Pub Date : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050541
Chi-yuan Gao, Xinming Zhang, Hui Wang, Liyao Song, Bingliang Hu, Quan Wang
Compared with face recognition in the environment of visible light, thermal infrared face recognition has the advantages of being independent of light, working around the clock, and capable of detecting hidden targets easily. In this paper, we propose a thermal infrared face recognition method based on the two-directional two-dimensional PCA (2D2DPCA) and random forest classifier. We compared this with two deep learning networks: Alexnet, Three-dimensional Convolutional Neural Networks (3DCNN), and applied these with two databases: the Terravic Facial IR database (with different facial angles) and the NVIE database (with various emotional expressions). Among these methods, the accuracy of face recognition with the 2D2DPCA method achieves the best recognition effect, it reached 99.92% and 99.97% in both databases, respectively. We statistically verified that our method could not only accurately and robustly recognize thermal infrared faces with large variations in angle and expression, but also greatly reduce computational complexity and data dimension, improving the speed of face recognition. With the two sample sets tested, our work has demonstrated that 2D2DPCA has excellent potential for facial image compression and may broaden thermal face recognition applications.
{"title":"Two-Directional Two-Dimensional PCA: An Efficient Face Recognition Method for Thermal Infrared Images","authors":"Chi-yuan Gao, Xinming Zhang, Hui Wang, Liyao Song, Bingliang Hu, Quan Wang","doi":"10.1109/ICICSP55539.2022.10050541","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050541","url":null,"abstract":"Compared with face recognition in the environment of visible light, thermal infrared face recognition has the advantages of being independent of light, working around the clock, and capable of detecting hidden targets easily. In this paper, we propose a thermal infrared face recognition method based on the two-directional two-dimensional PCA (2D2DPCA) and random forest classifier. We compared this with two deep learning networks: Alexnet, Three-dimensional Convolutional Neural Networks (3DCNN), and applied these with two databases: the Terravic Facial IR database (with different facial angles) and the NVIE database (with various emotional expressions). Among these methods, the accuracy of face recognition with the 2D2DPCA method achieves the best recognition effect, it reached 99.92% and 99.97% in both databases, respectively. We statistically verified that our method could not only accurately and robustly recognize thermal infrared faces with large variations in angle and expression, but also greatly reduce computational complexity and data dimension, improving the speed of face recognition. With the two sample sets tested, our work has demonstrated that 2D2DPCA has excellent potential for facial image compression and may broaden thermal face recognition applications.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"575 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132073573","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050617
W. Zhang, Bin Lin, Li Ma, Aolong Zhou, Guoli Wu
Our goal is to make full use of time-frequency domain features and spatial domain features of the multichannel speech signal, and we propose an end-to-end multichannel target speech separation method based on temporal-frequency-spatial feature fusion, called the cTFS model. For the target speech separation task, the cTFS model takes the angel feature of the target speech signal as the prior knowledge, then predicts the complex ideal ratio mask target with a complex U-shaped network. We achieve the reconstruction of the target speech signal by signal approximation. Furthermore, a multi-channel target speaker separation dataset is constructed based on the WSJ0-2mix dataset based on the signal reverberation model. The performance of each target speaker separation model is evaluated on this dataset using the evaluation metrics SDR, SI-SNR, PESQ, and STOI. Experimental results show the effectiveness of the proposed method as well as the benefit of incorporating angle feature information in multichannel speech separation.
