This paper focuses on designing an adaptive radial basis function neural network U+0028 RBFNN U+0029 control method for a class of nonlinear systems with unknown parameters and bounded disturbances. The problems raised by the functions external disturbances in system are overcome RBFNN, combined single parameter direct method. novel is designed to reduce amount computations effectively. uniform ultimate boundedness closed U+002D loop guaranteed proposed controller. A coupled motor drives CMD...

The diagnosis of mild cognitive impairment (MCI), a prodromal stage Alzheimer's disease (AD), is essential for initiating timely treatment to delay the onset AD. Previous studies have shown potential functional near-infrared spectroscopy (fNIRS) diagnosing MCI. However, preprocessing fNIRS measurements requires extensive experience identify poor-quality segments. Moreover, few explored how proper multi-dimensional features influence classification results disease. Thus, this study outlined...

Alzheimer's Disease (AD) accounts for the majority of dementia, and Mild Cognitive Impairment (MCI) is early stage AD. Early accurate diagnosis dementia plays a vital role in more targeted treatments effectively halting disease progression. However, clinical requires various examinations, which are expensive require high level expertise from doctor. In this paper, we proposed classification method based on multi-modal data including Electroencephalogram (EEG), eye tracking behavioral AD MCI....

Magnetic Resonance Imaging (MRI) has been proven to be an efficient way diagnose Alzheimer's disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based data-driven CNN methods using a large-scale longitudinal dataset. However, most of existing datasets are fragmented due unexpected quits volunteers. To tackle this problem, we propose novel Temporal Recurrent Generative Adversarial Network (TR-GAN) complete missing sessions datasets. Unlike GAN-based...

Train wheel sets must be periodically inspected for possible or actual premature failures and it is very significant to record the wear history full life of utilization sets. This means that an online measuring system could great benefit overall process control. An non-contact method a set’s geometric parameters based on opto-electronic technique presented in this paper. A charge coupled device (CCD) camera with selected optical lens frame grabber was used capture image light profile set...

Quantitative assessment of hand function can assist therapists in providing appropriate rehabilitation strategies, which plays an essential role post-stroke rehabilitation. Conventionally, the process relies heavily on clinical experience and lacks quantitative analysis. To quantitatively assess motor patients with hemiplegia, this study proposes a novel multi-modality fusion framework. This framework includes three components: kinematic feature extraction based graph convolutional network...

Recent advances in deep learning have led to increased adoption of convolutional neural networks (CNN) for structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) detection. AD results widespread damage neurons different brain regions and destroys their connections. However, current CNN-based methods struggle relate spatially distant information effectively. To solve this problem, we propose a graph reasoning module (GRM), which can be directly incorporated into detection...

During the rice milling process, single and continuous compression occurs between brown processing parts. When external load exceeds yield limit of rice, kernels are damaged; with an increase in deformation or extent compression, amount damage to expands accumulates, ultimately leading fracture breakage kernels. In order investigate mechanical characteristics under real-world working conditions, this study constructs elastic–plastic model a based on Hertz theory theory; accuracy is verified...

Recent advancements in AI have revolutionized property prediction materials science and accelerating material discovery. Graph neural networks (GNNs) stand out due to their ability represent crystal structures as graphs, effectively capturing local interactions delivering superior predictions. However, these methods often lose critical global information, such systems repetitive unit connectivity. To address this, we propose CAST, a cross-attention-based multimodal fusion model that...

Named entity recognition (NER) is the basic task of constructing a high-quality knowledge graph, which can provide reliable in auxiliary diagnosis dairy cow disease, thus alleviating problems missed and misdiagnosis due to lack professional veterinarians China. Targeting characteristics Chinese diseases corpus, we propose an ensemble NER model incorporating character-level, pinyin-level, glyph-level, lexical-level features characters. These multi-level were concatenated fed into...

Strawberry (Fragaria × ananassa) is the most widely cultivated small berries in world. They are not only delicious, juicy, and nutritious, but also have important economic value. However, current research on endophytic bacteria related to strawberry limited. This work provides a comprehensive description of composition diversity bacterial communities three niches (root, stem, leaf) cultivars (White Elves, Tokun, Akihime). study indicated that differ significantly between belowground niche...

For stroke patients, hand function assessment is an important part of the rehabilitation process. The assessment, however, requires patient to complete a series actions under guidance therapist who then scores patient’s performance. This type both time-consuming and highly subjective. Therefore, in order achieve fast, objective accurate this paper adopts non-contact infrared imaging device, Leap Motion, measure motion information uses these infer hand’s level. improves traditional way from...

Abstract This paper mainly focuses on designing an active vibration control for a flexible‐link manipulator in the presence of input constraint and unknown spatially infinite dimensional disturbances. The we studied can be taken as Euler–Bernoulli beam, dynamic model which has form partial differential equations. As existence disturbances first design disturbance observer to estimate proposed is guaranteed exponentially stable. Then, taking saturation into account, novel...

A sliding mode control method is developed in this study for application to a class of underactuated systems with bounded unknown disturbance and sensor actuator faults. In the proposed method, robustness item compensates Nussbaum function realises faults tolerance simultaneously, all signals system are proven be bounded. radial basis (RBF) neural network estimate functions system. Finally, Hurwitz stability analysis conducted guarantee closed-loop Simulations wherein coupled motor driving...

This article studies the stability problem for a three-dimensional string with variable length in case of input quantization. A nonlinear partial differential equation model is used to depict dynamic characteristics length-varying flexible distributed parameters. The control signals are effectively mapped from continuous region discrete set numerical before being transmitted through communication channels using quantizers. With no information about quantizers, vibration eliminated under...

Abstract In this article, boundary control strategy is adopted to suppress the vibration of a flexible three‐dimensional (3D) marine riser simultaneously against both sensor and actuator faults. The 3D distributed parameter system modeled as partial differential equations. During normal operation system, all components will behave optimally. However, if appear fault, work abnormally. While faulty, output signal have errors, error be input actuator. terms once appears fault problem, should...