Pub Date : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018066
R. Nagarajan, S. Yaacob, G. Sainarayanan
In this paper a system for navigation assistance for visually impaired (NAVI) is presented. The system includes a single board processing system (UPS), vision sensor mounted headgear and stereo earphones. The image of environment is captured by the vision sensor. The image is then processed by a novel real time image processing methodology using the fuzzy clustering algorithm. The proposed methodology incorporates certain human vision properties for clear representation of the environment. The image processed is mapped to a stereo acoustic pattern and transferred to the user's earphones. The sound produced varies with the gray value and orientation of the obstacle in front. Blind individuals are trained with NAVI and tested for obstacle identification. Suggestions from the blind volunteers regarding pleasantness and discrimination of sound pattern were also incorporated in the prototype. Certain improvements for faster convergence of clustering are also considered.
{"title":"Fuzzy clustering in vision recognition applied in NAVI","authors":"R. Nagarajan, S. Yaacob, G. Sainarayanan","doi":"10.1109/NAFIPS.2002.1018066","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018066","url":null,"abstract":"In this paper a system for navigation assistance for visually impaired (NAVI) is presented. The system includes a single board processing system (UPS), vision sensor mounted headgear and stereo earphones. The image of environment is captured by the vision sensor. The image is then processed by a novel real time image processing methodology using the fuzzy clustering algorithm. The proposed methodology incorporates certain human vision properties for clear representation of the environment. The image processed is mapped to a stereo acoustic pattern and transferred to the user's earphones. The sound produced varies with the gray value and orientation of the obstacle in front. Blind individuals are trained with NAVI and tested for obstacle identification. Suggestions from the blind volunteers regarding pleasantness and discrimination of sound pattern were also incorporated in the prototype. Certain improvements for faster convergence of clustering are also considered.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114602885","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018020
V. Robinson
Many aspects of geographic information systems (GIS) lend themselves to applications of fuzzy sets. Fuzzy databases, queries, and other areas of development have helped address problems in geographical information representation, management, query, and modeling. Cost, in a general sense, is an issue not generally considered when addressing the topic of fuzzy sets and GIS. By considering the issue of cost afresh perspective on the development of fuzzy sets in GIS applications is possible. A comparison of fuzzy versus nonfuzzy approaches shows that fuzzy logic-based approaches typically provide more detailed, useful information. As GIS becomes more complex, and intelligent, fuzzy logic-based methods will become a cost-effective approach for improving its problem-solving abilities.
{"title":"A perspective on geographic information systems and fuzzy sets","authors":"V. Robinson","doi":"10.1109/NAFIPS.2002.1018020","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018020","url":null,"abstract":"Many aspects of geographic information systems (GIS) lend themselves to applications of fuzzy sets. Fuzzy databases, queries, and other areas of development have helped address problems in geographical information representation, management, query, and modeling. Cost, in a general sense, is an issue not generally considered when addressing the topic of fuzzy sets and GIS. By considering the issue of cost afresh perspective on the development of fuzzy sets in GIS applications is possible. A comparison of fuzzy versus nonfuzzy approaches shows that fuzzy logic-based approaches typically provide more detailed, useful information. As GIS becomes more complex, and intelligent, fuzzy logic-based methods will become a cost-effective approach for improving its problem-solving abilities.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125339966","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018045
M. Nikravesh
Retrieving relevant information is a crucial component of cased-based reasoning systems for Internet applications such as search engines. The task is to use user-defined queries to retrieve useful information according to certain measures. Even though techniques exist for locating exact matches, finding relevant partial matches might be a problem. It may not be also easy to specify query requests precisely and completely - resulting in a situation known as a fuzzy-querying. It is usually not a problem for small domains, but for large repositories such as World Wide Web, a request specification becomes a bottleneck. Thus, a flexible retrieval algorithm is required, allowing for imprecise specification or search. Therefore, we envision that non-classical techniques such as fuzzy logic based-clustering methodology based on perception, fuzzy similarity, fuzzy aggregation, and FLSI for automatic information retrieval and search with partial matches are required.
