In order to satisfy data transmission in space data system, advanced orbiting systems(AOS) is proposed by consultative committee for space data systems(CCSDS). According to AOS space data link protocol, data transmission system in satellite is used to transfer valid data of different type from space to ground. Although there exist some validation systems for data transmission system, they can be applied to some specifical satellites only. In this paper, based on space communications protocols reference model, we propose an automated extensible validation system for satellite data transmission system, while the valid data from different virtual channel are separated exclusively in real-time, to be read by different processing and analyzing software. After configuring instructions appropriately in control and analysis equipment, which acts as the interactive interface, the system checks the data automatically. Validation results demonstrate that, the proposed automated validation system works well when receiving AOS transfer frame at rate of 800Mbps with seventeen virtual channels.
{"title":"The Design of Automated Validation System for Satellite Data Transmission System Based on AOS","authors":"Zheren Long, Lede Qiu, Wenliang Zhu, Liangyu Zhong, Zhicao Song, Wei Song","doi":"10.1109/CISP-BMEI56279.2022.9980084","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980084","url":null,"abstract":"In order to satisfy data transmission in space data system, advanced orbiting systems(AOS) is proposed by consultative committee for space data systems(CCSDS). According to AOS space data link protocol, data transmission system in satellite is used to transfer valid data of different type from space to ground. Although there exist some validation systems for data transmission system, they can be applied to some specifical satellites only. In this paper, based on space communications protocols reference model, we propose an automated extensible validation system for satellite data transmission system, while the valid data from different virtual channel are separated exclusively in real-time, to be read by different processing and analyzing software. After configuring instructions appropriately in control and analysis equipment, which acts as the interactive interface, the system checks the data automatically. Validation results demonstrate that, the proposed automated validation system works well when receiving AOS transfer frame at rate of 800Mbps with seventeen virtual channels.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"74 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":"115268910","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-BMEI56279.2022.9980267
Xinfei Jin, Fulin Su
In radar automatic target recognition (RATR), inverse synthetic aperture radar (ISAR) image recognition shows its advantages. During ISAR image feature extraction, the feature points extraction is a classic method. However, the scatterer amplitude might appear to undulate, causing the failure of the matching pair, and affecting the result of recognition. To solve this problem, this paper proposes a quadrangle-points affine transform reconstruction (QATR) algorithm. Firstly, using the four structures of the aircraft nose, tail, and wings, the affine transform coefficients are calculated to reconstruct the aircraft as the top view. Then the template matching algorithm is adopted to recognize the target. The proposed method only needs few templates for each class and has robustness with attitudes sensitivity. The experiments based on real data demonstrate the effectiveness of this method.
{"title":"Aircraft Recognition Using ISAR Image Based on Quadrangle-points Affine Transform","authors":"Xinfei Jin, Fulin Su","doi":"10.1109/CISP-BMEI56279.2022.9980267","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980267","url":null,"abstract":"In radar automatic target recognition (RATR), inverse synthetic aperture radar (ISAR) image recognition shows its advantages. During ISAR image feature extraction, the feature points extraction is a classic method. However, the scatterer amplitude might appear to undulate, causing the failure of the matching pair, and affecting the result of recognition. To solve this problem, this paper proposes a quadrangle-points affine transform reconstruction (QATR) algorithm. Firstly, using the four structures of the aircraft nose, tail, and wings, the affine transform coefficients are calculated to reconstruct the aircraft as the top view. Then the template matching algorithm is adopted to recognize the target. The proposed method only needs few templates for each class and has robustness with attitudes sensitivity. The experiments based on real data demonstrate the effectiveness of this method.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"34 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":"115743769","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-BMEI56279.2022.9979915
Yue Li, Yuanhui Yu, Yaxian Su, Tao Yang, Xu Zhang, Jiandong Shi
The huge amount of online review text data brings a great challenge to the extraction of valid information and hot words extraction work. This paper addresses this problem and designs a study on hot words extraction based on a Bidirectional LSTM(Long short term memory) online review text validity model. Firstly, data pre-processing is performed on the data set of online review texts collected by crawlers, secondly, a validity model of online review texts based on LSTM neural network is established to filter the valid online review texts, and finally, hot words are extracted from the valid review texts to get the hot words containing valuable information. In this paper, we take hotel review text as an example to conduct experiments, and the experimental results prove that the accuracy of LSTM online review text validity model reaches 90%, the loss value reaches 0.2, and the screening of valid text for hot words extraction achieves good results.
