1-11hit |
Takahiro YONEKAWA Atsuhiro NISHIKATA
This paper describes a rhythm pattern accuracy diagnosis system based on the rhythm pattern matching algorithm and a diagnosis feedback method by employing the SVM technique. A beat rhythm pattern is recorded by a PC and analyzed with an algorithm including cluster-analysis-based pattern matching. Rhythm performance is represented by a performance feature vector, which features note length deviation, note length instability, and tempo instability. The performance feature vector is effective for objectively evaluating the accuracy of rhythm patterns objectively. In addition, this system has the music experts' knowledge base, which is calculated from the performance feature vectors associated with the experts' subjective evaluation by listening to the performance. The system generates both an objective measuring report, and experts' comments for learners. Reproductivity of experts' comments is statistically indicated to be excellent for eight rhythm patterns, two tempo levels, and eight users. Reliability of experts' comments are also described considering the threshold of the decision function of SVM. Subjective evaluation of the system is carried out by fifteen users by a questionnaire using the SD method. As a result of factor analysis for the sixteen questions, four factors named "Audio-visual representation," "User-friendliness," "Reliability," and "Window representation," are extracted. Users' four factor scores indicate that the system is reliable and easy to use.
MinSuk LEE YeungGyu PARK ChoongShik PARK Jaihie KIM
An ATMS (Assumption-based Truth Maintenance System) has been widely used for maintaining the truth of an information by detecting and solving the contradictions in rule-based systems. However, the ATMS cannot correctly maintain the truth of the information in case that the generated information is satisfied within a time interval or includes data about temporal relations of events in time varying situations, because it has no mechanism manipulating temporal data. In this paper, we propose the extended ATMS that can maintain the truth of the information in the knowledge-based system using information changing over time or temporal relations of events. To maintain the contexts generated by relations of events, we modify the label representation method, the disjunction and conjunction simplification method in the label-propagation procedure and the nogood handling method of the conventional ATMS.
Satoshi HORI Hiromitsu SUGIMATSU Soshi FURUKAWA Hirokazu TAKI
We have developed a diagnostic Case-Based Reasoning (CBR) system, Doctor, which infers possible defects in a home electrical appliance and lists up necessary service parts. The CBR is suitable to build a diagnostic system for the field service because the CBR imitates how experienced service technicians infer and is able to learn defect trends and novel repair cases from a service report database. In order to apply a CBR system to this real-world problem, Our system has the following new features: (1) Its CBR mechanism utilizes not only repair cases, but also diagnostic rules that are elicited from human experts so that accurate diagnosis can be achieved. (2) Its casebase maintenance mechanism updates the casebase and adapts it to the changing real world.
Behrouz Homayoun FAR Sidi O.SOUEINA Hassan HAJJI Shadan SANIEPOUR Anete Hiromi HASHIMOTO
A major topic in the field of network and telecommunications is doing business on the World Wide Web (WWW), which is called Electronic Commerce (EC). Another major topic is blending Artificial Intelligence (AL) techniques with the WWW. In the Ex-W-Pert Project we have proposed an agent model for EC components that blends the traditional expert systems' reasoning engine with a multi-layer knowledge base, communication and documentation engines. In this project, EC is viewed as a society of software agents, such as customer, search, catalog, manufacturer, dealer, delivery and banker agents, interacting and negotiating with each other. Each agent has a knowledge-base and a reasoning engine, a communication engine and a documentation engine. The knowledge-base is organized in three layers: skill layer, rule layer and knowledge layer (S-R-K layers). In this project, for each EC agent, we identify the class of problems to be solved and build the knowledge base gradually for each layer. We believe that using this multi-layer knowledge base system will speed up the reasoning and ultimately reduce the operation costs.
Toshio TSUTSUMIDA Toshihiro MATSUI Tadashi NOUMI Toru WAKAHARA
Through comparing the results of two successive IPTP Character Recognition Competitions which focused on 3-digit handprinted postal codes, we herein analyze the methodologies of the submitted algorithms along with the substituted or rejected patterns of these algorithms. Regarding their methodologies, lesser diversity was apparent specifically concerning the contour-chain code based on local stroke directions and statistical discriminant functions for feature extraction and discrimination. Analysis of the patterns demonstrated that the misrecognized patterns being most often improved were categorized as a decrease in peculiarly shaped handwritten characters or heavy-handed and disconnected strokes. However, most of the remaining misrecognitions were still classed as peculiarly shaped handwriting as commonly shared between the best three algorithms. From these analyses, we could delineate a direction to be taken for developing more effective methodologies and clarify the remaining problems to be overcome by the subsequent intensive research. Furthermore, we evaluate in this article our multi-expert recognition system for achieving higher recognition performances by means of combining complementary recognition algorithms. We performed a subsequent investigation of the Candidate Appearance Likelihood Method using novel experimental conditions and a new examination of the application of the neural network as the combining method for accumulating the broader candidate appearances. The results obtained confirm that combining through the neural network constitutes one of the most effective ways of making the multi-expert recognition system a reality.
