{"title":"Insect vision based motion detection","authors":"X. T. Nguyen","doi":"10.1109/KES.1998.725931","DOIUrl":"https://doi.org/10.1109/KES.1998.725931","url":null,"abstract":"Significant progress has been made in the understanding of the insect visual system over the past 40 years. In the field of motion detection particularly, an elementary motion detector (EMD) which is based on a non-linear asymmetric interaction between signals mediated by adjacent points of the sampling lattice of the insect eye was discovered. Gradually, the EMD has been become an essential principle of visual motion detection exhibited in biological motion vision from insects to human beings. An empirical model named the template model was proposed by Horridge (1990). However, there is no unique way of interpreting the physical meanings of templates responding to motion. This paper attempts to resolve the problem of determining the meanings of templates by firstly proposing a directional selectivity function which is subsequently employed to identify template responses induced by coherent motion.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114322844","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":"Scheduling a cellular manufacturing system with GA","authors":"R. Lorenzo, S. Fichera, V. Grasso","doi":"10.1109/KES.1998.725961","DOIUrl":"https://doi.org/10.1109/KES.1998.725961","url":null,"abstract":"The flexible manufacturing cell scheduling problem is considered with a multi-objective approach, pursuing together makespan minimisation and the in process job wait minimisation. The formulation of the scheduling problem is discussed, analysing how to generate well suited sequences, like generalised permutation sequences, and the proper construction of a JIT timing of activities. An evolutionary sequencing algorithm based on both classic genetic operators and hybrid operators is then proposed. The hybrid operators have been introduced to construct highly fit initial population, to perform periodically a local search on the population and to maintain enough genetical diversity in the actual population. Simulation runs on a large number of randomly generated problems, showed the high performance of the proposed evolutionary hybrid algorithm, in front of a modified NEH algorithm, in the determination of schedules minimising makespan and in process job wait together.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114496424","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":"An information retrieval system based on personal viewpoints for everyday use","authors":"N. Otani, F. Itoh, S. Shibata, T. Ueda, Y. Ikeda","doi":"10.1109/KES.1998.725876","DOIUrl":"https://doi.org/10.1109/KES.1998.725876","url":null,"abstract":"We propose an information retrieval system, Fit, to support daily information gathering and utilization. Fit can adapt to shifts in personal viewpoint, which is essential for everyday use. Using simple folders for the representation of the viewpoint eases the adaptation, but browsing all the folders becomes difficult. Fit facilitates efficient gathering and effective utilization by features with two information retrieval technologies, the vector space model method and the Boolean model method, which are arranged for everyday use. An evaluation of the system involving reading a newspaper, saving articles and retrieving them demonstrates the effectiveness of the features.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117336664","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":"Improving the generalization ability of neural networks by interval arithmetic","authors":"H. Ishibuchi, M. Nii","doi":"10.1109/KES.1998.725852","DOIUrl":"https://doi.org/10.1109/KES.1998.725852","url":null,"abstract":"Recently, interval-arithmetic-based neural networks have been proposed for handling intervals as inputs of multilayer feedforward neural networks. This paper demonstrates that interval arithmetic can be utilized for improving the generalization ability of neural networks for pattern classification problems. We examine two approaches, each of which is used in the classification phase of new patterns and in the learning phase of neural networks, respectively. In the first approach, an interval input vector is generated from a new pattern by adding a certain width to its attribute values. In the second approach, neural networks are trained by interval input vectors generated from training patterns. These approaches are illustrated by a two-dimensional pattern classification problem. The effectiveness of these approaches is examined by computer simulations on a commonly used benchmark data set.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122148714","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":"Integrating databases in Internet","authors":"Zhibin Liu, Xiaoyong Du, N. Ishii","doi":"10.1109/KES.1998.725998","DOIUrl":"https://doi.org/10.1109/KES.1998.725998","url":null,"abstract":"One of the difficult problems in database integration is to find and resolve the semantic heterogeneity of the component databases. In this paper, we present a methodology for database integration by using an ontology. The ontology is mainly used to help the designers to understand the semantics of database objects. Anyone who wants to share his database with others should provide an export schema of the database and a mapping between the schema and one or many standard ontologies. According to this mapping, the designer can easily find and resolve the semantic heterogeneity of the component databases and build an integrated schema.