Onsjö
Mikael F. Onsjö, Kanagawa JP
Patent application number | Description | Published |
---|---|---|
20120209801 | DECIDING AN OPTIMAL ACTION IN CONSIDERATION OF RISK - A method and system for deciding an optimal action in consideration of risk. The method includes the steps of: generating sequentially, by way of a Markov decision process based on a Monte Carlo method, a series of data having states on a memory of a computer; computing a risk measure of a present data by tracking generated data from opposite order to generation order, where the risk measure is calculated from a value at risk or an exceedance probability that is derived from risk measures of a plurality of states transitionable from a state of the present data; and executing the step of computing the risk measure while tracking back to starting data, where at least one of the steps is carried out using a computer device. | 08-16-2012 |
20120330884 | DECIDING AN OPTIMAL ACTION IN CONSIDERATION OF RISK - A method and system for deciding an optimal action in consideration of risk. The method includes the steps of: generating sequentially, by way of a Markov decision process based on a Monte Carlo method, a series of data having states on a memory of a computer; computing a risk measure of a present data by tracking generated data from opposite order to generation order, where the risk measure is calculated from a value at risk or an exceedance probability that is derived from risk measures of a plurality of states transitionable from a state of the present data; and executing the step of computing the risk measure while tracking back to starting data, where at least one of the steps is carried out using a computer device. | 12-27-2012 |
Mikael F. Onsjö, Kanagawa JP
Patent application number | Description | Published |
---|---|---|
20120330884 | DECIDING AN OPTIMAL ACTION IN CONSIDERATION OF RISK - A method and system for deciding an optimal action in consideration of risk. The method includes the steps of: generating sequentially, by way of a Markov decision process based on a Monte Carlo method, a series of data having states on a memory of a computer; computing a risk measure of a present data by tracking generated data from opposite order to generation order, where the risk measure is calculated from a value at risk or an exceedance probability that is derived from risk measures of a plurality of states transitionable from a state of the present data; and executing the step of computing the risk measure while tracking back to starting data, where at least one of the steps is carried out using a computer device. | 12-27-2012 |
Mikael Folke Onsjö, Kanagawa-Ken JP
Patent application number | Description | Published |
---|---|---|
20130060463 | METHOD, APPARATUS AND COMPUTER PROGRAM FOR SELECTING AND DISPLAYING ROUTE FAVORABLE TO DRIVER - A method and apparatus for selecting and displaying a route preferable to a driver while reducing the frequency of changing the route. A dynamic strategy is computed which depends on time required to reach each intersection to be passed through between a departure place and a destination place. A probability distribution of the required time for each intersection and a driving direction to be selected is computed according to the computed dynamic strategy. A driving direction having the highest probability of the required time is sequentially selected to determine intersections to be passed through to the destination. At each intersection, the probability of the required time for each driving direction can be added and a driving direction that has the highest total probability among the results of the additions can be sequentially selected. | 03-07-2013 |
Mikael Folke Onsjö, Kanagawa-Ken JP
Patent application number | Description | Published |
---|---|---|
20130060463 | METHOD, APPARATUS AND COMPUTER PROGRAM FOR SELECTING AND DISPLAYING ROUTE FAVORABLE TO DRIVER - A method and apparatus for selecting and displaying a route preferable to a driver while reducing the frequency of changing the route. A dynamic strategy is computed which depends on time required to reach each intersection to be passed through between a departure place and a destination place. A probability distribution of the required time for each intersection and a driving direction to be selected is computed according to the computed dynamic strategy. A driving direction having the highest probability of the required time is sequentially selected to determine intersections to be passed through to the destination. At each intersection, the probability of the required time for each driving direction can be added and a driving direction that has the highest total probability among the results of the additions can be sequentially selected. | 03-07-2013 |