Eskildsenburke8030

Finally, practical and numerical examples are taken to verify the proposed optimization results.This article studies the multi-H∞ controls for the input-interference nonlinear systems via adaptive dynamic programming (ADP) method, which allows for multiple inputs to have the individual selfish component of the strategy to resist weighted interference. In this line, the ADP scheme is used to learn the Nash-optimization solutions of the input-interference nonlinear system such that multiple H∞ performance indices can reach the defined Nash equilibrium. First, the input-interference nonlinear system is given and the Nash equilibrium is defined. An adaptive neural network (NN) observer is introduced to identify the input-interference nonlinear dynamics. Then, the critic NNs are used to learn the multiple H∞ performance indices. A novel adaptive law is designed to update the critic NN weights by minimizing the Hamiltonian-Jacobi-Isaacs (HJI) equation, which can be used to directly calculate the multi-H∞ controls effectively by using input-output data such that the actor structure is avoided. Moreover, the control system stability and updated parameter convergence are proved. Finally, two numerical examples are simulated to verify the proposed ADP scheme for the input-interference nonlinear system.Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts the observations. Usually, due to such events' rarity, to train deep learning (DL) models on the anomaly detection (AD) task, scientists only rely on ``normal data, i.e., nonanomalous samples. Thus, letting the neural network infer the distribution beneath the input data. In such a context, we propose a novel framework, named multilayer one-class classification (MOCCA), to train and test DL models on the AD task. Specifically, we applied our approach to autoencoders. A key novelty in our work stems from the explicit optimization of the intermediate representations for the task at hand. Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i.e., using the output of the last layer only, MOCCA explicitly leverages the multilayer structure of deep ading the benefits of our training procedure.Segmenting breast tumors from dynamic contrast-enhanced magnetic resonance (DCE-MR) images is a critical step for early detection and diagnosis of breast cancer. However, variable shapes and sizes of breast tumors, as well as inhomogeneous background, make it challenging to accurately segment tumors in DCE-MR images. Therefore, in this article, we propose a novel tumor-sensitive synthesis module and demonstrate its usage after being integrated with tumor segmentation. To suppress false-positive segmentation with similar contrast enhancement characteristics to true breast tumors, our tumor-sensitive synthesis module can feedback differential loss of the true and false breast tumors. Thus, by following the tumor-sensitive synthesis module after the segmentation predictions, the false breast tumors with similar contrast enhancement characteristics to the true ones will be effectively reduced in the learned segmentation model. Moreover, the synthesis module also helps improve the boundary accuracy while inaccurate predictions near the boundary will lead to higher loss. For the evaluation, we build a very large-scale breast DCE-MR image dataset with 422 subjects from different patients, and conduct comprehensive experiments and comparisons with other algorithms to justify the effectiveness, adaptability, and robustness of our proposed method.Recently introduced deep reinforcement learning (DRL) techniques in discrete-time have resulted in significant advances in online games, robotics, and so on. Inspired from recent developments, we have proposed an approach referred to as Quantile Critic with Spiking Actor and Normalized Ensemble (QC_SANE) for continuous control problems, which uses quantile loss to train critic and a spiking neural network (NN) to train an ensemble of actors. The NN does an internal normalization using a scaled exponential linear unit (SELU) activation function and ensures robustness. The empirical study on multijoint dynamics with contact (MuJoCo)-based environments shows improved training and test results than the state-of-the-art approach population coded spiking actor network (PopSAN).This article proposes two adaptive asymptotic tracking control schemes for a class of interconnected systems with unmodeled dynamics and prescribed performance. By applying an inherent property of radial basis function (RBF) neural networks (NNs), the design difficulties aroused from the unknown interactions among subsystems and unmodeled dynamics are overcome. Then, in order to ensure that the tracking errors can be suppressed in the specified range, the constrained control problem is transformed into the stabilization problem by using an auxiliary function. Based on the adaptive backstepping method, a time-triggered controller is constructed. It is proven that under the framework of Barbalat's lemma, all the variables in the closed-loop system are bounded and the tracking errors are further ensured to converge to zero asymptotically. Furthermore, the event-triggered strategy with a variable threshold is adopted to make more precise control such that the better system performance can be obtained, which reduces the system communication burden under the condition of limited communication resources. Finally, an illustrative example is provided to demonstrate the effectiveness of the proposed control scheme.Data augmentation has been observed playing a crucial role in achieving better generalization in many machine learning tasks, especially in unsupervised domain adaptation (DA). It is particularly effective on visual object recognition tasks as images are high-dimensional with an enormous range of variations that can be simulated. Existing data augmentation techniques, however, are not explicitly designed to address the differences between different domains. Expert knowledge about the data is