{"title":"Temporal-Frequency-Spatial Features Fusion for Multi-channel Informed Target Speech Separation","authors":"W. Zhang, Bin Lin, Li Ma, Aolong Zhou, Guoli Wu","doi":"10.1109/ICICSP55539.2022.10050617","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050617","url":null,"abstract":"Our goal is to make full use of time-frequency domain features and spatial domain features of the multichannel speech signal, and we propose an end-to-end multichannel target speech separation method based on temporal-frequency-spatial feature fusion, called the cTFS model. For the target speech separation task, the cTFS model takes the angel feature of the target speech signal as the prior knowledge, then predicts the complex ideal ratio mask target with a complex U-shaped network. We achieve the reconstruction of the target speech signal by signal approximation. Furthermore, a multi-channel target speaker separation dataset is constructed based on the WSJ0-2mix dataset based on the signal reverberation model. The performance of each target speaker separation model is evaluated on this dataset using the evaluation metrics SDR, SI-SNR, PESQ, and STOI. Experimental results show the effectiveness of the proposed method as well as the benefit of incorporating angle feature information in multichannel speech separation.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124183646","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050596
Zhihang Liu, Pengfei He, Tongjing Zhang, Rong Nie
For small target detection of circuit board defects, traditional detection methods have problems such as false detection, missed detection and slow detection speed. Although excellent models for detecting small targets exist in mainstream algorithms based on deep learning, their network structures are complex, computationally intensive and detection efficiency is low. In order to solve the above problems, this paper proposes a light-weight printed circuit board defect detection method based on YOLOv5s. The method uses an improved spatial pyramid pooling instead of the CSP module in the Backbone stage to provide multilevel perceptual fields while significantly reducing the computational effort. Secondly, a residual structure is introduced in Backbone and Neck to enable the network to obtain a better feature learning capability and improve the stability of training while accelerating the network convergence. Finally, the model parameters, calculation amount, mAP and AP with different defects of the improved algorithm in this paper are compared with other mainstream algorithms. The experimental results show that the improved algorithm in this paper greatly reduces the model parameters and calculation amount and improves the detection efficiency under the condition of high accuracy. Compared with other algorithms, it has obvious advantages and provides a new method for PCB defect detection.
{"title":"Defect Detection of Printed Circuit Board Based on Light-weight YOLOv5s","authors":"Zhihang Liu, Pengfei He, Tongjing Zhang, Rong Nie","doi":"10.1109/ICICSP55539.2022.10050596","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050596","url":null,"abstract":"For small target detection of circuit board defects, traditional detection methods have problems such as false detection, missed detection and slow detection speed. Although excellent models for detecting small targets exist in mainstream algorithms based on deep learning, their network structures are complex, computationally intensive and detection efficiency is low. In order to solve the above problems, this paper proposes a light-weight printed circuit board defect detection method based on YOLOv5s. The method uses an improved spatial pyramid pooling instead of the CSP module in the Backbone stage to provide multilevel perceptual fields while significantly reducing the computational effort. Secondly, a residual structure is introduced in Backbone and Neck to enable the network to obtain a better feature learning capability and improve the stability of training while accelerating the network convergence. Finally, the model parameters, calculation amount, mAP and AP with different defects of the improved algorithm in this paper are compared with other mainstream algorithms. The experimental results show that the improved algorithm in this paper greatly reduces the model parameters and calculation amount and improves the detection efficiency under the condition of high accuracy. Compared with other algorithms, it has obvious advantages and provides a new method for PCB defect detection.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121437422","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050697
Sixian Zhao, Yu Fang, Weibo Wang, Dongbo Liu
The sleeping respiratory sounds can reflect the condition of the airway, which is meaningful for the diagnosis and therapeutic of sleep-related disorders. Snoring is an essential vital sign for monitoring obstructive sleep apnea (OSA) during all-night sleep. This study presents a spectral division method for analyzing respiratory sounds, such as stable breathing, snoring, etc. The sleep respiratory sound signal is acquired by a portable, wearable sound device. After segmentation, the spectrum of each segmented data is computed. The frequency energy features are extracted to display the spectrum distribution more clearly and applied to classify the different respiratory statuses. A set of data is used to validate the efficiency of the proposed features by the cubic SVM. The accuracy rate for identifying snoring and breath sounds is more than 80.0%. The proposed spectral division method shows good performance for sleep respiratory analysis and has potential for sleep health monitoring.
