Abstract: A machine learning model, in which core tensors are generated, is trained by a computer. The computer performs a process including: extracting, from a plurality of items of pseudo training data generated from a plurality of items of training data for the machine learning model, a plurality of items of determined pseudo training data that are determined as pseudo training data that promotes training of the machine learning model; and training the machine learning model by using the plurality of items of determined pseudo training data.

Abstract: An image forming apparatus includes first storage, a writing controller, a reading controller, a conveyance section, a detector, and a main controller. The conveyance section conveys a recording medium. The detector detects an overrun. Write addresses are designated in a predefined sequence from among addresses. Read addresses are designated in the predefined sequence from among the addresses. The writing process and the reading process are performed in storage areas included in the first storage in a first order. The overrun indicates that the writing and reading processes are performed in the storage areas included in the first storage in a second order that is opposite to the first order. While the conveyance section conveys the recording medium, the main controller controls the writing controller or the reading controller based on a detection result of the detector.

Abstract: An authentication system, is provided, which includes a control device configured to confirm validity of using a program installed in the control device by confirming whether identification information of the control device satisfies a given condition, and to confirm whether the target device having a function to be used by the control device falls under a valid range of use based on device restriction information that indicates a restriction on the target device permitted to be used and is stored in the control device.

Abstract: An image forming apparatus includes a controller. The controller generates page images of one or more pages by performing image processing on acquired input image data. The controller determines a job generation method to be either a first method or a second method. The job generation method is a method through which print job data is generated. The first method is a method through which the print job data is generated based on page image data indicating a page image of one page among the one or more pages upon completing the image processing on the page image of the one page. The second method is a method through which the print job data is generated based on the page image data of all pages included in the output image after completing the image processing on the page images of all the pages included in the output image.

Abstract: A non-transitory computer-readable storage medium storing a control program for causing a computer to execute for acquiring, from a sensor, multiple monitored values in multistep processes including a process related to fermentation of microbes; setting probability distributions for multiple specific parameters related to unmonitored data and included in multiple parameters included in a nonlinear mathematical model related to the fermentation of the microbes corresponding to the multistep processes; generating monitoring predicted values at next monitoring time of the mathematical model based on the multiple monitored values and the probability distributions; using a distribution of the monitoring predicted values and values monitored at the next monitoring time to update the multiple parameters; and controlling the mathematical model so that errors of the multiple specific parameters generated using the mathematical model including the updated multiple parameters are reduced.

Abstract: A non-transitory computer-readable recording medium stores a program that causes a computer to execute a process including: inputting input data including one or more records that have one of a plurality of formats, each of the plurality of formats including a plurality of items; generating conversion data by generating an integrated record having an integrated format from the one or more records; and causing a learner to execute a learning process using the conversion data as input tensor, the learner performing deep learning by performing tensor decomposition on input tensor.

Abstract: A non-transitory computer-readable recording medium stores a program that causes a computer to execute a process including: inputting input data generated from a plurality of logs, the input data including one or more records that have a plurality of items; generating conversion data by complementing, regarding a target record, included in the input data, in which one or more values in the plurality of items has been lost, at least one of the one or more lost values by a candidate value; and causing a learner to execute a learning process using the conversion data as input tensor, the learner performing deep learning by performing tensor decomposition on input tensor.

Abstract: This image forming device is provided with: an image reading unit; a control unit which generates distribution data indicating the distribution of an angle of inclination of documents (D) read during a pre-determined time period, performs a test to determine whether there is a significant difference between the distribution data and standard distribution data, and on the basis of the test result determines whether maintenance of the image forming device is required; and a communication unit which, if it has been determined that maintenance is required, transmits a maintenance request notification to a service system.

Abstract: A return-to-harbor notifying device is provided, which may include a user interface and processing circuitry. The user interface may receive an information related to a planned time of arrival at a home harbor that is a location to which a ship returns. The processing circuitry may generate a traveling route upon returning to the harbor, calculate a required time for traveling from a current location of the ship to the home harbor based on the traveling route, calculate a return-to-harbor start time of the ship based on the required time and the information related to the planned time of arrival, and notify a content based on the return-to-harbor start time.

Abstract: A traveling route generating device is provided, which may include a user interface and processing circuitry. The user interface may receive a home route that is a route on which a ship travels upon departing from a home harbor or upon returning to the home harbor, the home harbor being a location from which the ship departs. The processing circuitry may generate a traveling route between one of a destination of the ship and a current location of the ship, and a location on the home route.

Abstract: This image forming device is provided with: an image reading unit; a control unit which generates distribution data indicating the distribution of an angle of inclination of documents (D) read during a pre-determined time period, performs a test to determine whether there is a significant difference between the distribution data and standard distribution data, and on the basis of the test result determines whether maintenance of the image forming device is required; and a communication unit which, if it has been determined that maintenance is required, transmits a maintenance request notification to a service system.

Abstract: An authentication system, is provided, which includes a control device configured to confirm validity of using a program installed in the control device by confirming whether identification information of the control device satisfies a given condition, and to confirm whether the target device having a function to be used by the control device falls under a valid range of use based on device restriction information that indicates a restriction on the target device permitted to be used and is stored in the control device.

Abstract: An image processing apparatus includes a print processing portion, a first determination portion, a first determination target excluding portion, and a print color mode switching portion. The first determination portion determines, for each page of the document sheets, whether or not each of a plurality of divided areas is of a color type that is different from the print color mode. The first determination target excluding portion excludes divided areas that are determined as being of a color type that is different from the print color mode in a first set number or more of pages of the document sheets, from determination targets of the first determination portion from then. The print color mode switching portion is able to switch the print color mode during the print process when the number of divided areas that are the determination targets of the first determination portion becomes a predetermined number or smaller.

Abstract: An image processing apparatus includes a print processing portion, a first determination portion, a first determination target excluding portion, and a print color mode switching portion. The first determination portion determines, for each page of the document sheets, whether or not each of a plurality of divided areas is of a color type that is different from the print color mode. The first determination target excluding portion excludes divided areas that are determined as being of a color type that is different from the print color mode in a first set number or more of pages of the document sheets, from determination targets of the first determination portion from then. The print color mode switching portion is able to switch the print color mode during the print process when the number of divided areas that are the determination targets of the first determination portion becomes a predetermined number or smaller.