Pub Date : 2018-11-01DOI: 10.1109/ICDSP.2018.8631873
Qinghua Zhou, Xiaoqing Shen
This paper presents a new method amongst developing computer vision algorithms for the detection of multiple sclerosis (MS). Lesions caused by MS are detectable on MRI images. CV algorithms present subjective approaches in detection. In this study, we used the grey-level co-occurrence matrix to extract detailed texture features from the spatial distribution of greytone on MRI images. Multi-layered feedforward neural network was used as the classifier. Then, we selected biogeography-based optimisation algorithm to train this classifier. Through cross-validation, the method achieved sensitivity, specificity and accuracy of 92.75±1.31%, 92.76±1.65%, and 92.75±1.43% respectively. We validated the efficiency of the classifier, but overall, the method is inferior to state-of-art algorithms of MS lesion detection in all aspects.
{"title":"Multiple Sclerosis Identification by Grey-Level Cooccurrence Matrix and Biogeography-Based Optimization","authors":"Qinghua Zhou, Xiaoqing Shen","doi":"10.1109/ICDSP.2018.8631873","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631873","url":null,"abstract":"This paper presents a new method amongst developing computer vision algorithms for the detection of multiple sclerosis (MS). Lesions caused by MS are detectable on MRI images. CV algorithms present subjective approaches in detection. In this study, we used the grey-level co-occurrence matrix to extract detailed texture features from the spatial distribution of greytone on MRI images. Multi-layered feedforward neural network was used as the classifier. Then, we selected biogeography-based optimisation algorithm to train this classifier. Through cross-validation, the method achieved sensitivity, specificity and accuracy of 92.75±1.31%, 92.76±1.65%, and 92.75±1.43% respectively. We validated the efficiency of the classifier, but overall, the method is inferior to state-of-art algorithms of MS lesion detection in all aspects.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126710527","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631601
Sanduni U. Premaratne, C. Edussooriya, C. Wijenayake, L. Bruton, P. Agathoklis
A low-complexity 4-D sparse FIR hyperfan filter is proposed for volumetric refocusing of light fields. By exploiting the partial separability of the spectral region of support of a light field, the proposed filter is designed as a cascade of two 4-D hyperfan filters. The sparsity of the filter coefficients is achieved by hard thresholding the nonsparse filter coefficients. The experimental results confirm that the proposed 4-D sparse FIR hyperfan filter provides 72% mean reduction of computational complexity compared to a 4-D nonsparse FIR hyperfan filter withoudeteriorating the fidelity of volumetric refocused light fields. In particular, the mean structure similarity (SSIM) index between the volumetric refocused light fields by the proposed sparse filter and the nonsparse filter is 0.989.
{"title":"A 4-D Sparse FIR Hyperfan Filter for Volumetric Refocusing of Light Fields by Hard Thresholding","authors":"Sanduni U. Premaratne, C. Edussooriya, C. Wijenayake, L. Bruton, P. Agathoklis","doi":"10.1109/ICDSP.2018.8631601","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631601","url":null,"abstract":"A low-complexity 4-D sparse FIR hyperfan filter is proposed for volumetric refocusing of light fields. By exploiting the partial separability of the spectral region of support of a light field, the proposed filter is designed as a cascade of two 4-D hyperfan filters. The sparsity of the filter coefficients is achieved by hard thresholding the nonsparse filter coefficients. The experimental results confirm that the proposed 4-D sparse FIR hyperfan filter provides 72% mean reduction of computational complexity compared to a 4-D nonsparse FIR hyperfan filter withoudeteriorating the fidelity of volumetric refocused light fields. In particular, the mean structure similarity (SSIM) index between the volumetric refocused light fields by the proposed sparse filter and the nonsparse filter is 0.989.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114205964","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631679
Yuanyuan Tao, Meimei Shi, C. Lam
This study proposed an application of feedforward neural network (FNN) with particle swarm optimization(PSO) on angiosperms classification. We first collected petal images of three different angiosperm plants and each type contains 40 images. Second, we used gray-level co-occurrence matrix (GLCM) to extract texture features. Third, we used FNN as the classifier. Finally, we employed PSO to train the classifier. In the experiment, we utilized eight-fold cross validation techniques. The average sensitivity of our method is about 86%. This proposed method performs better than three genetic algorithm and simulated annealing.
