Pub Date : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9979952
Yashpal Singh, Seba Susan
Cancer subtyping from gene expression data is trending research in the field of bioinformatics. Classification of gene expression data is a challenging task due to the small number of samples and large number of features involved. The problem is further complicated due to the strong class imbalance issue prevalent in gene expression datasets. The challenge here is to find an end-to-end machine learning solution to classify cancer subtypes from small sample, high-dimensional, imbalanced gene expression datasets. In this study, we propose a SMOTE-LASSO-DeepNet framework for the identification of cancer subtypes from gene expression data. The proposed framework balances the training set using SMOTE, and then finds the most informative genes using LASSO. The balanced and pruned training set is then applied as input to a deep neural network (DeepNet) with four hidden layers having 512, 256, 128 and 64 neurons respectively. We tested our framework on four different cancer gene expression datasets: Leukemia, Lung cancer, Brain cancer and Breast cancer. It is observed from the results that our proposed SMOTE-LASSO-DeepNet framework performs consistently best as compared to the existing methods.
{"title":"SMOTE-LASSO-DeepNet Framework for Cancer Subtyping from Gene Expression Data","authors":"Yashpal Singh, Seba Susan","doi":"10.1109/CISP-BMEI56279.2022.9979952","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979952","url":null,"abstract":"Cancer subtyping from gene expression data is trending research in the field of bioinformatics. Classification of gene expression data is a challenging task due to the small number of samples and large number of features involved. The problem is further complicated due to the strong class imbalance issue prevalent in gene expression datasets. The challenge here is to find an end-to-end machine learning solution to classify cancer subtypes from small sample, high-dimensional, imbalanced gene expression datasets. In this study, we propose a SMOTE-LASSO-DeepNet framework for the identification of cancer subtypes from gene expression data. The proposed framework balances the training set using SMOTE, and then finds the most informative genes using LASSO. The balanced and pruned training set is then applied as input to a deep neural network (DeepNet) with four hidden layers having 512, 256, 128 and 64 neurons respectively. We tested our framework on four different cancer gene expression datasets: Leukemia, Lung cancer, Brain cancer and Breast cancer. It is observed from the results that our proposed SMOTE-LASSO-DeepNet framework performs consistently best as compared to the existing methods.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114439697","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9979917
Xin Tang, Juan Gao, Fan Yang, Chenxi Hu
Muti-b-value Diffusion Weighted Imaging (DWI) is commonly used in clinical and neuroscientific applications. The traditional single-shot Echo-Planer Imaging (EPI) sequence suffers from low image resolution. Although the multi-shot EPI sequence can increase spatial resolution, the multi-shot k-space sampling causes linearly increased scan time. An interleaved EPI acquisition can significantly reduce the scan time; however, the dynamic change of image phase and image contrast causes aliasing artifacts. To improve the scan efficiency and preserve the image quality, an interleaved keyhole-EPI multi-b-value multi-shot sequence is proposed, with the image reconstruction formulated as a Locally Low Rank (LLR) constrained problem. The resultant cost function is minimized by a computationally efficient ADMM algorithm. The proposed method was compared with interleaved EPI acquisition using the state-of-the-art SPatial-Angular Locally Low Rank (SPA-LLR) algorithm in two healthy subjects. The results showed that the proposed method achieved superior image quality and fewer aliasing artifacts compared with the state-of-the-art method in both the raw DWI images and Apparent Diffusion Coefficient (ADC) maps.