{"title":"Analysis of Sleeping Respiratory Signal Utilizing Frequency Energy Features","authors":"Sixian Zhao, Yu Fang, Weibo Wang, Dongbo Liu","doi":"10.1109/ICICSP55539.2022.10050697","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050697","url":null,"abstract":"The sleeping respiratory sounds can reflect the condition of the airway, which is meaningful for the diagnosis and therapeutic of sleep-related disorders. Snoring is an essential vital sign for monitoring obstructive sleep apnea (OSA) during all-night sleep. This study presents a spectral division method for analyzing respiratory sounds, such as stable breathing, snoring, etc. The sleep respiratory sound signal is acquired by a portable, wearable sound device. After segmentation, the spectrum of each segmented data is computed. The frequency energy features are extracted to display the spectrum distribution more clearly and applied to classify the different respiratory statuses. A set of data is used to validate the efficiency of the proposed features by the cubic SVM. The accuracy rate for identifying snoring and breath sounds is more than 80.0%. The proposed spectral division method shows good performance for sleep respiratory analysis and has potential for sleep health monitoring.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117070168","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050707
Su Yu, Chenyu Zhang, Dingyu Hu, Liang Yu
Equivalent source method (ESM) arouses a lot of interests in the field of noise source identification and fault diagnosis. However, the performance of ESM tends to be limited by the insufficient microphones, because the size of holography plane should be larger or consistent with the sound source plane. In this paper, the non-synchronous measurement (NSM) is used as a powerful tool to extend the number of microphones in the holography plane. First, ESM is reformulated under the form of NSM aiming to reconstruct the distributed acoustic source. Then, the phase-missing cross spectral matrix (CSM) is completed considering the low-rankness of acoustic source and continuity of acoustic field via FISTA algorithm. Finally, the complex acoustic pressure of a synthetic array with NSM can be obtained for ESM. The proposed method is validated by an excited steel plane sound source reconstruction.
{"title":"Sound Sources Reconstruction based on the Non-synchronous Measurements of Microphone Arrays and Equivalent Sources Modeling","authors":"Su Yu, Chenyu Zhang, Dingyu Hu, Liang Yu","doi":"10.1109/ICICSP55539.2022.10050707","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050707","url":null,"abstract":"Equivalent source method (ESM) arouses a lot of interests in the field of noise source identification and fault diagnosis. However, the performance of ESM tends to be limited by the insufficient microphones, because the size of holography plane should be larger or consistent with the sound source plane. In this paper, the non-synchronous measurement (NSM) is used as a powerful tool to extend the number of microphones in the holography plane. First, ESM is reformulated under the form of NSM aiming to reconstruct the distributed acoustic source. Then, the phase-missing cross spectral matrix (CSM) is completed considering the low-rankness of acoustic source and continuity of acoustic field via FISTA algorithm. Finally, the complex acoustic pressure of a synthetic array with NSM can be obtained for ESM. The proposed method is validated by an excited steel plane sound source reconstruction.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115424260","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050585
Chao Yang, Yi Yang, Defeng Liu, Nai Lin, Wei Liu, Jie Zhuang
The terahertz radar system can realize accurate detection, high-resolution imaging, and feature recognition of targets due to its small size, lightweight, and high resolution. Based on this special-shaped terahertz frequency-modulated continuous-wave radar, this paper studies the slope control of the transmitter and the local oscillator signal source and the change rule of the difference frequency signal and the effective acquisition interval. A short-time Fourier transform is used to simulate and verify the effective acquisition interval of the received intermediate frequency signal. It can be seen from the experimental results that under the special-shaped structure, controlling the FM continuous-wave slope at the transmitting and receiving ends can obtain the desired frequency-varying frequency signal, which can verify the correctness of the theoretical derivation.
{"title":"Beat Signal Analysis for Terahertz Frequency Modulation Continuous Wave","authors":"Chao Yang, Yi Yang, Defeng Liu, Nai Lin, Wei Liu, Jie Zhuang","doi":"10.1109/ICICSP55539.2022.10050585","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050585","url":null,"abstract":"The terahertz radar system can realize accurate detection, high-resolution imaging, and feature recognition of targets due to its small size, lightweight, and high resolution. Based on this special-shaped terahertz frequency-modulated continuous-wave radar, this paper studies the slope control of the transmitter and the local oscillator signal source and the change rule of the difference frequency signal and the effective acquisition interval. A short-time Fourier transform is used to simulate and verify the effective acquisition interval of the received intermediate frequency signal. It can be seen from the experimental results that under the special-shaped structure, controlling the FM continuous-wave slope at the transmitting and receiving ends can obtain the desired frequency-varying frequency signal, which can verify the correctness of the theoretical derivation.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128907256","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050642
Gan Quan, Tang Jie, Song Huan Huan, Wenjun Hong
In order to detect the angle-of-arrival(AOA) and the instantaneous frequency(IF) of spatial multi-component signals rapidly and effectively, an estimation approach of the spatial signal's AOA and IF is proposed using a kind of typical Cohen type time-frequency distribution Choi-Williams distribution(CWD). The method is realized by the comparison of the instantaneous frequency of the signal at the same moment using digital signal processing(DSP) based on the spatial sample of multi-component signals by the array antenna. Simulation results show that the method not only has a higher noise performance, but also improves the real-time performance of detection.
