Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299248
Halil Güvenç
Electrocardiography is the process of recording heartbeat. The output is typically represented as a scaled graphical Figure called Electrocardiogram (ECG). In this study, we present an experimental device that obtains ECG signal using AD8232 sensor board. The device operates real-time and transmits data wirelessly using nRF24L01+ RF modules located on Arduino Mega2560 I/O boards. The received ECG data was filtered and processed with Matlab.
{"title":"Wireless ECG Device with Arduino","authors":"Halil Güvenç","doi":"10.1109/TIPTEKNO50054.2020.9299248","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299248","url":null,"abstract":"Electrocardiography is the process of recording heartbeat. The output is typically represented as a scaled graphical Figure called Electrocardiogram (ECG). In this study, we present an experimental device that obtains ECG signal using AD8232 sensor board. The device operates real-time and transmits data wirelessly using nRF24L01+ RF modules located on Arduino Mega2560 I/O boards. The received ECG data was filtered and processed with Matlab.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132422406","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299268
E. Polat, A. Güvenis
Mutual information is an image similarity metric often used for the robust registration of multimodality images. The aim of this study is to investigate the use of a simple to implement similarity computation method based on a mutual information index for the automated detection of Alzheimer’s disease from FDG PET studies. 102 healthy and 95 Alzheimer’s disease FDG PET patient images from the online Alzheimer’s disease Neuroimaging Initiative (ADNI) database were used to develop and test the system. Images were preprocessed for enabling comparison. An index was computed for each new image based on its degree of similarity to images belonging to AD patients versus healthy control patients. Classification was made based on the value of this index. The leave-one-out method was used for performance evaluation. Performance was evaluated using Receiver Operating Characteristic (ROC) curves. The diagnostic reliability given by the area under the curve (AUC) was determined as $0.857pm 0.0261$. The results suggest that a mutual information based image similarity method can potentially be useful as a second opinion computer aided diagnostic (CAD) system providing verification to visual and black box approaches. The system does not need training with new data and does not require the computation of image features.
{"title":"Detecting Alzheimer Disease on FDG PET Images Using a Similarity Index Based on Mutual Information","authors":"E. Polat, A. Güvenis","doi":"10.1109/TIPTEKNO50054.2020.9299268","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299268","url":null,"abstract":"Mutual information is an image similarity metric often used for the robust registration of multimodality images. The aim of this study is to investigate the use of a simple to implement similarity computation method based on a mutual information index for the automated detection of Alzheimer’s disease from FDG PET studies. 102 healthy and 95 Alzheimer’s disease FDG PET patient images from the online Alzheimer’s disease Neuroimaging Initiative (ADNI) database were used to develop and test the system. Images were preprocessed for enabling comparison. An index was computed for each new image based on its degree of similarity to images belonging to AD patients versus healthy control patients. Classification was made based on the value of this index. The leave-one-out method was used for performance evaluation. Performance was evaluated using Receiver Operating Characteristic (ROC) curves. The diagnostic reliability given by the area under the curve (AUC) was determined as $0.857pm 0.0261$. The results suggest that a mutual information based image similarity method can potentially be useful as a second opinion computer aided diagnostic (CAD) system providing verification to visual and black box approaches. The system does not need training with new data and does not require the computation of image features.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130971862","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 : 2020-11-19DOI: 10.1109/tiptekno50054.2020.9299230
{"title":"TIPTEKNO 2020 TOC","authors":"","doi":"10.1109/tiptekno50054.2020.9299230","DOIUrl":"https://doi.org/10.1109/tiptekno50054.2020.9299230","url":null,"abstract":"","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120963079","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299256
Mehmet Akif Ozdemir, Berkay Elagoz, Aysegul Alaybeyoglu Soy, A. Akan
In this study, it was aimed to recognize the emotional state from facial images using the deep learning method. In the study, which was approved by the ethics committee, a custom data set was created using videos taken from 20 male and 20 female participants while simulating 7 different facial expressions (happy, sad, surprised, angry, disgusted, scared, and neutral). Firstly, obtained videos were divided into image frames, and then face images were segmented using the Haar library from image frames. The size of the custom data set obtained after the image preprocessing is more than 25 thousand images. The proposed convolutional neural network (CNN) architecture which is mimics of LeNet architecture has been trained with this custom dataset. According to the proposed CNN architecture experiment results, the training loss was found as 0.0115, the training accuracy was found as 99.62%, the validation loss was 0.0109, and the validation accuracy was 99.71%.