多b值弥散加权成像(DWI)广泛应用于临床和神经科学领域。传统的单镜头回波平面成像(EPI)序列存在图像分辨率低的问题。虽然多镜头EPI序列可以提高空间分辨率，但多镜头k空间采样导致扫描时间线性增加。交错的EPI采集可以显著缩短扫描时间;然而，图像相位和图像对比度的动态变化会引起混叠伪影。为了提高扫描效率和保持图像质量，提出了一种交错keyhole-EPI多b值多镜头序列，并将图像重建表述为局部低秩约束问题。所得到的代价函数通过计算效率高的ADMM算法最小化。将该方法与基于空间-角度局部低秩(spatial - angle local Low Rank, SPA-LLR)算法的交错EPI采集方法在两名健康受试者身上进行了比较。结果表明，该方法在原始DWI图像和表观扩散系数(ADC)图上均取得了较好的图像质量和较少的混叠伪影。
{"title":"Acceleration of Multi-b-value Multi-shot Diffusion-weighted Imaging using Interleaved Keyhole-EPI and Locally Low Rank Reconstruction","authors":"Xin Tang, Juan Gao, Fan Yang, Chenxi Hu","doi":"10.1109/CISP-BMEI56279.2022.9979917","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979917","url":null,"abstract":"Muti-b-value Diffusion Weighted Imaging (DWI) is commonly used in clinical and neuroscientific applications. The traditional single-shot Echo-Planer Imaging (EPI) sequence suffers from low image resolution. Although the multi-shot EPI sequence can increase spatial resolution, the multi-shot k-space sampling causes linearly increased scan time. An interleaved EPI acquisition can significantly reduce the scan time; however, the dynamic change of image phase and image contrast causes aliasing artifacts. To improve the scan efficiency and preserve the image quality, an interleaved keyhole-EPI multi-b-value multi-shot sequence is proposed, with the image reconstruction formulated as a Locally Low Rank (LLR) constrained problem. The resultant cost function is minimized by a computationally efficient ADMM algorithm. The proposed method was compared with interleaved EPI acquisition using the state-of-the-art SPatial-Angular Locally Low Rank (SPA-LLR) algorithm in two healthy subjects. The results showed that the proposed method achieved superior image quality and fewer aliasing artifacts compared with the state-of-the-art method in both the raw DWI images and Apparent Diffusion Coefficient (ADC) maps.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116592110","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}
With the continuous development of aerial photography technology, its imaging quality is higher and higher, and the post-processing technology requirements for aerial images are getting higher and higher. Aerial image target recognition technology has been a hot research content in recent years. This technology relies on computer vision and image processing algorithm. But aerial images have certain particularities, including long shooting distances, complex image backgrounds, and variable target angles. The above factors can easily lead to indistinguishability between the target boundary and the background information of the aerial images. In order to solve that problem, a smooth edge feature information recognition method for aerial images is proposed. The energy fitting term related to the gray value inside and outside the curve is introduced, with that the method can get rid of the dependence of the detection operator as the stopping function of the curve evolution. In order to prevent the algorithm from falling into a local optimal solution in the iterative process, the Dirac function with a non-zero value in the domain is adopted. With synthetic and natural images, the effectiveness and accuracy of the method is verified. The robustness of the algorithm will be verified in the future researches by the acquired aerial image data set.
{"title":"Research on Smooth Edge Feature Recognition Method for Aerial Image Segmentation","authors":"Heng Wang, Yanrong Yuan, Chuangang Zhuang, Rui Shi, Jiamei Zhao, Xinyi Guo, Jintian Tang","doi":"10.1109/CISP-BMEI56279.2022.9980141","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980141","url":null,"abstract":"With the continuous development of aerial photography technology, its imaging quality is higher and higher, and the post-processing technology requirements for aerial images are getting higher and higher. Aerial image target recognition technology has been a hot research content in recent years. This technology relies on computer vision and image processing algorithm. But aerial images have certain particularities, including long shooting distances, complex image backgrounds, and variable target angles. The above factors can easily lead to indistinguishability between the target boundary and the background information of the aerial images. In order to solve that problem, a smooth edge feature information recognition method for aerial images is proposed. The energy fitting term related to the gray value inside and outside the curve is introduced, with that the method can get rid of the dependence of the detection operator as the stopping function of the curve evolution. In order to prevent the algorithm from falling into a local optimal solution in the iterative process, the Dirac function with a non-zero value in the domain is adopted. With synthetic and natural images, the effectiveness and accuracy of the method is verified. The robustness of the algorithm will be verified in the future researches by the acquired aerial image data set.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117048174","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9980221
Chenglin Wu, Xuran Zhou, Guannan Chen
The most important subtypes of joint abnormalities in patients with temporomandibular disorders are different forms of disc displacement and deformation. An effective segmentation model for jaw joint detection to support the diagnosis of TMJ disease on magnetic resonance imaging is very crucial. Data for this study were obtained from 204 MRI images of patients with articular discs and the corresponding MRI segmentation labels of the temporomandibular joints. These images were used to evaluate four deep learning-based semantic segmentation methods. Using a multi-scale structured C2Ftrans segmentation model transformed from coarse to fine, it describes medical image segmentation as a coarse to fine process. It is able to perform accurate target boundary segmentation with lower computational complexity. Tested on this dataset, comparing U-Net, Unet ++ and Attention-U net models for data segmentation results show the C2Ftrans model performs best with the highest dice of 73.5% and the lowest computational complexity.
