Qinyu Zhang, Y. Cisse, H. Nagashino, Y. Kinouchi, A. Pandya
{"title":"Identification of biological sources by neural networks","authors":"Qinyu Zhang, Y. Cisse, H. Nagashino, Y. Kinouchi, A. Pandya","doi":"10.1109/KES.1999.820246","DOIUrl":"https://doi.org/10.1109/KES.1999.820246","url":null,"abstract":"Environmental stimulation, e.g., sound, light and temperature, may produce biological signal sources in the brain, which show autonomous activities without the stimuli. The properties of the source are identified by using BP neural networks. Auditory sources and a circadian source are identified as an example from measured data. This method may be very useful for analyzing brain functions and medical diagnoses.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129249209","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}
{"title":"Using feature trimming to improve the performance of Dystal","authors":"D. Clark","doi":"10.1109/KES.1999.820210","DOIUrl":"https://doi.org/10.1109/KES.1999.820210","url":null,"abstract":"Dystal is a simple, biologically-based artificial neural network which trains much faster than backpropagation. It's developers use the correlation coefficient as a measure of similarity when using Dystal to solve image processing problems. The correlation coefficient is not suitable as a distance measure between points in general data sets. In such data sets the Mahalauobis distance is more appropriate. The performance of Dystal with the Mahalauobis distance can be improved by removing \"noise\" features from the data set.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127618705","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}
{"title":"A neuro fuzzy time series prediction application in telephone banking","authors":"A. C. L. Pensee, N. Mort","doi":"10.1109/KES.1999.820209","DOIUrl":"https://doi.org/10.1109/KES.1999.820209","url":null,"abstract":"The prediction of financial time series is big business and large financial institutions are keen to utilise any prediction method that may give them an advantage in the market place. We consider the application of neuro fuzzy prediction to an application in the financial sector but the object is not to estimate financial indices such as exchange rates or stock market movements. Instead, we address the rather intriguing issue of the impact of television advertising on customer response for a telephone banking organisation.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127988563","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}
{"title":"Towards a real-world oriented workflow system-based on practical experiments for three years","authors":"M. Shikida, C. Kadowaki, S. Kunifuji","doi":"10.1109/KES.1999.820116","DOIUrl":"https://doi.org/10.1109/KES.1999.820116","url":null,"abstract":"Current commercial workflow systems handle only information that is in digital format. However, when they are applied to actual business in an office, we sometimes want to manage not only digital information but also human activities and documents, under some constraints such as the work context and computer environment. In this study, a workflow that handles information found in the real world as well as digital information in the system is called a \"real-world oriented workflow\". To study the workflow, we implemented a prototype workflow system for research budget management in a national facility as a case study. Based on this case study, this paper describes the design principles and methods of supporting the real-world oriented workflow. The effectiveness of the prototype workflow system, which was used for actual business for three years, is shown.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132770086","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}
{"title":"The automatic compression of multiple classification ripple down rule knowledge based systems: preliminary experiments","authors":"Hendra Suryanto, D. Richards, P. Compton","doi":"10.1109/KES.1999.820155","DOIUrl":"https://doi.org/10.1109/KES.1999.820155","url":null,"abstract":"Ripple down rules (RDR) have a longstanding (and successful) history in the field of biomedical engineering. RDR are a knowledge acquisition and representation technique that allow knowledge to be rapidly acquired and maintained by the domain expert. A key feature of RDR, and the reason why maintenance is easily managed, is that rules are never modified or deleted, but locally patched. That is, new rules are exceptions to previous rules and the new rule is validated within the context of previously seen cases. One drawback of local patching is that knowledge can be repeated in different locations of the knowledge base. This paper describes some work done on removing repeated knowledge. The experiments reported were performed on a pathology knowledge base but the algorithm is applicable to any multiple classification RDR knowledge based system. The results support the findings of others that exception structures are compact representations with few opportunities to reduce further. This also suggests that experts tend to provide overly general rules in the first instance which they modify by adding specialisations in the form of exception rules as new cases are seen.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133219438","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}
