Pub Date : 2016-11-01DOI: 10.1109/TAAI.2016.7880182
Hideko Kawakubo, Masashi Sugiyama
Sufficient dimension reduction (SDR) is a popular framework for supervised dimension reduction, aiming at reducing the dimensionality of input data while information on output data is maximally maintained. On the other hand, in many recent supervised classification learning tasks, it is conceivable that the balance of samples in each class varies between the training and testing phases. Such a phenomenon, referred to as class-prior change, causes existing SDR methods to perform undesirably particularly when the training data is highly imbalanced. In this paper, we extend the state-of-the-art SDR method called leastsquares gradients for dimension reduction (LSGDR) to be able to cope with such class-prior change under the semi-supervised learning setup where unlabeled test data are available in addition to labeled training data. Through experiments, we demonstrate the usefulness of our proposed method.
{"title":"Semi-supervised sufficient dimension reduction under class-prior change","authors":"Hideko Kawakubo, Masashi Sugiyama","doi":"10.1109/TAAI.2016.7880182","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880182","url":null,"abstract":"Sufficient dimension reduction (SDR) is a popular framework for supervised dimension reduction, aiming at reducing the dimensionality of input data while information on output data is maximally maintained. On the other hand, in many recent supervised classification learning tasks, it is conceivable that the balance of samples in each class varies between the training and testing phases. Such a phenomenon, referred to as class-prior change, causes existing SDR methods to perform undesirably particularly when the training data is highly imbalanced. In this paper, we extend the state-of-the-art SDR method called leastsquares gradients for dimension reduction (LSGDR) to be able to cope with such class-prior change under the semi-supervised learning setup where unlabeled test data are available in addition to labeled training data. Through experiments, we demonstrate the usefulness of our proposed method.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"47 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120982925","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880156
Taesung Lee, Seung-won Hwang
Entity tasks, such as linking, integration, and translation, are crucial for many search and NLP applications. For this purposed entity graphs have been manually built or automatically harvested. In this paper, we survey existing approaches abstracting these problems into a graph-based iterative matching on a pair of entity graphs.
{"title":"Linking, integrating, and translating entities via iterative graph matching","authors":"Taesung Lee, Seung-won Hwang","doi":"10.1109/TAAI.2016.7880156","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880156","url":null,"abstract":"Entity tasks, such as linking, integration, and translation, are crucial for many search and NLP applications. For this purposed entity graphs have been manually built or automatically harvested. In this paper, we survey existing approaches abstracting these problems into a graph-based iterative matching on a pair of entity graphs.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125182682","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880166
Jia-Fong Yeh, Pei-Hsiu Su, Shih-Heng Huang, T. Chiang
Snake game is a computer action game, whose goal is to control a snake to move and collect food in a map. In this paper we develop a controller based on movement rating functions considering smoothness, space, and food. Scores given by these functions are aggregated by linear weighted sum, and the snake takes the action that leads to the highest score. To find a set of good weight values, we apply an evolutionary algorithm. We examine several algorithm variants of different crossover and environmental selection operators. Experimental results show that our design method is able to generate smart controllers.
{"title":"Snake game AI: Movement rating functions and evolutionary algorithm-based optimization","authors":"Jia-Fong Yeh, Pei-Hsiu Su, Shih-Heng Huang, T. Chiang","doi":"10.1109/TAAI.2016.7880166","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880166","url":null,"abstract":"Snake game is a computer action game, whose goal is to control a snake to move and collect food in a map. In this paper we develop a controller based on movement rating functions considering smoothness, space, and food. Scores given by these functions are aggregated by linear weighted sum, and the snake takes the action that leads to the highest score. To find a set of good weight values, we apply an evolutionary algorithm. We examine several algorithm variants of different crossover and environmental selection operators. Experimental results show that our design method is able to generate smart controllers.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127234718","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880112
C. H. Wu, Hsung-Pin Chang, Y. C. Liu, G. H. Lee, L. Chi
This paper proposes a Modified Multiple Triangular Inequality Elimination (MMTIE) to further reduce the search number of candidate codevectors. The MMTIE adopts the same original search space as the MTIE scheme with the initial best-matched codevector selected by the Initial Index Code Assignment (IICA), and integrates the intersection rule of the Candidate Codevectors Group (CCG) scheme to further reduce the search space and find the best-matched candidate by table look-up operation in the coding stage. Since the IICA approach selects an initial best-matched codevector by exploiting the correlations of the neighboring blocks and the predefined CCG space is obtained from the off-line stage, the MMTIE algorithm achieves better coding efficiency than the original MTIE at a cost of extra memory. In addition, the proposed algorithm provides the same coding quality as the full search method. Experimental results demonstrate the effectiveness of the proposed scheme in comparison with our previous MTIE coding scheme.