{"title":"A Study of Review Hot Words Extraction Technology Based on the LSTM Web Review Validity Model","authors":"Yue Li, Yuanhui Yu, Yaxian Su, Tao Yang, Xu Zhang, Jiandong Shi","doi":"10.1109/CISP-BMEI56279.2022.9979915","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979915","url":null,"abstract":"The huge amount of online review text data brings a great challenge to the extraction of valid information and hot words extraction work. This paper addresses this problem and designs a study on hot words extraction based on a Bidirectional LSTM(Long short term memory) online review text validity model. Firstly, data pre-processing is performed on the data set of online review texts collected by crawlers, secondly, a validity model of online review texts based on LSTM neural network is established to filter the valid online review texts, and finally, hot words are extracted from the valid review texts to get the hot words containing valuable information. In this paper, we take hotel review text as an example to conduct experiments, and the experimental results prove that the accuracy of LSTM online review text validity model reaches 90%, the loss value reaches 0.2, and the screening of valid text for hot words extraction achieves good results.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"10 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":"124973039","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-BMEI56279.2022.9980280
Shuo Chen, Zhigang Cen, Haojie Li, Xuehua Li
Grant-free non-orthogonal multiple access (GF-NOMA) is a promising solution to solve the massive connectivity problem with low latency and signaling overhead. User activity detection (UAD) and channel estimation (CE) are two enabling technologies in GF-NOMA systems. In this paper, a correlation-enhanced sparse Bayesian learning algorithm based on fast marginal likelihood maximization (CSBL-FM) is proposed, which can improve the performance of the UAD and CE without prior knowledge of channel state information and sparsity. Firstly, a multi-frame sparse model is proposed so as to exploit the correlation and sparsity characteristics of single time slot and among multiple frames. Then, in order to accurately realize signal reconstruction, channel estimation process is described as sparse signal recovery process based on user indicators and training sequences. Next, based on the proposed multi-frame sparse model, the loss function is derived and optimized to detect active users by utilizing fast marginal likelihood maximization. Simulation results show that the proposed CSBL-FM algorithm is practical to be applied in GF-NOMA system by achieving the balance between high reconstruction performance and fast convergence speed.
{"title":"Sparse Bayesian Learning based on Fast Marginal Likelihood Maximization for Joint User Activity Detection and Channel Estimation in Grant-Free NOMA","authors":"Shuo Chen, Zhigang Cen, Haojie Li, Xuehua Li","doi":"10.1109/CISP-BMEI56279.2022.9980280","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980280","url":null,"abstract":"Grant-free non-orthogonal multiple access (GF-NOMA) is a promising solution to solve the massive connectivity problem with low latency and signaling overhead. User activity detection (UAD) and channel estimation (CE) are two enabling technologies in GF-NOMA systems. In this paper, a correlation-enhanced sparse Bayesian learning algorithm based on fast marginal likelihood maximization (CSBL-FM) is proposed, which can improve the performance of the UAD and CE without prior knowledge of channel state information and sparsity. Firstly, a multi-frame sparse model is proposed so as to exploit the correlation and sparsity characteristics of single time slot and among multiple frames. Then, in order to accurately realize signal reconstruction, channel estimation process is described as sparse signal recovery process based on user indicators and training sequences. Next, based on the proposed multi-frame sparse model, the loss function is derived and optimized to detect active users by utilizing fast marginal likelihood maximization. Simulation results show that the proposed CSBL-FM algorithm is practical to be applied in GF-NOMA system by achieving the balance between high reconstruction performance and fast convergence speed.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"34 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":"122741946","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-BMEI56279.2022.9980295
Chen Chen, Z. Shao, Ruotong Hao, Y. Li, Mingyang Li
After the Fukushima nuclear accident in Japan in 2011, people began to focus on the development and research of a new generation of nuclear fuel that can improve the safety of pressurized water reactors under accident conditions. Accident fault-tolerant fuel (ATF) is a new type of fuel developed to improve the ability of the reactor core to withstand serious accidents, which can ensure the safety of the reactor and the integrity of fuel elements under accident conditions. Full-ceramic microencapsulated fuel pellets show unique advantages in ATF field, and this study is carried out based on their sintering process. In this study, an algorithm based on joint BP neural network was designed for the first time to extract features from existing experimental data and summarize laws, so as to predict pellet density before sintering.