{"title":"Application of soft computing techniques for dealing Tokyo stock exchange prices indexes (TOPIX)","authors":"N. Baba, H. Asakawa, N. Inoue","doi":"10.1109/KES.1999.820243","DOIUrl":"https://doi.org/10.1109/KES.1999.820243","url":null,"abstract":"Soft computing techniques such as NNs and GAs have successfully been utilized for constructing various intelligent systems. We utilize neural networks to construct an intelligent decision support system for dealing TOPIX. Further, we suggest that the proposed decision support system can be improved by other soft computing techniques such as GAs, TD-Learning, etc.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132215879","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}
J. Schreiter, R. Srowik, A. Graupner, S. Getzlaff, R. Schüffny
{"title":"Design of parallel preprocessing image sensors","authors":"J. Schreiter, R. Srowik, A. Graupner, S. Getzlaff, R. Schüffny","doi":"10.1109/KES.1999.820206","DOIUrl":"https://doi.org/10.1109/KES.1999.820206","url":null,"abstract":"In this paper we propose an architecture for an image sensor with an embedded low-power analog preprocessing unit dedicated for convolution-type filtering. The convolution of the analog image data with the digital convolution kernel is realized using a sequential bit-wise principle. For the subsequent bit-shifted addition a modified current-mode pipelined A/D converter is suggested.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133791421","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}
{"title":"Search interface for query restructuring with discovering user interest","authors":"W. Sunayama, Y. Osawa, M. Yachida","doi":"10.1109/KES.1999.820242","DOIUrl":"https://doi.org/10.1109/KES.1999.820242","url":null,"abstract":"Most Internet users use search engines to get information on the WWW. However, users cannot be content with the output of search engines because it's hard to express the user's own interest as a search query. Therefore, we propose a system which provides users with keywords related to user interest. Users can recall keywords expressing user's hidden (not described in a search query) interest as search keywords. The system includes an interface to restructure a part of the user's search query. Users can compose a new search query expressing concrete user interest with the interface. Previous refinements are simple modifications of the search queries, for example, adding narrow keywords or relational keywords. However, the restructuring described in the paper includes replacement of the search keywords.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121338827","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}
{"title":"Evolution of a dynamical modular neural network and its application to associative memories","authors":"S. Ozawa, K. Tsutumi, N. Baba","doi":"10.1109/KES.1999.820140","DOIUrl":"https://doi.org/10.1109/KES.1999.820140","url":null,"abstract":"This paper presents an evolutionary approach to architecture design of dynamical modular neural networks. As one of the modular neural networks, we adopt Cross-Coupled Hopfield Nets (CCHN) in which Hopfield networks are coupled to each other. The architecture of CCHN is represented by some structural parameters such as the number of modules, the numbers of module units, module connectivity, and so forth. In this paper, these structural parameters are treated as the pheno-type of an individual, and a suitable modular architecture is searched by using genetic algorithms. To verify the usefulness of the proposed architecture design algorithm we apply CCHN to associative memories.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126063591","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}
{"title":"A secure DES implementation for real-time embedded applications","authors":"Sung-Ho Jee, Paul Montague","doi":"10.1109/KES.1999.820231","DOIUrl":"https://doi.org/10.1109/KES.1999.820231","url":null,"abstract":"Achieving a small code size and a fast execution time for an implementation of the Data Encryption Standard (DES) is crucial with regard to the practicalities of its use in real-time embedded applications. With increasing emphasis on the importance of secure data communication, a DES implementation must also be secure. In this paper, we describe various optimization techniques that achieve improvements in both the code size and the execution time, and we address some of the security issues.","PeriodicalId":192359,"journal":{"name":"1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems. Proceedings (Cat. No.99TH8410)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126084488","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}