Abstract: An estimator generation apparatus may include a first estimator and a second estimator sharing a common encoder. The first estimator may be trained to determine a target person's state from face image data. The second estimator may be trained to reconstruct physiological data from face image data. The machine learning may allow the common encoder to have its parameters converging toward higher-accuracy local solutions for estimating the target person's state, thus generating the estimator that may estimate the target person's state more accurately.

Abstract: A facial image identification system is provided to calculate a first feature amount related to each of features from first facial image data used in machine learning for constructing a first identifier that identifies the features of a face, calculate a second feature amount related to each feature from second facial image data obtained in the environment using the first identifier, and compare the first and the second feature amounts for each feature. The system extracts a feature having a large difference between the first and the second feature amounts as a difference feature, and constructs, by implementing machine learning that third facial image data is used, a second identifier for identifying the difference feature and/or a difference-related feature. The third facial image data is acquired in the environment that uses the first identifier and reflects the difference feature and/or the difference-related feature in the third facial image data.

Abstract: Vital sign measurement data and motion measurement data obtained from workers during operation are used as primary indicators. The primary indicators and learning data generated separately are used to estimate the emotion and the cognition of the worker. The estimated emotion and cognition are used as secondary indicators. The secondary indicators and relational expressions generated separately are used to estimate the productivity of the worker. The variation of the productivity estimate is compared with a threshold that defines the condition for providing an intervention. When the variation of the productivity estimate is determined to exceed the threshold, the intervention is provided for the worker.

Abstract: A quality estimation device includes: a first acquisition unit configured to acquire first information pertaining to the positioning of a worker executing a work step included in a process for manufacturing a product on a production line; a second acquisition unit configured to acquire second information pertaining to the usage condition of a tool the worker uses in the work step; an estimation unit configured to estimate the quality of a product being made through the work step according to the degree to which the positioning of the worker and the degree to which the usage condition of the tool represented by the acquired first information and the acquired second information conforms to a predetermined first standard and a predetermined second standard; and an output unit configured to output information pertaining to the result of estimating the quality of the product.

Abstract: An estimator generation apparatus may include a first estimator and a second estimator sharing a common encoder. The first estimator may be trained to determine a target person's state from face image data. The second estimator may be trained to reconstruct physiological data from face image data. The machine learning may allow the common encoder to have its parameters converging toward higher-accuracy local solutions for estimating the target person's state, thus generating the estimator that may estimate the target person's state more accurately.

Abstract: A facial image identification system is provided to calculate a first feature amount related to each of features from first facial image data used in machine learning for constructing a first identifier that identifies the features of a face, calculate a second feature amount related to each feature from second facial image data obtained in the environment using the first identifier, and compare the first and the second feature amounts for each feature. The system extracts a feature having a large difference between the first and the second feature amounts as a difference feature, and constructs, by implementing machine learning that third facial image data is used, a second identifier for identifying the difference feature and/or a difference-related feature. The third facial image data is acquired in the environment that uses the first identifier and reflects the difference feature and/or the difference-related feature in the third facial image data.

Abstract: A method for determining an intervention effect index for a person executing a task is provided and comprises: obtaining sensing information by at least one sensor coupled to the person, the sensing information includes first sensing information relating to performance in executing the task and second sensing information relating to an emotional state; determining, on the basis of said first sensing information, a performance value difference indicating a variation between performance in executing the task before and after an intervention is applied, the intervention representing an excitation affecting the person; estimating, on the basis of said second sensing information, an emotional value difference indicative of a variation between emotional states before and after the intervention is applied; determining the intervention effect index on the basis of said performance value difference and said emotional value difference, the intervention effect index representing an indication on effectiveness of the int

Abstract: A quality estimation device includes: a first acquisition unit configured to acquire first information pertaining to the positioning of a worker executing a work step included in a process for manufacturing a product on a production line; a second acquisition unit configured to acquire second information pertaining to the usage condition of a tool the worker uses in the work step; an estimation unit configured to estimate the quality of a product being made through the work step according to the degree to which the positioning of the worker and the degree to which the usage condition of the tool represented by the acquired first information and the acquired second information conforms to a predetermined first standard and a predetermined second standard; and an output unit configured to output information pertaining to the result of estimating the quality of the product.

Abstract: A performance measurement device according to one or more aspects is configured to acquire sensing data obtained by measuring an activity relating to at least one of sensory activity and physical activity for a relevant worker; analyze the sensing data acquired and thereby calculate a performance index for each of the basic operations; compare the performance index required for each of the basic operations in a work step and the performance index calculated for each of the basic operations; and assign the worker a second work step where the performance index calculated for each of the basic operations satisfies a predetermined criterion in relation to the required performance index for each of the basic operations.

Abstract: A performance measurement device is provided with a data acquisition unit configured to acquire sensing data obtained from one or a plurality of sensors configured to measure an activity relating to at least one of sensory activity and physical activity of a target operator while said target operator executes a task, said task including a plurality of basic operations; an index calculating unit configured to analyze the sensing data acquired to thereby calculate a performance index from the sensing data, the performance index indicating a degree of performance for the basic operations achieved through said activity; and a storage processor configured to store the target operator, the task, and the performance index calculated for each of the basic operations in association in a predetermined storage area.

Abstract: A work support device includes: a first acquisition unit configured to acquire movement data of a target operator performing a work step; a skill-level calculation unit configured to calculate the skill level of the target operator with respect to the work step, the skill level indicating a degree on a spectrum of whether the target operator can suitably accomplish the work step; a second acquisition unit configured to acquire movement data of a model operator at a skill level slightly higher than or equal to the skill level calculated for the target operator; and an instruction determination unit configured to compare the acquired movement data for the model operator with the acquired movement data of the target operator and determine an instruction that allows the movement of the target operator to approach the movement of the model operator on the basis of the results of comparison.

Abstract: A method for assisted driving, includes: storing information indicating an emotion of a subject, and information indicating an activity of the subject; generating learning data representing a relationship between the stored information indicating the emotion of the subject, and the stored information indicating the activity of the subject t and store the learning data into a memory; estimating, after the learning data is generated, a current emotion of the subject based on information indicating a current activity of the subject obtained by an obtaining unit, and the learning data stored in the memory; and providing driving assistance of the vehicle based on the estimated current emotion. Similarly, manufacturing line control, and health care support apparatus are provided, and the apparatuses provide for manufacturing line control and healthcare support on the basis of the estimated emotion.

Abstract: An image inspection method executed by an image inspection apparatus includes an acquisition step of acquiring an inspection target object image obtained by capturing an image of an inspection target object, a setting reading step of reading, from a storage device that stores inspection region defining information in advance, the inspection region defining information, an inspection region extraction step of extracting, as an inspection region image, a portion to be an inspection region from the inspection target object image, based on the inspection region defining information, and an inspection processing step of performing inspection on the inspection target object by analyzing the inspection region image. The inspection region defining information comprises information defining an initial contour of the inspection region and information defining a range based on the initial contour as a search range for searching a contour of the inspection region.

Abstract: An image inspection method executed by an image inspection apparatus includes an acquisition step of acquiring an inspection target object image obtained by capturing an image of an inspection target object, a setting reading step of reading, from a storage device that stores inspection region defining information in advance, the inspection region defining information, an inspection region extraction step of extracting, as an inspection region image, a portion to be an inspection region from the inspection target object image, based on the inspection region defining information, and an inspection processing step of performing inspection on the inspection target object by analyzing the inspection region image. The inspection region defining information comprises information defining an initial contour of the inspection region and information defining a range based on the initial contour as a search range for searching a contour of the inspection region.