{"title":"Fuzzy conceptual-based search engine using conceptual semantic indexing","authors":"M. Nikravesh","doi":"10.1109/NAFIPS.2002.1018045","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018045","url":null,"abstract":"Retrieving relevant information is a crucial component of cased-based reasoning systems for Internet applications such as search engines. The task is to use user-defined queries to retrieve useful information according to certain measures. Even though techniques exist for locating exact matches, finding relevant partial matches might be a problem. It may not be also easy to specify query requests precisely and completely - resulting in a situation known as a fuzzy-querying. It is usually not a problem for small domains, but for large repositories such as World Wide Web, a request specification becomes a bottleneck. Thus, a flexible retrieval algorithm is required, allowing for imprecise specification or search. Therefore, we envision that non-classical techniques such as fuzzy logic based-clustering methodology based on perception, fuzzy similarity, fuzzy aggregation, and FLSI for automatic information retrieval and search with partial matches are required.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"11 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120986899","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018035
O. Nasaroui, D. Dasgupta, M. Pavuluri
We present a soft structured genetic algorithm (s/sup 2/GA) that inherits all the advantages of its crisp (non-fuzzy) counterpart (sGA), but possesses several additional unique features compared to the sGA and other GA based techniques. We outline several strengths of the s/sup 2/GA approach with regard to several emerging problems, such as its ability to address the scalability issue in a very eloquent manner for most data and Web mining problems. We also illustrate the use if s/sup 2/GA for multimodal optimization by using it within a Deterministic Crowding framework, when used to find an unknown number of clusters underlying a data set Even though the proposed techniques inherit as legacy from the GA an almost unlimited number of different applications in all areas of science and engineering, we focus on an application of vital importance in today's networked environment-that of analyzing usage patterns on Web sites.
{"title":"S/sup 2/GA: a soft structured genetic algorithm, and its application in Web mining","authors":"O. Nasaroui, D. Dasgupta, M. Pavuluri","doi":"10.1109/NAFIPS.2002.1018035","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018035","url":null,"abstract":"We present a soft structured genetic algorithm (s/sup 2/GA) that inherits all the advantages of its crisp (non-fuzzy) counterpart (sGA), but possesses several additional unique features compared to the sGA and other GA based techniques. We outline several strengths of the s/sup 2/GA approach with regard to several emerging problems, such as its ability to address the scalability issue in a very eloquent manner for most data and Web mining problems. We also illustrate the use if s/sup 2/GA for multimodal optimization by using it within a Deterministic Crowding framework, when used to find an unknown number of clusters underlying a data set Even though the proposed techniques inherit as legacy from the GA an almost unlimited number of different applications in all areas of science and engineering, we focus on an application of vital importance in today's networked environment-that of analyzing usage patterns on Web sites.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115409055","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018100
R. Intan, M. Mukaidono
A fuzzy set is considered to represent deterministic uncertainty called fuzziness. In deterministic uncertainty of a fuzzy set, one may subjectively determine a membership function of a given element by one's knowledge. Different persons with different knowledge may provide different membership functions for elements in a universe with respect to a given fuzzy set. Here, knowledge plays important roles in determining or defining a fuzzy set. By adding a component of knowledge, we generalized a definition of a fuzzy set based on probability theory. In addition, by using a fuzzy conditional probability relation, granularity of knowledge is given in two frameworks, crisp granularity and fuzzy granularity. Also, two asymmetric similarity classes or subsets of knowledge are considered. When fuzzy sets represent problems or situations, a granule of knowledge might describe a class (group) of knowledge (persons) who has similar point of view in dealing the problems. In the paper, special attention is given to approximate reasoning in knowledge-based fuzzy sets representing fuzzy production rules as usually used in fuzzy expert systems.
