2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)最新文献

Detection of epileptiform spikes based on active learning 基于主动学习的癫痫状尖峰检测

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624433

Jinhan Wu, Zhen Mei, Zhihua Huang

{"title":"Detection of epileptiform spikes based on active learning","authors":"Jinhan Wu, Zhen Mei, Zhihua Huang","doi":"10.1109/CISP-BMEI53629.2021.9624433","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624433","url":null,"abstract":"Epilepsy is a neurological disorder characterized by recurrent abnormal neuronal discharges. Electroencephalogram is often used clinically to assist in the diagnosis and treatment of epilepsy. The spikes and sharps contain a large amount of epilepsy-related pathological information, so the detection of spikes and sharps among the abnormal epileptic waveforms has more clinical diagnostic value. There are two problems in using machine learning to achieve automatic recognition of spike and sharp waves. One is that most of the EEG data are unlabeled data, and it is difficult to obtain a large number of labeled training sets; the other is that spikes and sharps are mixed with plenty of background waves, which lead to a data imbalance trouble. Based on the above backdrop, this paper implements a detection framework of epileptiform spikes using active learning in order to achieve better recognition results with as little cost as possible, and its major contributions are as follows: (1)The KNN attention layer is introduced in the learning engine to improve the generalization ability of the model in the case of few samples; (2)In terms of the sampling engine, MPGR (Manifold Preserving Graph Reduction) pre-processing is first performed to initially reduce the imbalance rate of the data and remove redundant points, then density-weighted uncertainty based on GAN is used to accelerate the efficiency of active learning, and finally boundary distance-based clustering sampling is used, which is to ensure diversity while taking balanced samples as much as possible. Results of experiments conducted on a hospital-supplied dataset show that the proposed framework is effective.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116630005","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}

引用次数: 1

Underwater hyperspectral image recovery based on a single chromatic aberration blur image using deep learning 基于深度学习的单色差模糊图像水下高光谱图像恢复

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624214

Jiarui Zhao, Yunzhuo Liu, Shu-yue Zhan

{"title":"Underwater hyperspectral image recovery based on a single chromatic aberration blur image using deep learning","authors":"Jiarui Zhao, Yunzhuo Liu, Shu-yue Zhan","doi":"10.1109/CISP-BMEI53629.2021.9624214","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624214","url":null,"abstract":"Hyperspectral imaging technology can capture the spatial information and spectral information in the scene, so it has a wide range of application prospects in the fields of remote sensing and target recognition. The underwater environment will absorb or scatter the light beam emitted by the light source, which makes it difficult for the light sensing element to perceive all the spectral information of the target, resulting in problems such as low resolution, high complexity, and long exposure time of underwater hyperspectral imaging. We propose a novel underwater hyperspectral imaging method, using a self-developed lens with longitudinal chromatic aberration in front of a monochrome camera. This device captures a single frame of chromatic aberration blur image at a fixed focus position (550nm) to realize the recovery of 146 bands of hyperspectral image in the range of 430nm-720nm. In this paper, the U-NET network in the convolutional neural network is implemented to complete the training process from a single chromatic aberration blurred image to a hyperspectral image through the deep learning method, and achieve good experimental results in the laboratory. The results show that this method is feasible and can effectively extract hyperspectral images from monochromatic chromatic aberration blurred images.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117220407","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}

引用次数: 0

Completion of Global Navigation Satellite System Missing Data Based on Bidirectional Recurrent Neural Network 基于双向递归神经网络的全球卫星导航系统缺失数据补全