为了进一步减少候选编码向量的搜索次数，本文提出了一种改进的多重三角不等式消除算法(MMTIE)。MMTIE采用与MTIE方案相同的原始搜索空间，采用初始索引码分配(initial Index Code Assignment, IICA)选择的初始最匹配码向量，并融合候选码向量群(Candidate codevector Group, CCG)方案的交集规则，进一步缩小搜索空间，在编码阶段通过表查找操作找到最匹配的候选码向量。由于IICA方法通过利用相邻块的相关性来选择初始最匹配的编码向量，并且从离线阶段获得预定义的CCG空间，因此MMTIE算法以额外的内存为代价获得了比原始MTIE更好的编码效率。此外，该算法具有与全搜索方法相同的编码质量。实验结果表明，该方案与之前的MTIE编码方案相比是有效的。
{"title":"Fast-searching algorithm for vector quantization using modified multiple triangular inequality","authors":"C. H. Wu, Hsung-Pin Chang, Y. C. Liu, G. H. Lee, L. Chi","doi":"10.1109/TAAI.2016.7880112","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880112","url":null,"abstract":"This paper proposes a Modified Multiple Triangular Inequality Elimination (MMTIE) to further reduce the search number of candidate codevectors. The MMTIE adopts the same original search space as the MTIE scheme with the initial best-matched codevector selected by the Initial Index Code Assignment (IICA), and integrates the intersection rule of the Candidate Codevectors Group (CCG) scheme to further reduce the search space and find the best-matched candidate by table look-up operation in the coding stage. Since the IICA approach selects an initial best-matched codevector by exploiting the correlations of the neighboring blocks and the predefined CCG space is obtained from the off-line stage, the MMTIE algorithm achieves better coding efficiency than the original MTIE at a cost of extra memory. In addition, the proposed algorithm provides the same coding quality as the full search method. Experimental results demonstrate the effectiveness of the proposed scheme in comparison with our previous MTIE coding scheme.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134018218","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880168
Yu-Teng Chang, T. Chiang
This paper addresses the multiobjective permutation flow shop scheduling problem, where makespan and total flow time are to be minimized simultaneously. We solve the problem by an extended version of the multiobjective evolutionary algorithm based on decomposition (MOEA/D). We investigate the effects of scalarization functions and the replacement mechanism. We also incorporate local search into MOEA/D and investigate design issues including individuals to do local search and resource allocation. Experiments are conducted on 90 public problem instances with different scale, and research findings are reported. Comparing with the state of the art, our algorithm shows competitive performance on small-scale instances and superior performance on medium- and large-scale instances.
{"title":"Multiobjective permutation flow shop scheduling using MOEA/D with local search","authors":"Yu-Teng Chang, T. Chiang","doi":"10.1109/TAAI.2016.7880168","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880168","url":null,"abstract":"This paper addresses the multiobjective permutation flow shop scheduling problem, where makespan and total flow time are to be minimized simultaneously. We solve the problem by an extended version of the multiobjective evolutionary algorithm based on decomposition (MOEA/D). We investigate the effects of scalarization functions and the replacement mechanism. We also incorporate local search into MOEA/D and investigate design issues including individuals to do local search and resource allocation. Experiments are conducted on 90 public problem instances with different scale, and research findings are reported. Comparing with the state of the art, our algorithm shows competitive performance on small-scale instances and superior performance on medium- and large-scale instances.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133015065","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880184
Yi-Cheng Chen, Ju-Ying Cheng, Hui-Huang Hsu
Recently, opinion leader discovery has drawn much attention due to its widespread applicability. By identifying the opinion leader, companies or governments can manipulate the selling or guiding public opinion, respectively. However, mining opinion leader is a challenge task because of the complexity of processing social graph and analyzing leadership quality. In this study, a novel method, TCOL-Miner, is proposed to efficiently find the opinion leaders from a huge social network. We integrate the clustering and semantic analysis methods with some pruning strategies to tackle the influence overlapping issue and the potential leadership of individuals. The experimental results show that the proposed TCOL-Miner can effectively discover the influenced opinion leaders in different real social networks with efficiency.