{"title":"Deep Learning Based Facial Emotion Recognition System","authors":"Mehmet Akif Ozdemir, Berkay Elagoz, Aysegul Alaybeyoglu Soy, A. Akan","doi":"10.1109/TIPTEKNO50054.2020.9299256","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299256","url":null,"abstract":"In this study, it was aimed to recognize the emotional state from facial images using the deep learning method. In the study, which was approved by the ethics committee, a custom data set was created using videos taken from 20 male and 20 female participants while simulating 7 different facial expressions (happy, sad, surprised, angry, disgusted, scared, and neutral). Firstly, obtained videos were divided into image frames, and then face images were segmented using the Haar library from image frames. The size of the custom data set obtained after the image preprocessing is more than 25 thousand images. The proposed convolutional neural network (CNN) architecture which is mimics of LeNet architecture has been trained with this custom dataset. According to the proposed CNN architecture experiment results, the training loss was found as 0.0115, the training accuracy was found as 99.62%, the validation loss was 0.0109, and the validation accuracy was 99.71%.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127558044","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299273
Ebru Ergün, O. Aydemir
Brain-computer interfaces (BCIs) recognize specific features of a person’s brain signal relating to his/her intent, and output a control command that controls the outside devices or computers. BCI systems facilitate the lives of patients who cannot move any muscles but have no cognitive disorder. The high dimensions of features represent a research challenge. In recent years, especially nature inspired heuristic optimization algorithms became popular in order to eliminate unnecessary features. This paper addresses a crucial factor for effective classification of motor imaginary based EEG signals that are an optimal selection of relevant EEG features using firefly algorithm. Firefly algorithm (FA) works on the principle of directing the less shiny than the light intensity emitted by fireflies in nature towards the bright. The algorithm can adaptively select the best subset of features and improve classification accuracy. In this study, following extracted Katz Fractal Dimension based features, effective feature(s) were selected by FA. The proposed method successfully applied on open access dataset which was collected from 29 subjects. We obtained an average 76.14% classification accuracy (CA) using k-nearest neighbor classifier. This is 4.4% higher than the CA calculated by using all features. These results proved that used method is robust for this dataset.
{"title":"Firefly Algorithm Based Feature Selection for EEG Signal Classification","authors":"Ebru Ergün, O. Aydemir","doi":"10.1109/TIPTEKNO50054.2020.9299273","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299273","url":null,"abstract":"Brain-computer interfaces (BCIs) recognize specific features of a person’s brain signal relating to his/her intent, and output a control command that controls the outside devices or computers. BCI systems facilitate the lives of patients who cannot move any muscles but have no cognitive disorder. The high dimensions of features represent a research challenge. In recent years, especially nature inspired heuristic optimization algorithms became popular in order to eliminate unnecessary features. This paper addresses a crucial factor for effective classification of motor imaginary based EEG signals that are an optimal selection of relevant EEG features using firefly algorithm. Firefly algorithm (FA) works on the principle of directing the less shiny than the light intensity emitted by fireflies in nature towards the bright. The algorithm can adaptively select the best subset of features and improve classification accuracy. In this study, following extracted Katz Fractal Dimension based features, effective feature(s) were selected by FA. The proposed method successfully applied on open access dataset which was collected from 29 subjects. We obtained an average 76.14% classification accuracy (CA) using k-nearest neighbor classifier. This is 4.4% higher than the CA calculated by using all features. These results proved that used method is robust for this dataset.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127693197","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299214
Merve Özdemir, Ziyşan Buse Yaralı Çevik, N. Topaloglu
Photobiomodulation (PBM) is defined as the use of non-ionizing photonic energy to trigger photochemical changes, particularly in mitochondrial-sensitive cellular structures. Photobiomodulation is a form of treatment used in medicine in a practical and noninvasive way and it has a significant role in inflammation, ache, and pain reduction, wound healing, and tissue regeneration. It triggers proliferation and the activity of the cell, primarily by utilizing light from the near infrared-red to visible wavelength of the light (630-1000 nm). This in vitro study has analyzed comparatively the most appropriate energy doses with the wavelengths in the red and near-infrared spectrum to induce photobiomodulation on the keratinocyte cells. 1, 3, and $5mathrm{J}/ mathrm{m}^{2}$ energy densities of 655 nm and 808 nm diode lasers were used, which might affect wound healing mechanism and cell proliferation. The potential stimulating effect of photobiomodulation to promote wound healing and cell proliferation on human keratinocyte cells was analyzed via microscopic imaging of cell morphology, MTT analysis for cell proliferation and scratch assay for wound closure after light applications. The highest increase in cell viability was obtained with a rate of 112.6% after the triple treatment of 655-nm wavelength at 1 J/cm2. The best wound closure was achieved with a rate of 45% after the triple treatment of 655 nm wavelength at 3 J/cm2. This study revealed that PBM with 655-nm of wavelength was an effective tool to induce cell proliferation and speed up the wound healing process with specific energy doses.
