of image retrieval, rough searching and fine searching are combined. The experimental results show that our method is optimal than several hashing algorithms and CNN methods on the TCIA-CT database and VIA/I-ELCAP database.
{"title":"Medical image retrieval based on the deep convolution network and hash coding","authors":"C. Qiu, Yiheng Cai, X. Gao, Yize Cui","doi":"10.1109/CISP-BMEI.2017.8302194","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302194","url":null,"abstract":"Recent years CNN (Convolutional Neural Network) has performed well in image processing, including image retrieval. However, since the features of CNN extraction are usually high-dimensional, and in the massive data conditions, it is a rather time-consuming process to traverse all the images and calculate the distance between the feature vectors to accurately find the closest Top K images. The proposed paper uses an effective deep learning framework in which Deep Convolution Network is combined with Hash Coding to learn rich medical image representing through CNN. First, a hash layer is added to the network to represent the image information as binary hashing codes; Simultaneously, the dimension of feature vector is effectively reduced by the framework; then, In order to improve the accuracy of image retrieval, rough searching and fine searching are combined. The experimental results show that our method is optimal than several hashing algorithms and CNN methods on the TCIA-CT database and VIA/I-ELCAP database.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"22 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75975198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8302125
Chuang Han, Xiaofeng Ma, Hongyue Qu, Zhongzheng Li
According to the single vector hydrophone positioning theory, some experiments were done in the pool. The noncoherent sources positioning and coherent sources positioning were tested respectively. The experimental results agree with the theoretical results, which validate the feasibility of the academic and provides experimental basis for engineering application.
{"title":"Experimental study on single vector hydrophone positioning","authors":"Chuang Han, Xiaofeng Ma, Hongyue Qu, Zhongzheng Li","doi":"10.1109/CISP-BMEI.2017.8302125","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302125","url":null,"abstract":"According to the single vector hydrophone positioning theory, some experiments were done in the pool. The noncoherent sources positioning and coherent sources positioning were tested respectively. The experimental results agree with the theoretical results, which validate the feasibility of the academic and provides experimental basis for engineering application.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"170 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76197182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ABO blood type research is not only used for transfusion medicine, but also for the study of some diseases. In this study, principal component analysis is used to take the ABO blood group Raman spectrum of the Fourier transform, in order to improve the ABO blood typing sample recognition rate. When the principal component analysis is performed directly on the Raman spectrum, the differences between the ABO three blood samples can not be well recognized by the score data of the second and the twentieth main components. The Raman spectra of the fluorescence background is extracted from the Raman spectra by Fourier transform, so the imaginary part of the Raman spectrum is obtained. Then, the principal component of the imaginary part signal is analyzed, and fractional graphs of the second principal component and the twentieth principal component are used. In this way, the blood samples of type A, type B and O type are distinguished. The experimental results show that the principal component analysis is carried out by Fourier transform to improve the clustering effect of spectral data, making ABO three blood groups easier to be distinguished. The reason for the enhancement of the clustering effect is that the internal difference of the same kind of spectral data will be reduced and that the difference of the spectral data of different classes will be increased by Fourier transform.
{"title":"Raman spectroscopy analysis based on fourier transform for ABO blood group identification","authors":"Haihong Lin, Haotian Yu, Jichun Li, Encai Zhang, Guannan Chen","doi":"10.1109/CISP-BMEI.2017.8302232","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302232","url":null,"abstract":"ABO blood type research is not only used for transfusion medicine, but also for the study of some diseases. In this study, principal component analysis is used to take the ABO blood group Raman spectrum of the Fourier transform, in order to improve the ABO blood typing sample recognition rate. When the principal component analysis is performed directly on the Raman spectrum, the differences between the ABO three blood samples can not be well recognized by the score data of the second and the twentieth main components. The Raman spectra of the fluorescence background is extracted from the Raman spectra by Fourier transform, so the imaginary part of the Raman spectrum is obtained. Then, the principal component of the imaginary part signal is analyzed, and fractional graphs of the second principal component and the twentieth principal component are used. In this way, the blood samples of type A, type B and O type are distinguished. The experimental results show that the principal component analysis is carried out by Fourier transform to improve the clustering effect of spectral data, making ABO three blood groups easier to be distinguished. The reason for the enhancement of the clustering effect is that the internal difference of the same kind of spectral data will be reduced and that the difference of the spectral data of different classes will be increased by Fourier transform.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"13 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86810516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8301906
Siyang Wu, Dongfang Chen, Xiaofeng Wang
In view of the ghost phenomenon appear in the ViBe (Visual Background Extractor) algorithm, by analyzing the common motion detection algorithm, this paper presents an improved algorithm based on ViBe. The method uses real-time characteristic method of frame difference, combines the three frames difference images and ViBe difference image to logical operation, it can make up the frame difference method of moving objects which always appears empty phenomenon, and quickly eliminate the first frame ViBe background modeling appears “ghost” phenomenon. The experimental results show that the improved ViBe algorithm can quickly eliminate the “ghost” phenomenon, and has good robustness.