{"title":"A cluster-based opinion leader discovery in social network","authors":"Yi-Cheng Chen, Ju-Ying Cheng, Hui-Huang Hsu","doi":"10.1109/TAAI.2016.7880184","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880184","url":null,"abstract":"Recently, opinion leader discovery has drawn much attention due to its widespread applicability. By identifying the opinion leader, companies or governments can manipulate the selling or guiding public opinion, respectively. However, mining opinion leader is a challenge task because of the complexity of processing social graph and analyzing leadership quality. In this study, a novel method, TCOL-Miner, is proposed to efficiently find the opinion leaders from a huge social network. We integrate the clustering and semantic analysis methods with some pruning strategies to tackle the influence overlapping issue and the potential leadership of individuals. The experimental results show that the proposed TCOL-Miner can effectively discover the influenced opinion leaders in different real social networks with efficiency.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":" 674","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113946917","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880175
B. Chang, H. Tsai, Yi-Sheng Chang, Chien-Feng Huang
The integration of Hive, Impala and Spark SQL platforms has achieved to perform rapid data retrieval using SQL query in big data environment. This paper is to design the optimized platform selection for highly improving the response of data retrieval. It can automatically choose the best-perform platform to best perform SQL commands. In addition, the distributed memory storage systems using Memcached and the distributed file system Hadoop HDFS have implemented the caching so that the fastest data retrieval has done once the repeated SQL command has applied.
{"title":"Multiple big data processing platforms","authors":"B. Chang, H. Tsai, Yi-Sheng Chang, Chien-Feng Huang","doi":"10.1109/TAAI.2016.7880175","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880175","url":null,"abstract":"The integration of Hive, Impala and Spark SQL platforms has achieved to perform rapid data retrieval using SQL query in big data environment. This paper is to design the optimized platform selection for highly improving the response of data retrieval. It can automatically choose the best-perform platform to best perform SQL commands. In addition, the distributed memory storage systems using Memcached and the distributed file system Hadoop HDFS have implemented the caching so that the fastest data retrieval has done once the repeated SQL command has applied.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129737606","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}
One of the most important factors for enriching student life is the promotion of good relationships among the students. Furthermore, good relationships among students lead to effective learning. Accordingly, teachers need to help students form good friendships through classwork. Cooperative learning, student and a task for the group to accomplish, is one of the most common methods of active learning and generate friendships. We friendship networks among university students. We then propose methods for composing groups to generate friendships. We apply our proposed methods to actual cooperative learning activities and observe their effects. An analysis of the resulting friendship networks show that students grouped by the proposed methods made more friends than students grouped by a conventional method. Questionnaire results show that satisfaction with the lecture of the students grouped by the proposed methods were higher than that of the students grouped by the conventional method.
{"title":"Effects of grouping on friendships and group composition methods using social network analysis","authors":"Atsuko Mutoh, Kouta Aratani, Miwa Sakata, Nobuhiro Inuzuka","doi":"10.1109/TAAI.2016.7880167","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880167","url":null,"abstract":"One of the most important factors for enriching student life is the promotion of good relationships among the students. Furthermore, good relationships among students lead to effective learning. Accordingly, teachers need to help students form good friendships through classwork. Cooperative learning, student and a task for the group to accomplish, is one of the most common methods of active learning and generate friendships. We friendship networks among university students. We then propose methods for composing groups to generate friendships. We apply our proposed methods to actual cooperative learning activities and observe their effects. An analysis of the resulting friendship networks show that students grouped by the proposed methods made more friends than students grouped by a conventional method. Questionnaire results show that satisfaction with the lecture of the students grouped by the proposed methods were higher than that of the students grouped by the conventional method.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129514871","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880157
Chih-Yu Wang, Ming-Yen Lin
In response to globalization, International Financial Reporting Standards (IFRS) has become the norm of the global capital markets. Companies preparing financial statements using IFRS may make the financial situation fully disclosed. Nevertheless, an overestimated accrual expense of a balance sheet may not only underestimate the earnings data, but also increase the cash outflows of the statement of cash flows. When the accrual expense is underestimated, corporate earnings will inflate earnings statistics. In addition, the problem of funds shortage may occur upon actual payment because the cash outflows of the statement of cash flows is underestimated. In this paper, we adopt the prediction mechanism in data mining to predict the unused vacation time of employees, which in turn becomes a part of the accrual expenses in the balance sheet. The prediction target is the bonus of unused annual leave in terms of unused hours so that the estimated amount of fees payable accuracy in the balance sheet can be improved. Both decision-tree models and regression analysis are used. Comprehensive experiments show that the decision-tree method outperforms the regression analysis method, with MAE of −23.1 and RMSE of 43.1.
