Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862063
Junjie Bai, Jun Peng, Jinliang Shi, Dedong Tang, Ying Wu, Jianqing Li, Kan Luo
As hot topics in current research, music emotion recognition (MER) have been addressed by different disciplines such as physiology, psychology, musicology, cognitive science, etc. In this paper, music emotions was modeled as continuous variables composed of valence and arousal values (VA values) based on Valence-Arousal model, and MER is formulated as a regression problem. 548 dimensions of music features were extracted and selected. The support vector regression, random forest regression and regression neural networks were adopted to recognize music emotion. Experimental results show that these regression algorithms achieved good regression effect. The optimal R2 statistics of values of VA values are 29.3% and 62.5%, which are achieved respectively by RFR and SVR in Relief feature space.
{"title":"Dimensional music emotion recognition by valence-arousal regression","authors":"Junjie Bai, Jun Peng, Jinliang Shi, Dedong Tang, Ying Wu, Jianqing Li, Kan Luo","doi":"10.1109/ICCI-CC.2016.7862063","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862063","url":null,"abstract":"As hot topics in current research, music emotion recognition (MER) have been addressed by different disciplines such as physiology, psychology, musicology, cognitive science, etc. In this paper, music emotions was modeled as continuous variables composed of valence and arousal values (VA values) based on Valence-Arousal model, and MER is formulated as a regression problem. 548 dimensions of music features were extracted and selected. The support vector regression, random forest regression and regression neural networks were adopted to recognize music emotion. Experimental results show that these regression algorithms achieved good regression effect. The optimal R2 statistics of values of VA values are 29.3% and 62.5%, which are achieved respectively by RFR and SVR in Relief feature space.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127211684","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862015
Omar A. Zatarain, Yingxu Wang
Concept elicitation is a fundamental methodology for knowledge extraction and representation in cognitive robot learning. Traditional machine learning technologies deal with object identification, cluster classification, functional regression, and behavior acquisition. This paper presents a supervised machine knowledge learning methodology for concept elicitation from sample dictionaries in natural languages. Formal concepts are autonomously generated based on collective intention of attributes and collective extension of objects elicited from informal definitions in dictionaries. A system of formal concept generation for a cognitive robot is implemented by the Algorithm of Machine Concept Elicitation (AMCE) in MATLAB. Experiments on machine learning for creating a set of twenty formal concepts reveal that the cognitive robot is able to learn synergized concepts in human knowledge in order to build its own cognitive knowledge base. The results of machine-generated concepts demonstrate that the AMCE algorithm can over perform human knowledge expressions in dictionaries in terms of relevance, accuracy, quantitativeness, and cohesiveness.
{"title":"Experiments on the supervised learning algorithm for formal concept elicitation by cognitive robots","authors":"Omar A. Zatarain, Yingxu Wang","doi":"10.1109/ICCI-CC.2016.7862015","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862015","url":null,"abstract":"Concept elicitation is a fundamental methodology for knowledge extraction and representation in cognitive robot learning. Traditional machine learning technologies deal with object identification, cluster classification, functional regression, and behavior acquisition. This paper presents a supervised machine knowledge learning methodology for concept elicitation from sample dictionaries in natural languages. Formal concepts are autonomously generated based on collective intention of attributes and collective extension of objects elicited from informal definitions in dictionaries. A system of formal concept generation for a cognitive robot is implemented by the Algorithm of Machine Concept Elicitation (AMCE) in MATLAB. Experiments on machine learning for creating a set of twenty formal concepts reveal that the cognitive robot is able to learn synergized concepts in human knowledge in order to build its own cognitive knowledge base. The results of machine-generated concepts demonstrate that the AMCE algorithm can over perform human knowledge expressions in dictionaries in terms of relevance, accuracy, quantitativeness, and cohesiveness.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121667551","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862050
G. Luo, Chongyuan Yin
The satisfiability degree is a new means of describing the extent to which a proposition is satisfied, and employs deterministic logic rather than probabilistic logic or fuzzy logic. The independent formula-pair and the incompatible formula-pair of the propositions are discussed in this paper. Some properties of the satisfiability degree are given with a conditional satisfiability degree. Deductive reasoning methods based on the satisfiability degree are established. The formula reasoning and semantic checking are given by the conditional satisfiability degree. Some potential applications for the satisfiability degree are given.