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124662980","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 use of knowledge based engineering in the mechatronic embodiment of intelligent machines and systems","authors":"R. Parkin","doi":"10.1109/KES.1998.725826","DOIUrl":"https://doi.org/10.1109/KES.1998.725826","url":null,"abstract":"Conventional combinational design philosophies are, in many cases, proving inadequate for the sophisticated products and speed of response demanded by today's markets. Mechatronic design philosophies and concurrent practices for achieving the physical embodiment of the designers creative output are seen as an appropriate response to the challenge. Mechatronics is a holistic design philosophy which can yield intelligent machines (e.g. self-driving vehicles, robotic surgeons) for the benefit of mankind. The advent of new technologies has provided new possibilities for intelligent machines. The appropriate use of knowledge engineering has given much scope in this direction and this paper reports a number of applications across a range of industries from rock processing to food handling. It is clear that great benefit has been derived from the application of knowledge engineering and that techniques such as fuzzy logic and artificial neural networks have much to offer in complex systems where sensor data may be imprecise, where there may be a multiplicity of input data with possible conflicts or where it is not possible to generate precise algorithmic relationships or transfer functions. There is still, however, much research to be done regarding topologies of massively parallel systems, design rules for their creation, paradigms for sensor fusion and most importantly, reliability engineering and the concept of graceful degradation.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129862670","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":"Multimodal information retrieval, extraction and generation for use in the health domain","authors":"C. Wood, M. Cross, Phuong La","doi":"10.1109/KES.1998.725988","DOIUrl":"https://doi.org/10.1109/KES.1998.725988","url":null,"abstract":"If an organisation such as the Department of Defence is to maximise its use of information, it has to exchange and coordinate meanings between different kinds of information sources with information from a variety of domains. A multimodal meaning base is being developed that makes it possible to identify meanings that can be expressed in linguistic and cartographic modalities. The research involves the collection of multimodal resources including structured information (databases), unstructured information, the description of the semantics, and the expression in a computational resource. The outcome of the research is the development of a multimodal information management system, HINTS, that will help solve the problems of information exchange and coordination. Our domain is communicable diseases. The design of the multimodal information management tool utilised participatory design techniques involving researchers, designers, users and stake holders. Participatory design is a comprehensive and integrated methodology for designing graphical user interfaces using low-tech materials, object oriented methods, and frequent iterative usability testing. We extended this technique to include the design of the entire system. The techniques were effective across a multidisciplinary team that included researchers and clients.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128402313","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":"Job scheduling using ranking fuzzy number method","authors":"Koun-Tem Sun","doi":"10.1109/KES.1998.725958","DOIUrl":"https://doi.org/10.1109/KES.1998.725958","url":null,"abstract":"Proposes a fuzzy ranking method to solve job scheduling problems. The proposed fuzzy ranking method is based on the concept of the center of gravity method. For each job in a job scheduling problem, the profit is transferred into the membership value, and the deadline is transferred into the value of a fuzzy element X. Then, each job can be transferred into a fuzzy number, and we can find the centroid (center) of this fuzzy number by applying the proposed fuzzy ranking method. Based on these ranking values, a good job sequencing can be obtained. Simulation tests show that generated solutions by the ranking fuzzy number approach are better than by the traditional greedy algorithm for solving the complex job scheduling problems.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128457501","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":"Fuzzy arithmetic in neural networks for linguistic rule extraction","authors":"M. Nii, H. Ishibuchi","doi":"10.1109/KES.1998.725938","DOIUrl":"https://doi.org/10.1109/KES.1998.725938","url":null,"abstract":"We have previously (1996) proposed a fuzzy arithmetic-based method for extracting linguistic IF-THEN rules from trained neural networks for pattern classification problems with continuous attributes. In our method, antecedent linguistic values of a linguistic IF-THEN rule are presented to a trained neural network as inputs, and the corresponding fuzzy outputs are calculated by fuzzy arithmetic. The consequent class and the grade of certainty are determined based on the calculated fuzzy outputs. Thus the calculation of the fuzzy outputs is very important for the linguistic rule extraction. Because the fuzzy arithmetic is locally applied to the calculation at each unit, the fuzziness of the linguistic input values is usually increased by the feedforward calculation through the neural network. In this paper, we show how such increase of the fuzziness can be reduced by subdividing the level set (i.e., /spl alpha/-cut) of each linguistic input value in the calculation of the fuzzy outputs. The effect of such subdivision is illustrated by computer simulations.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130065309","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 consideration on the learning algorithm of neural network-utilization of the hierarchical structure stochastic automata for the backpropagation method with momentum","authors":"N. Baba, Ken Sato","doi":"10.1109/KES.1998.725945","DOIUrl":"https://doi.org/10.1109/KES.1998.725945","url":null,"abstract":"Backpropagation (BP) method with momentum has often been applied to adapt artificial neural networks for various pattern classification problems. However, an important limitation of this method is that its learning performance depends heavily upon the selection of the values of momentum factor and step size. In this paper, it is shown that the hierarchical structure stochastic automata can be used for finding appropriate values of the parameters involved in the BP method with momentum.","PeriodicalId":394492,"journal":{"name":"1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130108236","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}