Search

Brain decoding that classifies cognitive states using the functional fluctuations of the brain can provide insightful information for understanding the brain mechanisms of cognitive functions. Among the common procedures of decoding the brain cognitive states with functional magnetic resonance imaging (fMRI), extracting the time series of each brain region after brain parcellation traditionally averages across the voxels within a brain region. This neglects the spatial information among the voxels and the requirement of extracting information for the downstream tasks. In this study, we propose to use a fully connected neural network that is jointly trained with the brain decoder to perform an adaptively weighted average across the voxels within each brain region. We perform extensive evaluations by cognitive state decoding, manifold learning, and interpretability analysis on the Human Connectome Project (HCP) dataset. The performance comparison of the cognitive state decoding presents an accuracy increase of up to 5\% and stable accuracy improvement under different time window sizes, resampling sizes, and training data sizes. The results of manifold learning show that our method presents a considerable separability among cognitive states and basically excludes subject-specific information. The interpretability analysis shows that our method can identify reasonable brain regions corresponding to each cognitive state. Our study would aid the improvement of the basic pipeline of fMRI processing., Comment: 17 pages, 4 figures

Assessing the progression of muscle fatigue for daily exercises provides vital indicators for precise rehabilitation, personalized training dose, especially under the context of Metaverse. Assessing fatigue of multi-muscle coordination-involved daily exercises requires the neuromuscular features that represent the fatigue-induced characteristics of spatiotemporal adaptions of multiple muscles and the estimator that captures the time-evolving progression of fatigue. In this paper, we propose to depict fatigue by the features of muscle compensation and spinal module activation changes and estimate continuous fatigue by a physiological rationale model. First, we extract muscle synergy fractionation and the variance of spinal module spikings as features inspired by the prior of fatigue-induced neuromuscular adaptations. Second, we treat the features as observations and develop a Bayesian Gaussian process to capture the time-evolving progression. Third, we solve the issue of lacking supervision information by mathematically formulating the time-evolving characteristics of fatigue as the loss function. Finally, we adapt the metrics that follow the physiological principles of fatigue to quantitatively evaluate the performance. Our extensive experiments present a 0.99 similarity between days, a over 0.7 similarity with other views of fatigue and a nearly 1 weak monotonicity, which outperform other methods. This study would aim the objective assessment of muscle fatigue., Comment: submitted to IEEE JBHI

Deep learning-based human activity recognition (HAR) methods have shown great promise in the applications of smart healthcare systems and wireless body sensor network (BSN). Despite their demonstrated performance in laboratory settings, the real-world implementation of such methods is still hindered by the cross-subject issue when adapting to new users. To solve this issue, we propose ActiveSelfHAR, a framework that combines active learning's benefit of sparsely acquiring data with actual labels and self- training's benefit of effectively utilizing unlabeled data to enable the deep model to adapt to the target domain, i.e., the new users. In this framework, the model trained in the last iteration or the source domain is first utilized to generate pseudo labels of the target-domain samples and construct a self-training set based on the confidence score. Second, we propose to use the spatio-temporal relationships among the samples in the non-self-training set to augment the core set selected by active learning. Finally, we combine the self-training set and the augmented core set to fine-tune the model. We demonstrate our method by comparing it with state-of-the-art methods on two IMU-based datasets and an EMG-based dataset. Our method presents similar HAR accuracies with the upper bound, i.e. fully supervised fine-tuning with less than 1\% labeled data of the target dataset and significantly improves data efficiency and time cost. Our work highlights the potential of implementing user-independent HAR methods into smart healthcare systems and BSN.

Invisible cloaking is one of major outcomes of the metamaterial research, but the practical potential, in particular for high frequencies (e.g., microwave to visible light), is fatally challenged by the complex material properties they usually demand. On the other hand, it will be advantageous and also technologically instrumental to design cloaking devices for applications at low frequencies where electromagnetic components are favorably uncoupled. In this work, we vastly develop the bilayer approach to create a three-dimensional magnetic cloak able to work in both static and dynamic fields. Under the quasi-static approximation, we demonstrate a perfect magnetic cloaking device with a large frequency band from zero to 250 kHz. The practical potential of our device is experimentally verified by using a commercial metal detector, which may lead us to having a real cloaking application where the dynamic magnetic field can be manipulated in desired ways., Comment: 16 pages and 5 figures

We demonstrated an ultra-broadband, polarization-insensitive and wide-angle metamaterial absorber for terahertz (THz) frequencies using arrays of truncated pyramid unit structure made of metal-dielectric multilayer composite. In our design each sub-layer behaving as an effective waveguide is gradually modified in their lateral width to realize a wideband response by effectively stitching together the resonance bands of different waveguide modes. Experimentally, our five layer sample with a total thickness 21um is capable of producing a large absorptivity above 80% from 0.7 to 2.3 THz up to the maximum measurement angle 40{\deg}. The full absorption width at half maximum (FWHM) of our device is around 127%, greater than those previously reported for THz frequencies. Our absorber design has high practical feasibility and can be easily integrated with the semiconductor technology to make high efficient THz-oriented devices., Comment: 5 figures