required, as well as manual efforts in finding the optimal parameters. In this article, we propose a novel domain-adaptive augmentation method by making use of a state-of-the-art style transfer method and domain discrepancy measurement. Specifically, we measure the discrepancy between source and target domains, and use it as a guide to augment the original source samples using style transferred source-to-target samples. The proposed domain-adaptive augmentation method is data and model agnostic that can be easily incorporated with state-of-the-art DA algorithms. We show empirically that, by using this domain-adaptive augmentation, we are able to gradually reduce the discrepancy between the source and target samples, and further boost the adaptation performance using different DA algorithms on three popular domain adaption datasets.This paper presents a second-order voltage-controlled oscillator (VCO)-based front-end for the direct digitization of biopotential signals. This work addresses the non-linearity of VCO-based ADC architectures with a mismatch resilient, multi-phase quantizer, a gated-inverted-ring oscillator (GIRO), achieving >110-dB SFDR. Leveraging the time-domain encoding of the first integrator, the ADC's power is dynamically scaled with the input amplitude enabling up to 35% power savings in the absence of motion artifacts or interference. An auxiliary input-impedance booster increases the ADC's input impedance to 50 MΩ across the entire bandwidth. Fabricated in a 65-nm CMOS process, this ADC achieves 92.3-dB SNDR in a 1 kHz BW while consuming 5.8 µW for a 174.7 dB Schreier FoM.Low-intensity transcranial focused ultrasound stimulation (tFUS), as a noninvasive neuromodulation modality, has shown to be effective in animals and even humans with improved millimeter-scale spatial resolution compared to its noninvasive counterparts. But conventional tFUS systems are built with bulky single-element ultrasound (US) transducers that must be mechanically moved to change the stimulation target. To achieve large-scale ultrasound neuromodulation (USN) within a given tissue volume, a US transducer array should electronically be driven in a beamforming fashion (known as US phased array) to steer focused ultrasound beams towards different neural targets. This paper presents the theory and design methodology of US phased arrays for USN at a large scale. For a given tissue volume and sonication frequency (f), the optimal geometry of a US phased array is found with an iterative design procedure that maximizes a figure of merit (FoM) and minimizes side/grating lobes (avoiding off-target stimulation). The proposed FoM provides a balance between the power efficiency and spatial resolution of a US array in USN. BTK inhibitor nmr A design example of a US phased array has been presented for USN in a rat's brain with an optimized linear US array. In measurements, the fabricated US phased array with 16 elements (16.7×7.7×2 mm3), driven by 150 V (peak-peak) pulses at f = 833.3 kHz, could generate a focused US beam with a lateral resolution of 1.6 mm and pressure output of 1.15 MPa at a focal distance of 12 mm. The capability of the US phased array in beam steering and focusing from -60o to 60o angles was also verified in measurements.Despite the utility of musculoskeletal dynamics modeling, there exists no safe, noninvasive method of measuring in vivo muscle output force in real time - limiting both biomechanical insight into dexterous motion and intuitive control of assistive devices. In this paper, we demonstrate that muscle deformation constitutes a promising, yet unexplored signal from which to 1) infer such forces and 2) build novel device control schemes. Through a case study of the elbow joint on a preliminary cohort of 10 subjects, we show that muscle deformation (specifically, thickness change of the brachioradialis, as measured via ultrasound and tracked via optical flow) correlates well with elbow output force to an extent comparable with standard surface electromyography (sEMG) activation during varied isometric elbow contraction. We then show that, given real-time visual feedback, subjects can readily perform a trajectory tracking task using this deformation signal, and that they largely prefer this method to a comparable sEMG-based control scheme and perform the tracking task with similar accuracy. Together, these contributions illustrate muscle deformation's potential utility for both biomechanical study of individual muscle dynamics and device control, in a manner that - thanks to, unlike sEMG, the localized nature of the signal and its tight mechanistic coupling to output force - is readily extensible to multiple muscles and device degrees of freedom. To enable such future extensions, all modeling, tracking, and visualization software described in this paper, as well as all raw and processed data, have been made available on SimTK as part of the Open-Arm project (https//simtk.org/projects/openarm) for general research use.Predicting the next foot placement of humans during walking can help improve compliant interactions between humans and walking aid robots. Previous studies have focused on foot placement estimation with wearable inertial sensors after heel-strike, but few have predicted foot placements in advance during the early swing phase. In this study, a Bayesian inference-based foot placement prediction approach was proposed. Possible foot placements were modeled as a probability distribution grid map. With selected foot motion feature events detected sequentially in the early swing phase, the foot placement probability map could be updated iteratively using the feature models we built. The weighted center of the probability distribution was regarded as the predicted foot placement. Prediction errors were evaluated with collected walking data sets. When testing with the data from inertial measurement units, the prediction errors were (5.46 cm ± 10.89 cm, -0.83 cm ± 10.56 cm) for cross-velocity walking data and (-4.99 cm ± 12.