An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX)) are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases.

No abstract

We herein present results obtained from our study of flat and uniform polymer-blended smallmolecular semiconductor thin films. These films were produced for organic thin film transistors (OTFTs), using a simple pre-metered horizontal dipping process. The organic semiconductor thin films were composed of a small molecular 6,13-bis(triisopropylsilylethynyl)-pentacene (TIPS-PEN) composite blended with a polymer binder of poly(a-methylstyrene) (PaMS). We show that the premetered solution-coating process allowed the critical control of the thickness of the TIPS-PEN:PaMS film; extremely thin films could be produced using the downstream meniscus of the solution at high speeds (of the order of a few metres per minute). The fabricated TIPS-PEN:PaMS OTFTs exhibited a maximum field-effect mobility of 0.22 cm 2 V À1 s À1 , and on/off ratios of over 10 5 , that were consistently superior to those of conventional spin-cast devices. These results demonstrate that horizontal dipcoated TIPS-PEN:PaMS films show considerable promise for the production of reliable, reproducible, high-performance OTFTs.

No abstract

No abstract