In this paper, we propose the ensemble prediction method by using Self-Organizing-Maps (SOM) with the prediction reliability measurements. Splitting the training data to several groups, creating maps, and testing about each other groups obtained the prediction reliability measurements. Another group tested the map of certain group, and then the values (codebook vectors) of the tested nodes were evaluated. Collecting the nodes value and the reliability measurements about tested nodes, and inputting the values as new training data to SOM, then the map with prediction reliability measurements was obtained. Furthermore, difference models were able to create by setting various priority factors (weight) of the variables. The ensemble prediction was carried out by prediction values of these models.

View full abstract

This paper deals with an autonomous control and a remote control for a fuzzy navigation of an intelligent wheelchair (i.e. an electric wheelchair). This control system has two computers, a host machine set on the wheelchair and a remote machine set on the nurse center. This wheelchair is controlled by the operation commands, such as "turn right", "turn left", and "go straight" that are orders from a remote computer. Also, that is navigated to goals by the fuzzy navigation rule sets implemented on a host computer and autonomously runs toward a target (reference) point. This control system has two algorithms for a navigation control. One is a global navigation control. Other is a local navigation control. The difference in the algorithms is the navigation planning area. Furthermore, we employed a predictive fuzzy driving control. This aim is that an avoidance control is realized by the predictive control. The signals between the local computer (host) and the remote computer are communicated on non-wired broadband.

View full abstract

Direct responding DATAbase to human thinking has not been contrived. Because it is extremely difficult for a computer to detect a parson's thought. While for a human, the correct spelling is sometime difficult to input to computer, however, if slant-fitting theory in imagined matrix was applied, computer became possible to defuzzyfy a fuzzy word to a correct or a few resembled words. A line of a sentence search in the DATA base using fuzzy search targeting theory made the computer more a like human and increased the quality of computer DATA base. This looked as if computer imaged scientific definite descriptions like a human by input words.

View full abstract