Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680873
Qinru Fan, Donghong Wang
So far, the focus of most research on speech recognition was on speech recognition of mandarin Chinese or English. Since the feature of the research is that the same word pronounces the same, influence on speech recognition of the research concerns primarily with environmental factors. Ningbo dialect is very different than mandarin Chinese and English, for Ningbo dialect possesses some regional variations in pronunciation and intonation even in the area of Ningbo, thus pronunciation changes, or intonation changes is a more important factor than other factors. Therefore, finding a modeling way to suit pronunciation changes, or intonation changes is a vital prerequisite for speech recognition of Ningbo dialect. This paper is designed to probe into the speech recognition of Ningbo dialect, focusing on Fenghua county, Cixi county, Yinzhou district, and central Ningbo. We study the modeling method of Ningbo dialect from the angle of pronunciation changes and intonation changes and running time of recognition. In the research, 64 speech samples of 10 digits (1–10) used in the above-mentioned four regions were created, by using Mel frequency cepstrum coefficient (MFCC) to achieve feature of each digital speech. Then depending on the variations of the pronunciation and intonation of the digits, we do a lot of experiments, 20 models of training samples of digits (1–10) are constructed. A simplified Bayes decision rule is used for classification of Ningbo dialect digits. Experiment data suggested that the rate of speech recognition surpassed 75%. The recognition rate is superior to that recognition rate (52.5%) of a general modeling method that modeling of training samples do not consider factor of regional variations in pronunciation and intonation. We have a rise in robustness of speech recognition of Ningbo dialect. The modeling and recognition method used in the paper is easy to handle and get promoted.
{"title":"A statistical speech recognition of Ningbo dialect monosyllables","authors":"Qinru Fan, Donghong Wang","doi":"10.1109/ISKE.2010.5680873","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680873","url":null,"abstract":"So far, the focus of most research on speech recognition was on speech recognition of mandarin Chinese or English. Since the feature of the research is that the same word pronounces the same, influence on speech recognition of the research concerns primarily with environmental factors. Ningbo dialect is very different than mandarin Chinese and English, for Ningbo dialect possesses some regional variations in pronunciation and intonation even in the area of Ningbo, thus pronunciation changes, or intonation changes is a more important factor than other factors. Therefore, finding a modeling way to suit pronunciation changes, or intonation changes is a vital prerequisite for speech recognition of Ningbo dialect. This paper is designed to probe into the speech recognition of Ningbo dialect, focusing on Fenghua county, Cixi county, Yinzhou district, and central Ningbo. We study the modeling method of Ningbo dialect from the angle of pronunciation changes and intonation changes and running time of recognition. In the research, 64 speech samples of 10 digits (1–10) used in the above-mentioned four regions were created, by using Mel frequency cepstrum coefficient (MFCC) to achieve feature of each digital speech. Then depending on the variations of the pronunciation and intonation of the digits, we do a lot of experiments, 20 models of training samples of digits (1–10) are constructed. A simplified Bayes decision rule is used for classification of Ningbo dialect digits. Experiment data suggested that the rate of speech recognition surpassed 75%. The recognition rate is superior to that recognition rate (52.5%) of a general modeling method that modeling of training samples do not consider factor of regional variations in pronunciation and intonation. We have a rise in robustness of speech recognition of Ningbo dialect. The modeling and recognition method used in the paper is easy to handle and get promoted.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"10 1","pages":"266-269"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83448930","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680867
Yi Li, Xuesong Yin
When there is no sufficient labeled instances, supervised dimensionality reduction methods tend to perform poorly due to overfitting. In such cases, unlabeled instances are used to improve the performance. In this paper, we propose a dimensionality reduction method called semi-supervised TransductIve Discriminant Analysis (TIDA) which preserves the global and geometrical structure of the unlabeled instances in addition to separating labeled instances in different classes from each other. The proposed algorithm is efficient and has a closed form solution. Experiments on a broad range of data sets show that TIDA is superior to many relevant dimensionality reduction methods.
