Abstract: A learning model optimization device includes a binarization matrix setting unit configured to set a binarization matrix m in which each element is a numerical value of “0” or “1” and a transformed matrix setting unit configured to set a transformed matrix M having, as an element, a product of each element of the parameter matrix and each element of the binarization matrix in the same row and the same column. The learning model optimization device further includes a learning unit configured to perform machine learning using the transformed matrix M and change a numerical value of each element of the binarization matrix m such that a result of the machine learning approaches teacher data, thereby optimizing the binarization matrix m, and a re-randomization processing unit configured to change again a parameter of the parameter matrix w.

Abstract: A processing device includes: a first processing unit that refers to function data including a labeling function that labels an input dataset or abstain if it cannot label, to output first output data that associates each input dataset with a probability of corresponding to each label from a result of labeling the input dataset by the labeling function; and an identifying unit that identifies an input dataset in which a variation in the probability of corresponding to each label in the first output data satisfies a predetermined condition among the input datasets. A labeling function newly created for the input dataset identified from the first output data by the identifying unit is inserted into the function data.

Abstract: A processing server includes a storage device that stores program revision data for identifying a revision of a program and the program of the revision, and runtime revision data for identifying a revision of runtime data input and output to and from the program and the runtime data of the revision, a generating unit that, after receiving a revision of a program that is a target of execution, secures an execution area in the storage device and generates execution target data for executing the program of the revision that is the target of execution in the secured execution area, and an executing unit that executes the execution target data using the runtime data that is the target of execution in the execution area.

Abstract: An electromyography processing apparatus 1 includes a storage device 10 that stores electromyography data 11 of a predetermined muscle, and a balance indicator processing unit 28 that calculates a root-mean-square value of the electromyography for each predetermined time, repeats a process for each of pieces of electromyography data of each of a plurality of muscles, the process being of outputting, as a balance evaluation value of the predetermined muscle, a value acquired by subjecting, to time differentiation, the time course of an average value of the root-mean-square value in a sliding window for calculating balance evaluation value, and outputs a balance indicator based on a balance evaluation value of each of the plurality of muscles.

Abstract: An electromyography processing apparatus 1 includes a storage device 10 that stores electromyography data 11 of a predetermined muscle, an onset detection unit 23 that detects an onset section of the electromyography data 11 in which an electromyography increases by a repetitive exercise performed by an athlete, and an ON/OFF indicator processing unit 25 that calculates a variance a probability distribution acquired by normalizing a root-mean-square value of the electromyography for each onset section, and outputs the calculated variance as an ON/OFF indicator for each onset section.

Abstract: An electromyography processing apparatus 1 includes a storage device 10 that stores electromyography data 11 of a predetermined muscle, a pre-processing unit 22 that calculates a root-mean-square value in the electromyography data 11 for each predetermined time and generates root-mean-square value data including the root-mean-square value for each time, and an onset detection unit 23 that sets a sliding window for onset detection to a predetermined time of the root-mean-square value data and determines that a predetermined time is an onset portion if the average of the root-mean-square values in the sliding window is higher than a threshold value, and the onset detection unit 23 further includes a threshold value determination unit 24 that sets a sliding window for threshold value detection to the predetermined time and determines a threshold value based on the average of the root-mean-square values in the sliding window for threshold value detection.

Abstract: An information communication terminal (100) that includes: a speech recognition module (6) for recognizing speech information to identify a plurality of words in the recognized speech information; a storage medium (20) for storing keyword extraction condition setting data (24) in which a condition for extracting a keyword is set; a keyword extraction module (8) for reading the keyword extraction condition setting data (24) to extract a plurality of keywords from the plurality of words; a related information acquisition module (11) for acquiring related information related to a plurality of keywords; and a related information output module (14) for providing related information to a monitor (2).

Abstract: An information communication terminal (100) that includes: a speech recognition module (6) for recognizing speech information to identify a plurality of words in the recognized speech information; a storage medium (20) for storing keyword extraction condition setting data (24) in which a condition for extracting a keyword is set; a keyword extraction module (8) for reading the keyword extraction condition setting data (24) to extract a plurality of keywords from the plurality of words; a related information acquisition module (11) for acquiring related information related to a plurality of keywords; and a related information output module (14) for providing related information to a monitor (2).