Fujitsu Corporation

Shohei Yamane

Hiroaki Yamada

Yoichi Kochibe

Takashi Yamazaki

Toshiyasu Ohara

Kotaro Ohori

Masatoshi Ogawa

Hiroaki Watanabe

Yusuke Oishi

Shingo Takahashi

Takashi Kobayashi

Hirokazu Anai

Takanori Ukai

The present invention relates to a machine learning program for causing a computer to execute a process. In an example, the process executed by the computer when the program is executed includes: acquiring a current distribution image by an equivalent circuit simulation based on circuit information; acquiring a shape image that indicates a shape of a circuit based on the circuit information; acquiring an EMI value by electromagnetic field analysis based on the circuit information; and generating an EMI prediction model by machine learning based on training data that includes the current distribution image, the shape image, and the EMI value.

Computer-readable recording medium storing machine learning program, information processing apparatus, and machine learning method

A radiated electromagnetic wave estimation is performed by a computer. The estimation process includes: converting a circuit diagram of an electronic circuit board into a combination of a plurality of partial circuits; and predicting radiated electromagnetic waves from the electronic circuit board by using a prediction result of a radiated electromagnetic wave for each of the partial circuits obtained by the converting.

Program storage medium, method, and information processing device for radiated electromagnetic wave estimation

A non-transitory computer-readable storage medium storing a n EMI calculation program that causes at least one computer to execute a process, the process includes inputting circuit information of a first circuit to a machine learning model; acquiring an EMI value at a certain frequency of the first circuit; selecting, based on an impedance characteristic of the first circuit and the EMI value at the certain frequency, first EMI information from a plurality of pieces of EMI information in each of which an impedance characteristic of each of a plurality of circuits is associated with EMI values at a plurality of frequencies of each of the plurality of circuits; and acquiring an EMI value at another frequency different from the certain frequency of the first circuit based on the EMI value at the certain frequency and the first EMI information.

Storage medium, EMI calculation method, and EMI calculation apparatus

An information processing apparatus calculates a value based on the lengths of wires included in inner layers selecting the inner layers other than outermost layers and layers adjacent to the outermost layers from among a plurality of layers included in circuit data. The information processing apparatus generates training data including first layer data corresponding to the patterns of the outermost layers, second layer data corresponding to the patterns of the layers adjacent to the outermost layers, and the value based on the lengths of the wires. The information processing apparatus trains a machine learning model by using the training data.

Machine learning method and computing system

An information processing apparatus specifies a first pattern indicating a first layer included in first circuit data. The information processing apparatus generates, based on first wiring included in a second pattern indicating a second layer that is adjacent to the first layer and a slit included in the first pattern, second circuit data by changing the first pattern to a third pattern including second wiring corresponding to the first wiring. The information processing apparatus generates, based on the second circuit data, training data for machine learning.

Training data generating method and computing system

An estimation method is performed by a computer for estimating a far field of electromagnetic waves or heat. The method includes: generating an emphasis pattern image obtained by emphasizing each target element of a pattern image of a target circuit by an emphasizing method that corresponds to a type of each target element, with respect to the target element which is at least a part of elements included in the target circuit; and estimating the far field of electromagnetic waves or heat radiated from the target circuit by an existing estimation model using the emphasis pattern image.

Non-transitory computer-readable storage medium storing estimation program, estimation device, and estimation method

A recording medium records a simulation program for causing a computer to execute a process including: arranging an agent, which has cognitive information and behaves in a virtual space based on the cognitive information, in the virtual space in which a plurality of guidance displays is set; when, with respect to each of the plurality of guidance displays, the agent enters within a first range of the respective guidance displays, and first guidance information corresponding to the first range is related with a destination of the agent, changing cognitive information up to the destination of the agent; and when, with respect to each of the plurality of guidance displays, the agent enters within a second range different from the first range, and second guidance information corresponding to the second range is related with the destination of the agent, changing cognitive information not directly related with the destination of the agent.

Recording medium recording simulation program, simulation method, and information processing device for people flow in sign system

A simulation method is performed by a computer by using an agent disposed in a virtual space. The method includes: controlling the agent so that the agent behaves in the virtual space under influence of each of a plurality of signs disposed in the virtual space; and determining the influence of each of the plurality of signs on the agent in accordance with an attribute relating to a display mode of the sign and an attribute of the agent.

Simulation program, simulation method, and simulation apparatus

A non-transitory computer-readable recording medium has stored therein a program that causes a computer to execute a process including: inputting, to each of a plurality of agents, a plurality of purchasing behavioral objectives, a first purchasing behavioral objective, and facilities information indicating a plurality of facilities corresponding to the plurality of purchasing behavioral objectives; and causing each of the plurality of agents to determine, based on a condition that has been set in accordance with a facility search behavior with respect to a facility that is selected from the plurality of facilities in response to the purchasing behavioral objective of each of the plurality of agents at a time of execution of simulation, a second purchasing behavioral objective of each of the plurality of agents from among the plurality of purchasing behavioral objectives.

Computer-readable recording medium, simulation method, and simulation apparatus

An information processing apparatus includes a memory and a processor. The processor is configured to receive an input physical quantity, a value of the input physical quantity, and an output physical quantity. The processor is configured to generate a first array of first conversion operations or a second array of second conversion operations by using conversion rules each for converting a value of a source physical quantity into a value of a target physical quantity. Each conversion operation is a conversion according to a conversion rule or a reverse operation thereof. The first array enables a conversion of the input physical quantity into the output physical quantity. The second array enables the reverse. The processor is configured to convert the received value of the input physical quantity into a value of the output physical quantity by using the first array or the second array.

Growing community of inventors

Kawasaki, Japan

Shohei Yamane