{"title":"Classification of angiosperms by gray-level co-occurrence matrix and combination of feedforward neural network with particle swarm optimization","authors":"Yuanyuan Tao, Meimei Shi, C. Lam","doi":"10.1109/ICDSP.2018.8631679","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631679","url":null,"abstract":"This study proposed an application of feedforward neural network (FNN) with particle swarm optimization(PSO) on angiosperms classification. We first collected petal images of three different angiosperm plants and each type contains 40 images. Second, we used gray-level co-occurrence matrix (GLCM) to extract texture features. Third, we used FNN as the classifier. Finally, we employed PSO to train the classifier. In the experiment, we utilized eight-fold cross validation techniques. The average sensitivity of our method is about 86%. This proposed method performs better than three genetic algorithm and simulated annealing.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121700199","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631545
Zheng Li, Qiuliang Ye, Yitong Guo, Zikang Tian, B. Ling, R. W. Lam
Wearable non-invasive blood glucose estimation plays an important role in the biomedical signal processing community. The common blood glucose estimation method is via the direct random forest algorithm. However, since the useful information of the signal is usually corrupted due to the low SNR, the distorted features inputted for the training algorithm result to a poor estimation performance. This paper proposes to employ an empirical mode decomposition (EMD) based hierarchical multiresolution analysis for performing the pre-processing and the random forest for performing the wearable non-invasive blood glucose estimation. More precisely, two levels of decompositions are employed in the EMD based hierarchical multiresolution analysis and only the first two intrinsic mode functions (IMF) in the second level of decomposition are discarded. Next, the features exacted from the processed near infrared (NIR) signal are trained via the random forest regression algorithm. The computer numerical simulation results show that the proposed method outperforms the classical method without the EMD pre-processing and with conventional EMD based pre-processing in terms of the average estimation accuracy and the distribution error shown on the Clarke error gird.
{"title":"Wearable Non-invasive Blood Glucose Estimation via Empirical Mode Decomposition Based Hierarchical Multiresolution Analysis and Random Forest","authors":"Zheng Li, Qiuliang Ye, Yitong Guo, Zikang Tian, B. Ling, R. W. Lam","doi":"10.1109/ICDSP.2018.8631545","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631545","url":null,"abstract":"Wearable non-invasive blood glucose estimation plays an important role in the biomedical signal processing community. The common blood glucose estimation method is via the direct random forest algorithm. However, since the useful information of the signal is usually corrupted due to the low SNR, the distorted features inputted for the training algorithm result to a poor estimation performance. This paper proposes to employ an empirical mode decomposition (EMD) based hierarchical multiresolution analysis for performing the pre-processing and the random forest for performing the wearable non-invasive blood glucose estimation. More precisely, two levels of decompositions are employed in the EMD based hierarchical multiresolution analysis and only the first two intrinsic mode functions (IMF) in the second level of decomposition are discarded. Next, the features exacted from the processed near infrared (NIR) signal are trained via the random forest regression algorithm. The computer numerical simulation results show that the proposed method outperforms the classical method without the EMD pre-processing and with conventional EMD based pre-processing in terms of the average estimation accuracy and the distribution error shown on the Clarke error gird.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123877197","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631562
Siyuan Lu, Zhihai Lu, Soriya Aok, Logan Graham
Automatic fruit classification is a difficult problem because there are so many types of fruits and the large inter-class similarity. In this study, we proposed to use convolutional neural network (CNN) for fruit classification. We designed a six-layer CNN consisting of convolution layers, pooling layers and fully connected layers. The experiment results suggested that our method achieved promising performance with accuracy of 91.44%, better than three state-of-the-art approaches: voting-based support vector machine, wavelet entropy, and genetic algorithm.