{"title":"The Effect of Photobiomodulation with Red and Near-Infrared Wavelengths on Keratinocyte Cells","authors":"Merve Özdemir, Ziyşan Buse Yaralı Çevik, N. Topaloglu","doi":"10.1109/TIPTEKNO50054.2020.9299214","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299214","url":null,"abstract":"Photobiomodulation (PBM) is defined as the use of non-ionizing photonic energy to trigger photochemical changes, particularly in mitochondrial-sensitive cellular structures. Photobiomodulation is a form of treatment used in medicine in a practical and noninvasive way and it has a significant role in inflammation, ache, and pain reduction, wound healing, and tissue regeneration. It triggers proliferation and the activity of the cell, primarily by utilizing light from the near infrared-red to visible wavelength of the light (630-1000 nm). This in vitro study has analyzed comparatively the most appropriate energy doses with the wavelengths in the red and near-infrared spectrum to induce photobiomodulation on the keratinocyte cells. 1, 3, and $5mathrm{J}/ mathrm{m}^{2}$ energy densities of 655 nm and 808 nm diode lasers were used, which might affect wound healing mechanism and cell proliferation. The potential stimulating effect of photobiomodulation to promote wound healing and cell proliferation on human keratinocyte cells was analyzed via microscopic imaging of cell morphology, MTT analysis for cell proliferation and scratch assay for wound closure after light applications. The highest increase in cell viability was obtained with a rate of 112.6% after the triple treatment of 655-nm wavelength at 1 J/cm2. The best wound closure was achieved with a rate of 45% after the triple treatment of 655 nm wavelength at 3 J/cm2. This study revealed that PBM with 655-nm of wavelength was an effective tool to induce cell proliferation and speed up the wound healing process with specific energy doses.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125618523","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299246
Delal Şeker, M. S. Özerdem
In this study, discrimination of normal and schizophrenic EEG is aimed by using lineer features with different classifiers. Fort his purpose, 1 minutes of EEG records through 16 channels were recorded from 39 normal and 39 schizophrenia patients and minimum, maximum, mean, standard deviation and median feautes were extracted from these records. k-neighbors, Multi-layer perceptron, support vector machines and Random forest classifier were applied to feature vectors extracted from each channel. Highest classification accuracy is reached to 99.95% in proposed work. While MLP seems to be best classifier, channel C4 is observed most relevant to discriminate schizophrenic EEG from healthy control group. As a result of independent sample t-test and Mann-Whitney U Test for the purpose of statistical analysis, there is a distinct statistical significance for whole channels.When considering proposed work, obtained results are so promising and make contributions to literatüre view according to related works.