{"title":"Prediction of Sintering Density of Full-ceramic Microencapsulated Fuel Pellets Based on Joint BP Neural Network","authors":"Chen Chen, Z. Shao, Ruotong Hao, Y. Li, Mingyang Li","doi":"10.1109/CISP-BMEI56279.2022.9980295","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980295","url":null,"abstract":"After the Fukushima nuclear accident in Japan in 2011, people began to focus on the development and research of a new generation of nuclear fuel that can improve the safety of pressurized water reactors under accident conditions. Accident fault-tolerant fuel (ATF) is a new type of fuel developed to improve the ability of the reactor core to withstand serious accidents, which can ensure the safety of the reactor and the integrity of fuel elements under accident conditions. Full-ceramic microencapsulated fuel pellets show unique advantages in ATF field, and this study is carried out based on their sintering process. In this study, an algorithm based on joint BP neural network was designed for the first time to extract features from existing experimental data and summarize laws, so as to predict pellet density before sintering.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"19 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":"122943747","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 recent years, many convolutional neural network (CNN) based works have demonstrated the great potential and more possibilities of CNN in improving HCIS performance. In addition to numerous studies on network models, many data preprocessing methods have been proposed. But few people think about the problem from other perspectives than the two mentioned above. Deep learning methods have the following basic steps: data preprocessing, building neural network models, and training and evaluation of the models. There are often drastic fluctuations in loss and accuracy during actual model training, which affects the training efficiency of the model. To mitigate this problem, a new Adam-based learning rate optimization method is proposed: the discount factor method abbreviated as Adam-DF, which takes inspiration from game theory and corrects the learning rate to some extent by the effect of the previous model training, so that the model can be trained better in the next parameter update using the gradient descent algorithm. A comparison with some other methods in the experiments confirms that this method can make the fluctuation of loss and accuracy in the training of the model significantly alleviate and reach the fitting state faster.
{"title":"A learning rate optimization method for model convergence of hyperspectral image classification","authors":"Chenming Li, Sikang Yao, Hongmin Gao, Yunfei Zhang","doi":"10.1109/CISP-BMEI56279.2022.9979838","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979838","url":null,"abstract":"In recent years, many convolutional neural network (CNN) based works have demonstrated the great potential and more possibilities of CNN in improving HCIS performance. In addition to numerous studies on network models, many data preprocessing methods have been proposed. But few people think about the problem from other perspectives than the two mentioned above. Deep learning methods have the following basic steps: data preprocessing, building neural network models, and training and evaluation of the models. There are often drastic fluctuations in loss and accuracy during actual model training, which affects the training efficiency of the model. To mitigate this problem, a new Adam-based learning rate optimization method is proposed: the discount factor method abbreviated as Adam-DF, which takes inspiration from game theory and corrects the learning rate to some extent by the effect of the previous model training, so that the model can be trained better in the next parameter update using the gradient descent algorithm. A comparison with some other methods in the experiments confirms that this method can make the fluctuation of loss and accuracy in the training of the model significantly alleviate and reach the fitting state faster.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"77 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":"124788696","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-BMEI56279.2022.9980254
Qiping Huang, Yi Liu, Fujian Feng, Yihui Liang
Image matting is an ill-posed problem that aims to extract the opacity of foreground objects in an image. Pixel-pair-optimization-based (PPO-based) image matting approaches are widely adopted in natural image matting, whereby the alpha value is estimated by choosing the optimal pixel pair according to a pixel pair evaluation (PPE) function. Multiple PPE criteria are employed to improve the accuracy of PPE, resulting in the weight setting problem of PPE criteria. Existing PPE functions use fixed weight PPE criteria, which cannot provide the accuracy of PPE on the little transparent images due to the satisfaction degree of PPE criteria related to the type of the image. To address this shortcoming, in this work, an adaptive weight criteria PPE method is presented, which adaptively adjusts the contribution of chromatic distortion and spatial closeness criteria to the PPE function by analyzing the type of the image. Experimental results show that the proposed adaptive weight criteria PPE method provides accurate PPE compared with existing PPE methods, especially on the little transparent Images.
