Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090315
N. Nwulu
In this work, we present a performance comparison of the Multi Layer Perceptron (MLP), Support Vector Machines (SVM) and Voted Perceptron (VP) when applied to a social signal processing task. The signal processing task is in the field of computational politics where the aim is to predict the political parties of American congress members based on their response to certain questions. Using this dataset which is publicly available, we investigate the use of four methods to impute or approximate missing values. The four imputed datasets are used to train MLP, SVM and VP classifiers to associate the congress members' responses to their political party affiliation and we compare the results from the three classifiers. The aim is to design a practical system or model to be able to predict another person's political affiliations based on their responses to similar questions. The obtained experimental results suggest that machine learning classifiers can be used to accurately predict an individual's political leaning.
{"title":"Evaluation of machine learning classification algorithms & missing data imputation techniques","authors":"N. Nwulu","doi":"10.1109/IDAP.2017.8090315","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090315","url":null,"abstract":"In this work, we present a performance comparison of the Multi Layer Perceptron (MLP), Support Vector Machines (SVM) and Voted Perceptron (VP) when applied to a social signal processing task. The signal processing task is in the field of computational politics where the aim is to predict the political parties of American congress members based on their response to certain questions. Using this dataset which is publicly available, we investigate the use of four methods to impute or approximate missing values. The four imputed datasets are used to train MLP, SVM and VP classifiers to associate the congress members' responses to their political party affiliation and we compare the results from the three classifiers. The aim is to design a practical system or model to be able to predict another person's political affiliations based on their responses to similar questions. The obtained experimental results suggest that machine learning classifiers can be used to accurately predict an individual's political leaning.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133570237","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090190
Çağlayan Durlu, H. T. Hayvaci
In this paper, the design, analysis and numerical results of back scattering field of winged almond model with ammunition and without ammunition are presented. Simulations with using Physical Optics (PO) method in Ansys HFSS software for monostatic Radar Cross Section (RCS) were made in 1 GHz and 9 GHz. By using PO method to obtain the total scattered field received part of the radar, the body of the target is seperated into number of facets, then all these facets scattered field components are super imposed. When the electrical size of the target is twice as large as the wavelength, the order diffraction field is not considered. The fractured area from the first order will be sufficient to calculate the RCS of the target. Effects of ammunition quantity of modeled winged almon model with ammunition on RCS are compared in different frequencies.
{"title":"The analysis of RCS of winged almond model with ammunition and without ammunition","authors":"Çağlayan Durlu, H. T. Hayvaci","doi":"10.1109/IDAP.2017.8090190","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090190","url":null,"abstract":"In this paper, the design, analysis and numerical results of back scattering field of winged almond model with ammunition and without ammunition are presented. Simulations with using Physical Optics (PO) method in Ansys HFSS software for monostatic Radar Cross Section (RCS) were made in 1 GHz and 9 GHz. By using PO method to obtain the total scattered field received part of the radar, the body of the target is seperated into number of facets, then all these facets scattered field components are super imposed. When the electrical size of the target is twice as large as the wavelength, the order diffraction field is not considered. The fractured area from the first order will be sufficient to calculate the RCS of the target. Effects of ammunition quantity of modeled winged almon model with ammunition on RCS are compared in different frequencies.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121280148","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090169
Ş. Aymaz, Tugrul Çavdar, A. Cavdar
Fire may cause people in the building to be scared, distracted. In that case, some evacuation systems may help people to leave the building safely. This paper proposes a technique to explore a wayfinding during fire. Wayfinding depends on building type. We also investigated the possible influence of smoke, light and distance on route determination for fire evacuation. When the fire occurs, the system provides evacuation route guidance to people for them to be able to avoid hazard. It is important to optimize the evacuation route for minimum effects of dangerous conditions. Fire evacuation system can recommend the shortest and safety route. Here, Particle Swarm Optimization is used to optimize the evacuation route. On the other advantage of Particle Swarm Optimization is that it is easy to implement and has very few parameters.