{"title":"Classification and Statistical Analysis of Schizophrenic and Normal EEG Time Series","authors":"Delal Şeker, M. S. Özerdem","doi":"10.1109/TIPTEKNO50054.2020.9299246","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299246","url":null,"abstract":"In this study, discrimination of normal and schizophrenic EEG is aimed by using lineer features with different classifiers. Fort his purpose, 1 minutes of EEG records through 16 channels were recorded from 39 normal and 39 schizophrenia patients and minimum, maximum, mean, standard deviation and median feautes were extracted from these records. k-neighbors, Multi-layer perceptron, support vector machines and Random forest classifier were applied to feature vectors extracted from each channel. Highest classification accuracy is reached to 99.95% in proposed work. While MLP seems to be best classifier, channel C4 is observed most relevant to discriminate schizophrenic EEG from healthy control group. As a result of independent sample t-test and Mann-Whitney U Test for the purpose of statistical analysis, there is a distinct statistical significance for whole channels.When considering proposed work, obtained results are so promising and make contributions to literatüre view according to related works.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"25 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124301766","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299231
Kaya Dağlı, O. Eroğul
Brain tumors threathen human health significantly. Misdiagnosis of these tumors decrease effectiveness of decisions for intervention and patient’s state of health. The conventional method to differentiate brain tumors is by the inspection of magnetic resonance images by clinicians. Since there are various types of brain tumors and there are many images that clinicians should examine, this method is both prone to human errors and causes excessive time consumption. In this study, the most common brain tumor types; Glioma, Meningioma and Pituitary are classified using deep learning models. While the main objective of this study is to have a high rate of accuracy, the time spent is also examined. The aim of this study is to ease clinicians work load and have a time efficient classification system. The system which has been built has an accuracy up to 90%.
{"title":"Classification of Brain Tumors via Deep Learning Models","authors":"Kaya Dağlı, O. Eroğul","doi":"10.1109/TIPTEKNO50054.2020.9299231","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299231","url":null,"abstract":"Brain tumors threathen human health significantly. Misdiagnosis of these tumors decrease effectiveness of decisions for intervention and patient’s state of health. The conventional method to differentiate brain tumors is by the inspection of magnetic resonance images by clinicians. Since there are various types of brain tumors and there are many images that clinicians should examine, this method is both prone to human errors and causes excessive time consumption. In this study, the most common brain tumor types; Glioma, Meningioma and Pituitary are classified using deep learning models. While the main objective of this study is to have a high rate of accuracy, the time spent is also examined. The aim of this study is to ease clinicians work load and have a time efficient classification system. The system which has been built has an accuracy up to 90%.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117018853","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 : 2020-11-19DOI: 10.1109/tiptekno50054.2020.9299271
{"title":"TIPTEKNO 2020 Cover Page","authors":"","doi":"10.1109/tiptekno50054.2020.9299271","DOIUrl":"https://doi.org/10.1109/tiptekno50054.2020.9299271","url":null,"abstract":"","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128612995","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 : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299232
Ahmet Demir, F. Yilmaz
Pneumonia is one of the most commonly seen illnesses in the world and its diagnosis needs some expertise. Computer aided diagnosis methods are used extensively in a lot of fields like health care. This study uses Inception-ResNet-v2 deep learning architecture. Classification is done by using this architecture. ReLU activation function seen in network architecture is changed with LeakyReLU activation function and classification task is done. After that, all of the maxpooling layers seen in network architecture is changed with avepooling layers and again classification task is done. Lastly, this seperate changes done in network architecture is combined in one network and again classification task is done with new network architecture. Four experiments are done in total and their results are compared. The best case with a sensitivity value of 93.16% and with a specificity value of 93.59% is obtained in Inception Resnet V2 with together application of LeakyReLU and Averagepooling.
{"title":"Inception-ResNet-v2 with Leakyrelu and Averagepooling for More Reliable and Accurate Classification of Chest X-ray Images","authors":"Ahmet Demir, F. Yilmaz","doi":"10.1109/TIPTEKNO50054.2020.9299232","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299232","url":null,"abstract":"Pneumonia is one of the most commonly seen illnesses in the world and its diagnosis needs some expertise. Computer aided diagnosis methods are used extensively in a lot of fields like health care. This study uses Inception-ResNet-v2 deep learning architecture. Classification is done by using this architecture. ReLU activation function seen in network architecture is changed with LeakyReLU activation function and classification task is done. After that, all of the maxpooling layers seen in network architecture is changed with avepooling layers and again classification task is done. Lastly, this seperate changes done in network architecture is combined in one network and again classification task is done with new network architecture. Four experiments are done in total and their results are compared. The best case with a sensitivity value of 93.16% and with a specificity value of 93.59% is obtained in Inception Resnet V2 with together application of LeakyReLU and Averagepooling.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128769465","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：