Multi-sensor integration system based on fuzzy inference and neural network for industrial application

Fukuda, Toshio; Shimojima, Koji; Arai, Fumihito; Matsuura, Hideo

doi:10.1109/fuzzy.1992.258778

Cited by 12 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, PM is not affected by the variation of the outlier and the EOMF method meets both robustness requirements for MOM defuzzification. Equation (9) shows that the most likely position can be affected by the outlier and Eq. (1 1) shows that the most likely position of the EOMF changes by a small amount due to small variation of the outlier and the EOMF method meets the first robustness requirement for COG defuzzification.…”

Section: Robustness Of the Eomf Methodsmentioning

confidence: 99%

Adaptive data fusion using the expected output membership function

Choi

Dickerson

1999

SPIE Proceedings

View full text Add to dashboard Cite

Fuzzy set methods can improve the fusion of uncertain sensor data. The expected output membership function (EOMF) method uses the fuzzified inputs and possible fuzzy outputs to estimate the fused output. The most likely fuzzy output comes from fusability measures which are calculated using the degrees of the intersections of the possible fuzzy outputs with the fuzzified inputs. The support lengths of the fuzzified inputs can be set proportional to the sensor variance in the fixed case. However, individual measurements can deviate widely from the true value even in accurate sensors. The support length of input sets can be varied by estimating the variation of the input. This adaptation helps deal with occasional bad or noisy measurements. The variation is defined as the absolute change rate of the input with respect to previous output estimates. The EOMF can also be too wide or too narrow compared to the fuzzified inputs. Adaptive methods can help select the size of the EOMF. An example from the control of automated vehicles shows the effectiveness of the adaptive EOMF method, compared to the fixed EOMF method and the weighted average method. The EOMF method shows robustness to outlying measurements when the average fusion operator is used.

show abstract

Section: Robustness Of the Eomf Methodsmentioning

confidence: 99%

Adaptive data fusion using the expected output membership function

Choi

Dickerson

1999

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…We use a fuzzy set based approach because fuzzy sets can model uncertainty well. Most existing fuzzy data fusion methods use fuzzy inference techniques that use if-then rules to fuse information [5][6][7][8][9]. However, it is often difficult to choose effective if -then rules.…”

Section: Objectives and Motivationmentioning

confidence: 99%

“…The adaptive EOMF method used Product/COG defiizzification set. Plot of proportionality constant (C/) versus increment(5). The adaptive EOMF method used Product/COG set 39.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Data fusion using expected output membership functions

Choi

View full text Add to dashboard Cite

show abstract

“…To solve these problems, we proposed an automated carving system with an integrated measurement system [3]. The system measured each target's surface shapes with the measuring system and made the carving path from the measurement data.…”

Section: Introductlonmentioning

confidence: 99%

Sensor integration system utilizing fuzzy inference with LED displacement sensor and vision system

Shimojima

Fukuda

Arai

et al.

[Proceedings 1993] Second IEEE International Conference on Fuzzy Systems

Self Cite

View full text Add to dashboard Cite

This paper deals with a 3-D measurement system applied to a curved metal surface carving system, and a multi-sensor integration system based on fuzzy inference. The measurement system consists of two different sensors, a LED displacement sensor and a vision system. The LED displacement sensor is used as a part of the vision system based on the active stereo sensing method. In addition, the LED displacement sensor's outputs are used for calibrating camera parameters. Therefore, the system can calibrate the camera parameters easily. Neural networks are used to compensate the output of the image processing for some errors, such as camera parameter's error and lens distortion. By utilizing the neural network, we can use a vision system as accurately as possible. We use a sensor integration method based on the fuzzy inference. Fuzzy inference's input consists of information on the change in the sensor output and the position change of the sensor system, together with the environmental data of measurement. For this integration system, we can use the sensory system accurately. The proposed system is shown to be effective through extensive experiments.

show abstract

Multi-sensor integration system based on fuzzy inference and neural network for industrial application

Cited by 12 publications

References 7 publications

Adaptive data fusion using the expected output membership function

Adaptive data fusion using the expected output membership function

Data fusion using expected output membership functions

Sensor integration system utilizing fuzzy inference with LED displacement sensor and vision system

Contact Info

Product

Resources

About