{"title":"Adaptive Pixel Pair Evaluation Method for Image Matting","authors":"Qiping Huang, Yi Liu, Fujian Feng, Yihui Liang","doi":"10.1109/CISP-BMEI56279.2022.9980254","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980254","url":null,"abstract":"Image matting is an ill-posed problem that aims to extract the opacity of foreground objects in an image. Pixel-pair-optimization-based (PPO-based) image matting approaches are widely adopted in natural image matting, whereby the alpha value is estimated by choosing the optimal pixel pair according to a pixel pair evaluation (PPE) function. Multiple PPE criteria are employed to improve the accuracy of PPE, resulting in the weight setting problem of PPE criteria. Existing PPE functions use fixed weight PPE criteria, which cannot provide the accuracy of PPE on the little transparent images due to the satisfaction degree of PPE criteria related to the type of the image. To address this shortcoming, in this work, an adaptive weight criteria PPE method is presented, which adaptively adjusts the contribution of chromatic distortion and spatial closeness criteria to the PPE function by analyzing the type of the image. Experimental results show that the proposed adaptive weight criteria PPE method provides accurate PPE compared with existing PPE methods, especially on the little transparent Images.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"69 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":"129078692","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-BMEI56279.2022.9979826
Siru Feng, Yu Wang, Jiangzhen Guo
Preoperative registration of robotic-assisted surgery is a laborious and time-consuming process which reqiures manual operation of a surgeon. To automate this process and improve accuracy, this paper proposed a simplified KiU-Net for passive marker spheres segmentation in CT images with fewer parameters. The architecture of the simplified KiU-Net has two branches: (1) Kite-Net which learns to capture fine details and accurate edges of the passive marker spheres, and (2) U-Net which learns high level features of the passive marker spheres. The dataset contains images of 14 trackers (56 passive marker spheres) scanned by CT. After training the network for 150 epochs, the dice accuracy of validation set reaches 95.2 %. After post-processing, only the complete passive marker spheres are segmented. In this way, the locations of passive marker spheres in preoperative registration can be obtained by CT image segmentation faster with higher accuracy; and the laborious manual operation can be replaced.
{"title":"CT Image Segmentation for Preoperative Tracker Registration of Robot-Assisted Surgery","authors":"Siru Feng, Yu Wang, Jiangzhen Guo","doi":"10.1109/CISP-BMEI56279.2022.9979826","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979826","url":null,"abstract":"Preoperative registration of robotic-assisted surgery is a laborious and time-consuming process which reqiures manual operation of a surgeon. To automate this process and improve accuracy, this paper proposed a simplified KiU-Net for passive marker spheres segmentation in CT images with fewer parameters. The architecture of the simplified KiU-Net has two branches: (1) Kite-Net which learns to capture fine details and accurate edges of the passive marker spheres, and (2) U-Net which learns high level features of the passive marker spheres. The dataset contains images of 14 trackers (56 passive marker spheres) scanned by CT. After training the network for 150 epochs, the dice accuracy of validation set reaches 95.2 %. After post-processing, only the complete passive marker spheres are segmented. In this way, the locations of passive marker spheres in preoperative registration can be obtained by CT image segmentation faster with higher accuracy; and the laborious manual operation can be replaced.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"27 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":"125727255","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}
Accurate lung markings tracking in real time is a cornerstone to percutaneous puncture robots. We present a method of lung markings tracking used in fluoroscopic video in this paper, which employs correlation filters combined with shallow and deep features. After that, we propose some improvements aiming to make it real-time. We evaluate our method on fluoroscopic video of dog and orthogonal digitally reconstructed radiographs generated by four-dimensional computed tomography and wish to implement it to aid percutaneous puncture robots soon. Results demonstrate great real-time performance and high accuracy when tracking lung markings and tumors. As far as we know, this is the first time such method for real-time lung markings tracking has been proposed which is applicable for various types of target.
