Pub Date : 2018-11-01DOI: 10.1109/CIS2018.2018.00088
Bo Chen, Shan Huang, Wensheng Chen, Zhengrong Liang
In this paper, a novel hybrid active contour model for medical image segmentation is proposed, which integrates the global information of image and Legendre level set. It is a region-based segmentation approach, in which the illumination of the regions of interest is represented by a set of Legendre basis functions in a lower dimensional subspace. Firstly, we present a framework which generalizes the Chan-Vese model and segmentation method based on Legendre level set. The weighting parameter is introduced to control the effect of global and local term on the total energy functional. Secondly, a corresponding termination criterion is employed to ensure the evolving curve automatically stops on true boundaries of objects. Thirdly, experiment results on medical images demonstrate that our method is less sensitive to the initial contour and effective to segment images with inhomogeneous intensity distributions.
{"title":"A Novel Hybrid Active Contour Model for Medical Image Segmentation Driven by Legendre Polynomials","authors":"Bo Chen, Shan Huang, Wensheng Chen, Zhengrong Liang","doi":"10.1109/CIS2018.2018.00088","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00088","url":null,"abstract":"In this paper, a novel hybrid active contour model for medical image segmentation is proposed, which integrates the global information of image and Legendre level set. It is a region-based segmentation approach, in which the illumination of the regions of interest is represented by a set of Legendre basis functions in a lower dimensional subspace. Firstly, we present a framework which generalizes the Chan-Vese model and segmentation method based on Legendre level set. The weighting parameter is introduced to control the effect of global and local term on the total energy functional. Secondly, a corresponding termination criterion is employed to ensure the evolving curve automatically stops on true boundaries of objects. Thirdly, experiment results on medical images demonstrate that our method is less sensitive to the initial contour and effective to segment images with inhomogeneous intensity distributions.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123803461","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}
The number of different RNA secondary structures makes it impossible to enumerate the entire landscape except for short RNA sequences, so one has to resort to coarse-grained approximations. The landscape of the barrier tree encodes the local minima and their connecting energy barriers. The idea that it elucidates the basin structure of a landscape by means of a barrier tree has been developed independently in different contexts. The exact computation of barrier trees in general requires the enumeration of the landscape. There are many methods to compute the barrier tree, such as the Euclidean metric and the Huffman tree. We adopt the idea of the Huffman tree to compute the barrier tree, the thought is that we can see the every node in the tree as a separate tree, and then choose the smallest roots to merge into a tree. This process will not end until only one tree left in the forest.
{"title":"The Computation of the Barrier Tree for BHG of RNA Folding Structure","authors":"Qingxia Kong, Zhendong Liu, Xiaobing Tang, Zhaohui Yang, Yaoyao Fu, Hengfei Li","doi":"10.1109/CIS2018.2018.00010","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00010","url":null,"abstract":"The number of different RNA secondary structures makes it impossible to enumerate the entire landscape except for short RNA sequences, so one has to resort to coarse-grained approximations. The landscape of the barrier tree encodes the local minima and their connecting energy barriers. The idea that it elucidates the basin structure of a landscape by means of a barrier tree has been developed independently in different contexts. The exact computation of barrier trees in general requires the enumeration of the landscape. There are many methods to compute the barrier tree, such as the Euclidean metric and the Huffman tree. We adopt the idea of the Huffman tree to compute the barrier tree, the thought is that we can see the every node in the tree as a separate tree, and then choose the smallest roots to merge into a tree. This process will not end until only one tree left in the forest.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121962060","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00025
Wenyi Zeng, Yue Xi, Qian Yin, Ping Guo
The dual hesitant fuzzy set(DHFS) is a useful tool to deal with situations in which people are hesitant in providing their satisfaction degree and dissatisfaction degree. In this paper, we introduce the concepts of weighted dual hesitant fuzzy set(WDHFS) and weighted dual hesitant fuzzy element(WDHFE). Furthermore, we introduce some basic operations of WDHFE, investigate their operation properties, propose the score function and accuracy function of WDHFE to compare two weighted dual hesitant fuzzy elements, and present two aggregation operators to aggregate weighted dual hesitant fuzzy information. In addition, we develop an approach of group decision making based on weighted dual hesitant fuzzy environment. Finally, one numerical example is used to illustrate the effectiveness and practicality of our proposed approach.