{"title":"Instantaneous Frequency and AOA Estimation of Multicomponent Signals Based on Choi-Williams Distribution","authors":"Gan Quan, Tang Jie, Song Huan Huan, Wenjun Hong","doi":"10.1109/ICICSP55539.2022.10050642","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050642","url":null,"abstract":"In order to detect the angle-of-arrival(AOA) and the instantaneous frequency(IF) of spatial multi-component signals rapidly and effectively, an estimation approach of the spatial signal's AOA and IF is proposed using a kind of typical Cohen type time-frequency distribution Choi-Williams distribution(CWD). The method is realized by the comparison of the instantaneous frequency of the signal at the same moment using digital signal processing(DSP) based on the spatial sample of multi-component signals by the array antenna. Simulation results show that the method not only has a higher noise performance, but also improves the real-time performance of detection.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129875007","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}
This study extends recent Sea Surface Salinity (SSS) comparisons to explore improvements to several next-generation ocean reanalysis products, including the Simple Ocean Data Assimilation version 3.11.2 (SODA 3.11.2), the Hybrid Coordinate Ocean Model (HYCOM), the GLORYS12 Reanalysis version 1 (GLORYS12V1) and the Global Ocean Data Assimilation System (GODAS) during the satellite era of SSS (2010–2020). All the four reanalysis products share similar inputs of historical hydrographic measurements, but their forward model, surface forcing and bias correction algorithms are distinctly different. A comprehensive SSS validation is conducted, taking the signals of climatological SSS field, interannual biases series, seasonal biases distributions, and zonal/meridional averaged biases into account. The comparison is conducted using both satellite products gridded in situ databases. The spatial distributions of SSS from four reanalysis products generally agree with both the satellite data and the in situ measurement. Except for GODAS, the biases carried by the other three reanalysis products are smaller than 0.3 PSU in the open sea. The seasonal to interannual analysis of RMSDs show that all the four reanalysis products tend to overestimate the SSS in open seas from tropical to subpolar regions. Finally, the SSS reanalysis are compared with tropical buoys, which shows optimistic results and suggests the potential of ocean reanalysis data to serve as quality control of buoy data.
