Abstract: A machine learning method includes: generating, by a computer, a sine wave using a basic period of input data having a periodic property; determining a sampling period based on a degree of roundness of an attractor generated from the sine wave; sampling the input data at the determined sampling period to generate a pseudo attractor; and performing a machine learning by using the pseudo attractor.

Abstract: An apparatus obtains time series data to which a label indicating a category of classification is attached, where the time series data contains variations of target values during a period to which the label is attached. The apparatus divides the time series data into a plurality of sections, and generates an attractor for each of the plurality of sections where the attractor indicates a set of numerical values toward which the variations of the target values tends to evolve. The apparatus calculates a Betti sequence in accordance with the generated attractor for each of the plurality of sections, and obtains a feature for the Betti sequences of the plurality of sections by clustering the Betti sequences or by calculating a statistical quantity of the Betti sequences. The apparatus performs machine learning by using the obtained feature as an input.

Abstract: A detection device generates plural attractors based on brainwave data. Subsequently, the detection device calculates a Betti number by subjecting the attractors to persistent homology transform. The detection device determines an onset of encephalopathy based on a first order component of a Betti sequence calculated based on the Betti number.

Abstract: A method for extracting features, the method being implemented by a computer, the method includes generating attractors from time series data having a cyclic characteristic; generating a persistence diagram by performing persistent homology conversion for the attractors; changing a degree of influence with respect to individual items of data in the persistence diagram in accordance with a time of existence or an appearance time of a hole generated by performing the persistent homology conversion; and extracting features of the time series data from the changed persistence diagram in which the degree of influence has been changed.

Abstract: A noise determination method executed by a computer, the noise determination method includes: acquiring time-series data; identifying a shape of a waveform of the time-series data using a persistent diagram; extracting a cluster whose lifetime from birth to death is equal to or greater than a threshold value in the persistent diagram; determining, from statistical information regarding time intervals related to pieces of data included in the cluster, whether or not peaks appear at regular intervals in the waveform of the time-series data; and controlling, based on a result of the determining, notification of an alert indicating that the time-series data includes noise.

Abstract: A method for computing an index on a sediment disaster, performed by a computer, the method includes: creating a computation model for computing the index on a sediment disaster at a specific point using information on a geometry of a precipitation zone at the specific point and long rainfall and short rainfall at the specific point, the information being created from past precipitation data accumulated in a storage unit; and computing the index on a sediment disaster using the computation model from the information on the geometry of the precipitation zone at the specific point, the information being created from the input precipitation data.

Abstract: An apparatus obtains time series data to which a label indicating a category of classification is attached, where the time series data contains variations of target values during a period to which the label is attached. The apparatus divides the time series data into a plurality of sections, and generates an attractor for each of the plurality of sections where the attractor indicates a set of numerical values toward which the variations of the target values tends to evolve. The apparatus calculates a Betti sequence in accordance with the generated attractor for each of the plurality of sections, and obtains a feature for the Betti sequences of the plurality of sections by clustering the Betti sequences or by calculating a statistical quantity of the Betti sequences. The apparatus performs machine learning by using the obtained feature as an input.

Abstract: A machine learning method includes: generating, by a computer, a sine wave using a basic period of input data having a periodic property; determining a sampling period based on a degree of roundness of an attractor generated from the sine wave; sampling the input data at the determined sampling period to generate a pseudo attractor; and performing a machine learning by using the pseudo attractor.

Abstract: A method for computing an index on a sediment disaster, performed by a computer, the method includes: creating a computation model for computing the index on a sediment disaster at a specific point using information on a geometry of a precipitation zone at the specific point and long rainfall and short rainfall at the specific point, the information being created from past precipitation data accumulated in a storage unit; and computing the index on a sediment disaster using the computation model from the information on the geometry of the precipitation zone at the specific point, the information being created from the input precipitation data.

Abstract: A communication system includes a first communication device, a plurality of transfer destination devices and a plurality of communication devices. The first communication device receives distribution of data and transfers the data to the plurality of transfer destination devices. The plurality of communication devices receive the data via any of the plurality of transfer destination devices. The first communication device requests that a second communication device included among the plurality of transfer destination devices receive the data from a third communication device included among the plurality of communication devices when reception quality of the data in the third communication device is higher than reception quality of the data in the second communication device. The second communication device receives a request from the first communication device and changes a connection destination from the first communication device to the third communication device.

Abstract: A first communication device compares communication quality between a target communication device selected from among communication devices having a possibility of becoming a connection destination and the first communication device, with a quality threshold. The first communication device obtains the quality threshold as a function of data reception quality in the target communication device and a number of communication devices to which connections were attempted by the first communication device excluding the target communication device. The first communication device sets the quality threshold as a detection threshold for detecting an opportunity to change a connection destination when the communication quality is equal to or higher than the quality threshold.

Abstract: An electric power steering system comprising an upper bracket, a steering column, a steering shaft provided rotatably within the steering column, a tilt mechanism comprising a tilt clamp which tightly fastens the steering column between tightening plate portions of the upper bracket and a tilt pivot which oscillates the steering column, an electric assist unit provided at a lower end of the steering column, and a lower bracket fixed to the vehicle body at an opposite side of the electric assist unit to the steering column to rotatably support a pivot shaft of the tile pivot. A housing of the electric assist unit is brought into engagement with a pivot shaft of the tilt pivot in such a manner as to be allowed to move loosely, so that the steering column is allowed to oscillate about the pivot shaft, and a column rotation restricting portion is provided between the lower bracket and the housing.

Abstract: There is provided a steering apparatus having a vehicle-body-mounted bracket mountable in a vehicle body, a steering shaft to which a steering wheel is attached, a column which is supported by the vehicle-body-mounted bracket so that a tilt position thereof is adjustable, rotatably supports the steering shaft and a clamp unit that clamps the column to the vehicle-body-mounted bracket through a tilt friction plate at a desired tilt position and a connection member connecting the tilt friction plate with the vehicle-body-mounted bracket. When an impact force, whose magnitude is equal to or more than a predetermined value, acts at a collision, connection of the tilt friction plate to the vehicle-body-mounted bracket is canceled, so that the column moves together with the tilt friction plate in a tilt direction relative to the vehicle-body-mounted bracket.