{"title":"Semi-supervised Transductive Discriminant Analysis","authors":"Yi Li, Xuesong Yin","doi":"10.1109/ISKE.2010.5680867","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680867","url":null,"abstract":"When there is no sufficient labeled instances, supervised dimensionality reduction methods tend to perform poorly due to overfitting. In such cases, unlabeled instances are used to improve the performance. In this paper, we propose a dimensionality reduction method called semi-supervised TransductIve Discriminant Analysis (TIDA) which preserves the global and geometrical structure of the unlabeled instances in addition to separating labeled instances in different classes from each other. The proposed algorithm is efficient and has a closed form solution. Experiments on a broad range of data sets show that TIDA is superior to many relevant dimensionality reduction methods.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"1 1","pages":"291-295"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83939536","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680816
Rangding Wang, Yiqun Xiong
A novel algorithm of audio aggregation watermarking was proposed in this paper for copyright protection. The algorithm not only protects copyright of a single audio in audio aggregation but also protects copyright of the whole audio aggregation. The experimental results showed the watermark of aggregate audio can resist to some attacks, for example, deleting audio, substituting audio and adding audio; at the same time, watermark of every single audio is robust to some attacks such as low-filtering, resampling, requantization, noise addition and mp3 compression. The proposed algorithm has good imperceptibility and strong robustness.
{"title":"A novel audio aggregation watermarking for copyright protection","authors":"Rangding Wang, Yiqun Xiong","doi":"10.1109/ISKE.2010.5680816","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680816","url":null,"abstract":"A novel algorithm of audio aggregation watermarking was proposed in this paper for copyright protection. The algorithm not only protects copyright of a single audio in audio aggregation but also protects copyright of the whole audio aggregation. The experimental results showed the watermark of aggregate audio can resist to some attacks, for example, deleting audio, substituting audio and adding audio; at the same time, watermark of every single audio is robust to some attacks such as low-filtering, resampling, requantization, noise addition and mp3 compression. The proposed algorithm has good imperceptibility and strong robustness.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"123 1","pages":"166-172"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85051078","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680822
Dongyun Wang, Kai Wang
The automatic weighing system can automatically and immediately calculate and analyze the weight of material in bucket of a loader. To compensate affection caused by velocity of the left arm reasonably is very important for improve the accuracy of the system. The design of the hardware and the realization of experiment of dynamic weighing system will be discussed in this paper. First of all, a realization scheme is set up, and then designed a hardware platform to realize it. At last, by a large amount of experiments, the affection caused by velocity of the left arm is analyzed and the method of the velocity-compensation is discussed and applied in the system. Finally, the system is applied in the practice. The practical application results show that the accuracy, stability and reliability of the presenting system are desired and the error is with in 1%.
{"title":"The method of the velocity compensation in dynamic weighing system","authors":"Dongyun Wang, Kai Wang","doi":"10.1109/ISKE.2010.5680822","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680822","url":null,"abstract":"The automatic weighing system can automatically and immediately calculate and analyze the weight of material in bucket of a loader. To compensate affection caused by velocity of the left arm reasonably is very important for improve the accuracy of the system. The design of the hardware and the realization of experiment of dynamic weighing system will be discussed in this paper. First of all, a realization scheme is set up, and then designed a hardware platform to realize it. At last, by a large amount of experiments, the affection caused by velocity of the left arm is analyzed and the method of the velocity-compensation is discussed and applied in the system. Finally, the system is applied in the practice. The practical application results show that the accuracy, stability and reliability of the presenting system are desired and the error is with in 1%.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"14 1","pages":"488-491"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81478794","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680855
Shusong Li, Shiyong Zhang
We present and analyze a model of Opinion Dynamics and Bounded Confidence on the Flocking movement world. There are two systems for interaction. The theorem of ‘Flocking’ limits the agent's movement around the world and ‘Bounded Confidence’ chooses the agents to exchange the opinion. Every time step, agent i looks for the agents in its eyeshot and adjusts their opinion based on the algorithm of Bounded Confidence. When the exchange ends, every agent moves itself in a specifically direction according to Flocking theorem. We simulated the opinion formation process using the proposed model, results show the system is more realistic than the classic BC model.