{"title":"Weighted Dual Hesitant Fuzzy Sets and Its Application in Group Decision Making","authors":"Wenyi Zeng, Yue Xi, Qian Yin, Ping Guo","doi":"10.1109/CIS2018.2018.00025","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00025","url":null,"abstract":"The dual hesitant fuzzy set(DHFS) is a useful tool to deal with situations in which people are hesitant in providing their satisfaction degree and dissatisfaction degree. In this paper, we introduce the concepts of weighted dual hesitant fuzzy set(WDHFS) and weighted dual hesitant fuzzy element(WDHFE). Furthermore, we introduce some basic operations of WDHFE, investigate their operation properties, propose the score function and accuracy function of WDHFE to compare two weighted dual hesitant fuzzy elements, and present two aggregation operators to aggregate weighted dual hesitant fuzzy information. In addition, we develop an approach of group decision making based on weighted dual hesitant fuzzy environment. Finally, one numerical example is used to illustrate the effectiveness and practicality of our proposed approach.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127746856","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00027
Haokuan Qin, Zhengfeng Ming, Tao Wen, Yuhu Zhao
This paper presents a calculation model for the electromagnetic force of the hybrid magnetic levitation systems composed of electromagnets and permanent magnets, based on which, theoretical derivation is presented for electromagnetic induction intensity distribution of a single solenoid. According to the molecular circulation hypothesis and Biot-Savart Law, the permanent magnet is equivalent to the corresponding current model, so that the electromagnetic force calculation model is obtained. Moreover, according to the model, the calculation formula of permanent magnet subjected to electromagnetic force is deduced. Finally, a simulation experiment is presented based on Maxwell, which illustrates the effectiveness of the provided calculation model, as well as its better performance in the calculation speed compared with the finite element method.
{"title":"Force Calculation for Hybrid Magnetic Levitation System","authors":"Haokuan Qin, Zhengfeng Ming, Tao Wen, Yuhu Zhao","doi":"10.1109/CIS2018.2018.00027","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00027","url":null,"abstract":"This paper presents a calculation model for the electromagnetic force of the hybrid magnetic levitation systems composed of electromagnets and permanent magnets, based on which, theoretical derivation is presented for electromagnetic induction intensity distribution of a single solenoid. According to the molecular circulation hypothesis and Biot-Savart Law, the permanent magnet is equivalent to the corresponding current model, so that the electromagnetic force calculation model is obtained. Moreover, according to the model, the calculation formula of permanent magnet subjected to electromagnetic force is deduced. Finally, a simulation experiment is presented based on Maxwell, which illustrates the effectiveness of the provided calculation model, as well as its better performance in the calculation speed compared with the finite element method.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127961206","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00107
Y. Yu
An information system is introduced to make fire risk evaluation nationwide, standardized, informative and web-based, along with practices of real projects from Shanghai Fire Research Institute in recent years. Technique details of five main modules of the system, User Management, Data Collection, Statistical Analysis, Risk Evaluation, and Information Visualization are discussed.
{"title":"Design of Information System for Fire Risk Evaluation","authors":"Y. Yu","doi":"10.1109/CIS2018.2018.00107","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00107","url":null,"abstract":"An information system is introduced to make fire risk evaluation nationwide, standardized, informative and web-based, along with practices of real projects from Shanghai Fire Research Institute in recent years. Technique details of five main modules of the system, User Management, Data Collection, Statistical Analysis, Risk Evaluation, and Information Visualization are discussed.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121179882","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00112
Lei Yang, Longqing Zhang
With the development of science and technology, the application of information technology in the logistics industry is becoming more mature. At present, in order to improve the safety, punctuality and speediness of cargo transportation, people have higher requirements on cargo transportation. Therefore, the application of wireless sensor network in logistics tracking management system promotes the development of freight transportation, strengthens the smooth progress of freight transportation, and reduces the cost of freight transportation. In this paper, the author analyzes the hardware and software design of logistics tracking management system based on wireless sensor networks to explore the tracking management of goods in wireless sensor networks.
