{"title":"Constitution Identification of Tongue Image Based on CNN","authors":"Hao Zhou, Guangqin Hu, Xinfeng Zhang","doi":"10.1109/CISP-BMEI.2018.8633075","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633075","url":null,"abstract":"The physique of traditional Chinese medicine (TCM) is the quality of our body and the tongue image is a manifestation based on the metabolism of the body. The constitution can be easily and objectively identified by the image of the tongue. In this paper, the classical convolution neural network (CNN) and gray level co-occurrence matrix, minimum enclosing rectangle and edge curve are used to extract the features of human tongue. Then different classifier are used to classify different constitution, and finally by comparing the accuracy and complexity of the two methods, we proposed a method constitution identification of TCM which is based on tongue images. The data set used in the experiment is provided and acquired by the Department of TCM in the hospital of Beijing University of Technology. In this paper, the accuracy of the three types of physique classification of Qi deficiency, damp heat and phlegm dampness is 63%, and the accuracy of traditional machine learning algorithm is respectively 30%,56% and 66%. It is of great significance to clinical, teaching and scientific research of TCM by making the most of the deep learning network and the auxiliary identification of physique.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126242920","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}
Xiaochun Wang, Sheng Zhou, Yanqun Wang, Jianjun Ji, Jun Yang
{"title":"Experimental Study of a Simulated Blood Flow Velocity Measurement System via Very-High-Frequency Ultrasound","authors":"Xiaochun Wang, Sheng Zhou, Yanqun Wang, Jianjun Ji, Jun Yang","doi":"10.1109/CISP-BMEI.2018.8633096","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633096","url":null,"abstract":"To design and implement a simulated blood flow velocity measurement system via very-high-frequency (VHF)ultrasound, which can be used to complete an experimental study that simulates the real-time detection of blood flow information from human superficial organs. We prepared a blood phantom that was composed of nylon particles, pure water, glycerol, dextran and non-ionic surfactant. The experimental platform of this system included a simulated blood circulation system consisting of a medical injection pump for controlling the flow velocity, a medical silicone tube, and a simulated blood phantom; a single pulse, mechanical, linear scanning probe with an operation frequency of 50 MHz; the ultrasound echo signal acquisition circuit of the slave computer; and the VHF ultrasound blood flow imaging system composed of the host computer modules. The transducer was placed approximately 9 mm above the simulated blood vessel, and the direction of blood flow was same to the scanning direction of the probe. The pushing speed of the injection pump was adjusted to obtain the simulated blood imaging near the focal area. The acoustic characteristics of the homemade blood phantom were nearly unchanged for 150 days, which met the requirements of experimental research. According to the imaging results of the simulated blood flow at various flow velocities, the red blood cell imaging particles are large and the number is small when the flow velocity is low, and the red blood cell imaging particles are small and the number is large when the flow velocity is high. The directly proportional relationship between the number of red blood cell imaging particles of the simulated blood and the blood flow velocity can preliminarily be obtained by the designed blood flow velocity measurement system via VHF ultrasound, and the blood flow velocity can be determined accordingly.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126689808","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}
{"title":"Shape Adaptive Texture Coding Based on Wavelet-Based Contourlet Transform","authors":"Zhenghua Shu, Guodong Liu, Zhihua Xie, Z. Ren","doi":"10.1109/CISP-BMEI.2018.8633164","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633164","url":null,"abstract":"Transform coding of arbitrary shape object is one of the core technologies of MPEG-4 video coding. In this chapter, we propose a shape adaptive Wavelet-Based Contourlet Transform framework for MPEG4 texture coding. In the shape adaptive texture coding framework, Wavelet-Based Contourlet Transform is divided into two parts: the Wavelet-Based Contourlet Transform of the shape mask, and the Wavelet-Based Contourlet Transform of the object texture. In the Wavelet-Based Contourlet Transform phase, the shape coding is carried out using lazy Wavelet-Based Contourlet Transform, and the texture coding is carried out by 9/7 wavelets in the form of lifting. In the zerotree quantization stage of wavelet coefficients, three quantization methods are adopted according to different needs. The experimental results show that the Wavelet-Based Contourlet Transform texture coding based on object has similar low complexity with the texture coding, such as SADCT, and the performance is better. Moreover, the coding effect is better than that of SADCT at low bit rate.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121054025","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}
{"title":"Least Squares Twin SVM Based on Partial Binary Tree Algorithm","authors":"Qing Yu, R. Liu","doi":"10.1109/CISP-BMEI.2018.8633117","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633117","url":null,"abstract":"Based on the classic least squares twin support vector machine (LSTSVM), an efficient but simple Least Squares Twin Support Vector Machine-Partial Binary Tree (LSTSVM-PBT)for binary classification problem was proposed. This algorithm introduces binary tree into LSTSVM, the problem summed up as binary tree classification for each data ultimately. Compared to traditional SVM, LSTSVM-PBT has low time complexity. Reliable theoretical analysis and extensive experiments show that LSTBSVM-PBT is fast computationally and obtain the higher performance than traditional algorithm.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114259349","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}
