Virtual reality is a brand‐new technology that can be applied extensively. To realize virtual reality, certain types of human–computer interaction equipment are necessary. Existing virtual reality technologies often rely on cameras, data gloves, game pads, and other equipment. These equipment are either bulky, inconvenient to carry and use, or expensive to popularize. Therefore, the development of a convenient and low‐cost high‐precision human–computer interaction device can contribute positively to the development of virtual reality technology. In this study, a gesture recognition wristband that can realize a full keyboard and multicommand input is developed. The wristband is convenient to wear, low in cost, and does not affect other daily operations of the hand. This wristband is based on physiological anatomy as well as aided by active sensor and machine learning technology; it can achieve a maximum accuracy of 92.6% in recognizing 26 letters. This wristband offers broad application prospects in the fields of gesture command recognition, assistive devices for the disabled, and wearable electronics.

No abstract

No abstract

To efficiently solve high-dimensional problems with complicated constraints, projection-free online learning has received ever-increasing research interest. However, previous studies either focused on static regret that is not suitable for dynamic environments, or only established the dynamic regret bound under the smoothness of losses. In this paper, without the condition of the smoothness, we propose a novel projection-free online algorithm, and achieve an O(max{T^{2/3}V_T^{1/3},T^{1/2}}) dynamic regret bound for convex functions and an O(max{(TV_Tlog T)^{1/2},log T}) dynamic regret bound for strongly convex functions, where T is the time horizon and V_T denotes the variation of loss functions. Specifically, we first improve an existing projection-free algorithm called online conditional gradient (OCG) to enjoy small dynamic regret bounds with the prior knowledge of V_T. To work with unknowable V_T, we maintain multiple instances of the improved OCG that can handle different functional variations, and combine them with a meta-algorithm that can track the best one. Experimental results validate the efficiency and effectiveness of our algorithm.

No abstract