{"title":"Logistics Tracking Management System Based on Wireless Sensor Network","authors":"Lei Yang, Longqing Zhang","doi":"10.1109/CIS2018.2018.00112","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00112","url":null,"abstract":"With the development of science and technology, the application of information technology in the logistics industry is becoming more mature. At present, in order to improve the safety, punctuality and speediness of cargo transportation, people have higher requirements on cargo transportation. Therefore, the application of wireless sensor network in logistics tracking management system promotes the development of freight transportation, strengthens the smooth progress of freight transportation, and reduces the cost of freight transportation. In this paper, the author analyzes the hardware and software design of logistics tracking management system based on wireless sensor networks to explore the tracking management of goods in wireless sensor networks.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114951428","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00034
Yang Li, Wensheng Chen, Binbin Pan, Bo Chen
Nonnegative matrix factorization (NMF) is an effectively parts-based feature representation approach and has achieved good performance in different tasks such as computer vision, clustering and so on. To enhance the discriminative power of NMF in nonnegative feature space, this paper proposes a novel supervised matrix decomposition method, called Class-Cone based Nonnegative Matrix Factorization (CCNMF). We establish a loss function with class-cone regularization which contains the volumes of class-cones and the quantity of between class-cones. To minimize the objective function will leads to small class-cones and large distance between class-cones. This good property is beneficial to the performance of NMF algorithm. We solve the optimization problem using KKT conditions and obtain the updating rules of CCNMF. Our approach is experimentally shown to be convergence and successfully applied to face recognition. Experimental results demonstrate the effectiveness of the proposed CCNMF algorithm.
{"title":"Class-Cone Based Nonnegative Matrix Factorization for Face Recognition","authors":"Yang Li, Wensheng Chen, Binbin Pan, Bo Chen","doi":"10.1109/CIS2018.2018.00034","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00034","url":null,"abstract":"Nonnegative matrix factorization (NMF) is an effectively parts-based feature representation approach and has achieved good performance in different tasks such as computer vision, clustering and so on. To enhance the discriminative power of NMF in nonnegative feature space, this paper proposes a novel supervised matrix decomposition method, called Class-Cone based Nonnegative Matrix Factorization (CCNMF). We establish a loss function with class-cone regularization which contains the volumes of class-cones and the quantity of between class-cones. To minimize the objective function will leads to small class-cones and large distance between class-cones. This good property is beneficial to the performance of NMF algorithm. We solve the optimization problem using KKT conditions and obtain the updating rules of CCNMF. Our approach is experimentally shown to be convergence and successfully applied to face recognition. Experimental results demonstrate the effectiveness of the proposed CCNMF algorithm.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130080603","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00040
Wei Wang, Yanni Yao, Lei Zhu, Xinhong Hei, Yichuan Wang
The usage of graphs has led to the emergence of schema queries in knowledge graph and graph databases, where subgraph queries have become one of the most important research problems. In this paper, we study the directed weighted graphs, and propose a subgraph querying method NGraph based on shortest weight paths. Specifically, we extract three features: vertices, edges and shortest weight paths, which can effectively describe a data graph. Then, the extracted three features are encoded according to corresponding coding approaches and the coding results are combined to form vertex codes and graph codes. The index tree is then built by the encoding of the graph, which is each of the graph sets. According to the filtering-and-verification framework, the candidate set is obtained. Finally, the result set is verified according to VF2 algorithm. The experimental results show that the proposed method can accelerate the querying on directed graphs, and thus improves the querying efficiency.
