Denso Corporation

Masahiko Tateishi

Shinichi Tamura

Takayoshi Kawai

Katsuhiko Samukawa

Kunio Yokoi

Combined control patterns corresponding to the actual control coordinates point (px) are formed by morphing a shape of the model control patterns PA, PB, PC having J pieces and corresponding to each morphing coordinates (pa, pb, pc), in the control pattern space CPS extended by the second type of input variable &#x3b2; and the output variable &#x3b1;. The morphing is performed according to weight between the morphing coordinates (pa, pb, pc) in the M-dimensional input space MPS and the actual control coordinates point (px). Combined control patterns Px are formed, and output variable value &#x3b1; corresponding to the input value (px) based on the combined control pattern Px is calculated.

Method and device for controlling equipment based on multiple-input/one-output control

A voice recognition unit recognizes a recognition word code corresponding to a speech uttered by a user along with a command code for executing a function of a control object. A function execution unit executes a function corresponding to the command code from the voice recognition unit. A message outputting unit extracts a recognition word corresponding to the recognition word code from a recognition word storing unit, and generates a message properly utilizing the extracted recognition word. The generated message is notified to the user via a display or a speaker, so that the user can confirm that the uttered speech is adequately recognized.

Voice control system notifying execution result including uttered speech content

A controlled variable-calculating apparatus and method that can easily calculate a controlled variable from one or more input variables and that can appropriately learn control characteristics for the calculation of the controlled variable. The control characteristics are represented as a surface embedded in an (n&plus;1)-dimensional space, and are used to control one controlled variable from n variables. The control characteristics are approximated by an assemblage of flat planes corresponding to subspaces obtained by dividing an n-dimensional input space. For example, a two-dimensional input space defined by the interior temperature and the amount of sunlight is divided into 15 subspaces. Flat planes are made to correspond to the subspaces, respectively. If the interior temperature and the amount of sunlight are entered, a decision is made as to which subspace the environmental conditions belong. The airflow is then calculated using an equation for any one of the flat planes . If the airflow is needs to be modified, the equation for the flat plane corresponding to the corresponding subspace is updated.

Apparatus and method for calculating an air-conditioning system controlled variable

A verification method and a verification apparatus of a neural network for guaranteeing the operation of the neural network to any input signals which might be inputted. The neural network verification apparatus comprises a data file storage section for storing a verification data file DFK concerning on the structure of the neural network to be verified, a network structuring section for structuring a neural network NET to be verified by reading the neural network data file DFN from the data file storage section, an input data generating section for generating initial interval input vector database DBI by reading the verification data file DFK from the data file storage section, a verification executing section for executing the verification of the neural network NET based on the neural network NET structured by the network structuring section and the initial interval input vector database DBI created by the input data generating section and for generating a verification result database DBO based on the verification result, and others. The verification apparatus generates an interval input vector signal per input signal subspace which is obtained by dividing an input signal space formed by the input signal to the neural network NET into a plurality of input. signal subspaces and accumulates them in a stack.

Verification method of neural network and verification apparatus thereof

A signal extraction system for extracting one or more signal components from an input signal including a plurality of signal components. This system is equipped with a neural network arithmetic section designed to process information through the use of a recurrent neural network. The neural network arithmetic section extracts one or more signal components, for example, a speech signal component and a noise signal component from an input signal including a plurality of signal components such as a speech and noises and outputs the extracted signal components. Owing to the presence of this neural network arithmetic section, the signal extraction becomes possible with a high accuracy.

Growing community of inventors

Nagoya, Japan

Masahiko Tateishi