Abstract: A danger detection system for detecting a danger on a road, the danger that changes over time and may not be a danger due to the change over time, the danger detection system including a vibration acquisition unit 11 configured to acquire an acoustic signal collected by a microphone mounted on a vehicle when the vehicle passes through a region on a predetermined road, a danger determination unit 12 configured to determine whether the acoustic signal is derived from the danger, a danger location detection unit 2 configured to determine whether the danger is present in the region on the predetermined road based on the number of times an acoustic signal acquired from each of the plurality of vehicles is determined to be derived from the danger, and a danger information notification unit 3 configured to notify a communication device that can pass through the region on the predetermined road of danger information that is information about a region on a road determined to have a danger.

Abstract: An estimation apparatus includes a state estimation unit that estimates a state from an observed amount using an encoder, an observed amount estimation unit that estimates an observed amount from a state using a decoder, and a future observed amount estimation unit that estimates a future observed amount, which is a value to which the observed amount changes with time, using a parameter K representing time evolution, where a parameter of the encoder, a parameter of the decoder, and the parameter K are optimized simultaneously.

Abstract: An abnormality detection device 1 includes: a vibration acquisition unit 11 configured to acquire an acoustic signal generated during passage of a vehicle on a road; a frequency domain conversion unit 12 configured to convert the acquired acoustic signal into a frequency domain signal; an unexpectedness determination unit 13 configured to determine whether there is unexpectedness at each predetermined frequency using the frequency domain signal; and an abnormality determination unit 14 configured to determine whether there is an abnormality in the road based on the number of frequencies at which it is determined that there is the unexpectedness.

Abstract: A road condition estimation device 2 includes: a reception unit 21 that receives pieces of sensor information from automobiles respectively, each piece of sensor information including positional information that is information regarding a position at which an automobile travels, and spectral information obtained by converting an acoustic signal generated when the automobile travels at the position into information in a frequency domain; a first classification unit 22 that classifies the pieces of spectral information respectively for roads on which the automobiles travel, based on pieces of positional information included in the pieces of sensor information thus received; and an estimation unit 23 that estimates a condition of a road for each of the pieces of spectral information classified by the first classification unit.

Abstract: Information regarding an impact occurring in a vehicle is analyzed from an observed signal by a sensor installed in the vehicle. An acquisition unit (11) acquires an observed signal by a sensor (S) installed at a predetermined position of the vehicle. The analysis unit (12) analyzes the type of impact at each time from the observed signal with respect to the impact occurring on the vehicle at a position different from the position at which the sensor (S) is installed in the vehicle. The type of impact includes at least one type of impact among impact from collision of an obstacle with the vehicle, impact from the vehicle driving over a curb, impact from collision of a flying object with the vehicle, impact from the vehicle rubbing against an object other than the vehicle, and impact from an object other than the vehicle rubbing against the vehicle. An output unit (13) outputs a result obtained by analyzing a time at which the impact occurs and the type of impact.

Abstract: A notification method is a notification method of providing a notification of a warning indicating that an infant is left unattended in an automobile, the notification method including: a detection step of detecting, by a detection unit 1, whether the infant is left unattended; and a notification step of providing, by a notification unit 2, the notification of the warning when the infant is left unattended. The detection step includes detecting that the infant is left unattended when at least both of a case where a door used by a driver of the automobile is closed after being opened and a case where the driver is not in a driver's seat of the automobile are satisfied within a time frame and the infant is in the automobile.

Abstract: Provided is an abnormal data generation device capable of generating highly accurate abnormal data. The abnormal data generation device includes an abnormal data generation unit for generating pseudo generated data of abnormal data that has, in the same latent space, a normal distribution as a normal data generation model and an abnormal distribution expressed as a complementary set of the normal distribution and that is optimized such that pseudo generated data cannot be discriminated from observed actual abnormal data by a latent variable sampled from the abnormal distribution.

Abstract: A battery pack may include battery cells, each of which may have a pair of first surface portions facing each other in a first direction and have a positive electrode plate and a negative electrode plate stacked so as to be arranged in the first direction, an outer shell portion that houses the stacked battery cells, elastic structures, each of which may be provided between the battery cells adjacent to each other in the first direction, and a plurality of frames that may fix the battery cells to the outer shell portion. The elastic structures may be disposed so as to cover the central portions of the first surface portions and the frames may be disposed so as to cover an outer circumference portions of the first surface portions.

Abstract: Sounds arriving from outside of a mobile body are collected by a microphone disposed inside the mobile body. A sound collecting apparatus according to the present disclosure is attached to the mobile body. The sound collecting apparatus according to the present disclosure includes a microphone that is directly or indirectly in contact with an outer face member, which is a member forming an outer face of the mobile body, from an inner side of the mobile body and collects sounds propagating through the outer face member. In a case where the microphone has directivity, the microphone is disposed in a direction in which sounds propagating from the outer face of the outer face member to the inner side are collected. The outer face member is, for example, glass.

Abstract: Audibility of an outside sound needed for a driver inside an automobile to apprehend a danger and obtain a grasp of a situation necessary for driving is improved. A sound collection and emission apparatus (10) emits, on the basis of an outside acoustic signal which emanates from a sound source outside an automobile (90) and arrives at the automobile (90), an inside acoustic signal which is an acoustic signal derived from the outside acoustic signal to inside the automobile (90). A sound collection unit (M1) collects the outside acoustic signal. A sound emission unit (S1) emits the inside acoustic signal. A danger sound detection unit (11) determines whether the outside acoustic signal has a feature representing a danger defined in advance. A control unit (12) performs control that emits the inside acoustic signal from the sound emission unit (S1) such that a driver of the automobile (90) is capable of perceiving the danger if the outside acoustic signal is determined to represent the danger.

