Search for: All records

Abstract Spectroscopic techniques generate one-dimensional spectra with distinct peaks and specific widths in the frequency domain. These features act as unique identities for material characteristics. Deep neural networks (DNNs) has recently been considered a powerful tool for automatically categorizing experimental spectra data by supervised classification to evaluate material characteristics. However, most existing work assumes balanced spectral data among various classes in the training data, contrary to actual experiments, where the spectral data is usually imbalanced. The imbalanced training data deteriorates the supervised classification performance, hindering understanding of the phase behavior, specifically, sol-gel transition (gelation) of soft materials and glycomaterials. To address this issue, this paper applies a novel data augmentation method based on a generative adversarial network (GAN) proposed by the authors in their prior work. To demonstrate the effectiveness of the proposed method, the actual imbalanced spectral data from Pluronic F-127 hydrogel and Alpha-Cyclodextrin hydrogel are used to classify the phases of data. Specifically, our approach improves 8.8%, 6.4%, and 6.2% of the performance of the existing data augmentation methods regarding the classifier’s F-score, Precision, and Recall on average, respectively. Specifically, our method consists of three DNNs: the generator, discriminator, and classifier. The method generates samples that are not only authentic but emphasize the differentiation between material characteristics to provide balanced training data, improving the classification results. Based on these validated results, we expect the method’s broader applications in addressing imbalanced measurement data across diverse domains in materials science and chemical engineering. 

Abstract Highly stretchable fiber sensors have attracted significant interest recently due to their applications in wearable electronics, human–machine interfaces, and biomedical implantable devices. Here, a scalable approach for fabricating stretchable multifunctional electrical and optical fiber sensors using a thermal drawing process is reported. The fiber sensors can sustain at least 580% strain and up to 750% strain with a helix structure. The electrical fiber sensor simultaneously exhibits ultrahigh stretchability (400%), high gauge factors (≈1960), and excellent durability during 1000 stretching and bending cycles. It is also shown that the stretchable step‐index optical fibers facilitate detection of bending and stretching deformation through changes in the light transmission. By combining both electrical and optical detection schemes, multifunctional fibers can be used for quantifying and distinguishing multimodal deformations such as bending and stretching. The fibers’ utility and functionality in sensing and control applications are demonstrated in a smart glove for controlling a virtual hand model, a wrist brace for wrist motion tracking, fiber meshes for strain mapping, and real‐time monitoring of multiaxial expansion and shrinkage of porcine bladders. These results demonstrate that the fiber sensors can be promising candidates for smart textiles, robotics, prosthetics, and biomedical implantable devices.