{"title":"Prediction of accrual expenses in balance sheet using decision trees and linear regression","authors":"Chih-Yu Wang, Ming-Yen Lin","doi":"10.1109/TAAI.2016.7880157","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880157","url":null,"abstract":"In response to globalization, International Financial Reporting Standards (IFRS) has become the norm of the global capital markets. Companies preparing financial statements using IFRS may make the financial situation fully disclosed. Nevertheless, an overestimated accrual expense of a balance sheet may not only underestimate the earnings data, but also increase the cash outflows of the statement of cash flows. When the accrual expense is underestimated, corporate earnings will inflate earnings statistics. In addition, the problem of funds shortage may occur upon actual payment because the cash outflows of the statement of cash flows is underestimated. In this paper, we adopt the prediction mechanism in data mining to predict the unused vacation time of employees, which in turn becomes a part of the accrual expenses in the balance sheet. The prediction target is the bonus of unused annual leave in terms of unused hours so that the estimated amount of fees payable accuracy in the balance sheet can be improved. Both decision-tree models and regression analysis are used. Comprehensive experiments show that the decision-tree method outperforms the regression analysis method, with MAE of −23.1 and RMSE of 43.1.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133660183","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 : 2016-11-01DOI: 10.1109/TAAI.2016.7880163
LiJung Chi, Chi-Hsuan Huang, Kun-Ta Chuang
We in this paper introduce a novel data visualization package, called the ADD framework, to support responsive and adaptive data-driven visualization. Currently, interactive data visualization, which is generally achieved by Javascript-based libraries such as D3.js, cannot be easily manipulated as the responsive way like the RWD principle in the CSS design. Visualization of abundant information becomes challenging while switching between the desktop view or the mobile view. To ease of code maintenance and to get rid of coding complication for diversified screen resolution, we incorporate advantages from React and D3.js. The main contribution of the ADD framework, released as an open-source library, is to facilitate the development of data manipulation and visualization in the responsive way, pursuing better user mobile experience. In addition, we also present the future direction of developing websocket-based streaming data loader for Javascript, to enable the seamless update of JSON data in the web page without user re-click. Currently, the ADD framework is open source and the streaming data loader will be released soon as the same way.
{"title":"Mobile-friendly and streaming web-based data visualization","authors":"LiJung Chi, Chi-Hsuan Huang, Kun-Ta Chuang","doi":"10.1109/TAAI.2016.7880163","DOIUrl":"https://doi.org/10.1109/TAAI.2016.7880163","url":null,"abstract":"We in this paper introduce a novel data visualization package, called the ADD framework, to support responsive and adaptive data-driven visualization. Currently, interactive data visualization, which is generally achieved by Javascript-based libraries such as D3.js, cannot be easily manipulated as the responsive way like the RWD principle in the CSS design. Visualization of abundant information becomes challenging while switching between the desktop view or the mobile view. To ease of code maintenance and to get rid of coding complication for diversified screen resolution, we incorporate advantages from React and D3.js. The main contribution of the ADD framework, released as an open-source library, is to facilitate the development of data manipulation and visualization in the responsive way, pursuing better user mobile experience. In addition, we also present the future direction of developing websocket-based streaming data loader for Javascript, to enable the seamless update of JSON data in the web page without user re-click. Currently, the ADD framework is open source and the streaming data loader will be released soon as the same way.","PeriodicalId":159858,"journal":{"name":"2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124209655","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：