{"title":"Fire evacuation route determination based on particle swarm optimization","authors":"Ş. Aymaz, Tugrul Çavdar, A. Cavdar","doi":"10.1109/IDAP.2017.8090169","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090169","url":null,"abstract":"Fire may cause people in the building to be scared, distracted. In that case, some evacuation systems may help people to leave the building safely. This paper proposes a technique to explore a wayfinding during fire. Wayfinding depends on building type. We also investigated the possible influence of smoke, light and distance on route determination for fire evacuation. When the fire occurs, the system provides evacuation route guidance to people for them to be able to avoid hazard. It is important to optimize the evacuation route for minimum effects of dangerous conditions. Fire evacuation system can recommend the shortest and safety route. Here, Particle Swarm Optimization is used to optimize the evacuation route. On the other advantage of Particle Swarm Optimization is that it is easy to implement and has very few parameters.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133597685","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090331
A. Şengür, Yanhui Guo, Ümit Budak, Lucas J. Vespa
Computer-aided detection (CAD) provides an efficient way to assist doctors to interpret fundus images. In a CAD system, retinal vessel (RV) detection is an important step to identify the retinal disease regions automatically and accurately. However, RV detection is still a challenging problem due to variations in morphology of the vessels on a noisy background. In this paper, we formulate the detection task as a classification problem and solve it using a convolutional neural network (CNN) as a two-class classifier. The proposed model has 2 convolution layers, 2 pooling layers, 1 dropout layer and 1 loss layer. The proposed CNN achieves better performance and significantly outperforms the state-of-the-art for automatic retinal vessel segmentation on the DRIVE dataset with 91.78% accuracy and 0.96743 AUC score. We further compare our result with several state of the art methods based on AUC values. The comparison shows that our proposal yields the second best AUC value. This demonstrates the efficiency of the proposed method which has no pre-processing steps.
{"title":"A retinal vessel detection approach using convolution neural network","authors":"A. Şengür, Yanhui Guo, Ümit Budak, Lucas J. Vespa","doi":"10.1109/IDAP.2017.8090331","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090331","url":null,"abstract":"Computer-aided detection (CAD) provides an efficient way to assist doctors to interpret fundus images. In a CAD system, retinal vessel (RV) detection is an important step to identify the retinal disease regions automatically and accurately. However, RV detection is still a challenging problem due to variations in morphology of the vessels on a noisy background. In this paper, we formulate the detection task as a classification problem and solve it using a convolutional neural network (CNN) as a two-class classifier. The proposed model has 2 convolution layers, 2 pooling layers, 1 dropout layer and 1 loss layer. The proposed CNN achieves better performance and significantly outperforms the state-of-the-art for automatic retinal vessel segmentation on the DRIVE dataset with 91.78% accuracy and 0.96743 AUC score. We further compare our result with several state of the art methods based on AUC values. The comparison shows that our proposal yields the second best AUC value. This demonstrates the efficiency of the proposed method which has no pre-processing steps.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131825268","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090343
Sibel Birtane, Seda Kazdal, O. K. Sahingoz
In last few decades, as a result of the advances in microelectromechanical systems, Wireless Sensor Networks (WSNs) have gained a considerable attention due to their low-cost, low-power and small-scale sensor nodes which are used to integrate sensing, processing, communicating capabilities to solve many different real world problems. The placement of sensor nodes is a very important step to cover the theater of these application areas. Increasing the coverage of WSN system is one of the important research interests to determine the quality of service of the system. The location of sensor nodes can be determined by humans to increase the coverage area. However, in the remote or hostile environments, the random deployment of sensor nodes is needed to be used. In this paper, the different random deployment techniques have been studied, and the experimental results are obtained have been shared to show the effectiveness of these techniques. Finally, the alternative approaches are mentioned to guide the researchers, as well.
