All issues
Volume 112, Issue 3
Displaying 1-9 of 9 articles from this issue
- |<
- <
- 1
- >
- >|
-
Masafumi Hagiwara, Yuichiro Anzai1992 Volume 112 Issue 3 Pages 165-171
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSCombination of Artificial Intelligence (AI) and Connectionist model is very effective to construct an intelligent information processing system. There are several studies based on such a concept. An example, a knowledge base system based on connectionist model has the following features.
(1) Robustness: even when there are some errors in a user's question or in a knowledge base, a near right answer can be obtained.
(2) Context dependecy: retrieval with prediction is possible.
(3) Easy parallel retrieval for multiple concepts.
(4) Easy maintenance of knowledge base: facts are expressed by symbols.
In spite of the above advantages, the conventional system has a great shortcming: it can only make inference of facts.
This paper proposes a connectionist model data base system with a tamplate for association. The proposed system has two features: inference is possible when data is insufficient, and new knowledge can be generated by inference. The proposed system uses a template to create a network for associtive reasoning, and it can be done by interactive activation and competition process. Computer simulation result indicates the effectiveness of the proposed system.View full abstractDownload PDF (1145K) -
Tetsuo Ideguchi, Kazuki Kotaka, Yuji Koui1992 Volume 112 Issue 3 Pages 172-179
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSThe Manufacturing Automation Protocol (MAP) is the communication protocol for factory LAN systems. MAP complies with the definition of the Open Systems Interconnection (OSI) Reference model. At present, the intoroduction of many kinds of controller and device with MAP functions are intended to realize the Computer Integrated Manufacturing (CIM).
This paper describes the implementation of communication board based on the MAP 3.0 specification. This communication board has the communication functions with the OSI lower layer protocols, the Transport protocol through the MAC protocol. This paper also presents the performance model to estimate the performance of this communication board and the comparison with the performance measurement.View full abstractDownload PDF (1695K) -
Toyohisa Kaneko, Koichi Ishibashi, Shoichi Hosokawa, Kazumi Yamashita1992 Volume 112 Issue 3 Pages 180-188
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSCarrier Sense Multiple Access with Collision Detection (CSMA/CD) protocol is one of remarkable access protocol on Local Area Network (LAN). The recent interest in the application of LAN is the communication for the demand of immediacy and continuity. Furthermore, each terminal connected to LAN has multi-tasks by multi-users. So the system that each terminal has some buffer is efficient. Up to the present, a number of studies on the analysis for buffered CSMA/CD has already appeared. But these are restricted or complicated or unpractical analysis. In this paper, using embedded Markov chain, we analyze non-persistent CSMA/CD protocol that each terminal possesses finite buffer. We present a practical analysis by describing all status of backlogged packest in buffers. Especially this paper focuses on the throughput-delay tradeoff and rejection probability. This analytical results are very close to the simulation results, for example, on the condition that bus type LAN consists of ten terminals, each possessing 1, 2, and 3 buffers.View full abstractDownload PDF (1320K) -
Shigeyoshi Nakajima, Kiyotsugu Satoh, Jiro Okamoto, Kazumi Yamashita1992 Volume 112 Issue 3 Pages 189-196
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSIn the problem of scheduling data flow computers, the optimization of scheduling needs much cost. The cost often increases in non-polynomial order as the number of the processing elements and tasks increases. Many studies have been tried to decrease the order. We have used Hopfield-type neural network model for this problem. We have achieved the reduction of calculation cost in proportion as the number of tasks and the number of processing elements. Our algorithm schedules flow graphs onto the data flow architectures. Our algorithm optimizes communication delays and parallel processing delays only on the critical path of the graph. So the result of our scheduling is more superior to therecent other studies which employs neural network models. Our method is so good at being processed in parallel for it employs neural networ model.View full abstractDownload PDF (820K) -
Takeo Miyata, Takeyuki Kobayashi, Masashi Ienaka, Kousuke Tsukamoto1992 Volume 112 Issue 3 Pages 197-198
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSDownload PDF (611K) -
Kazuhisa Matsuo, Takehiko Tomikawa, Toshimi Katayama1992 Volume 112 Issue 3 Pages 199-200
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSDownload PDF (751K) -
Tohru Takahashi, Yoshiro Tajima1992 Volume 112 Issue 3 Pages 201-202
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSDownload PDF (668K) -
Hyuk Lee1992 Volume 112 Issue 3 Pages 203-204
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSDownload PDF (459K) -
Seiichi Serikawa, Teruo Shimomura1992 Volume 112 Issue 3 Pages 205-206
Published: March 20, 1992
Released on J-STAGE: December 19, 2008
JOURNAL FREE ACCESSDownload PDF (624K)
- |<
- <
- 1
- >
- >|