{"title":"Evaluation of Global Sea Surface Salinity from Four Ocean Reanalysis Products","authors":"Haodi Wang, Wen Zhang, Senliang Bao, Wen Chen, Kaijun Ren","doi":"10.1109/ICICSP55539.2022.10050572","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050572","url":null,"abstract":"This study extends recent Sea Surface Salinity (SSS) comparisons to explore improvements to several next-generation ocean reanalysis products, including the Simple Ocean Data Assimilation version 3.11.2 (SODA 3.11.2), the Hybrid Coordinate Ocean Model (HYCOM), the GLORYS12 Reanalysis version 1 (GLORYS12V1) and the Global Ocean Data Assimilation System (GODAS) during the satellite era of SSS (2010–2020). All the four reanalysis products share similar inputs of historical hydrographic measurements, but their forward model, surface forcing and bias correction algorithms are distinctly different. A comprehensive SSS validation is conducted, taking the signals of climatological SSS field, interannual biases series, seasonal biases distributions, and zonal/meridional averaged biases into account. The comparison is conducted using both satellite products gridded in situ databases. The spatial distributions of SSS from four reanalysis products generally agree with both the satellite data and the in situ measurement. Except for GODAS, the biases carried by the other three reanalysis products are smaller than 0.3 PSU in the open sea. The seasonal to interannual analysis of RMSDs show that all the four reanalysis products tend to overestimate the SSS in open seas from tropical to subpolar regions. Finally, the SSS reanalysis are compared with tropical buoys, which shows optimistic results and suggests the potential of ocean reanalysis data to serve as quality control of buoy data.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133979018","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050639
Rui Wu, Haoyuan Gao, Chao Zhang, Xiao-pei Wu
Resting heart rate is an independent predictor of cardiovascular disease and all-cause mortality from cardiovascular disease. Imaging photoplethysmography (IPPG) provides a more comfortable environment for heart rate estimation than electrocardiography and photoplethysmography. However, existing studies usually focus on the videos of facial skin, rather than the other skin regions. In our research, we collected the videos containing face and palm simultaneously and compared the reliability of blood volume pulse (BVP) signals extracted from facial and palmar regions. We also collected the videos containing palms in different age groups and calculated the signal-to-noise ratio (SNR) to analyze the BVP signal quality extracted from palms of different ages. Based on the video data from 17 subjects, the experimental results showed that the heart rate estimated in the palmar region is more reliable than that in the facial region. This study also revealed that the quality of palmer BVP signal extracted from the elderly is higher than that extracted from the young.
{"title":"To Investigate the Feasibility of Palm-Video-Based IPPG Technique","authors":"Rui Wu, Haoyuan Gao, Chao Zhang, Xiao-pei Wu","doi":"10.1109/ICICSP55539.2022.10050639","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050639","url":null,"abstract":"Resting heart rate is an independent predictor of cardiovascular disease and all-cause mortality from cardiovascular disease. Imaging photoplethysmography (IPPG) provides a more comfortable environment for heart rate estimation than electrocardiography and photoplethysmography. However, existing studies usually focus on the videos of facial skin, rather than the other skin regions. In our research, we collected the videos containing face and palm simultaneously and compared the reliability of blood volume pulse (BVP) signals extracted from facial and palmar regions. We also collected the videos containing palms in different age groups and calculated the signal-to-noise ratio (SNR) to analyze the BVP signal quality extracted from palms of different ages. Based on the video data from 17 subjects, the experimental results showed that the heart rate estimated in the palmar region is more reliable than that in the facial region. This study also revealed that the quality of palmer BVP signal extracted from the elderly is higher than that extracted from the young.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134561615","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 : 2022-11-26DOI: 10.1109/ICICSP55539.2022.10050601
Jianjuan Xiu, Kai Dong, Meng Wang
Because system error may cause the same target measured by different radar to be misjudged as two targets, the system error estimation is an important process for data fusion and target tracking in radar networking system. In order to eliminate system error in real time, a new algorithm based on iterative generalized least squares (GLS) algorithm in earth-centered earth-fixed (ECEF) coordinate systems(CS) is studied in this paper. In this method the system error is modeled by state vector, and the corresponding state equation is obtained. The measurement equation is modeled based on GLS algorithm, and the iterative estimation filtering model is used to improve the real-time and convergent performance of the system error estimation in ECEF. Simulation results reveal the feasibility and validity of the algorithm presented in this paper.
{"title":"System Error Real-Time Estimation of Radar Network based on Iterative Generalized Least Squares","authors":"Jianjuan Xiu, Kai Dong, Meng Wang","doi":"10.1109/ICICSP55539.2022.10050601","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050601","url":null,"abstract":"Because system error may cause the same target measured by different radar to be misjudged as two targets, the system error estimation is an important process for data fusion and target tracking in radar networking system. In order to eliminate system error in real time, a new algorithm based on iterative generalized least squares (GLS) algorithm in earth-centered earth-fixed (ECEF) coordinate systems(CS) is studied in this paper. In this method the system error is modeled by state vector, and the corresponding state equation is obtained. The measurement equation is modeled based on GLS algorithm, and the iterative estimation filtering model is used to improve the real-time and convergent performance of the system error estimation in ECEF. Simulation results reveal the feasibility and validity of the algorithm presented in this paper.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132099921","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：