{"title":"2D coverage analysis of sensor networks with random node deployment","authors":"Sibel Birtane, Seda Kazdal, O. K. Sahingoz","doi":"10.1109/IDAP.2017.8090343","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090343","url":null,"abstract":"In last few decades, as a result of the advances in microelectromechanical systems, Wireless Sensor Networks (WSNs) have gained a considerable attention due to their low-cost, low-power and small-scale sensor nodes which are used to integrate sensing, processing, communicating capabilities to solve many different real world problems. The placement of sensor nodes is a very important step to cover the theater of these application areas. Increasing the coverage of WSN system is one of the important research interests to determine the quality of service of the system. The location of sensor nodes can be determined by humans to increase the coverage area. However, in the remote or hostile environments, the random deployment of sensor nodes is needed to be used. In this paper, the different random deployment techniques have been studied, and the experimental results are obtained have been shared to show the effectiveness of these techniques. Finally, the alternative approaches are mentioned to guide the researchers, as well.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122131639","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090245
Yunus Santur, Mehmet Karaköse, E. Akin
Rail systems are one of the most important transportation methods used in today's world. The abnormalities that occur on railway tracks due to various causes result in breakdowns and accidents. For this reason, railway tracks must be periodically inspected. This study proposes a new approach for rail inspection. Today, the railway inspection process is generally performed using computer vision. But the oil and dust residues occurring on railway surfaces can be detected as an false-positive by the image processing software can lead to loss of time and additional costs in the railway maintenance process. In this study, a hardware and software architecture are presented to perform railway surface inspection using 3D laser camera and deep learning. The use of 3D laser cameras in railway inspection process provides high accuracy rates in real time. The reading rate of laser cameras to read up to 25.000 profiles per second is another important advantage provided in real time railway inspection. Consequently, a computer vision-based approach in which 3D laser cameras that could allow for contact-free and fast detection of the railway surface and lateral defects such as fracture, scouring and wear with high accuracy are used in the railway inspection process was proposed in the study.
{"title":"A new rail inspection method based on deep learning using laser cameras","authors":"Yunus Santur, Mehmet Karaköse, E. Akin","doi":"10.1109/IDAP.2017.8090245","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090245","url":null,"abstract":"Rail systems are one of the most important transportation methods used in today's world. The abnormalities that occur on railway tracks due to various causes result in breakdowns and accidents. For this reason, railway tracks must be periodically inspected. This study proposes a new approach for rail inspection. Today, the railway inspection process is generally performed using computer vision. But the oil and dust residues occurring on railway surfaces can be detected as an false-positive by the image processing software can lead to loss of time and additional costs in the railway maintenance process. In this study, a hardware and software architecture are presented to perform railway surface inspection using 3D laser camera and deep learning. The use of 3D laser cameras in railway inspection process provides high accuracy rates in real time. The reading rate of laser cameras to read up to 25.000 profiles per second is another important advantage provided in real time railway inspection. Consequently, a computer vision-based approach in which 3D laser cameras that could allow for contact-free and fast detection of the railway surface and lateral defects such as fracture, scouring and wear with high accuracy are used in the railway inspection process was proposed in the study.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125679770","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090208
A. Abdulrahman, Serkan Öztürk
In recent years, due to the development of computer, internet and mobile technologies the copyright protection of the multimedia documents such as digital audio, image and video has become important. Digital watermarking has become the most popular method for protecting multimedia documents. In this work, a novel robust image watermarking method based on Discrete Cosine Transform, Discrete Wavelet Transform and Arnold Transform is presented. The experiment results show that the proposed method is robust against different attacks.
{"title":"Ayrik kosinüs dönüşümü ve ayrik dalgacik dönüşümü tabanli Çoklu resim damgalama yöntemi","authors":"A. Abdulrahman, Serkan Öztürk","doi":"10.1109/IDAP.2017.8090208","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090208","url":null,"abstract":"In recent years, due to the development of computer, internet and mobile technologies the copyright protection of the multimedia documents such as digital audio, image and video has become important. Digital watermarking has become the most popular method for protecting multimedia documents. In this work, a novel robust image watermarking method based on Discrete Cosine Transform, Discrete Wavelet Transform and Arnold Transform is presented. The experiment results show that the proposed method is robust against different attacks.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115860624","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090303
Ibrahim Isik, Huseyin Birkan Yilmaz, M. Tagluk
Molecular Communication (MC) is a new multidisciplinary subject concerning medicine, biology, and communication engineering. MC concept is introduced for modeling of communication of nano/micro scale devices. In MC systems, chemical signals carrying information in gaseous or liquid media are used. Similar to other communication systems, in MC sending information from transmitter to receiver with minimum error is one of the most important goals. In MC systems due to physical characteristics of medium, higher rates of inter symbol interference (ISI) and noise increase error probability. Figures of receiver mechanisms and signal detection techniques are therefore the main factors to be tuned for decreasing error probability. In this view, so far, many receiver models such as reversible adsorption and desorption (A&D), protrusion method, ligand receptor, and linear catalytic or CAT receiver models have been introduced. In this study, these models and the results obtained through their implementation are investigated and briefly reviewed.