Abstract: There is provided a neural network learning technique for learning a parameter of a probability density function representing the distribution of data with high accuracy using an autoencoder. A neural network learning apparatus, wherein ? is a parameter of a probability density function q?(x) representing distribution of data x, and M? is a neural network that is an autoencoder that learns the parameter ?, the neural network learning apparatus including: a neural network calculation unit that calculates an output value M?(xn) of the neural network from learning data xn using the parameter ? for n=1, . . .

Abstract: Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anomaly model expressing the pieces of anomalous sound data, and decides a minimum value among the anomaly scores as a threshold. A weight updating part (14) updates, using a plurality of pieces of normal sound data, the pieces of anomalous sound data and the threshold, weights of the anomaly model so that all the pieces of anomalous sound data are judged as anomalous, and probability of the pieces of normal sound data being judged as anomalous is minimized.

Abstract: Provided is an anomaly detection device capable of acquiring a degree of anomaly required for anomaly detection even when a feature pattern of time series data changes over time. The anomaly detection device of the present invention is a device that detects the degree of anomaly in the time series data. The anomaly detection device includes a first acquisition unit, a prediction unit, and an anomaly degree acquisition unit. The first acquisition unit acquires, from a first section that is a partial section of the time series data, a dynamic feature pattern of the first section. The prediction unit predicts data of a second section that is a partial section of the time series data later than the first section by using the feature pattern to obtain predicted second section data. The anomaly degree acquisition unit acquires the degree of anomaly based on a difference between the predicted second section data and actual data of the second section in the time series data.

Abstract: A road condition estimation device 2 includes: a reception unit 21 that receives pieces of sensor information from automobiles respectively, each piece of sensor information including positional information that is information regarding a position at which an automobile travels, and spectral information obtained by converting an acoustic signal generated when the automobile travels at the position into information in a frequency domain; a first classification unit 22 that classifies the pieces of spectral information respectively for roads on which the automobiles travel, based on pieces of positional information included in the pieces of sensor information thus received; and an estimation unit 23 that estimates a condition of a road for each of the pieces of spectral information classified by the first classification unit.

Abstract: A danger detection system for detecting a danger on a road, the danger that changes over time and may not be a danger due to the change over time, the danger detection system including a vibration acquisition unit 11 configured to acquire an acoustic signal collected by a microphone mounted on a vehicle when the vehicle passes through a region on a predetermined road, a danger determination unit 12 configured to determine whether the acoustic signal is derived from the danger, a danger location detection unit 2 configured to determine whether the danger is present in the region on the predetermined road based on the number of times an acoustic signal acquired from each of the plurality of vehicles is determined to be derived from the danger, and a danger information notification unit 3 configured to notify a communication device that can pass through the region on the predetermined road of danger information that is information about a region on a road determined to have a danger.

Abstract: Provided is a technology capable of supporting an operation of a car by a driver when an alarm sound notifying the approach of a train is sounding at a railroad crossing. The alarm sound processing apparatus includes: an observed sound sensor that generates an observed sound signal from an observed sound or vibration related to the observed sound; an alarm sound detection unit that generates an alarm sound detection result indicating whether the observed sound contains an alarm sound at a railroad crossing from the observed sound signal; and an alarm sound reaction unit that executes processing for issuing a warning to notify a driver that a train is approaching the railroad crossing and/or executes processing for applying a brake to a car driven by the driver when the alarm sound detection result indicates that the alarm sound is contained.

Abstract: An abnormality detection device 1 includes: a vibration acquisition unit 11 configured to acquire an acoustic signal generated during passage of a vehicle on a road; a frequency domain conversion unit 12 configured to convert the acquired acoustic signal into a frequency domain signal; an unexpectedness determination unit 13 configured to determine whether there is unexpectedness at each predetermined frequency using the frequency domain signal; and an abnormality determination unit 14 configured to determine whether there is an abnormality in the road based on the number of frequencies at which it is determined that there is the unexpectedness.

Abstract: The accuracy of unsupervised anomalous sound detection is improved. An anomalous sound generation unit 12 generates a pseudo-anomalous sound by associating a sound obtained from a predetermined device with a probability distribution followed by a sound obtained from a desired device group. A threshold value setting unit 13 sets a threshold value so that all anomaly scores calculated from the pseudo-anomalous sound are determined to be anomalous. A parameter update unit 14 uses an obtained normal sound and an obtained anomalous sound, or a threshold value and a value based on the obtained anomalous sound, to update a parameter so to reliably determine an anomalous sound as anomalous and minimize the probability of determining a normal sound as anomalous.

Abstract: A possible region of encoding results of anomalous samples is limited. An encoder storage unit 14 stores an encoder for projecting an input feature value into a latent space in which the latent space is a closed manifold, a normal distribution obtained by learning normal data and an anomalous distribution obtained by learning anomalous data are held on the manifold, and a decoder for reconstructing the output of the encoder. An encoding unit 15 obtains a reconstruction result output by the decoder when a feature value of target data is input to the encoder. An anomaly score calculation unit 16 calculates an anomaly score of the target data based on distances between the reconstruction result and the normal distribution and distances between the reconstruction result and the anomalous distribution.

Abstract: Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anomaly model expressing the pieces of anomalous sound data, and decides a minimum value among the anomaly scores as a threshold. A weight updating part (14) updates, using a plurality of pieces of normal sound data, the pieces of anomalous sound data and the threshold, weights of the anomaly model so that all the pieces of anomalous sound data are judged as anomalous, and probability of the pieces of normal sound data being judged as anomalous is minimized.