{"title":"Moving target detection based on improved three frame difference and visual background extractor","authors":"Siyang Wu, Dongfang Chen, Xiaofeng Wang","doi":"10.1109/CISP-BMEI.2017.8301906","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8301906","url":null,"abstract":"In view of the ghost phenomenon appear in the ViBe (Visual Background Extractor) algorithm, by analyzing the common motion detection algorithm, this paper presents an improved algorithm based on ViBe. The method uses real-time characteristic method of frame difference, combines the three frames difference images and ViBe difference image to logical operation, it can make up the frame difference method of moving objects which always appears empty phenomenon, and quickly eliminate the first frame ViBe background modeling appears “ghost” phenomenon. The experimental results show that the improved ViBe algorithm can quickly eliminate the “ghost” phenomenon, and has good robustness.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"2 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86938446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8301974
Gang Shen, Yuteng Ye
Spectral clustering has recently achieved a plenty of successful applications in the fields of image processing and object pattern recognition. However, it is a frequent challenging problem that many spectral clustering algorithms suffer from the sensitivity in the selection of the parameters for their Gaussian kernel functions and K-means partitioning processes. To alleviate this situation, we first construct a distance matrix and project the data points into the eigen-space spanned by the selected eigenvectors, then we apply the proposed partitioning algorithm inspired by the continuity of data distribution. In order to partition the data points projected on the eigenvectors, we formulate a cost function with quadratic data-fidelity and L0 gradient constraint, and the optimal solution can be obtained with the use of alternating direction method of multipliers (ADMM). The proposed approach has been tested for the image segmentation problems. The experiments on the benchmark image datasets showed that the proposal was able to achieve efficient and effective results with the help of the superpixels.
{"title":"A distance-based spectral clustering approach with L0 Gradient Minimization","authors":"Gang Shen, Yuteng Ye","doi":"10.1109/CISP-BMEI.2017.8301974","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8301974","url":null,"abstract":"Spectral clustering has recently achieved a plenty of successful applications in the fields of image processing and object pattern recognition. However, it is a frequent challenging problem that many spectral clustering algorithms suffer from the sensitivity in the selection of the parameters for their Gaussian kernel functions and K-means partitioning processes. To alleviate this situation, we first construct a distance matrix and project the data points into the eigen-space spanned by the selected eigenvectors, then we apply the proposed partitioning algorithm inspired by the continuity of data distribution. In order to partition the data points projected on the eigenvectors, we formulate a cost function with quadratic data-fidelity and L0 gradient constraint, and the optimal solution can be obtained with the use of alternating direction method of multipliers (ADMM). The proposed approach has been tested for the image segmentation problems. The experiments on the benchmark image datasets showed that the proposal was able to achieve efficient and effective results with the help of the superpixels.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"205 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87130039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8302267
Zhifeng Lin, Zhihua Huang
The prospect of Motor Imagery (MI) BCI is attracting the researchers around the world. For MI BCI, training a user is a difficult and time-consuming task. This study aims at finding the pattern of Event-related Potentials, by which we can improve the training process, during training MI users. We designed the experiments, acquired the EEG signals and analyzed them during the periods when the subjects were executing the training trials and when they completed the training trials. The results show that the obvious potential patterns that are related to small probability events exist in the both situations and the elicited potentials on frontal lobe are commonly stronger than ones on other brain areas. We speculate that Attention Mechanism is deeply involved in the process of MI training. The finding would underlie our future work intending to develop the new MI training means and algorithm.
{"title":"Research on event-related potentials in motor imagery BCI","authors":"Zhifeng Lin, Zhihua Huang","doi":"10.1109/CISP-BMEI.2017.8302267","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302267","url":null,"abstract":"The prospect of Motor Imagery (MI) BCI is attracting the researchers around the world. For MI BCI, training a user is a difficult and time-consuming task. This study aims at finding the pattern of Event-related Potentials, by which we can improve the training process, during training MI users. We designed the experiments, acquired the EEG signals and analyzed them during the periods when the subjects were executing the training trials and when they completed the training trials. The results show that the obvious potential patterns that are related to small probability events exist in the both situations and the elicited potentials on frontal lobe are commonly stronger than ones on other brain areas. We speculate that Attention Mechanism is deeply involved in the process of MI training. The finding would underlie our future work intending to develop the new MI training means and algorithm.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88382719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-10-01DOI: 10.1109/CISP-BMEI.2017.8302027
Zhang Tao, L. Wan, Xiaolei Lv, Jun Hong
A modified joint-pixel algorithm for autoregistration and interferometric phase denoising is proposed in this paper. For the blindness of the sample selection in joint-pixel method, this paper first analyzes the distribution that the sample obeyed. Under the guidance of this distribution, amplitude and phase estimation models of joint-pixel method are established. Through the preprocessing on the phase and amplitude of the two interferometric SAR images, an effective sample to estimate the true value is achieved. Moreover, taking advantage of the coherence information of the effective samples, the proposed method automatically registers the SAR images while denoising without the loss of detail. Compared with the original method, the interferogram can be estimated more accurate and the influence of the abnormal amplitude points on the surrounding is reduced. Furthermore, in order to solve the contradiction of preserving texture and filtering strength, an iterative algorithm is invented. In the end, the effectiveness of this modified algorithm is validated by both simulated and real data.
{"title":"A modified joint-pixel based SAR interferogram auto-registration and denoising method","authors":"Zhang Tao, L. Wan, Xiaolei Lv, Jun Hong","doi":"10.1109/CISP-BMEI.2017.8302027","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2017.8302027","url":null,"abstract":"A modified joint-pixel algorithm for autoregistration and interferometric phase denoising is proposed in this paper. For the blindness of the sample selection in joint-pixel method, this paper first analyzes the distribution that the sample obeyed. Under the guidance of this distribution, amplitude and phase estimation models of joint-pixel method are established. Through the preprocessing on the phase and amplitude of the two interferometric SAR images, an effective sample to estimate the true value is achieved. Moreover, taking advantage of the coherence information of the effective samples, the proposed method automatically registers the SAR images while denoising without the loss of detail. Compared with the original method, the interferogram can be estimated more accurate and the influence of the abnormal amplitude points on the surrounding is reduced. Furthermore, in order to solve the contradiction of preserving texture and filtering strength, an iterative algorithm is invented. In the end, the effectiveness of this modified algorithm is validated by both simulated and real data.","PeriodicalId":6474,"journal":{"name":"2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"27 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82684211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：