|
1. |
One‐dimensional processing architecture for gray‐scale morphology |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 1-9
Shiji Kojima,
Tatsuo Miyakawa,
Preview
|
PDF (704KB)
|
|
摘要:
AbstractMathematical morphology is logically very clear, and has many applications because of its adaptability. They are two types of morphology — binary and gray‐scale. The mathematical base of binary morphology is expressed in logical AND/OR notation. Gray‐scale morphology is based on the addition and comparison of gray‐scale values. However, in this type of processing, the computational cost is proportional to the area of both the original image and the structuring element. Therefore, the computational cost increases very rapidly when a large‐scale structuring element is required. For this reason, specialized architecture, e.g. a Cytocomputer, had been built for fast morphological processing, but large‐scale structuring elements are difficult to build by this method because it requires a large number of devices. In this paper, we describe an efficient architecture for gray‐scale morphological processing, in which we decompose the gray‐scale structuring element to one dimension, thereby efficiently reducing computational cost. We also propose the architecture for a pipelined parallel processor that calculates the gray‐scale dilation. This method greatly reduces the size of the hardware and maximizes the
ISSN:0882-1666
DOI:10.1002/scj.4690271201
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
2. |
Ionic current model of the retinal photoreceptor and simulation analysis of the photoresponses |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 10-21
Toshihiko Ogura,
Shiro Usui,
Yoshimi Kamiyama,
Preview
|
PDF (933KB)
|
|
摘要:
AbstractThe fact that the reception of optical information by the retinal photoreceptor and the process of its transformation to the membrane voltage response are due to an interaction between the photocurrent from the outer segment and each ionic current in the inner segment has been confirmed by many physiological experiments. However, the properties of each ionic current in the photoreceptor have not been clear since no physiologically reliable model of the retinal photoreceptor has been constructed.This paper proposes a model of a retinal photoreceptor, which is a combination of the outer segment model (devised by Torre et al.) and the inner segment model (devised by the present authors). It has been confirmed that this model can accurately represent the electron physiological properties of a retinal photoreceptor. Using this model simulation, the relationship between the photocurrent and the photoresponse dynamics, and an oscillatory phenomena caused by a strong light flash have been analyzed. The results show that the dynamic and nonlinear response characteristics of a retinal photoreceptor are due to the interactions between the nonlinear ionic current in the inner segment and the mechanism of the intracellular calcium.
ISSN:0882-1666
DOI:10.1002/scj.4690271202
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
3. |
Comparative study of searching method in recurrent neural networks |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 22-32
Kunio Yokoi,
Kazutoshi Gouhara,
Yoshiki Uchikawa,
Preview
|
PDF (894KB)
|
|
摘要:
AbstractThe off‐line learning with a supervisor in the recurrent neural network can be considered as the minimum search on the surface (called learning surface) formed by the evaluation functions. The learning surface in the search has a characteristic shape, and the authors are proposing the valley searching method, based on the global shape of the learning surface.As the search for the minimum, various methods, such as the steepest descent (gradient) and the conjugate gradient methods, often are employed. The relation between the search method and the characteristic shape of the learning surface has not been clarified and it has been difficult to assess quantitatively the usefulness of the searching methods.From such a viewpoint, this paper considers three methods, i.e., the method of steepest descent, the conjugate gradient method, and the valley searching method, and analyzes the relation between the searching method and the learning surface. It is experimentally shown based on the result of simulation that the valley searching method is better. More precisely, the parameter dependencies of the searching method on the learning curve and the searching process are examined experimentally, and it is shown that the parameters are set more easily in the valley searching method than in other methods. It is also shown that the valley searching method is better also in terms of the convergence time and the dependency on the initial valu
ISSN:0882-1666
DOI:10.1002/scj.4690271203
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
4. |
Text understanding using a two‐dimensional spatial imagery |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 33-52
Motoyuki Itoh,
Shin Kubo,
Yukihiro Itoh,
Preview
|
PDF (1735KB)
|
|
摘要:
AbstractThis paper describes the framework of a system that can understand a textbook for machine operation, based on the model of an object world that can retain informations not only by symbolic representation but also by image. In any understanding of the description for machine operation, spatial information is important, and there must be a model that can retain the informations with natural reflection of the continuity and relative location, independently of the particular point of observation. Such a representation is difficult, dealing only with the symbolic knowledge representation used in the conventional language understanding system. From such a viewpoint, this paper notes the usefulness of the representation by the image and proposes the imagery object world model, which can utilize partially the properties of the image, using mathematical expressions in a two‐dimensional real coordinate system. Mechanisms both to execute the simulation on the proposed model and to read the text using the simulation mechanism, are investigated. A system is constructed experimentally based on the proposed idea, which can construct the model for the input sentence, while executing a simulation and generating symbolic recognition expressions. With those functions, the identity or the similarity of the language expressions derived from the same object or event from different viewpoints, can adequately be decide
ISSN:0882-1666
DOI:10.1002/scj.4690271204
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
5. |
Associative image retrieval using knowledge in encyclopedia text |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 53-62
Ikuo Keshi,
Hiroshi Ikeuchi,
Ken'Ichi Kuromusha,
Preview
|
PDF (1813KB)
|
|
摘要:
AbstractApplying existing keyword retrieval to image retrieval causes some problems. Among them, database developers must describe photograph contents in detail and adequate retrieval is difficult. These problems have been resolved by developing an associative retrieval technology using not keywords but semantic vectors as a retrieval method with an associative function such as a human being possesses. A semantic vector dictionary of more than 100,000 words was made from encyclopedia text. This paper explains the experimental image retrieval system for 36,000 photographs with the semantic vector dictionary made from the encyclopedia text. This system associates the words input by a user with the knowledge in the encyclopedia text and outputs ranked retrieval results. The effectiveness of this associative retrieval method is confirmed by evaluating content retrieval of images by a small benchmark and making an adaptive learning function of semantic vectors in the case in which a retrieval result is not the same as a user's subjective perspective would impose.