{"title":"Real-time Lung Markings Tracking for Percutaneous Puncture Robots","authors":"Tianliang Fan, Chenhaowen Li, Ziwei Wan, Qianghao Huang, Luming Wang, Honghai Ma, Chunlin Zhou","doi":"10.1109/CISP-BMEI56279.2022.9980192","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9980192","url":null,"abstract":"Accurate lung markings tracking in real time is a cornerstone to percutaneous puncture robots. We present a method of lung markings tracking used in fluoroscopic video in this paper, which employs correlation filters combined with shallow and deep features. After that, we propose some improvements aiming to make it real-time. We evaluate our method on fluoroscopic video of dog and orthogonal digitally reconstructed radiographs generated by four-dimensional computed tomography and wish to implement it to aid percutaneous puncture robots soon. Results demonstrate great real-time performance and high accuracy when tracking lung markings and tumors. As far as we know, this is the first time such method for real-time lung markings tracking has been proposed which is applicable for various types of target.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"305 4 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":"132520946","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-BMEI56279.2022.9979862
Qingyu Li, Yi Gong, Fanke Meng, Lingyi Han, Zhan Xu
Orthogonal time-frequency space (OTFS) is a waveform technology designed in recent years, which can be applied to wireless communication scenarios with high Doppler extension. An accurate channel estimation result is critical in the OTFS system. Therefore, this paper focuses on channel estimation techniques based on the deep learning (DL) for the OTFS system. In our presented scheme, the delay-Doppler (DD) domain channel estimation problem is modeled as a recovery problem of sparse signal and then processed by orthogonal matching pursuit (OMP). Next, we present a five-layer deep neural network (DNN) to enhance the rough channel estimation result. Moreover, because our proposed DL-based channel estimation scheme is a model-driven paradigm, it has the advantages of a small scale of training data and a short training time. Simulation results prove that the presented DNN-based scheme obviously outperforms the traditional OMP algorithm, and the NMSE performance gain is about 5dB when the NMSE is 0.0012. In addition, we also show that the presented scheme has excellent robustness to channel mismatch and applies to different scenarios.
{"title":"A novel Channel Estimation Method based on Deep Neural Network for OTFS system","authors":"Qingyu Li, Yi Gong, Fanke Meng, Lingyi Han, Zhan Xu","doi":"10.1109/CISP-BMEI56279.2022.9979862","DOIUrl":"https://doi.org/10.1109/CISP-BMEI56279.2022.9979862","url":null,"abstract":"Orthogonal time-frequency space (OTFS) is a waveform technology designed in recent years, which can be applied to wireless communication scenarios with high Doppler extension. An accurate channel estimation result is critical in the OTFS system. Therefore, this paper focuses on channel estimation techniques based on the deep learning (DL) for the OTFS system. In our presented scheme, the delay-Doppler (DD) domain channel estimation problem is modeled as a recovery problem of sparse signal and then processed by orthogonal matching pursuit (OMP). Next, we present a five-layer deep neural network (DNN) to enhance the rough channel estimation result. Moreover, because our proposed DL-based channel estimation scheme is a model-driven paradigm, it has the advantages of a small scale of training data and a short training time. Simulation results prove that the presented DNN-based scheme obviously outperforms the traditional OMP algorithm, and the NMSE performance gain is about 5dB when the NMSE is 0.0012. In addition, we also show that the presented scheme has excellent robustness to channel mismatch and applies to different scenarios.","PeriodicalId":198522,"journal":{"name":"2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"3 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":"131526192","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：