{"title":"The Opinion Dynamics and Bounded Confidence model on Flocking movement world","authors":"Shusong Li, Shiyong Zhang","doi":"10.1109/ISKE.2010.5680855","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680855","url":null,"abstract":"We present and analyze a model of Opinion Dynamics and Bounded Confidence on the Flocking movement world. There are two systems for interaction. The theorem of ‘Flocking’ limits the agent's movement around the world and ‘Bounded Confidence’ chooses the agents to exchange the opinion. Every time step, agent i looks for the agents in its eyeshot and adjusts their opinion based on the algorithm of Bounded Confidence. When the exchange ends, every agent moves itself in a specifically direction according to Flocking theorem. We simulated the opinion formation process using the proposed model, results show the system is more realistic than the classic BC model.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"1 1","pages":"355-359"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72687716","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680879
G. Fang, Cheng-Sheng Tu, Jiang Xiong, Zi-Quan Wang
This paper focuses on character of present frequent neighboring class set mining algorithms which is suitable for mining short frequent neighboring class set, and introduces a top-down algorithm in frequent neighboring class set mining. This algorithm is suitable for mining long frequent neighboring class set in large spatial data according to top-down strategy, and it creates digital database of neighboring class set via neighboring class bit sequence. The algorithm generates candidate frequent neighboring class set via top-down search strategy, namely, it gains k-neighboring class set as candidate frequent items by computing k-subset of (k+1)-non frequent neighboring class set. The mining algorithm computes support of candidate frequent neighboring class set by digit logical operation. The algorithm improves mining efficiency through these two methods. The result of experiment indicates that the algorithm is faster and more efficient than present algorithms when mining long frequent neighboring class set in large spatial data.
{"title":"The application of a top-down algorithm in neighboring class set mining","authors":"G. Fang, Cheng-Sheng Tu, Jiang Xiong, Zi-Quan Wang","doi":"10.1109/ISKE.2010.5680879","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680879","url":null,"abstract":"This paper focuses on character of present frequent neighboring class set mining algorithms which is suitable for mining short frequent neighboring class set, and introduces a top-down algorithm in frequent neighboring class set mining. This algorithm is suitable for mining long frequent neighboring class set in large spatial data according to top-down strategy, and it creates digital database of neighboring class set via neighboring class bit sequence. The algorithm generates candidate frequent neighboring class set via top-down search strategy, namely, it gains k-neighboring class set as candidate frequent items by computing k-subset of (k+1)-non frequent neighboring class set. The mining algorithm computes support of candidate frequent neighboring class set by digit logical operation. The algorithm improves mining efficiency through these two methods. The result of experiment indicates that the algorithm is faster and more efficient than present algorithms when mining long frequent neighboring class set in large spatial data.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"149 1","pages":"234-237"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72875880","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680865
Martin H. Jose Antonio, J. Montero, J. Yáñez, D. Gómez
In this paper we present a divisive hierarchical method for the analysis and segmentation of visual images. The proposed method is based on the use of the k-means method embedded in a recursive algorithm to obtain a clustering at each node of the hierarchy. The recursive algorithm determines automatically at each node a good estimate of the parameter k (the number of clusters in the k-means algorithm) based on relevant statistics. We have made several experiments with different kinds of images obtaining encouraging results showing that the method can be used effectively not only for automatic image segmentation but also for image analysis and, even more, data mining.
{"title":"A divisive hierarchical k-means based algorithm for image segmentation","authors":"Martin H. Jose Antonio, J. Montero, J. Yáñez, D. Gómez","doi":"10.1109/ISKE.2010.5680865","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680865","url":null,"abstract":"In this paper we present a divisive hierarchical method for the analysis and segmentation of visual images. The proposed method is based on the use of the k-means method embedded in a recursive algorithm to obtain a clustering at each node of the hierarchy. The recursive algorithm determines automatically at each node a good estimate of the parameter k (the number of clusters in the k-means algorithm) based on relevant statistics. We have made several experiments with different kinds of images obtaining encouraging results showing that the method can be used effectively not only for automatic image segmentation but also for image analysis and, even more, data mining.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"63 1","pages":"300-304"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78333054","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680870
Hsu-Kun Wu, J. Hsieh, Yih-Lon Lin
Nonparametric Wilcoxon regressors, which generalize the rank-based Wilcoxon approach for linear parametric regression problems to nonparametric neural networks, were recently developed aiming at improving robustness against outliers in nonlinear regression problems. It is natural to investigate if the Wilcoxon approach can also be generalized to nonparametric classification problems. Motivated by support vector classifiers (SVCs), we propose in this paper a novel family of classifiers, called kernel-based Wilcoxon classifiers (KWCs), for nonlinear classification problems. KWC has the same functional form as that of SVC, but with a totally different objective function. Simple weight updating rules based on gradient projection will be provided. Simulation results show that performances of KWCs and SVCs are about the same.