{"title":"Novel Image Dehazing Algorithm Using Scene Segmentation and Open Channel Model","authors":"Taian Xu","doi":"10.1109/CISP-BMEI.2018.8633159","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633159","url":null,"abstract":"This paper presents a novel image dehazing method based upon scene depth segmentation and the open dark channel model. After analysis of the fog-day imaging model and the nature of the captured image fog distribution in the distant and near-field regions, the original image is divided into two areas, namely, the near and the far field. Subsequently, the transmittance in the far field is corrected further. Furthermore, the method uses an open-dark channel model and guided filtering to restore the image twice, so that the deblurred image boundary transition is more natural leading to the avoidance of the halo artifacts. The experimental results show that the proposed method recovers the clear fog shooting images better, the visual effects are significantly improved, and it has a wide domain of application.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131507323","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}
{"title":"Understanding the Scattering Transform Using Univariate Signals","authors":"Youngmi Hur, Hyojae Lim","doi":"10.1109/CISP-BMEI.2018.8633161","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633161","url":null,"abstract":"In this paper, we review the scattering transform in the univariate setting. After reviewing its properties including translation invariance, stability under small diffeomorphism, and ability to carry high-frequency information, we investigate how these properties can be used in understanding the effect of the scattering transform when various types of signal deformation are considered. We find that, together with the Fourier transform modulus, the scattering transform can be used in classifying some of these deformations.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130189587","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}
{"title":"Chirplet-Atoms Network Approach to High-Resolution Range Profiles Automatic Target Recognition","authors":"Yifei Li, Zunhua Guo","doi":"10.1109/CISP-BMEI.2018.8633206","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633206","url":null,"abstract":"Since radar back-scattering from a real target can be very complex, a Chirplet-atoms network approach to automatic target recognition using high resolution range profiles (HRRP)is proposed in this paper. Based on the multilayer feed-forward neural network structure, the Chirplet-atom transform is used to the input layer for feature extraction, and the hidden layer and output layer constitute a classifier. The network weights and the parameters of Chirplet-atom node are simultaneously adjusted to achieve joint feature extraction and target classification. The simulation results of four aircrafts have shown that the Chirplet-atoms network approach has better recognition rates and noisy immunity.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133291524","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}
{"title":"NBI Parameter Estimation in DSSS Communications Based on Partial Reconstruction","authors":"Yongshun Zhang, Weigang Zhu, Xin Jia, Yonghua He","doi":"10.1109/CISP-BMEI.2018.8633168","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633168","url":null,"abstract":"The existing NBI parameter estimation algorithms for DSSS communications are confined to the high sampling rate. In order to solve the problem above, the compressive sensing (CS)is applied to the NBI parameter estimation in DSSS communications. A partial reconstruction algorithm is proposed to get the NBI feature vector from the compressed signal using the different feature of DSSS signal and NBI in compressed domain and the block sparsity feature of NBI in frequency domain. Besides, an edge location estimation method is proposed to realize the NBI parameter estimation by estimating the edge of the transformed feature vector. We will achieve the NBI bandwidth estimation after we get the edge location. Reported simulation results demonstrate that the proposed methods are effective to the NBI parameter estimation in DSSS communications. The performance is mainly affected by the variety of interference intensity and compression rate. Under the condition of same interference bandwidth, the larger the interference intensity is and the greater the compression rate is, the better the interference parameter estimation performance is.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134538440","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}
{"title":"The Design of Seven-Lead Electrocardiograph Monitoring System Based on Wi-Fi","authors":"Jinling Zhang, Ruijie Sun, Siyi Wang","doi":"10.1109/CISP-BMEI.2018.8633042","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633042","url":null,"abstract":"Aiming at the needs of applications of home-based care for the aged and communities, this paper presents a seven-lead electrocardiograph (ECG) monitoring system based on Wi-Fi short-range wireless transmission technology. The system mainly consists of two parts: the seven-lead ECG monitoring device and the ECG monitoring platform. The Seven-lead ECG monitoring device mainly consists of the ECG pre-processing module, integrated analog front end, the micro-controller, the Wi-Fi wireless transmission module and the power module. This system has the advantages of miniaturization, low power consumption and high performance. The ECG monitoring system uses Wi-Fi wireless transmission technology to send the ECG data of monitored by the seven-lead ECG monitoring device to the ECG monitoring platform of the monitoring center for real-time display of ECG waveforms. Doctors can obtain the health status of the patients who recuperates at home or the aged of community by the community ECG monitoring system and which can also remind the aged of abnormal ECG signals in time to go for a further physical examination for reducing the sudden death rate of the cardiovascular disease.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115046135","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}
{"title":"Blind Estimation of Chaotic Spread Spectrum Sequences by Neural Network","authors":"Lili Xiao, Guixin Xuan, Yongbin Wu","doi":"10.1109/CISP-BMEI.2018.8633136","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2018.8633136","url":null,"abstract":"Chaotic spread spectrum sequences have higher complexity than traditional direct spread sequences, but they are difficult to estimate chaotic direct spread sequences blindly. In order to blind estimate it effectively, an improved method is proposed to blind estimate the chaotic spread spectrum sequences based on the neural network. This method takes full advantages of the neural network's nonlinearity and increases the blind signal separation module. The simulation results show that the method does not need to search the synchronization point between the information code and the spreading sequence. Even under the condition of low SNR(signal to noise ratio), the chaotic spread spectrum signal can be effectively separated from the noise background and blind. The original chaotic sequence is also estimated.","PeriodicalId":117227,"journal":{"name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123170357","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}