{"title":"Approximate reasoning in knowledge-based fuzzy sets","authors":"R. Intan, M. Mukaidono","doi":"10.1109/NAFIPS.2002.1018100","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018100","url":null,"abstract":"A fuzzy set is considered to represent deterministic uncertainty called fuzziness. In deterministic uncertainty of a fuzzy set, one may subjectively determine a membership function of a given element by one's knowledge. Different persons with different knowledge may provide different membership functions for elements in a universe with respect to a given fuzzy set. Here, knowledge plays important roles in determining or defining a fuzzy set. By adding a component of knowledge, we generalized a definition of a fuzzy set based on probability theory. In addition, by using a fuzzy conditional probability relation, granularity of knowledge is given in two frameworks, crisp granularity and fuzzy granularity. Also, two asymmetric similarity classes or subsets of knowledge are considered. When fuzzy sets represent problems or situations, a granule of knowledge might describe a class (group) of knowledge (persons) who has similar point of view in dealing the problems. In the paper, special attention is given to approximate reasoning in knowledge-based fuzzy sets representing fuzzy production rules as usually used in fuzzy expert systems.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117275159","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018032
S. Romaní, E. Montseny, P. Sobrevilla
We propose a method for characterizing a set of training colors, based on sample color pixels captured with a camera. The system tries to detect the training colors on test pixels within images captured under illumination level conditions different from those used in the training process. The training color characterization is based on Smith's perceptual color model, but using only hue and saturation components. Both, training and classification processes make use of fuzzy techniques to assume vagueness involved within training and test data.
{"title":"An approach to a fuzzy color detection method, robust with regard to variable illuminant level conditions","authors":"S. Romaní, E. Montseny, P. Sobrevilla","doi":"10.1109/NAFIPS.2002.1018032","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018032","url":null,"abstract":"We propose a method for characterizing a set of training colors, based on sample color pixels captured with a camera. The system tries to detect the training colors on test pixels within images captured under illumination level conditions different from those used in the training process. The training color characterization is based on Smith's perceptual color model, but using only hue and saturation components. Both, training and classification processes make use of fuzzy techniques to assume vagueness involved within training and test data.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122645371","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018023
A. Haj-Ali, H. Ying
PID control is of particular importance because it presently controls the vast majority of industrial processes worldwide. In our previous papers and those by other researchers, explicit connections between PID control and various Mamdani fuzzy controllers, all of which use piecewise linear input fuzzy sets, have been established. In the present paper, we extend the study to cover fuzzy controllers that employ nonlinear fuzzy sets. The fuzzy controllers in this study consist of two fuzzy sets for each input variable, product or Zadeh AND operators, and the centroid defuzzifier. We have developed a new approach that establishes necessary and sufficient conditions on the input fuzzy sets in order for the fuzzy controllers to be nonlinear PI, PD, or PID controllers with variable gains. The treatment is general and covers two different and general types of nonlinear fuzzy sets.
{"title":"Structure analysis of Mamdani fuzzy PID controllers with nonlinear input fuzzy sets","authors":"A. Haj-Ali, H. Ying","doi":"10.1109/NAFIPS.2002.1018023","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018023","url":null,"abstract":"PID control is of particular importance because it presently controls the vast majority of industrial processes worldwide. In our previous papers and those by other researchers, explicit connections between PID control and various Mamdani fuzzy controllers, all of which use piecewise linear input fuzzy sets, have been established. In the present paper, we extend the study to cover fuzzy controllers that employ nonlinear fuzzy sets. The fuzzy controllers in this study consist of two fuzzy sets for each input variable, product or Zadeh AND operators, and the centroid defuzzifier. We have developed a new approach that establishes necessary and sufficient conditions on the input fuzzy sets in order for the fuzzy controllers to be nonlinear PI, PD, or PID controllers with variable gains. The treatment is general and covers two different and general types of nonlinear fuzzy sets.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129863160","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018092
C. Frélicot, L. Mascarilla
The design of a rejection-based classifier can be made according to two well-identified strategies operating in two sequential steps: the accept-first strategy and the reject-first one. The first one is the most usual. Recently, we have proposed a general class of the latter classifiers using fuzzy XOR operators based on dual triples (t-norm, t-conorm, complement) (2001). In this paper, we investigate a new approach. It consists in starting with testing for ambiguity rejection, and if needed, testing for either exclusive classification or distance rejection. For this purpose, we define a new operator called the fuzzy OR-2 allowing us to propose a new class of classifiers.
