No abstract

No abstract

No abstract

SUMMARY Switching and ON/OFF controls are effective control techniques for control systems equipped with low‐resolution actuators. Such control mechanisms can be modeled as control systems that restrict the control input to discrete values. In this paper, a controller design method based on a machine‐learning technique is discussed. The relationship between the current situation (previous input sequence and previous output sequence), applied input, and output evolution is learned by applying certain machine‐learning methods. Specifically, machine‐learning methods such as the approximate nearest neighbor (ANN) method and support vector machine (SVM) are used in this study. The trained classifier will be a controller that connects the current situation and a suitable control input that can drive the current output to the desired one. The effectiveness of the proposed method is verified for discrete input systems via simulations and experiments.

There is an increasing tendency that elderly people live separately from their children or relatives with the advance of low-birth-rate, aging society and the changes in living environment. Under such circumstances, a number of systems to remotely watch vulnerable people by utilizing sensor devices and communication functions have been proposed. Existing systems to watch vulnerable people are, however, mainly aiming at health management or obtaining merely locational information of vulnerable people, and they are not able to perform a high-level observation to grasp the actual situation of those people. In this paper, we introduce a new system to remotely watch conditions of vulnerable people while they are walking or driving a car, by utilizing various types of sensors embedded in a smartphone. In our system, information obtained is periodically sent to and accumulated in the management server on the Internet, and watching people can observe their vulnerable relatives from anywhere and cope with emergency situations promptly.