Synthesis of sEMG Signals for Hand Gestures Using a 1DDCGAN

The emergence of modern prosthetics controlled by bio-signals has been facilitated by AI and microchip technology innovations. AI algorithms are trained using sEMG produced by muscles during contractions. The data acquisition procedure may result in discomfort and fatigue, particularly for amputees. Furthermore, prosthetic companies restrict sEMG signal exchange, limiting data-driven research and reproducibility. GANs present a viable solution to the aforementioned concerns. GANs can generate high-quality sEMG, which can be utilised for data augmentation, decrease the training time required by prosthetic users, enhance classification accuracy and ensure research reproducibility. This research proposes the utilisation of a one-dimensional deep convolutional GAN (1DDCGAN) to generate the sEMG of hand gestures. This approach involves the incorporation of dynamic time wrapping, fast Fourier transform and wavelets as discriminator inputs. Two datasets were utilised to validate the methodology, where five windows and increments were utilised to extract features to evaluate the synthesised sEMG quality. In addition to the traditional classification and augmentation metrics, two novel metrics-the Mantel test and the classifier two-sample test-were used for evaluation. The 1DDCGAN preserved the inter-feature correlations and generated high-quality signals, which resembled the original data. Additionally, the classification accuracy improved by an average of 1.21-5%.

Edge-Enhanced Object-Space Model Optimization of Tomographic Reconstructions for Additive Manufacturing

Object-space model optimization (OSMO) has been proven to be a simple and high-accuracy approach for additive manufacturing of tomographic reconstructions compared with other approaches. In this paper, an improved OSMO algorithm is proposed in the context of OSMO. In addition to the two model optimization steps in each iteration of OSMO, another two steps are introduced: one step enhances the target regions' in-part edges of the intermediate model, and the other step weakens the target regions' out-of-part edges of the intermediate model to further improve the reconstruction accuracy of the target boundary. Accordingly, a new quality metric for volumetric printing, named 'Edge Error', is defined. Finally, reconstructions on diverse exemplary geometries show that all the quality metrics, such as VER, PW, IPDR, and Edge Error, of the new algorithm are significantly improved; thus, this improved OSMO approach achieves better performance in convergence and accuracy compared with OSMO.