{"title":"Deductive reasoning and computing based on propositional logic","authors":"G. Luo, Chongyuan Yin","doi":"10.1109/ICCI-CC.2016.7862050","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862050","url":null,"abstract":"The satisfiability degree is a new means of describing the extent to which a proposition is satisfied, and employs deterministic logic rather than probabilistic logic or fuzzy logic. The independent formula-pair and the incompatible formula-pair of the propositions are discussed in this paper. Some properties of the satisfiability degree are given with a conditional satisfiability degree. Deductive reasoning methods based on the satisfiability degree are established. The formula reasoning and semantic checking are given by the conditional satisfiability degree. Some potential applications for the satisfiability degree are given.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122151568","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862064
Hiroaki Koma, Taku Harada, Akira Yoshizawa, H. Iwasaki
Eye movements are well known to express cognitive distraction. Detecting cognitive distraction can help to prevent work-related accidents; thus, it is very useful to detect cognitive distraction using eye movements. Eye movements can be classified into various types. In this paper, we apply an identification-based machine learning algorithm considering eye movement types. We apply Random Forest as the machine learning algorithm. We show the effectiveness of considering eye movement types when applying Random Forest to detect cognitive distraction.
{"title":"Considering eye movement type when applying random forest to detect cognitive distraction","authors":"Hiroaki Koma, Taku Harada, Akira Yoshizawa, H. Iwasaki","doi":"10.1109/ICCI-CC.2016.7862064","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862064","url":null,"abstract":"Eye movements are well known to express cognitive distraction. Detecting cognitive distraction can help to prevent work-related accidents; thus, it is very useful to detect cognitive distraction using eye movements. Eye movements can be classified into various types. In this paper, we apply an identification-based machine learning algorithm considering eye movement types. We apply Random Forest as the machine learning algorithm. We show the effectiveness of considering eye movement types when applying Random Forest to detect cognitive distraction.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130352419","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862078
Yoshihiro Hayakawa, Takanori Oonuma, Hideyuki Kobayashi, Akiko Takahashi, Shinji Chiba, N. M. Fujiki
In deep neural networks, which have been gaining attention in recent years, the features of input images are expressed in a middle layer. Using the information on this feature layer, high performance can be demonstrated in the image recognition field. In the present study, we achieve image recognition, without using convolutional neural networks or sparse coding, through an image feature extraction function obtained when identity mapping learning is applied to sandglass-style feed-forward neural networks. In sports form analysis, for example, a state trajectory is mapped in a low-dimensional feature space based on a consecutive series of actions. Here, we discuss ideas related to image analysis by applying the above method.
{"title":"Feature extraction of video using deep neural network","authors":"Yoshihiro Hayakawa, Takanori Oonuma, Hideyuki Kobayashi, Akiko Takahashi, Shinji Chiba, N. M. Fujiki","doi":"10.1109/ICCI-CC.2016.7862078","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862078","url":null,"abstract":"In deep neural networks, which have been gaining attention in recent years, the features of input images are expressed in a middle layer. Using the information on this feature layer, high performance can be demonstrated in the image recognition field. In the present study, we achieve image recognition, without using convolutional neural networks or sparse coding, through an image feature extraction function obtained when identity mapping learning is applied to sandglass-style feed-forward neural networks. In sports form analysis, for example, a state trajectory is mapped in a low-dimensional feature space based on a consecutive series of actions. Here, we discuss ideas related to image analysis by applying the above method.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114959472","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 : 2016-08-01DOI: 10.4018/IJSSCI.2017010102
G. Baciu, Yungzhe Wang, Chenhui Li
Hardware virtualization has enabled large scale computational service delivery models with significant cost leverage and has improved resource utilization of cloud computing platforms. This has completely changed the landscape of computing in the last decade. It has enabled very large-scale data analytics through distributed, high performance computing. However, due to the infrastructure complexity, end-users and administrators of cloud platforms can rarely obtain a complete picture of the state of cloud computing systems and data centers. Recent monitoring tools enable users to obtain large amounts of data with respect to many utilization parameters of cloud platforms. However, they often fall short of maximizing the overall insight into the resource utilization dynamics of cloud platforms. Furthermore, existing tools make it difficult to observe large scale patterns making it difficult to learn from the past behavior of cloud system dynamics. New operating platforms for cloud management and service provisioning allow live migration and dynamic resource re-allocation at multiple levels of the hardware virtualization layers. Hence, it has become necessary to provide cognitive visualizing tools for monitoring the activities in an active cloud environment. In this work, we describe a perceptual-based interactive visualization platform that gives users and administrators a cognitive view of cloud computing system dynamics. We define machine states and aggregate states at multiple levels of detail to construct a multiview presentation of the resource utilization according to the scalability and the elasticity features of a cloud computing system.