{"title":"Coarse-to-Fine Tranformer for articular disc of the temporomandibular joint Segmentation","authors":"Chenglin Wu, Xuran Zhou, Guannan Chen","doi":"10.1109/CISP-BMEI56279.2022.9980221","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980221","url":null,"abstract":"The most important subtypes of joint abnormalities in patients with temporomandibular disorders are different forms of disc displacement and deformation. An effective segmentation model for jaw joint detection to support the diagnosis of TMJ disease on magnetic resonance imaging is very crucial. Data for this study were obtained from 204 MRI images of patients with articular discs and the corresponding MRI segmentation labels of the temporomandibular joints. These images were used to evaluate four deep learning-based semantic segmentation methods. Using a multi-scale structured C2Ftrans segmentation model transformed from coarse to fine, it describes medical image segmentation as a coarse to fine process. It is able to perform accurate target boundary segmentation with lower computational complexity. Tested on this dataset, comparing U-Net, Unet ++ and Attention-U net models for data segmentation results show the C2Ftrans model performs best with the highest dice of 73.5% and the lowest computational complexity.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123101254","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9980307
Hongyu Zhao, Zhiping Yin
Aiming at the problem of low efficiency of remote sensing imagery for PV (Photovoltaic) panel extraction in desert areas, this paper proposes a remote sensing identification method for PV panels based on the optimization of multi-feature combinations, taking Qinghai province as an example. The research uses the GEE cloud platform to construct a feature set containing topographic features, spectral features and index features, filters the feature set according to the feature importance and recursive elimination idea, and introduces feature correlation analysis to filter the feature set to get the optimal feature combination, and uses random forest RF to achieve PV panel extraction, and designs four experiments to verify the effectiveness of the preferred features. The results show that: the best effect of PV panel extraction is achieved by the random forest algorithm with feature selection, the overall accuracy of classification reaches 95.86%, and the Kappa coefficient reaches 0.9197; and the accuracy of PV panel area extraction for Qinghai province can reach 95.68%; the feature optimization method proposed in this paper can effectively improve the extraction accuracy of PV panels in desert areas.
{"title":"Remote Sensing Extraction of Photovoltaic Panels in Desert Areas Based on Feature Optimization","authors":"Hongyu Zhao, Zhiping Yin","doi":"10.1109/CISP-BMEI56279.2022.9980307","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980307","url":null,"abstract":"Aiming at the problem of low efficiency of remote sensing imagery for PV (Photovoltaic) panel extraction in desert areas, this paper proposes a remote sensing identification method for PV panels based on the optimization of multi-feature combinations, taking Qinghai province as an example. The research uses the GEE cloud platform to construct a feature set containing topographic features, spectral features and index features, filters the feature set according to the feature importance and recursive elimination idea, and introduces feature correlation analysis to filter the feature set to get the optimal feature combination, and uses random forest RF to achieve PV panel extraction, and designs four experiments to verify the effectiveness of the preferred features. The results show that: the best effect of PV panel extraction is achieved by the random forest algorithm with feature selection, the overall accuracy of classification reaches 95.86%, and the Kappa coefficient reaches 0.9197; and the accuracy of PV panel area extraction for Qinghai province can reach 95.68%; the feature optimization method proposed in this paper can effectively improve the extraction accuracy of PV panels in desert areas.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125048858","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9980052
Wang Lintao, Yu Yuanhui, Guo Qisong, Li Xinxin
“Rita” is short for “right teacher AI” which is a learning assistant app developed for college teachers and students, aiming to provide an intelligent platform to assist teachers and students in learning and teaching. The system includes subject content tag graphic database, intelligent article push module, intelligent Q&A module, user service module, etc. This paper studies the structure, classification and application of knowledge map in the field of intelligent education, points out the practical efficacy of knowledge map in mobile teaching assistant system, and establishes a subject tree relationship model, which provides a basis for intelligent recommendation and subject analysis.
