公开(公告)号：US20220068181A1

公开(公告)日：2022-03-03

申请号：US17423237

申请日：2020-01-20

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Kazunori WATANABE ,  Susumu KAWASHIMA ,  Masataka SHIOKAWA ,  Daisuke KUBOTA ,  Jiro IMADA ,  Katsuki YANAGAWA ,  Koji KUSUNOKI

IPC: G09G3/20

Abstract: A functional panel is provided. The functional panel includes a first driver circuit, a second driver circuit, and a region. The first driver circuit supplies a first selection signal, the second driver circuit supplies a second selection signal and a third selection signal, and the region includes a pixel. The pixel includes a first pixel circuit, a light-emitting element, a second pixel circuit, and a photoelectric conversion element. The first pixel circuit is supplied with the first selection signal, the first pixel circuit obtains an image signal on the basis of the first selection signal, the light-emitting element is electrically connected to the first pixel circuit, and the light-emitting element emits light on the basis of the image signal. The second pixel circuit is supplied with the second selection signal and the third selection signal in a period during which the first selection signal is not supplied, the second pixel circuit obtains an imaging signal on the basis of the second selection signal and supplies the imaging signal on the basis of the third selection signal, and the photoelectric conversion element is electrically connected to the second pixel circuit and generates the imaging signal.

公开(公告)号：US20200051211A1

公开(公告)日：2020-02-13

申请号：US16500535

申请日：2018-04-09

Applicant: Semiconductor Energy Laboratory Co., Ltd.

Inventor： Masataka SHIOKAWA ,  Kei TAKAHASHI ,  Yuji IWAKI ,  Hiromichi GODO

IPC: G06T3/40 ,  G06T5/00

Abstract: An image processing method that generates high-resolution image data from low-resolution image data and an image receiving apparatus that is operated by the image processing method are provided.In the image processing method that generates high-resolution image data from low-resolution image data, the low-resolution image data is divided to generate a plurality of first image data, among the plurality of first image data, one of two adjacent image data is second image data, and the other is third image data. Surroundings of the second image data are supplemented with pixel data to generate fourth image data. The pixel data includes part of the third image data. A convolutional neural network using the fourth image data as an input is implemented, fifth image data is output from the convolutional neural network, and a plurality of the fifth image data is combined to generate high-resolution image data. The image receiving apparatus is operated by the image processing method.

公开(公告)号：US20210116511A1

公开(公告)日：2021-04-22

申请号：US17050388

申请日：2019-04-12

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Ryota TAJIMA ,  Akihiro CHIDA ,  Masataka SHIOKAWA

IPC: G01R31/367 ,  G01R31/3842 ,  H01M10/48 ,  H01M10/42 ,  H02J7/00

Abstract: A capacity measurement system of a secondary battery that estimates an SOC with high estimation accuracy in a short time at low cost is provided. The capacity measurement system of a secondary battery is an estimation system of a state of charge of a power storage device that includes a unit for acquiring time-series data of a voltage measured value and a current measured value of a first power storage device; a unit for normalizing the time-series data of the voltage measured value; a unit for normalizing the time-series data of the current measured value; a database creation unit for creating a database where an SOC of the first power storage device is linked to superimposed data of time-series data of a time axis corresponding to a vertical axis and time-series data of a time axis corresponding to a horizontal axis; and a neural network unit where a neural network is constructed using the database created in advance as learning data, superimposed data of time-series data of a time axis corresponding to a vertical axis and time-series data of a time axis corresponding to a horizontal axis of a second power storage device is input, and an estimated SOC value of the second power storage device is output.

公开(公告)号：US20200242730A1

公开(公告)日：2020-07-30

申请号：US16636705

申请日：2018-08-23

Applicant: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.

Inventor： Masataka SHIOKAWA ,  Yuki TAMATSUKURI

IPC: G06T3/40 ,  H04N7/01

Abstract: A semiconductor device which performs upconversion without a large amount of learning data is provided. The semiconductor device increasing the resolution of a first image data to generate a high-resolution image data. It includes the first step of generating a second image data by decreasing the resolution of the first image data, the second step of generating a third image data having a higher resolution than the second image data by inputting the second image data to a neural network, the third step of calculating an error for the third image data relative to the first image data by their comparison, and the fourth step of modifying a weight coefficient of the neural network on the basis of the error; and then the high resolution image data is generated by inputting the first image data into the neural network after a prescribed number of the second to fourth steps.