This paper presents a literature review on pattern recognition of electromyography (EMG) signals and its applications. The EMG technology is introduced and the most relevant aspects for the design of an EMG-based system are highlighted, including signal acquisition and filtering. EMG-based systems have been used with relative success to control upper-and lower-limb prostheses, electronic devices and machines, and for monitoring human behavior. Nevertheless, the existing systems are still inadequate and are often abandoned by their users, prompting for further research. Besides controlling prostheses, EMG technology is also beneficial for the development of machine learning-based devices that can capture the intention of able-bodied users by detecting their gestures, opening the way for new human-machine interaction (HMI) modalities. This paper also reviews the current feature extraction techniques, including signal processing and data dimensionality reduction. Novel classification methods and approaches for detecting non-trained gestures are discussed. Finally, current applications are reviewed, through the comparison of different EMG systems and discussion of their advantages and drawbacks.INDEX TERMS EMG, human-machine interaction, pattern classification, regression.

No abstract

In this paper we present a continuous-time network loading procedure based on Lighthill-Whitham-Richards model proposed by Lighthill and Whitham (1955); Richards (1956). A system of differential algebraic equations (DAEs) is proposed for describing traffic flow propagation, travel delay and route choices. We employ a novel numerical apparatus to reformulate the scalar conservation law as a flow-based PDE, which is then solved semi-analytically with Lax-Hopf formula. This approach allows for an efficient computational scheme for large-scale applications. We will embed this network loading procedure into the dynamic user equilibrium (DUE) model proposed by Friesz et al. (1993). The DUE is solved as a differential variational inequality (DVI) and with the fixed-point algorithm. Several numerical examples of DUE on networks of varying sizes will be presented, including the Sioux Falls network with a significant number of paths and origin-destination pairs. The DUE model presented in this article can be formulated as a variational inequality (VI) as reported in Friesz et al. (1993). We will present the Kuhn-Tucker (KT) conditions for the VI, which is systematically formulated as a linear system. In order to solve the system with reasonable time and memory usage, we present a decomposition of the linear system that allows for the efficient computation of the dual variables. The numerical solutions of DUE obtained from the fixed-point iterations will be tested against the KT condition and validated to be in fact the solutions to the VIs.

Abstract:This survey presents a literature review on friction stir welding (FSW) modeling with a special focus on the heat generation due to the contact conditions between the FSW tool and the workpiece. The physical process is described and the main process parameters that are relevant to its modeling are highlighted. The contact conditions (sliding/sticking) are presented as well as an analytical model that allows estimating the associated heat generation. The modeling of the FSW process requires the knowledge of the heat loss mechanisms, which are discussed mainly considering the more commonly adopted formulations. Different approaches that have been used to investigate the material flow are presented and their advantages/drawbacks are discussed.A reliable FSW process modeling depends on the fine tuning of some process and material parameters.Usually, these parameters are achieved with base on experimental data. The numerical modeling of the FSW process can help to achieve such parameters with less effort and with economic advantages.

This paper focuses on intuitive and direct off-line robot programming from a CAD drawing running on a common 3-D CAD package. It explores the most suitable way to represent robot motion in a CAD drawing, how to automatically extract such motion data from the drawing, make the mapping of data from the virtual (CAD model) to the real environment and the process of automatic generation of robot paths/programs. In summary, this study aims to present a novel CAD-based robot programming system accessible to anyone with basic knowledge of CAD and robotics. Experiments on different manipulation tasks show the effectiveness and versatility of the proposed approach