{"title":"An Application Of Knowledge Map In Intelligent Education","authors":"Wang Lintao, Yu Yuanhui, Guo Qisong, Li Xinxin","doi":"10.1109/CISP-BMEI56279.2022.9980052","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980052","url":null,"abstract":"“Rita” is short for “right teacher AI” which is a learning assistant app developed for college teachers and students, aiming to provide an intelligent platform to assist teachers and students in learning and teaching. The system includes subject content tag graphic database, intelligent article push module, intelligent Q&A module, user service module, etc. This paper studies the structure, classification and application of knowledge map in the field of intelligent education, points out the practical efficacy of knowledge map in mobile teaching assistant system, and establishes a subject tree relationship model, which provides a basis for intelligent recommendation and subject analysis.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122458675","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}
In this paper, the Hurst index calculation method based on multipoint fractional Brown bridge was used to analyze the electroencephalogram(EEG) of schizophrenia patients and healthy people under the same sound paradigm experiment. We used this method to analyze the short-term EEG signals of the healthy group and the patient group around the time point 100ms after stimulation and found that the method can effectively analyze the Hurst index of short-time series, in the frontal lobe and central area. There were significant differences in passage, and the Hurst index was lower in healthy people than in patients. The results show that in this experiment, the long-term correlation of EEG signals after stimulation in patients with schizophrenia is higher, and the complexity of EEG signals is lower, which can help clinical diagnosis of schizophrenia better. At the same time, this paper compares the Hurst exponent calculation method based on the multi-point fractional Brown bridge with the traditional rescaled range analysis method. The Hurst index calculation of the sequence can analyze the difference between the healthy group and the patient group on a smaller scale.
{"title":"Hurst Exponent Analysis Of Schizophrenia Electroencephalogram Based On Multi-point Fractional Brownian Bridge","authors":"Congzhou Zhong, Wenpo Yao, Wanyi Yi, Jui-Pin Wang, Dengxuan Bai, Qiong Wang","doi":"10.1109/CISP-BMEI56279.2022.9980315","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980315","url":null,"abstract":"In this paper, the Hurst index calculation method based on multipoint fractional Brown bridge was used to analyze the electroencephalogram(EEG) of schizophrenia patients and healthy people under the same sound paradigm experiment. We used this method to analyze the short-term EEG signals of the healthy group and the patient group around the time point 100ms after stimulation and found that the method can effectively analyze the Hurst index of short-time series, in the frontal lobe and central area. There were significant differences in passage, and the Hurst index was lower in healthy people than in patients. The results show that in this experiment, the long-term correlation of EEG signals after stimulation in patients with schizophrenia is higher, and the complexity of EEG signals is lower, which can help clinical diagnosis of schizophrenia better. At the same time, this paper compares the Hurst exponent calculation method based on the multi-point fractional Brown bridge with the traditional rescaled range analysis method. The Hurst index calculation of the sequence can analyze the difference between the healthy group and the patient group on a smaller scale.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122787693","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9980189
Ying Zhu, Dexin Kong, Yumeng Mao, Ying Yu
The background of imaging photoplethysmography (IPPG) is briefly presented from biological and physical perspectives. Taking the optimization of the IPPG signal as the starting point, the effects of external factors and the original signal extraction process are introduced respectively. External factors such as the green light source in the ambient light source have the highest signal-noise ratio (SNR), with No significant effect on light intensity. The lighter the skin color of the human body, the higher the SNR, with gender having no effect. The extraction of the original signal such as the region of interest (ROI) region selects the face T -zone with the highest SNR. The original signals are extracted by the Cg channel in the YCbCr, which is better than other color spaces. Face detection algorithms and tracking algorithms are intended to solve the problem of signal quality degradation caused by small movements, background changes, and missing angles in face video shooting, including the degradation of video quality during transmission. physiological parameters are measured by formula conversion and fitting. At present, there is still a lot of room for the development of this detection technology, and domestic and foreign research should be towards eliminating motion artifacts. Efforts have been made to improve the detection effect in the absence of local information, develop new applications of IPPG detection technology, better process compressed data, and combine daily portable devices with the direction of use.