{"title":"A third way to design pattern classifiers with reject options","authors":"C. Frélicot, L. Mascarilla","doi":"10.1109/NAFIPS.2002.1018092","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018092","url":null,"abstract":"The design of a rejection-based classifier can be made according to two well-identified strategies operating in two sequential steps: the accept-first strategy and the reject-first one. The first one is the most usual. Recently, we have proposed a general class of the latter classifiers using fuzzy XOR operators based on dual triples (t-norm, t-conorm, complement) (2001). In this paper, we investigate a new approach. It consists in starting with testing for ambiguity rejection, and if needed, testing for either exclusive classification or distance rejection. For this purpose, we define a new operator called the fuzzy OR-2 allowing us to propose a new class of classifiers.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123824053","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018031
H. Timm, F. Klawonn, R. Kruse
We propose an approach to handling class information in fuzzy cluster analysis, where a class can consist of several clusters. The approach is based on a penalty term for clusters comprising several clusters.
{"title":"An extension of partially supervised fuzzy cluster analysis","authors":"H. Timm, F. Klawonn, R. Kruse","doi":"10.1109/NAFIPS.2002.1018031","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018031","url":null,"abstract":"We propose an approach to handling class information in fuzzy cluster analysis, where a class can consist of several clusters. The approach is based on a penalty term for clusters comprising several clusters.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"344 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123102042","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 : 2002-08-07DOI: 10.1109/NAFIPS.2002.1018107
F. Cheong, R. Lai
With the availability of a wide range of evolutionary algorithms such as genetic algorithms, evolutionary programming, evolution strategies and differential evolution, every conceivable aspect of the design of a fuzzy logic controller has been optimized and automated. Although there is no doubt that these automated techniques can produce an optimal fuzzy logic controller, the structure of such a controller is often obscure and in many cases these optimizations are simply not needed. We believe that the automatic design of a fuzzy logic controller can be simplified by using a generic rule base such as the Mac Vicar-Whelan rule base and using an evolutionary algorithm to optimize only the membership functions of the fuzzy sets. Furthermore, by restricting the overlapping of fuzzy sets, using triangular membership functions and singletons, and reducing the number of parameters to represent the membership functions, the design can be further simplified. This paper describes this method of simplifying the design and some experiments performed to ascertain its validity.
{"title":"On simplifying the automatic design of a fuzzy logic controller","authors":"F. Cheong, R. Lai","doi":"10.1109/NAFIPS.2002.1018107","DOIUrl":"https://doi.org/10.1109/NAFIPS.2002.1018107","url":null,"abstract":"With the availability of a wide range of evolutionary algorithms such as genetic algorithms, evolutionary programming, evolution strategies and differential evolution, every conceivable aspect of the design of a fuzzy logic controller has been optimized and automated. Although there is no doubt that these automated techniques can produce an optimal fuzzy logic controller, the structure of such a controller is often obscure and in many cases these optimizations are simply not needed. We believe that the automatic design of a fuzzy logic controller can be simplified by using a generic rule base such as the Mac Vicar-Whelan rule base and using an evolutionary algorithm to optimize only the membership functions of the fuzzy sets. Furthermore, by restricting the overlapping of fuzzy sets, using triangular membership functions and singletons, and reducing the number of parameters to represent the membership functions, the design can be further simplified. This paper describes this method of simplifying the design and some experiments performed to ascertain its validity.","PeriodicalId":348314,"journal":{"name":"2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116373724","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：