ISSN:0882-1666
DOI:10.1002/scj.4690271205
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
6. |
Communication computation model for modeling dynamic human communication |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 63-72
Masahiro Hiji,
Masatoshi Miyazaki,
Hiroshi Nunokawa,
Preview
|
PDF (828KB)
|
|
摘要:
AbstractA communication computation model for modeling human communication is proposed. In this computation model, an individual communicator is represented by an Autonomous Object and a group communicator is represented by a Group Field. The mode of communication is represented by the communicative functions appropriate to each mode.A method is described for modeling the dynamic character of communication while changing among these various communication types. The dynamic character of communication is described as the selection of the communicative function corresponding to the mode of communication as well as the resultant information exchanges. A communication process is described as a combination of these communicative functions.
ISSN:0882-1666
DOI:10.1002/scj.4690271206
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
7. |
Program slicing using a path dependence flow graph |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 73-91
Kuniaki Naoi,
Naohisa Takahashi,
Preview
|
PDF (1344KB)
|
|
摘要:
AbstractA method that formally represents various program slices with a unified framework is presented; it uses a previously proposed directed graph called a path dependence flow graph (PDFG). Program slicing is a technique of extracting a set of statements (called slices) with certain desired features from an imperative program. The method proposed here has the following properties. (1) Since slices are represented by operations on dependence relationships defined on a PDFG, properties of slices such as an inclusion relationship among slices can be discussed independently of slicing procedures. (2) Since various slices are represented with the same framework, appropriate slices can be selected for specific purposes using one representation. (3) Since slices are generalized using orthogonal primitive attributes, slices can be represented comprehensively; this includes the ones for which there have been no known construction methods. It is also proven herein that major known slices and the slices represented by this method are identical as a set of statements, thereby demonstrating the appropriateness of this proposed method.
ISSN:0882-1666
DOI:10.1002/scj.4690271207
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
8. |
Optimization methods for look‐up table‐type FPGAs based on permissible functions |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 92-101
Shigeru Yamashita,
Yahiko Kambayashi,
Sabura Muroga,
Preview
|
PDF (707KB)
|
|
摘要:
AbstractRecently, due to remarkable technological developments and because their logic can be modified flexibly and easily, Field Programmable Gate Arrays (FPGAs) have increasingly been applied to hardware prototyping and the design of restructurable computer architectures. For this reason, it is highly necessary to establish logic design techniques for FPGAs.This paper describes methods for optimizing the circuits mapped in look‐up table‐type FPGAs. These methods apply the concept of permissible functions from the transduction method, which is a logic circuit optimization technique based on design improvement, and attempt to reduce the degree of redundancy. The following two methods were investigated: 1) reducing the number of blocks by using a logic block to replace another; and 2) together with replacing logic blocks, modifying the internal logic that implements a logic block as long as the outputs are not affected. Although the latter generally is more flexible, the former requires less processing time and sometimes produces better results. The effectiveness of these methods is demonstrated by showing that the degree of redundancy was reduced by about 9 percent when the methods were applied to circuits mapped in look‐up table‐type FPGAs. The methods proposed in this paper can also be applied to designs using standard cells and gate
ISSN:0882-1666
DOI:10.1002/scj.4690271208
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
9. |
Obstacle avoidance travel control of robot vehicle using neural network |
|
Systems and Computers in Japan,
Volume 27,
Issue 12,
1996,
Page 102-112
Minoru Kodaira,
Teruhiko Ohtomo,
Atsushi Tanaka,
Masami Iwatsuki,
Takao Ohuchi,
Preview
|
PDF (1024KB)
|
|
摘要:
AbstractThis paper describes an intelligent travel control algorithm for a mobile robot vehicle using neural networks, and proposes a method that realizes path planning and generation of motion commands simultaneously. Smooth moving trajectories are controlled by the outputs of cascaded identification modules that have learned the dynamic characteristics of a mobile robot vehicle with strong nonlinearities of both driving force and steering angle. A system is adopted that mutually transforms the absolute coordinate and dynamic coordinate. Because a consequence of the coordinate transformation in this system is that the dynamic position values are normally zero, it is possible to reduce greatly the number of training patterns and, at the same time, to be able to construct an environment similar to that in which a human being drives a vehicle. A travel control system, by which a mobile robot vehicle can move on a smooth traveling path and avoid obstacles, is created by introducing a danger function as an expression of static and dynamic obstacles in an unstructured environment. Finally, the validity of the proposed travel control system is confirmed by computer simulations.
ISSN:0882-1666
DOI:10.1002/scj.4690271209
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1996
数据来源: WILEY
|
|