{"title":"Research on the non-contact physiological parameter measurement technology based on imaging photoplethysmography","authors":"Ying Zhu, Dexin Kong, Yumeng Mao, Ying Yu","doi":"10.1109/CISP-BMEI56279.2022.9980189","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980189","url":null,"abstract":"The background of imaging photoplethysmography (IPPG) is briefly presented from biological and physical perspectives. Taking the optimization of the IPPG signal as the starting point, the effects of external factors and the original signal extraction process are introduced respectively. External factors such as the green light source in the ambient light source have the highest signal-noise ratio (SNR), with No significant effect on light intensity. The lighter the skin color of the human body, the higher the SNR, with gender having no effect. The extraction of the original signal such as the region of interest (ROI) region selects the face T -zone with the highest SNR. The original signals are extracted by the Cg channel in the YCbCr, which is better than other color spaces. Face detection algorithms and tracking algorithms are intended to solve the problem of signal quality degradation caused by small movements, background changes, and missing angles in face video shooting, including the degradation of video quality during transmission. physiological parameters are measured by formula conversion and fitting. At present, there is still a lot of room for the development of this detection technology, and domestic and foreign research should be towards eliminating motion artifacts. Efforts have been made to improve the detection effect in the absence of local information, develop new applications of IPPG detection technology, better process compressed data, and combine daily portable devices with the direction of use.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122910115","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9980111
Qing Li
In face recognition, we may encounter face images with shadow and illumination, which will affect the recognition. In this scenario, the low-rank matrix and a sparse matrix can be obtained by low-rank matrix decomposition of the collected original face image, where the low-rank matrix is the face image without shadow and illumination. In order to obtain the low-rank matrix, the Sub-gradient method and AIRLS method are used in this paper, and their effects are compared in the experimental verification of Yale face database.
{"title":"Face Recognition with Robust Matrix Factorization","authors":"Qing Li","doi":"10.1109/CISP-BMEI56279.2022.9980111","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980111","url":null,"abstract":"In face recognition, we may encounter face images with shadow and illumination, which will affect the recognition. In this scenario, the low-rank matrix and a sparse matrix can be obtained by low-rank matrix decomposition of the collected original face image, where the low-rank matrix is the face image without shadow and illumination. In order to obtain the low-rank matrix, the Sub-gradient method and AIRLS method are used in this paper, and their effects are compared in the experimental verification of Yale face database.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125811628","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 : 2022-11-05DOI: 10.1109/CISP-BMEI56279.2022.9979870
Yunlong Zhu, Wenlong Zhang, Biao Yan, Rongqian Yang
Intramuscular (IM) injection is mainly performed manually at present. Large-scale COVID-19 vaccination has exposed various problems of manual IM injection. In addition, the clinical success rate of manual IM injection is also unsatisfactory. Using robotic intramuscular injection system (RIMIS) is expected to realize automated vaccination and improve the success rate of IM injection. The existing robotic needle insertion system based on image guidance is not a practical option for IM injection because of the time-consuming medical imaging process. In this paper, an optical guidance method for RIMIS is proposed, which uses near-infrared optical tracking system and retro-reflective patch to achieve rapid acquisition of surface normal vector. A closed loop formed by six coordinate systems is used to realize the accurate control of the injection angle and depth. Experimental results show that the RIMIS based on the proposed method can complete the simulated IM injection operation without image guidance and possess accurate control of the injection angle and depth.
{"title":"An Optical Guidance Method for Robotic Intramuscular Injection System","authors":"Yunlong Zhu, Wenlong Zhang, Biao Yan, Rongqian Yang","doi":"10.1109/CISP-BMEI56279.2022.9979870","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979870","url":null,"abstract":"Intramuscular (IM) injection is mainly performed manually at present. Large-scale COVID-19 vaccination has exposed various problems of manual IM injection. In addition, the clinical success rate of manual IM injection is also unsatisfactory. Using robotic intramuscular injection system (RIMIS) is expected to realize automated vaccination and improve the success rate of IM injection. The existing robotic needle insertion system based on image guidance is not a practical option for IM injection because of the time-consuming medical imaging process. In this paper, an optical guidance method for RIMIS is proposed, which uses near-infrared optical tracking system and retro-reflective patch to achieve rapid acquisition of surface normal vector. A closed loop formed by six coordinate systems is used to realize the accurate control of the injection angle and depth. Experimental results show that the RIMIS based on the proposed method can complete the simulated IM injection operation without image guidance and possess accurate control of the injection angle and depth.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129360349","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：