{"title":"Cognitive visual analytics of multi-dimensional cloud system monitoring data","authors":"G. Baciu, Yungzhe Wang, Chenhui Li","doi":"10.4018/IJSSCI.2017010102","DOIUrl":"https://doi.org/10.4018/IJSSCI.2017010102","url":null,"abstract":"Hardware virtualization has enabled large scale computational service delivery models with significant cost leverage and has improved resource utilization of cloud computing platforms. This has completely changed the landscape of computing in the last decade. It has enabled very large-scale data analytics through distributed, high performance computing. However, due to the infrastructure complexity, end-users and administrators of cloud platforms can rarely obtain a complete picture of the state of cloud computing systems and data centers. Recent monitoring tools enable users to obtain large amounts of data with respect to many utilization parameters of cloud platforms. However, they often fall short of maximizing the overall insight into the resource utilization dynamics of cloud platforms. Furthermore, existing tools make it difficult to observe large scale patterns making it difficult to learn from the past behavior of cloud system dynamics. New operating platforms for cloud management and service provisioning allow live migration and dynamic resource re-allocation at multiple levels of the hardware virtualization layers. Hence, it has become necessary to provide cognitive visualizing tools for monitoring the activities in an active cloud environment. In this work, we describe a perceptual-based interactive visualization platform that gives users and administrators a cognitive view of cloud computing system dynamics. We define machine states and aggregate states at multiple levels of detail to construct a multiview presentation of the resource utilization according to the scalability and the elasticity features of a cloud computing system.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115156228","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862048
Kaizhong Zhang
Similarity metric and distance metric are widely used in many research areas and applications. In this paper, for a given similarity metric, we will introduce a family of distance metrics of Minkowski type. We will then show general solutions to construct normalized similarity metric and normalized distance metric from a similarity metric and a distance metric. Applying the general solutions to a given non-negative similarity metric and its induced family of distance metrics, we derive general normalized similarity metrics and normalized distance metrics. Finally we briefly discuss some of the applications of our general similarity and distance metric formulations.
{"title":"Similarity metric induced metrics with application in machine learning and bioinformatics","authors":"Kaizhong Zhang","doi":"10.1109/ICCI-CC.2016.7862048","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862048","url":null,"abstract":"Similarity metric and distance metric are widely used in many research areas and applications. In this paper, for a given similarity metric, we will introduce a family of distance metrics of Minkowski type. We will then show general solutions to construct normalized similarity metric and normalized distance metric from a similarity metric and a distance metric. Applying the general solutions to a given non-negative similarity metric and its induced family of distance metrics, we derive general normalized similarity metrics and normalized distance metrics. Finally we briefly discuss some of the applications of our general similarity and distance metric formulations.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130103922","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862084
Julia Taylor Rayz, V. Raskin
The meat of the paper is a small innovation in Ontological Semantic Technology describing how to calculate weights in text meaning representations. It is reset here as a component of a complex and apparently unprecedented global logic of natural language, a topic that was abortively entertained in the 1960–70s and since then mostly abandoned.
