Abstract: The present invention provides a data analysis system capable of performing analysis appropriately using a CNN model while reducing communication traffic. A data analysis system 90 includes: an instrument 10 that performs a conversion process of outputting compression data obtained as a result of processing observation data received via an input layer of a learned neural network 18A using portions ranging from the input layer to a predetermined intermediate layer; and a device 20 that performs an analysis process of inputting the compression data to a subsequent intermediate layer in a learned neural network 18B, inputting data obtained by decoding the compression data, which is an output of the subsequent intermediate layer, to an output layer configured using a CNN model, and obtaining an analysis result of the observation data as an output of the output layer.

Abstract: A computer executes: a learning procedure of learning a model for estimating an addition mode of a symbol representing a state of a person in a video to the video on the basis of learning data indicating the addition mode of the symbol to the video; and an addition procedure of estimating the addition mode of the symbol to the video of a web conference using the model learned and adding the symbol to the video in the addition mode estimated, thereby increasing an amount of information that can be grasped from the video.

Abstract: A position where a user is located can be estimated easily and quickly. When a hold detection unit 122 detects that the user holds a mobile terminal 100 by hand to use the mobile terminal 100 that is held by at least one hand of the user when used by the user and has a camera 130 on the surface facing the ceiling when used by the user, the estimation unit 240 estimates a position where a ceiling is located as the position where the user is located by using an image of the ceiling captured by the camera 130.

Abstract: A barrier data collection device includes a unit estimation unit that estimates, based on sensor data with position information including height at a time when a mobile body including a flying mobile body moving in the air moves, the sensor data being collected in advance about each of geographical ranges, with an estimator, about each of sets of the geographical ranges and heights included in the sensor data in a predetermined time unit, a barrier state obtained by estimating a state of which of barrier types the set is, a shape estimation unit that estimates, about a set satisfying a condition among the sets, a barrier shape based on the sensor data and an estimation result of the barrier state estimated about each of the sets in the time unit, and a barrier estimation unit that estimates, based on the estimation result of the barrier state estimated about the each of the sets, the estimated barrier shape, and a correct answer ratio of the estimator calculated in advance, a probability for each of the barri

Abstract: To make it possible to generate, at low cost, learning data for accurately estimating a state. A first learning unit 103 learns a generation model based on a set of first learning data to which a first correct answer label and a second correct answer label are given, the first correct answer label indicating a correct answer about any one of a plurality of conditions, the second correct answer label indicating a predetermined state, the generation model outputting, when data to which the second correct answer label is given is input, data to which the first correct answer label indicating any one of the plurality of conditions is given.

Abstract: A generalized data generation device and estimation device, a generalized data generation method and estimation method, and a generalized data generation program and estimation program are provided, which are capable of estimating the state of a target object accurately with the amount of training data being reduced.

Abstract: A training data generation apparatus (10) according to the present invention includes a noise determination unit (11) that determines whether or not training data that is to be used in machine learning includes noise, and a noise addition unit (12) that generates new training data by adding noise to training data that has been determined by the noise determination unit (11) as not including noise.

Abstract: It is possible to learn a model for accurately estimating a label indicating the condition of data. A first model for determining, for each label, the likelihood of the label is learned, time-series likelihood data that is the likelihood of each label at each time is output for each piece of learning data, the time-series likelihood data for each piece of the learning data given a correct label is input, and machine learning is performed to learn a second model for outputting one of the labels based on a change in the likelihood of each label.

Abstract: The present invention provides a data analysis system capable of performing analysis appropriately using a CNN model while reducing communication traffic. A data analysis system 90 includes: an instrument 10 that performs a conversion process of outputting compression data obtained as a result of processing observation data received via an input layer of a learned neural network 18A using portions ranging from the input layer to a predetermined intermediate layer; and a device 20 that performs an analysis process of inputting the compression data to a subsequent intermediate layer in a learned neural network 18B, inputting data obtained by decoding the compression data, which is an output of the subsequent intermediate layer, to an output layer configured using a CNN model, and obtaining an analysis result of the observation data as an output of the output layer.

Abstract: It is possible to learn a model for accurately estimating a label indicating the condition of data. A batch size, which is a unit of learning data used in machine learning, is set to a predetermined size, learning data having the batch size in a learning data set is used to learn a first model for determining, for each label, the likelihood of the label, and time-series likelihood data that is the likelihood of each label at each time is output for each piece of the learning data. The time-series likelihood data for each piece of the learning data given a correct label is input, the batch size is set to a size larger than the predetermined size in a first learning unit 24, and machine learning is performed to learn a second model for outputting one of the labels based on a change in the likelihood of each label.

Abstract: A learning apparatus (10) according to the present invention includes: a normalization/standardization unit (13) that performs normalization or standardization on data detected by a plurality of types of sensors; and a learning unit (14) that builds a model by performing machine learning, using, as training data, the detected data on which normalization or standardization has been performed by the normalization/standardization unit (13). The normalization/standardization unit (13) performs normalization or standardization for each type of sensor, on the data detected by the sensor.

Abstract: A position where a user is located can be estimated easily and quickly. When a hold detection unit 122 detects that the user holds a mobile terminal 100 by hand to use the mobile terminal 100 that is held by at least one hand of the user when used by the user and has a camera 130 on the surface facing the ceiling when used by the user, the estimation unit 240 estimates a position where a ceiling is located as the position where the user is located by using an image of the ceiling captured by the camera 130.

Abstract: A training data generation device (10) according to the present invention includes a training data correction unit (11) configured to correct training data that is time-series data that indicates states of an object and in which a label corresponding to a state of the object is assigned to each section that corresponds to the state indicated by the label, wherein the training data correction unit (11) corrects a break time that divides a first section from a second section adjacent to the first section, based on time-series data in the first section and time-series data in the second section.

Abstract: A data analysis system capable of performing appropriate analysis while reducing an amount of communication is provided. The data analysis system (90) includes an instrument (10) that performs conversion processing of outputting low-dimensional observation data that is output of an intermediate layer acquired by processing, from the input layer to a predetermined intermediate layer, observation data received through an input layer of a trained neural network (18A) and a device (20) that performs analysis processing of inputting the low-dimensional observation data to an intermediate layer next to the predetermined intermediate layer, in a trained neural network (18B), and acquiring, as a result of analyzing the observation data, output of an output layer using the next intermediate layer and the output layer.