{"title":"A Novel Subgraph Querying Method on Directed Weighted Graphs","authors":"Wei Wang, Yanni Yao, Lei Zhu, Xinhong Hei, Yichuan Wang","doi":"10.1109/CIS2018.2018.00040","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00040","url":null,"abstract":"The usage of graphs has led to the emergence of schema queries in knowledge graph and graph databases, where subgraph queries have become one of the most important research problems. In this paper, we study the directed weighted graphs, and propose a subgraph querying method NGraph based on shortest weight paths. Specifically, we extract three features: vertices, edges and shortest weight paths, which can effectively describe a data graph. Then, the extracted three features are encoded according to corresponding coding approaches and the coding results are combined to form vertex codes and graph codes. The index tree is then built by the encoding of the graph, which is each of the graph sets. According to the filtering-and-verification framework, the candidate set is obtained. Finally, the result set is verified according to VF2 algorithm. The experimental results show that the proposed method can accelerate the querying on directed graphs, and thus improves the querying efficiency.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121903879","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00041
Yao Sun, Hong Jia, Jiwu Huang
The target of ensemble clustering is to improve the accuracy of clustering by integrating multiple clustering results and solve the problem of scalability existed in traditional and single clustering algorithms. In recent years, ensemble clustering has attracted increasing attention due to its remarkable achievements. However, the limitation of most existing ensemble clustering approaches is that all base clusterings are treated equally without considering the validity of them. Some ensemble clustering algorithms are aware of using weighting strategy but also ignoring the negative impact of base clusterings with poor performance. In this paper, we propose an ensemble clustering method based on a novel weighting strategy. Specifically, the validity of each base clustering is measured by the optimal matching score between the base clustering and the whole to obtain the corresponding weight. Then, the weights of base clusterings which have negative contribution are further adjusted to get the final weight vector. Subsequently, a weighted co-association matrix is constructed to serve as the ensemble matrix and a hierarchical clustering algorithm is applied to it to generate the final result. Experimental results on different types of real-world datasets show the superiority of proposed methods.
{"title":"Ensemble Clustering with Novel Weighting Strategy","authors":"Yao Sun, Hong Jia, Jiwu Huang","doi":"10.1109/CIS2018.2018.00041","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00041","url":null,"abstract":"The target of ensemble clustering is to improve the accuracy of clustering by integrating multiple clustering results and solve the problem of scalability existed in traditional and single clustering algorithms. In recent years, ensemble clustering has attracted increasing attention due to its remarkable achievements. However, the limitation of most existing ensemble clustering approaches is that all base clusterings are treated equally without considering the validity of them. Some ensemble clustering algorithms are aware of using weighting strategy but also ignoring the negative impact of base clusterings with poor performance. In this paper, we propose an ensemble clustering method based on a novel weighting strategy. Specifically, the validity of each base clustering is measured by the optimal matching score between the base clustering and the whole to obtain the corresponding weight. Then, the weights of base clusterings which have negative contribution are further adjusted to get the final weight vector. Subsequently, a weighted co-association matrix is constructed to serve as the ensemble matrix and a hierarchical clustering algorithm is applied to it to generate the final result. Experimental results on different types of real-world datasets show the superiority of proposed methods.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123942127","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00103
Sijia Zhang, Xinyue Zhang, Yijin Wang
A subset of vertices of a graph G is called a feedback vertex set of G if its removal results in an acyclic subgraph. We use f(BHn) to denote the feedback number of balanced hypercubes BHn. In this paper, we construct a feedback vertex set of BHn and obtain ⌜2^2^n-1) (1-1/(2n-1)+1/2n-1 ⌝ ≤ f(BH_n ) ≤ 2^2^n-1- 2^n-1 for n ≤ 3 and ⌜2^2^n-1) (1-1/(2n-1)+1/(2n-1) ⌝ ≤ f(BH n ) ≤ 2^2^n-1) -2^n for n ≥ 4.
{"title":"Feedback Numbers of Balanced Hypercubes BH_n","authors":"Sijia Zhang, Xinyue Zhang, Yijin Wang","doi":"10.1109/CIS2018.2018.00103","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00103","url":null,"abstract":"A subset of vertices of a graph G is called a feedback vertex set of G if its removal results in an acyclic subgraph. We use f(BHn) to denote the feedback number of balanced hypercubes BHn. In this paper, we construct a feedback vertex set of BHn and obtain ⌜2^2^n-1) (1-1/(2n-1)+1/2n-1 ⌝ ≤ f(BH_n ) ≤ 2^2^n-1- 2^n-1 for n ≤ 3 and ⌜2^2^n-1) (1-1/(2n-1)+1/(2n-1) ⌝ ≤ f(BH n ) ≤ 2^2^n-1) -2^n for n ≥ 4.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126438907","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：