Masami SHISHIBORI Junichi AOE Ki-Hong PARK Hisatoshi MOCHIZUKI
The selection of an appropriate key search algorithm for a specific application field is an important issue in application systems development. This is because data retrieval is the most time-consuming part of many application programs. An automatic selection method for key search algorithms is presented in this paper. The methodology has been implemented in a system called KESE2 (KEy-SEarch ALgorithm SElection). Key search algorithms are selected according to the user's requirements through interaction with KESE2 which bases its inferences on an evaluation table. This evaluation table contains values rating the performance of each key search algorithm for the different searching properties, or characteristics. The selection algorithm presented is based on step by step reduction of unsuitable key search algorithms and searching properties. The paper also proposes assistance facilities that consist of both a support function and a program synthesis function. Experimental results show that the appropriate key search algorithms are effectively selected, and that the necessary number of questions asked, to select the appropriate algorithm, is reduced to less than half of the total number of possible questions. The support function is useful for the user during the selection process and the program synthesis function fully translates a selected key search algorithm into high level language in an average of less than 1 hour.
Toshihiro MATSUI Ikuo YAMASHITA Toru WAKAHARA
The Institute for Posts and Telecommunications Policy (IPTP) held its first character recognition competition in 1992 to ascertain the present status of ongoing research in character recognition and to find promising algorithms for handwritten numerals. In this paper, we report and analyze the results of this competition. In the competition, we adopted 3-digit handwritten postal code images gathered from live mail as recognition objects. Prior to the competition, 2,500 samples (7,500 characters) were distributed to the participants as traning data. By using about 10,000 different samples (29,883 characters), we tested 13 recognition programs submitted by five universities and eight manufacturing companies. According to the four kinds of evaluation criteria: recognition accuracy, recognition speed, robustness against degradation, and theroretical originality, we selected the best three recognition algorithms as the Prize of Highest Excellence. Interestingly enough, the best three recognition algorithms showed considerable diversity in their methodologies and had very few commonly substituted or rejected patterns. We analyzed the causes for these commonly substituted or rejected patterns and, moreover, examined the human ability to discriminate between these patterns. Next, by considering the complementary characteristics of each recognition algorithm, we studied a multi-expert recognition strategy using the best three recognition algorithms. Three kinds of combination rules: voting on the first candidate rule, minimal sum of candidate order rule, and minimal sum of dissimilarities rule were examined, and the latter two rules decreased the substitution rate to one third of that obtained by one-expert in the competition. Furthermore, we proposed a candidate appearance likelihood method which utilizes the conditional probability of each of ten digits given the candidate combination obtained by each algorithm. From the experiments, this method achieved surprisingly low values of both substitution and rejection rates. By taking account of its learning ability, the candidate appearance likelihood method is considered one of the most promising multi-expert systems.
Recent developments and case studies regarding VLSI device chip failure analysis are reviewed. The key failure analysis techniques reviewed include EMMS (emission microscopy), OBIC (optical beam induced current), LCM (liquid crystal method), EBP (electron beam probing), and FIB (focused ion beam method). Further, future possibilities in failure analysis, and some promising new tools are introduced.
Based on distributed artificial intelligence technology, the paper proposes a distributed expert system for distribution system planning. The developed expert system is made up of a set of problem-solving agents that autonomously process local tasks and cooperatively interoperate with each other by a shared database in order to reach a proper distribution plan. In addition, a two-level control mechanism composed of local-control and meta-control is also proposed to achieve a high degree of goodness in distribution system planning. To demonstrate its effect, the distributed expert system is implemented on basis of NASA's CLIPS and SUN's RPC and applied to the planning of distribution system in Taiwan. Test results indicate that the distributed expert system assists system planners in making an appropriate plan.
Chang Hoon LEE Moon Hae KIM Jung Wan CHO
In general, the work on developing an expert system has relied on domain experts to provide all domain-specific knowledge. The method for acquiring knowledge directly from experts is inadequate in oriental medicine because it is hard to find an appropriate expert and the development cost becomes too high. Therefore, we have developed two effective methods for acquiring knowledge indirectly from sample cases. One is to refine a constructed knowledge base by using sample cases. The other is to train a neural network by using sample cases. To demonstrate the effectiveness of our methods, we have implemented two prototype systems; the Oriental Medicine Expert System (OMES) and the Oriental Medicine Neural Network (OMNN). These systems have been compared with the system with the knowledge base built directly by domain experts (OLDS). Among these systems, OMES are considered to be superior to other systems in terms of performances, development costs, and practicalness. In this paper, we present our methods, and describe our experimental and comparison results.
Glenn MANSFIELD Makoto MURATA Kenichi HIGUCHI Krishnamachari JAYANTHI Basabi CHAKRABORTY Yoshiaki NEMOTO Shoichi NOGUCHI
In this paper we examine the architectural and operational design issues of a practical network management system using the Simple Network Management Protocol (SNMP) in the context of a large-scale OSI-based campus-network TAINS. Various design aspects are examined and the importance of time-management is elicited. In the proposed design, intelligent, time-synchronised agents are deployed to collect information about the network segments to which they are attached. The manager talks to the agents and gathers relevant network information. This information is used by the expert network manager, in conjunction with a network knowledge base (NKB) and a management information knowledge base (MIKB) , to reconstruct the overall network-traffic characteristic, to evaluate the status of the network and to take/suggest some action. This model is particularly useful in networks where some global control, monitoring and management is desired and installing agents on all elements, connected to the network, is impossible. The use of time labels and narrow time windows enables the manager to obtain a reasonably accurate picture of the network status. The introduction of time-labelled composite objects in the Management Information Base (MIB) provides a means of reducing the load of management-related traffic on the network. The MIKB containing a logical description of the behaviour of the managed objects defined in the MIB, drives the expert system and provides the knowledge of general nature that a human expert has about networks. The proposed MIKB concept provides a very convenient schema for building the knowledge base in an expert network management system. Further since the MIKB is MIB-specific, it can be used in network management systems for managing similar MIB's.