{"title":"Fruit Classification Based on Six Layer Convolutional Neural Network","authors":"Siyuan Lu, Zhihai Lu, Soriya Aok, Logan Graham","doi":"10.1109/ICDSP.2018.8631562","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631562","url":null,"abstract":"Automatic fruit classification is a difficult problem because there are so many types of fruits and the large inter-class similarity. In this study, we proposed to use convolutional neural network (CNN) for fruit classification. We designed a six-layer CNN consisting of convolution layers, pooling layers and fully connected layers. The experiment results suggested that our method achieved promising performance with accuracy of 91.44%, better than three state-of-the-art approaches: voting-based support vector machine, wavelet entropy, and genetic algorithm.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123890213","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631589
Boxiao Liu, C. Heng, Guoxing Wang, Y. Lian
An on-chip data compression scheme, suitable for electrical impedance tomography signal acquisition and recovery is proposed. For typical 16 electrode lung electrical impedance tomography system, 13 channel high frequency signals are acquired and I/Q demodulated to different frequencies. Frequency division signals are summed up and sampled by only two delta sigma modulators with high resolution. Thus 84.6% reduction of ADC usage is achieved, and the output data is repacked with compression ratio of 9.75. After decimation, each I/Q signal is recovered with 10-bit resolution by applying Blackman window corrected fast Fourier transformation algorithm.
{"title":"On-chip Data Compression Scheme for Lung EIT Signal Acquisition and Recovery","authors":"Boxiao Liu, C. Heng, Guoxing Wang, Y. Lian","doi":"10.1109/ICDSP.2018.8631589","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631589","url":null,"abstract":"An on-chip data compression scheme, suitable for electrical impedance tomography signal acquisition and recovery is proposed. For typical 16 electrode lung electrical impedance tomography system, 13 channel high frequency signals are acquired and I/Q demodulated to different frequencies. Frequency division signals are summed up and sampled by only two delta sigma modulators with high resolution. Thus 84.6% reduction of ADC usage is achieved, and the output data is repacked with compression ratio of 9.75. After decimation, each I/Q signal is recovered with 10-bit resolution by applying Blackman window corrected fast Fourier transformation algorithm.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115176587","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631884
H. Mendoza, Adrián Ramírez, G. Corral-Briones
Data dissemination using Unmanned Aerial Vehicles (UAVs) is currently emerging as an alternative to effectively integrate remote devices to Internet of Things core networks. This paper proposes the use of a closed loop transmission diversity scheme in order to disseminate information toward almost static and battery-limited devices typically unable to communicate over long distances. We present results that show the multiplexing gain that is possible to get in UAV scenarios, which are characterized by the presence of a strong Line-of-Sight (LOS) component. Moreover, we show that in presence of a large amount of users or devices, data separation can be significantly improved by the use of low complexity blind receivers.
{"title":"Internet of Remote Things: A Communication Scheme for Air-to-Ground Information Dissemination","authors":"H. Mendoza, Adrián Ramírez, G. Corral-Briones","doi":"10.1109/ICDSP.2018.8631884","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631884","url":null,"abstract":"Data dissemination using Unmanned Aerial Vehicles (UAVs) is currently emerging as an alternative to effectively integrate remote devices to Internet of Things core networks. This paper proposes the use of a closed loop transmission diversity scheme in order to disseminate information toward almost static and battery-limited devices typically unable to communicate over long distances. We present results that show the multiplexing gain that is possible to get in UAV scenarios, which are characterized by the presence of a strong Line-of-Sight (LOS) component. Moreover, we show that in presence of a large amount of users or devices, data separation can be significantly improved by the use of low complexity blind receivers.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"93 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114030189","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631597
Qing Miao, B. Ling
This paper proposes $l_{2}$ norm, $l_{1}$ norm and $iota _{infty }$ norm of clustering optimization algorithms based on dictionary learning. By solving an optimization problem to assign each feature to a cluster and solving another optimization problem to re-calculating the vectors representing the clusters, each algorithm keeps iterating until it converges. Computer simulation experiments show that the three algorithms have good clustering results and the convergence is confirmed. The runtime of l2 norm clustering optimization algorithm is much faster than h norm and $ linfty $ norm clustering optimization algorithms.