{"title":"Logic of natural language: Through the eyes of ontological semantics","authors":"Julia Taylor Rayz, V. Raskin","doi":"10.1109/ICCI-CC.2016.7862084","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862084","url":null,"abstract":"The meat of the paper is a small innovation in Ontological Semantic Technology describing how to calculate weights in text meaning representations. It is reset here as a component of a complex and apparently unprecedented global logic of natural language, a topic that was abortively entertained in the 1960–70s and since then mostly abandoned.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130411944","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862070
Jingliang Shi, Ying Wu, Lu Liao, Xin-ping Yan, J. Zeng, Rusen Yang
In the iron-making process, the state of burning through point (BTP) is the closure of sintering which is one of the most important parameters in judging the state of sintering. Based on the PSO (Particle Swarm Optimization)-inversion soft-sensing method, the BTP which can not be directly measured in the iron-making process is soft-sensed in this paper. Firstly, the principle of sintering is studied. Four parameters are employed to forecast the BTP, including the suction pressure of main chimney flue, air input, velocity of sintering machine and ignition temperature. And then, a prediction model using PSO is established. At last, the model is applied to production process. It is proved to be effective.
{"title":"Soft sensing of the burning through point in iron-making process","authors":"Jingliang Shi, Ying Wu, Lu Liao, Xin-ping Yan, J. Zeng, Rusen Yang","doi":"10.1109/ICCI-CC.2016.7862070","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862070","url":null,"abstract":"In the iron-making process, the state of burning through point (BTP) is the closure of sintering which is one of the most important parameters in judging the state of sintering. Based on the PSO (Particle Swarm Optimization)-inversion soft-sensing method, the BTP which can not be directly measured in the iron-making process is soft-sensed in this paper. Firstly, the principle of sintering is studied. Four parameters are employed to forecast the BTP, including the suction pressure of main chimney flue, air input, velocity of sintering machine and ignition temperature. And then, a prediction model using PSO is established. At last, the model is applied to production process. It is proved to be effective.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126324432","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 : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862079
Raj Singh Dhawal, Liang Chen
The proposed work develops a method for classification of the species of a fish given in an image, which is a sub-ordinate level classification problem. Sub-ordinate classification is complex as it relies on identifying the notable distinction among the part level characteristics of subjects rather than relying on presence or absence of parts for classification, as done in basic level categorization. Fish image categorization is unique and challenging as the images of same fish species can show significant differences in the fish's attributes when taken in different conditions. Our approach analyses the local patches of images, cropped based on specific body parts, and hence keep comparison more specific to grab more finer details rather than comparing global postures. We have used state-of-the-art multidimensional image descriptor HOG (Histogram of Oriented Gradients) and, colour histograms to create representative feature vectors; feature vectors are summarized using Copula theory which has not been used in many applications in analysing multi-dimensional space despite being one of the most used tools to analyse bivariate data from complex industries like finance and medical science. Our method is very simple yet we have matched the classification accuracy of other proposed complex work for such problems.
{"title":"A copula based method for fish species classification","authors":"Raj Singh Dhawal, Liang Chen","doi":"10.1109/ICCI-CC.2016.7862079","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862079","url":null,"abstract":"The proposed work develops a method for classification of the species of a fish given in an image, which is a sub-ordinate level classification problem. Sub-ordinate classification is complex as it relies on identifying the notable distinction among the part level characteristics of subjects rather than relying on presence or absence of parts for classification, as done in basic level categorization. Fish image categorization is unique and challenging as the images of same fish species can show significant differences in the fish's attributes when taken in different conditions. Our approach analyses the local patches of images, cropped based on specific body parts, and hence keep comparison more specific to grab more finer details rather than comparing global postures. We have used state-of-the-art multidimensional image descriptor HOG (Histogram of Oriented Gradients) and, colour histograms to create representative feature vectors; feature vectors are summarized using Copula theory which has not been used in many applications in analysing multi-dimensional space despite being one of the most used tools to analyse bivariate data from complex industries like finance and medical science. Our method is very simple yet we have matched the classification accuracy of other proposed complex work for such problems.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121390549","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：