Hirohide Ushida

Multilayered reasoning by means of conceptual fuzzy sets

The real world consists of instances of events and continuous numeric values, while people represent and process their knowledge in terms of symbols. Fuzzy sets provide a strong notation connecting the symbolic representation to the real world. In previously proposed Conceptual Fuzzy Sets (CFS), the meaning of a concept is represented by the distribution of activations of labels in a bidirectional associative memory. In particular, a multilayered structured CFS represents the meaning of the same concept as it is used in various expressions in each layer. The propagation of activations corresponds to reasoning. Therefore, we propose a multilayered reasoning method associated to a multilayered structured CFS, which has the following features: (1) capable of simultaneous symbolic and quantitative processing, (2) capable of simultaneous top‐down and bottom‐up processing. The effectiveness of the proposed method is illustrated by practical examples of decision regarding the amount of steering in the task of parking a car, and recognition of facial expressions for an image understanding system.

Conceptual fuzzy sets as a meaning representation and their inductive construction

Fuzzy sets provide a strong notation for representing real world concepts which are essentially vague. However they have problems caused by the restriction of numerical membership functions, restriction of logical expression, lack of context dependency, etc. These problems relate to the representation of the meaning of a concept. In this article, we propose Conceptual Fuzzy Sets (CFS), a new type of fuzzy sets which conform to Wittgensteins ideas (Philosophical Investigations, Basil Blackwell, Oxford, 1953) on concept meaning. A CFS is realized as an associative memory, combining a long‐term memory and a short‐term memory thus reducing the complexity of knowledge representation. In addition to solving the above problems CFS provide simple formula for knowledge representation and the procedure to use this knowledge. We introduce an inductive method for constructing CFS based on neural network learning. the effectiveness of CFS and of the learning method is illustrated through their application to the recognition of facial expressions.

Recognition of facial expressions using conceptual fuzzy sets

A facial expression is a vague concept that is difficult to describe explicitly. Conceptual fuzzy sets (CFSs), which have the ability to explicitly represent vague concepts, are realized using bidirectional associative memories, and a multilayer structured CFS represents the meaning of a concept by various expressions in each layer. Multilayered reasoning in CFS has the capability of simultaneous abstract and concrete representation and of simultaneous top-down and bottom-up processing. CFS has been applied to the recognition of facial expressions and shown to achieve context-sensitive recognition.<<ETX>>

Fuzzy-associative-memory-based knowledge construction with an application to a human-machine interface

A fuzzy knowledge construction method is proposed for application to human-machine interfaces. This paper considers a human movement estimation system to be one of the interfaces. This estimation system transforms human physical movements into qualitative linguistic labels. For example, the degrees of magnitude and speed of the physical movement are represented by qualitative words. It is difficult to construct the transformation knowledge because the relation between the movements and the labels is fuzzy. This paper proposes a method of constructing the knowledge. This proposed method uses a fuzzy associative memory organizing units system and is applied to estimating human sports movements. Experimental results show that the proposed method is suitable for application to human-machine interfaces.

Human-motion recognition via a fuzzy associative memory system

Human-motion recognition techniques so far present several problems, such as difficult knowledge representation and poor robustness. With the aim of achieving recognition of human motion in a robust way by using knowledge representation that is easy to be understood, this paper proposes a method utilizing a fuzzy associative memory system. In the proposed method, the fuzzy associative memory system embodies fuzzy inference rules which define motion patterns of characteristic states contained in the time-series pattern representing the motion. In the fuzzy associative memory system, inference is carried out with state transition patterns as input, and motion recognition is performed. The inference in the fuzzy associative memory system has the following two characteristics: (1) since knowledge can be represented as inference rules, it is easy to be understood by humans; (2) even in ambiguous situations or when part of the input information is missing, the information can be restored, or the degree of ambiguity can be controlled at inference time, etc., by the bidirectional processing of the conditional and action parts of the rules, so that appropriate inference results are obtained. In the proposed method, the time-series motion patterns are converted into state transition patterns, and by using an associative inference system with the aforementionedcharacteristics, it is possible to perform robust recognition. The effectiveness of the proposed method is demonstrated through on-line experimental results for the motion of nonspecific individuals.

Conceptual Fuzzy Sets Application to Facial Expression Recognition using Associative Memory System

Real world consists of a very large number of events and continuous numeric values. The concepts used in logical thinking process are essentially vague, since they are derived from generalization of these instances and numeric values. We have constructed Fuzzy Associative Memory Organizing Units System (FAMOUS) as a software package tool implemented on a Unix-workstation. In this paper, we realize previously proposed Conceptual Fuzzy Seis[3] (CFS) to represent vague concepts on FAMOUS, which are capable of context sensitive recognition based on fusion of bottom-up and top-down processing. We also discuss the representation and recognition of facial expressions as an illustrative example.

Associative memory based fuzzy inference

Over the past few years, a considerable number of studies have been done on fuzzy knowledge representation and inference using neural networks in order to develop a new type of fuzzy knowledge processing. This paper introduces a method of fuzzy inference based on associative memories, that is, fuzzy associative inference, and discusses its features.<<ETX>>

Associative memory based fuzzy knowledge construction and refinement

A construction method and a refinement method of fuzzy knowledge are proposed in order to apply them to intelligent multi-modal interfaces. This paper supposes that the interface requires the following three functions at least: 1) a function that constructs knowledge using instances instead of if-then rules; 2) a function that transforms mutually between the upper conceptual label represented by words and the lower conceptual label represented by physical values in order to realize multi-modality; and 3) a function that refines the knowledge using qualitative instruction such as a learning process. This paper proposes the methods using fuzzy associative memory organizing units system (FAMOUS) in order to realize these functions and applies them to estimation of human movements. Experimental results show proposed methods provide functions and are suitable to intelligent multi-modal.<<ETX>>

Fuzzy Associative Memory System and Its Application to Multi-Modal Interface

A construction method and a refinement method of fuzzy knowledge are proposed in order to apply them to intelligent multi-modal interfaces. This paper supposes that the interface requires the following three functions at least. 1) A function that constructs knowledge using instances instead of if-then rules. 2) A function that transforms mutually between the upper conceptual label represented by words and the lower conceptual label represented by physical values in order to realize multi-modality. 3) A function that refines the knowledge using macro qualitative instruction such as a human learning process. This paper proposes the methods using Fuzzy Associative Memory Organizing Units System (FAMOUS) in order to realize these functions and applies them to estimation of human movements. Experimental results show that the proposed methods provide the three functions and are suitable for application to intelligent multi-modal interfaces.

Human Sign Recognition Using Fuzzy Associative Inference System

The spotting recognition system is one system that recognizes human motion to a certain extent using moving images, it uses a dynamic programming method (Takahashi et al., 1993). This method, however, is limited because it is difficult to recognize the motions of unspecified people. This is because the system compares input patterns with standard patterns in its memory.