{"title":"Three clustering optimization algorithms based on dictionary learning","authors":"Qing Miao, B. Ling","doi":"10.1109/ICDSP.2018.8631597","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631597","url":null,"abstract":"This paper proposes $l_{2}$ norm, $l_{1}$ norm and $iota _{infty }$ norm of clustering optimization algorithms based on dictionary learning. By solving an optimization problem to assign each feature to a cluster and solving another optimization problem to re-calculating the vectors representing the clusters, each algorithm keeps iterating until it converges. Computer simulation experiments show that the three algorithms have good clustering results and the convergence is confirmed. The runtime of l2 norm clustering optimization algorithm is much faster than h norm and $ linfty $ norm clustering optimization algorithms.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122489590","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 : 2018-11-01DOI: 10.1109/ICDSP.2018.8631626
Qiuxiang Shen, Huan Wan, B. Liao
In this paper, a new method for direction-of-arrival (DOA) estimation in unknown nonuniform noise based on iterative noise covariance and noise-free covariance matrix estimation and sparse representation is proposed. More specifically, in the first stage, the noise covariance matrix and noise-free covariance matrix are iteratively estimated through a weighted least square (WLS) minimization problem. Next, the DOA estimation problem is reduced to a sparse reconstruction problem with nonnegativity constraint by exploiting the sparsity of the prewhitened noise- free covariance matrix after vectorization. Numerical examples are conducted to validate the effectiveness and superior performance of the proposed approach over the existing sparsity-aware methods we have tested.
{"title":"A Sparse Representation Based Method for DOA Estimation Based in Nonuniform Noise","authors":"Qiuxiang Shen, Huan Wan, B. Liao","doi":"10.1109/ICDSP.2018.8631626","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631626","url":null,"abstract":"In this paper, a new method for direction-of-arrival (DOA) estimation in unknown nonuniform noise based on iterative noise covariance and noise-free covariance matrix estimation and sparse representation is proposed. More specifically, in the first stage, the noise covariance matrix and noise-free covariance matrix are iteratively estimated through a weighted least square (WLS) minimization problem. Next, the DOA estimation problem is reduced to a sparse reconstruction problem with nonnegativity constraint by exploiting the sparsity of the prewhitened noise- free covariance matrix after vectorization. Numerical examples are conducted to validate the effectiveness and superior performance of the proposed approach over the existing sparsity-aware methods we have tested.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122931097","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}
The use of small and miniature unmanned air vehicles(UAVs) for remote sensing and detecting applications has become increasingly popular in recent years. The intermittent connectivity in a dynamically mobile UAV network (UAVN) makes it challenging to efficiently gather sensed target data. Distributed parallel detection and centralized fusion rules in classical fusion systems are based on global message connectivity. This paper investigates the communication of sensed data from a set of mobile survey UAVs to a fusion center in large indoor or outdoor severe environment. Given the dynamic connectivity of links in UAV network, a general model of Fusion System of UAV Network (FS-UAVN) is proposed to schedule the UAVs to collect detection data. Based on this FS-UAVN model, a specific fusion method named Maximal-ratio Combining Fusion Rule (MRC-FR) is provided for the fusion center. MRC-FR utilizes the theory of Maximal Ratio Combiner (MRC) to discuss the fusion performance in view of link connectivity. Evaluation shows that the proposed MRC-FR can realize the centralized fusion system with simpler formulas and express the numerical relationship between outage probability, outage capacity, connectivity probability, signal-to-noise ratio of channel, and so on.
{"title":"A General Fusion System and Maximal-Ratio Combining Fusion Rule in Unmanned Air Vehicle Network","authors":"Shufang Xu, Dazhuan Xu, Huibin Wang, Yingchi Mao, Xuejie Zhang, Longbao Wang","doi":"10.1109/ICDSP.2018.8631687","DOIUrl":"https://doi.org/10.1109/ICDSP.2018.8631687","url":null,"abstract":"The use of small and miniature unmanned air vehicles(UAVs) for remote sensing and detecting applications has become increasingly popular in recent years. The intermittent connectivity in a dynamically mobile UAV network (UAVN) makes it challenging to efficiently gather sensed target data. Distributed parallel detection and centralized fusion rules in classical fusion systems are based on global message connectivity. This paper investigates the communication of sensed data from a set of mobile survey UAVs to a fusion center in large indoor or outdoor severe environment. Given the dynamic connectivity of links in UAV network, a general model of Fusion System of UAV Network (FS-UAVN) is proposed to schedule the UAVs to collect detection data. Based on this FS-UAVN model, a specific fusion method named Maximal-ratio Combining Fusion Rule (MRC-FR) is provided for the fusion center. MRC-FR utilizes the theory of Maximal Ratio Combiner (MRC) to discuss the fusion performance in view of link connectivity. Evaluation shows that the proposed MRC-FR can realize the centralized fusion system with simpler formulas and express the numerical relationship between outage probability, outage capacity, connectivity probability, signal-to-noise ratio of channel, and so on.","PeriodicalId":218806,"journal":{"name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131165294","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：