{"title":"A preliminary investigation of receiver models in molecular communication via diffusion","authors":"Ibrahim Isik, Huseyin Birkan Yilmaz, M. Tagluk","doi":"10.1109/IDAP.2017.8090303","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090303","url":null,"abstract":"Molecular Communication (MC) is a new multidisciplinary subject concerning medicine, biology, and communication engineering. MC concept is introduced for modeling of communication of nano/micro scale devices. In MC systems, chemical signals carrying information in gaseous or liquid media are used. Similar to other communication systems, in MC sending information from transmitter to receiver with minimum error is one of the most important goals. In MC systems due to physical characteristics of medium, higher rates of inter symbol interference (ISI) and noise increase error probability. Figures of receiver mechanisms and signal detection techniques are therefore the main factors to be tuned for decreasing error probability. In this view, so far, many receiver models such as reversible adsorption and desorption (A&D), protrusion method, ligand receptor, and linear catalytic or CAT receiver models have been introduced. In this study, these models and the results obtained through their implementation are investigated and briefly reviewed.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134174559","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090288
Fatma Kuncan, M. Şahin
In this study, a model was developed to estimate monthly-average daily solar radiation over Turkey. Artificial neural network method was used in improved model. The solar radiation values of 53 different locations over Turkey were taken as data. Land surface temperature, altitude, latitude, longitude and month values were used as input variables for modeling artificial neural network and solar radiation has been estimated as output of artificial neural network model. The RMSE, MBE and correlation coefficient for the best developed model were calculated as 1.550 MJ/m2, ‘0.172 MJ/m2 and 0.972, respectively.
{"title":"Yapay sinir aği ve uydu datalari kullanilarak güneş radyasyonunun tahmini","authors":"Fatma Kuncan, M. Şahin","doi":"10.1109/IDAP.2017.8090288","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090288","url":null,"abstract":"In this study, a model was developed to estimate monthly-average daily solar radiation over Turkey. Artificial neural network method was used in improved model. The solar radiation values of 53 different locations over Turkey were taken as data. Land surface temperature, altitude, latitude, longitude and month values were used as input variables for modeling artificial neural network and solar radiation has been estimated as output of artificial neural network model. The RMSE, MBE and correlation coefficient for the best developed model were calculated as 1.550 MJ/m2, ‘0.172 MJ/m2 and 0.972, respectively.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132454555","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090310
F. Başkaya, Ilhan Aydin
With the development of technology, people are entering the virtual world more and more. Parallel to this, the internet becomes a bigger network every day and it gets a complex structure depending on this growth. Achieving the desired information with structred data becomes an increasingly important problem. One of the useful ways to find solution for this problem is to divide this complex data into categories by text mining methods. By creating semantic similarities with this categorization, data can be achieved effectively and quickly. In this study, it is aimed to classify the news text data that have four different categories (economy, politics, sports and health) with different feature extraction and term weighting methods using different text mining techniques and to test the efficiency and success of the methods. By the proposed method, 100% classification success rate was obtained on news texts.
{"title":"Haber metinlerinin farkli metin madenciliği yöntemleriyle siniflandirilmasi","authors":"F. Başkaya, Ilhan Aydin","doi":"10.1109/IDAP.2017.8090310","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090310","url":null,"abstract":"With the development of technology, people are entering the virtual world more and more. Parallel to this, the internet becomes a bigger network every day and it gets a complex structure depending on this growth. Achieving the desired information with structred data becomes an increasingly important problem. One of the useful ways to find solution for this problem is to divide this complex data into categories by text mining methods. By creating semantic similarities with this categorization, data can be achieved effectively and quickly. In this study, it is aimed to classify the news text data that have four different categories (economy, politics, sports and health) with different feature extraction and term weighting methods using different text mining techniques and to test the efficiency and success of the methods. By the proposed method, 100% classification success rate was obtained on news texts.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117341645","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：