Abstract: An anomaly detection apparatus includes a device identification database that stores device identification information for identifying a specific device for each type of a device, a hierarchical conditional vector generation unit that generates a hierarchical conditional vector based on the device identification information, an extraction unit that extracts a target device feature amount vector indicating a feature amount of an acoustic signal acquired from a target device by analyzing the acoustic signal, a hierarchical condition adversarial neural network that outputs background noise level information indicating a background noise level of a surrounding environment of the target device and true/false determination information indicating true/false of the target device feature amount vector by analyzing the hierarchical conditional vector and the target device feature amount vector, and an anomaly determination unit that determines whether an anomaly exists in the target device feature amount vector.

Abstract: Provided are an abnormality detection system and an abnormality detection method capable of performing more stable abnormality detection. An abnormality detection system that detects an abnormality of the target machine by a computer includes a communication unit configured to acquire first data from a first sensor attached to the target machine and second data from a second sensor attached to the target machine, an arithmetic unit, and a memory unit. The arithmetic unit includes an encoding unit trained to generate latent expressions including a predetermined latent expression that estimates the second data on the basis of the first data, a decoding unit trained to restore the first data from the latent expressions, and an abnormality detection unit configured to detect the abnormality of the target machine on the basis of a restoration error between the first data and the first data restored by the decoding unit.

Abstract: The hyperparameter management device of the present invention includes a compression network to dimensionally compress data to produce a low dimensional representation, an estimation network to estimate a density distribution of the low dimensional representation and a hyperparameter calculation unit to calculate hyperparameters for the compression network and the estimation network, wherein the hyperparameter calculation unit calculates, based on a set of subject data and a set of uniform data, a gap statistic using a gap statistic calculation technique, and calculates, using a curve fitting technique, an estimation network hyperparameter based on at least the gap statistic, calculates a ratio of variance of principal components of the set of subject data, and calculates, using a curve fitting technique, a compression network hyperparameter based on at least the ratio of variance, and sets the estimation network hyperparameter in the estimation network and sets the compression network hyperparameter in the c

Abstract: An anomaly detection apparatus includes a device identification database that stores device identification information for identifying a specific device for each type of a device, a hierarchical conditional vector generation unit that generates a hierarchical conditional vector based on the device identification information, an extraction unit that extracts a target device feature amount vector indicating a feature amount of an acoustic signal acquired from a target device by analyzing the acoustic signal, a hierarchical condition adversarial neural network that outputs background noise level information indicating a background noise level of a surrounding environment of the target device and true/false determination information indicating true/false of the target device feature amount vector by analyzing the hierarchical conditional vector and the target device feature amount vector, and an anomaly determination unit that determines whether an anomaly exists in the target device feature amount vector.

Abstract: The hyperparameter management device of the present invention includes a compression network to dimensionally compress data to produce a low dimensional representation, an estimation network to estimate a density distribution of the low dimensional representation and a hyperparameter calculation unit to calculate hyperparameters for the compression network and the estimation network, wherein the hyperparameter calculation unit calculates, based on a set of subject data and a set of uniform data, a gap statistic using a gap statistic calculation technique, and calculates, using a curve fitting technique, an estimation network hyperparameter based on at least the gap statistic, calculates a ratio of variance of principal components of the set of subject data, and calculates, using a curve fitting technique, a compression network hyperparameter based on at least the ratio of variance, and sets the estimation network hyperparameter in the estimation network and sets the compression network hyperparameter in the c