{"title":"Study on kernel-based Wilcoxon classifiers","authors":"Hsu-Kun Wu, J. Hsieh, Yih-Lon Lin","doi":"10.1109/ISKE.2010.5680870","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680870","url":null,"abstract":"Nonparametric Wilcoxon regressors, which generalize the rank-based Wilcoxon approach for linear parametric regression problems to nonparametric neural networks, were recently developed aiming at improving robustness against outliers in nonlinear regression problems. It is natural to investigate if the Wilcoxon approach can also be generalized to nonparametric classification problems. Motivated by support vector classifiers (SVCs), we propose in this paper a novel family of classifiers, called kernel-based Wilcoxon classifiers (KWCs), for nonlinear classification problems. KWC has the same functional form as that of SVC, but with a totally different objective function. Simple weight updating rules based on gradient projection will be provided. Simulation results show that performances of KWCs and SVCs are about the same.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"127 1","pages":"249-253"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75114178","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680789
Vahid Behbood, Jie Lu, Guangquan Zhang
Creating an applicable and precise failure prediction system is highly desirable for decision makers and regulators in the finance industry. This study develops a new Failure Prediction (FP) approach which effectively integrates a fuzzy logic-based adaptive inference system with the learning ability of a neural network to generate knowledge in the form of a fuzzy rule base. This FP approach uses a preprocessing phase to deal with the imbalanced data-sets problem and develops a new Fuzzy Neural Network (FNN) including an adaptive inference system in the learning algorithm along with its network structure and rule generation algorithm as a means to reduce prediction error in the FP approach.
{"title":"Adaptive inference-based learning and rule generation algorithms in Fuzzy Neural Network for failure prediction","authors":"Vahid Behbood, Jie Lu, Guangquan Zhang","doi":"10.1109/ISKE.2010.5680789","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680789","url":null,"abstract":"Creating an applicable and precise failure prediction system is highly desirable for decision makers and regulators in the finance industry. This study develops a new Failure Prediction (FP) approach which effectively integrates a fuzzy logic-based adaptive inference system with the learning ability of a neural network to generate knowledge in the form of a fuzzy rule base. This FP approach uses a preprocessing phase to deal with the imbalanced data-sets problem and develops a new Fuzzy Neural Network (FNN) including an adaptive inference system in the learning algorithm along with its network structure and rule generation algorithm as a means to reduce prediction error in the FP approach.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"196 1","pages":"33-38"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74496762","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 : 2010-11-01DOI: 10.1109/ISKE.2010.5680793
Yun Chen, Ping Liu, Li Yu
The rapid development of automobile industry in China promotes the stable growth of the automotive aftermarket. For optimizing supply chain operations and reducing costs, it is critical for a company to forecast the demands for auto spare parts in the future. This paper proposes an improved Regression-Bayesian-BBNN (RBBPNN) based model to realize the demands forecasting. Compared with a classic ARMA model, the proposed RBBPNN model has higher accuracy and better robustness. These advantages are illustrated through the case study with the real sales data of a 4s shop in Shanghai.
{"title":"Aftermarket demands forecasting with a Regression-Bayesian-BPNN model","authors":"Yun Chen, Ping Liu, Li Yu","doi":"10.1109/ISKE.2010.5680793","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680793","url":null,"abstract":"The rapid development of automobile industry in China promotes the stable growth of the automotive aftermarket. For optimizing supply chain operations and reducing costs, it is critical for a company to forecast the demands for auto spare parts in the future. This paper proposes an improved Regression-Bayesian-BBNN (RBBPNN) based model to realize the demands forecasting. Compared with a classic ARMA model, the proposed RBBPNN model has higher accuracy and better robustness. These advantages are illustrated through the case study with the real sales data of a 4s shop in Shanghai.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"5 1","pages":"52-55"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78794087","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：