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624414

Xiangwei Kong, Linxuan Wang, Hong Li, Zhen-duo Wu, Yu Wu

{"title":"Completion of Global Navigation Satellite System Missing Data Based on Bidirectional Recurrent Neural Network","authors":"Xiangwei Kong, Linxuan Wang, Hong Li, Zhen-duo Wu, Yu Wu","doi":"10.1109/CISP-BMEI53629.2021.9624414","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624414","url":null,"abstract":"In fight test, Global Navigation Satellite System (GNSS) data missing inevitably in GNSS data recording attribute to such factors as satellite anomalies, follow-up reject of gross errors and so on. It has serious effects on the data correlation, principle component analysis and spectral analysis. Thus it is significant to fill missing values by interpolation method in the GNSS time series of aircraft. The research result of time series interpolation problem has already rich but time serious methods frequently-used such as traditional interpolation method, empirical Orthogonal Function and Singular Spectrum Analysis still have some disadvantages: For example, local feature fitting of the time series is not very good or the conditions of appliance is so harsh that it is hard to application and extension and It is easy to cause artificial distortion of the reconstructed time series. The article has presented a way of filling missing GNSS values of aircraft based on bidirectional recurrent neural network. Experiments in the article are carried out with samples from the complete time series of a plane throughout the year. Then we trained the bidirectional recurrent neural network and used the interpolation method to complete some groups missing GNSS values that missing time is three minutes, six minutes, nine minutes, twelve minutes, fifteen minutes respectively. Finally, the accuracy and validity of the experimental model used for completing the time seriously by interpolation method are verified.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124797375","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}

引用次数: 0

Positional Mask Attention for Video Sequence Modeling 视频序列建模中的位置掩码注意事项

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624361

Jiaxuan Wang, Chaoyi Wang, Yang Hua, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

{"title":"Positional Mask Attention for Video Sequence Modeling","authors":"Jiaxuan Wang, Chaoyi Wang, Yang Hua, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan","doi":"10.1109/CISP-BMEI53629.2021.9624361","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624361","url":null,"abstract":"The attention mechanism has been widely developed in different domains. Some recent studies apply position embedding to encode relative positions in the attention mechanism for learning better representations in both natural language processing and computer vision tasks. However, this position embedding method is limited to the “fixed input size” problem and requires large additional memory to store the position embedding parameters. In this paper, we present the positional mask attention, which is a new approach to incorporate position information into the attention mechanism. Specifically, a positional distance mask is proposed to encode the relative positions as a type of prior knowledge, which is different from the existing position embedding methods. To verify the generality and effectiveness of the proposed method, we evaluate our positional mask attention on two general video understanding tasks, i.e., video object detection and video instance segmentation. Experimental results demonstrate that our method can achieve significant improvement by aggregating the position information.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124876627","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}

引用次数: 0

Reliability and Validity of a Wearable Inertial Sensor System for Gait Assessment in Healthy Young Adults 用于健康年轻人步态评估的可穿戴惯性传感器系统的可靠性和有效性

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624463

Ying Hou, Shujia Wang, Jinping Li, Sana Komal, Ke Li

{"title":"Reliability and Validity of a Wearable Inertial Sensor System for Gait Assessment in Healthy Young Adults","authors":"Ying Hou, Shujia Wang, Jinping Li, Sana Komal, Ke Li","doi":"10.1109/CISP-BMEI53629.2021.9624463","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624463","url":null,"abstract":"Wearable inertial sensors are considered to be low cost, portable and user-friendly for gait assessment. But relatively little is known about their reliability and validity compared with the other well-established, sophisticated techniques. This study aimed to determine the reliability and validity of an inertial sensor system (APDM Mobility Lab). A total of 20 participants were commanded to take a 10-m walk at their self-selected speeds. A series of gait parameters were collected and analyzed by this wearable gait analysis system and a three-dimension (3-D) motion analysis system simultaneously. The reliability of APDM system was evaluated using interclass correlation coefficient (ICC). The Pearson correlation analysis was used to evaluate the relations of spatiotemporal parameters from the two systems. Furthermore, Bland-Altman analysis was applied to evaluate the validity of APDM system. Results showed that the inertial sensor system of APDM Mobility Lab demonstrated excellent reliability $(text{ICC}=0.905-0.991)$. The parameters analyzed by APDM system and 3-D motion capture system showed moderate to high correlations for stride length, mean velocity and cadence $(mathrm{r}= 0.551-0.875)$. Moreover, Bland-Altman analysis demonstrated that the bias of all parameters approached to zero, particularly for the stride time, stride length and mean velocity. The wearable inertial sensor-based system used in this study is a comparatively reliable and valid tool for spatiotemporal gait assessment in healthy adults.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126723980","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}

