International Business Machines Corporation

Takayuki Yoshizumi

Toshiyuki Hama

Takayuki Katsuki

Kun Zhao

Hiroki Yanagisawa

Hiroyuki Okano

A computer-implemented method for detecting an operation tendency is disclosed. The method includes preparing a general model for generating a general anomaly score. The method also includes preparing a specific model, for generating a specific anomaly score, trained with a set of a plurality of operation data related to operation by a target operator. The method further includes receiving input operation data. The method includes also calculating a detection score related to the operation tendency by using a general anomaly score and a specific anomaly score generated for the input operation data. Further the method includes outputting a result based on the detection score.

Detection of operation tendency based on anomaly detection

Provided is an apparatus comprising a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to: acquire a candidate for a solution of an optimization problem for optimizing a third objective function based on a first objective function and a second objective function; obtain, as another candidate for the solution of the optimization problem, a solution that optimizes the second objective function under a constraint corresponding to a value of the first objective function for the acquired candidate; and select the solution of the optimization problem from among the plurality of candidates for the solution of the optimization problem. Also provided as the first aspect are a method and non-transitory computer readable storage medium.

Calculating a solution for an objective function based on two objective functions

A computer-implemented method of predicting a risk of an accident is disclosed. The method includes computing an anomaly score based on sensor data to obtain a series of anomaly scores. The method also includes processing the anomaly score to limit a processed anomaly score below a predetermined value. The method further includes calculating an accident risk score at time of prediction by using a series of processed anomaly scores up to the time of the prediction. The method includes further outputting a prediction result based on the accident risk score.

Prediction of accident risk based on anomaly detection

A computer-implemented method executed by a robotic system for performing a positional search process in an assembly task is presented. The method includes applying forces to a first component to be inserted into a second component, detecting the forces applied to the first component by employing a plurality of force sensors attached to a robotic arm of the robotic system, extracting training samples corresponding to the forces applied to the first component, normalizing time-series data for each of the training samples by applying a variable transformation about a right tilt direction, creating a time-series prediction model of transformed training data, applying the variable transformation with different directions for a test sample, and calculating a matching ratio between the created time-series prediction model and the transformed test sample.

Perform peg-in-hole task with unknown tilt

Provided is an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to: acquire a candidate for a solution of an optimization problem for optimizing a third objective function based on a first objective function and a second objective function; obtain, as another candidate for the solution of the optimization problem, a solution that optimizes the second objective function under a constraint corresponding to a value of the first objective function for the acquired candidate; and select the solution of the optimization problem from among the plurality of candidates for the solution of the optimization problem. Also provided as the first aspect are a method and non-transitory computer readable storage medium.

A computer-implemented method is disclosed. The method includes preparing a base of an anomaly detection model for generating a score that indicates an estimation of a concentration decline. The anomaly detection model has parameters affecting the score. The method also includes preparing a set of training data, each of which includes a sequence of sensor data relating to activity performed by an individual. The method also includes optimizing the parameters of the anomaly detection model using the set of the training data so as to make a score for longer cumulative activity high as compared to shorter cumulative activity. The method further includes outputting the parameters of the anomaly detection model, in which the anomaly detection model having the parameters is used for detecting a concentration decline of a target individual.

Detection of decline in concentration based on anomaly detection

Groups of metrics to form objective functions may be generated by obtaining a judgment that represents whether a first subject is comparable to a second subject, obtaining a plurality of evaluation values for each of the first subject and the second subject, each evaluation value corresponding to a metric among a plurality of metrics, comparing, for each metric, a corresponding evaluation value of a first subject to a corresponding evaluation value of the second subject, and generating one or more groups based on a result of the comparison and the judgment, each group of the one or more groups including at least one metric of the plurality of metrics, wherein metrics in each group are determined to be comparable with respect to evaluating subjects.

Aggregated multi-objective optimization

A method to generate a plurality of groups each including at least one of a plurality of elements. The method includes selecting at least one candidate element from the plurality of elements as a candidate to be included in a group, determining whether or not to generate the group including the at least one candidate element selected in the selecting step, based on an element evaluation value associated with each of the at least one candidate element selected in the selecting step, provided that a determination is made to generate the group in the determining step, generating the group including the at least one candidate element selected in the selecting step, and weighting the element evaluation value of each of the at least one element according to how many times the each element is included in already-generated groups to reflect the weighted element evaluation value in next group generation.

Iterative pattern generation algorithm for plate design problems

An information processing apparatus includes a generation section configured to generate, from a state of a mobile vehicle in each position obtained by discretizing a traveling route along which the mobile vehicle travels, a state of the mobile vehicle in a next position for each use state of drive means contained in the mobile vehicle; and an optimization section configured to optimize the use state of the drive means in each position based on at least one of states of the mobile vehicle in each position generated by the generation section.

Optimizing use states of a hybrid mobile vehicle along a discretized travel route

An information processing apparatus, article of manufacture and method for discriminating between combined results of a plurality of elements. The apparatus includes: an assigning unit that assigns an element identification value to each of a plurality of basic elements, a generating unit that combines two or more basic elements, among the plurality of basic elements, so as to generate a combined element representing the two or more combined basic elements, and a calculating unit that merges, through an operation corresponding to an element combination method, a plurality of element identification values individually assigned to the plurality of basic elements contained in the combined element so as to calculate one element identification value for the combined element, where two elements are combined by an order-considered or ordered-ignored combination method, the calculating unit merges two corresponding element identification values through an operation where the commutative law holds or does not hold.

Information processing apparatus for discriminating between combined results of plurality of elements, program product and method for same

A method for searching transition routes from an initial state of a plurality of stackable items to a target state by a computer at predetermined conditions includes connecting between transitionable states at an edge by a single handling operation transitioning from the initial state to the target state, to generate a state space graph; evaluating a lower bound of handling operation cost from a certain state to the target state, based on both the stacking sequence of the plurality of items in the certain state and the stacking sequence of the plurality of items in the target state; and searching a route from the initial state to the target state where the handling operation cost is minimal on the state space graph using a heuristic search algorithm based on the lower bound.

Growing community of inventors

Tokyo, Japan

Takayuki Yoshizumi