Abstract: It is intended to allow an appropriate route search to be performed even with a geographical NW in which accessibility information includes an uninvestigated link. A route appropriateness value calculation unit 160 calculates, for each of a plurality of routes each connecting a departure point and a destination extracted by a route extraction unit 120 and including links connecting individual spots including the departure point and the destination, a route appropriateness value of the route.

Abstract: A collection device includes a deciding unit that, on the basis of data obtained in advance for each area, decides a collection interval and a collection time for each of the areas, a communication unit that acquires a current position from each of measurement terminals, and an allocating unit that, in a case where there is an area corresponding to the current position acquired regarding each of the measurement terminals, calculates a slot count of slots regarding which the collection interval and the collection time are cyclically allocated, on the basis of the collection interval and the collection time of this area, and allocates slot Nos. of an amount equivalent to the slot count, to any of the measurement terminals present in this area, by a predetermined method. The communication unit transmits, to each of the measurement terminals to which slot Nos.

Abstract: A light detection sensor includes a light source that irradiates a detection target with light, a rod lens that collects emitted light from the detection target, a first light receiving element that detects the emitted light that has passed through the rod lens, and a second light receiving element that detects the emitted light that has passed through the rod lens, at a position different from a position at which the first light receiving element detects the light.

Abstract: A collection device includes a deciding unit that, on the basis of data obtained in advance for each area, decides a collection interval and a collection time for each of the areas, a communication unit that acquires a current position from each of measurement terminals, and an allocating unit that, in a case where there is an area corresponding to the current position acquired regarding each of the measurement terminals, calculates a slot count of slots regarding which the collection interval and the collection time are cyclically allocated, on the basis of the collection interval and the collection time of this area, and allocates slot Nos. of an amount equivalent to the slot count, to any of the measurement terminals present in this area, by a predetermined method. The communication unit transmits, to each of the measurement terminals to which slot Nos.

Abstract: An aim is to reduce the size of an optical sensor which detects radiated light such as phosphorescence radiated from a detection target excited by exciting light, and to increase a radiated light receiving surface of the optical sensor. An optical sensor is configured to be provided with: a light source which irradiates excitation light; a light detector which detects radiation light emitted from a detection target excited by the excitation light; and a single light guide unit which guides the excitation light to the detection target and guides the radiation light to the light detector.

Abstract: Information relating to each link based on location information of a user can be generated with high accuracy even without measuring the location information at a high frequency. A map matching unit (101) associates location information of a moving user at each time with pedestrian network data (120) formed by a plurality of nodes and links connecting the nodes through a map matching process, and a calculation unit (102) calculates a passage record of a link of interest as link information based on whether or not the link of interest is connected to preceding and succeeding links in a link row acquired by aligning the links with which the location information is associated in order of times of pieces of the location information.

Abstract: An input unit receives an input of posted information including information regarding passage of links which connect sites in a geographic network. A posted information credibility determination unit (30) determines credibility of the posted information by comparing movement features obtaining from the posted information with movement features obtained in advance with regard to the links in the geographic network and obtained from movement results during the passage of the links.

Abstract: An information extracting device includes an acquiring unit that acquires, with regard to each information source, a data group made up of data including a content relating to an object, a location where the content was recorded, and a date and time at which the content was recorded, a generating unit that generates a word vector of which the date and time, the location, content using a weight based on the date and time, and a type of the content, are each components, for each of the data of the data group, a distance calculating unit that calculates a distance among the word vectors, a classifying unit that classifies each of data of the data group on the basis of the distance among the word vectors, and an extracting unit that calculates a reliability with regard to the classification, and extracts data from the data group on the basis of the reliability.

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 intended to allow an appropriate route search to be performed even with a geographical NW in which accessibility information includes an uninvestigated link. A route appropriateness value calculation unit 160 calculates, for each of a plurality of routes each connecting a departure point and a destination extracted by a route extraction unit 120 and including links connecting individual spots including the departure point and the destination, a route appropriateness value of the route.

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 current position of a user can be estimated with high accuracy. A movability calculation unit 210 calculates, for each of a plurality of candidate routes, movability indicating the degree to which movement along the candidate route is possible, based on a movement cost that is calculated, the movement cost indicating the degree of difficulty in traveling along the candidate route by a movement means, an expected route movement time that is calculated, the expected route movement time being a time necessary to travel along the candidate route by the movement means, and a time taken to travel from a past position to a current position, and a current position estimation unit 220 estimates a candidate current position on the candidate route with the highest movability to be the current position of a user on a geographic network.

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: To appropriately evaluate an evaluation target based on posts related to an evaluation target from a user. An acquisition unit 24 of an evaluation device 14 acquires, from a group of pieces of post data including a plurality of pieces of post data each including post information indicating a post content related to an evaluation target and poster information indicating a user who has posted the post information, based on a user reliability that indicates the user and becomes greater for the user, indicated by the poster information, with a larger number of pieces of the post information posted in past and with a larger number of pieces of the post information adopted as information having a predetermined reliability or higher, the post data with the user reliability being equal to or greater than a threshold. Then, an evaluation unit 26 evaluates whether the evaluation target exists, based on the post data acquired by the acquisition unit 24.

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: To appropriately update evaluation on an evaluation target based on posts related to an evaluation target from a user. When a reliability of an evaluation information drops equal to or below a threshold related to the reliability of the evaluation information, the evaluation information representing an evaluation on an evaluation target, the reliability representing an index provided to evaluation information when the evaluation information is generated, an evaluation unit 26 of an evaluation device 14 generates evaluation information on the evaluation target again based on post information different from post information used for generating the evaluation information on the evaluation target.

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.

Abstract: An aim is to reduce the size of an optical sensor which detects radiated light such as phosphorescence radiated from a detection target excited by exciting light, and to increase a radiated light receiving surface of the optical sensor. An optical sensor is configured to be provided with: a light source which irradiates excitation light; a light detector which detects radiation light emitted from a detection target excited by the excitation light; and a single light guide unit which guides the excitation light to the detection target and guides the radiation light to the light detector.

Abstract: A light detection sensor includes a light source that irradiates a detection target with light, a rod lens that collects emitted light from the detection target, a first light receiving element that detects the emitted light that has passed through the rod lens, and a second light receiving element that detects the emitted light that has passed through the rod lens, at a position different from a position at which the first light receiving element detects the light.

Abstract: A light detection sensor 10 comprises a light source 12 for radiating light to a detection object T and a light receiver 11 comprising a plurality of detectors for detecting intensity of light from the detection object T. The plurality of detectors comprises at least, a first detector 11a for detecting intensity of light of a first wavelength band, and a second detector 11b for detecting intensity of light of a second wavelength band different from the first wavelength band. Sensitivity of the first detector 11a to the light of the first wavelength band is lower than sensitivity of the second detector 11b to the light of the second wavelength band. A light receiving area of the first detector 11a is larger than a light receiving area of the second detector 11b.