引用次数: 5

Human Activity Recognition in Thermal Infrared Imaging Based on Deep Recurrent Neural Networks 基于深度递归神经网络的热红外成像人体活动识别

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624325

Samah A. F. Manssor, Zhengyun Ren, Rong Huang, Shaoyuan Sun

{"title":"Human Activity Recognition in Thermal Infrared Imaging Based on Deep Recurrent Neural Networks","authors":"Samah A. F. Manssor, Zhengyun Ren, Rong Huang, Shaoyuan Sun","doi":"10.1109/CISP-BMEI53629.2021.9624325","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624325","url":null,"abstract":"Human activity recognition (HAR) is a vast branch of research that focuses on determining the specific action of a person according to sensor data. However, predicting human activity at night is still challenging due to the lack of sufficient accuracy of sensor data. A new model for multimodal thermal infrared data-based HAR (MTIR-HAR) is presented in this paper which can enhance the HAR accuracy by automatically learning the human features from the raw data. Six extra deep layers are added to the recurrent neural network (RNN) to improve the performance of the HAR system at night. These layers extract the most complex features from thermal infrared imaging for classification. The sequence classification technique is applied to separately merged data. The experimental results showed that the proposed method outperformed (up to 98.0%) on the MHAD dataset than the SVM and LSTM methods. Furthermore, the method has achieved the highest accuracy rates (up to 80.2%) compared with other related results in the same DHU Night Dataset under different walking conditions.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115257813","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}

引用次数: 4

Research of Public Opinion Based on Opinion Leaders and Saturated Contact Rates 基于意见领袖与饱和接触率的民意研究

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624407

Shan Liu, Chenyang Qian, Qiting Tan, Miaoru Zhang, Rui Xia, Min Du

引用次数: 0

Multi-Task Learning for False-Positive Reduction and Segmentation of Cerebral Aneurysms in CTA Scans 多任务学习在CTA扫描中对脑动脉瘤的假阳性复位和分割

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624435

Heng Lin, Yuanfang Qiao, F. Shi, Dahong Qian, Na Hu, Lizhou Chen, Bin Song, Ke Wu, Lichi Zhang

{"title":"Multi-Task Learning for False-Positive Reduction and Segmentation of Cerebral Aneurysms in CTA Scans","authors":"Heng Lin, Yuanfang Qiao, F. Shi, Dahong Qian, Na Hu, Lizhou Chen, Bin Song, Ke Wu, Lichi Zhang","doi":"10.1109/CISP-BMEI53629.2021.9624435","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624435","url":null,"abstract":"The computer-aided diagnosis for cerebral aneurysms consists of three major steps, which are lesion detection, false-positive reduction, and segmentation. Many methods based on deep learning technology have been designed for each of these tasks separately, without the shared information to further collaborate these models with each other, and therefore limit their further performance improvements. In this paper, we propose a novel framework to perform false positive reduction and aneurysm segmentation jointly in a multi-task manner. In this way, both false-positive reduction and segmentation networks can mutually share information between each other and facilitate together. We also incorporate the vessel segmentation information in the framework, which can provide important priors for false-positive reduction and segmentation. The proposed network is evaluated on a public dataset of cerebral aneurysms. Experimental results show that our vessel-guided multi-task model can achieve improved performance than separately training the false positive reduction and segmentation models for single tasks.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122637796","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}

引用次数: 0

A 112dB SNDR Delta-Sigma Modulator for Low-Power Audio Applications 用于低功耗音频应用的112dB SNDR Delta-Sigma调制器

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624444

Lvkun Qian, Shengxi Diao

引用次数: 1

New COVID protocol for elite athletes to returning to sport 精英运动员重返体育运动的新COVID协议

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) Pub Date : 2021-10-23 DOI: 10.1109/CISP-BMEI53629.2021.9624364

Z. Horvath, D. Nagy

引用次数: 0