Network

Contrastive learning (CL) has emerged as a powerful approach for self-supervised learning. However, it suffers from sampling bias, which hinders its performance. While the mainstream solutions, hard negative mining (HNM) and supervised CL (SCL), have been proposed to mitigate this critical issue, they do not effectively address graph CL (GCL). To address it, we propose graph positive sampling (GPS) and three contrastive objectives. The former is a novel learning paradigm designed to leverage the inherent properties of graphs for improved GCL models, which utilizes four complementary similarity measurements, including node centrality, topological distance, neighborhood overlapping, and semantic distance, to select positive counterparts for each node...

Probabilistic latent variable models (PLVMs), such as probabilistic principal component analysis (PPCA), are widely employed in process monitoring and fault detection of industrial processes. This article proposes a novel deep PPCA (DePPCA) model, which has the advantages of both probabilistic modeling and deep learning. The construction of DePPCA includes a greedy layer-wise pretraining phase and a unified end-to-end fine-tuning phase. The former establishes a hierarchical deep structure based on cascading multiple layers of the PPCA module to extract high-level features...

Recently, the multiscale problem in computer vision has gradually attracted people's attention. This article focuses on multiscale representation for object detection and recognition, comprehensively introduces the development of multiscale deep learning, and constructs an easy-to-understand, but powerful knowledge structure. First, we give the definition of scale, explain the multiscale mechanism of human vision, and then lead to the multiscale problem discussed in computer vision. Second, advanced multiscale representation methods are introduced, including pyramid representation, scale-space representation, and multiscale geometric representation...

In zero-shot learning (ZSL), attribute knowledge plays a vital role in transferring knowledge from seen classes to unseen classes. However, most existing ZSL methods learn biased attribute knowledge, which usually results in biased attribute prediction and a decline in zero-shot recognition performance. To solve this problem and learn unbiased attribute knowledge, we propose a visual attribute Transformer for zero-shot recognition (ZS-VAT), which is an effective and interpretable Transformer designed specifically for ZSL...

High-efficiency deep learning (DL) models are necessary not only to facilitate their use in devices with limited resources but also to improve resources required for training. Convolutional neural networks (ConvNets) typically exert severe demands on local device resources and this conventionally limits their adoption within mobile and embedded platforms. This brief presents work toward utilizing static convolutional filters generated from the space of local binary patterns (LBPs) and Haar features to design efficient ConvNet architectures...

Knowledge tracing (KT) refers to predicting learners' performance in the future according to their historical responses, which has become an essential task in intelligent tutoring systems. Most deep learning-based methods usually model the learners' knowledge states via recurrent neural networks (RNNs) or attention mechanisms. Recently emerging graph neural networks (GNNs) assist the KT model to capture the relationships such as question-skill and question-learner. However, non-pairwise and complex higher-order information among responses is ignored...

Individuals with neurological disorders often exhibit altered manual dexterity and muscle weakness in their upper limbs. These motor impairments with tremor lead to severe difficulties in performing Activities of Daily Living (ADL). There is a critical need for ADL-focused robotic training that improves individual's strength when engaging with dexterous ADL tasks. This research introduces a new approach to training ADLs by employing a novel robotic rehabilitation system, Spherical Parallel INstrument for Daily Living Emulation (SPINDLE), which incorporates Virtual Reality (VR) to simulate ADL tasks...

Graph neural networks (GNN) suffer from severe inefficiency due to the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the training of GNN is usually time-consuming. To address this problem, we propose to decouple a multi-layer GNN as multiple simple modules for more efficient training, which is comprised of classical forward training (FT) and designed backward training (BT). Under the proposed framework, each module can be trained efficiently in FT by stochastic algorithms without distortion of graph information owing to its simplicity...

Deep Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robustness problems and solved separately, since they belong to training-time and inference-time attacks respectively. However, this paper revealed that there is an intriguing connection between them: (1) planting a backdoor into a model will significantly affect the model's adversarial examples; (2) for an infected model, its adversarial examples have similar features as the triggered images...

With the rapid development of Quantum Machine Learning, quantum neural networks (QNN) have experienced great advancement in the past few years, harnessing the advantages of quantum computing to significantly speed up classical machine learning tasks. Despite their increasing popularity, the quantum neural network is quite counter-intuitive and difficult to understand, due to their unique quantum-specific layers (e.g., data encoding and measurement) in their architecture. It prevents QNN users and researchers from effectively understanding its inner workings and exploring the model training status...

Emotion recognition from electroencephalogram (EEG) signals is a critical domain in biomedical research with applications ranging from mental disorder regulation to human-computer interaction. In this paper, we address two fundamental aspects of EEG emotion recognition: continuous regression of emotional states and discrete classification of emotions. While classification methods have garnered significant attention, regression methods remain relatively under-explored. To bridge this gap, we introduce MASA-TCN, a novel unified model that leverages the spatial learning capabilities of Temporal Convolutional Networks (TCNs) for EEG emotion regression and classification tasks...

Proximal femoral fracture segmentation in computed tomography (CT) is essential in the preoperative planning of orthopedic surgeons. Recently, numerous deep learning-based approaches have been proposed for segmenting various structures within CT scans. Nevertheless, distinguishing various attributes between fracture fragments and soft tissue regions in CT scans frequently poses challenges, which have received comparatively limited research attention. Besides, the cornerstone of contemporary deep learning methodologies is the availability of annotated data, while detailed CT annotations remain scarce...

The brain networks for the first (L1) and second (L2) languages are dynamically formed in the bilingual brain. This study delves into the neural mechanisms associated with logographic-logographic bilingualism, where both languages employ visually complex and conceptually rich logographic scripts. Using functional Magnetic Resonance Imaging, we examined the brain activity of Chinese-Japanese bilinguals and Japanese-Chinese bilinguals as they engaged in rhyming tasks with Chinese characters and Japanese Kanji...

Acupuncture, a traditional Chinese therapy, is gaining attention for its impact on the brain. While existing electroencephalogram and functional magnetic resonance image research has made significant contributions, this paper utilizes stereo-electroencephalography data for a comprehensive exploration of neurophysiological effects. Employing a multi-scale approach, channel-level analysis reveals notable $\delta $-band activity changes during acupuncture. At the brain region level, acupuncture modulated connectivity between the paracentral lobule and the precentral gyrus...

Esophageal squamous cell carcinoma (ESCC) is the predominant form of esophageal cancer and is characterized by an unfavorable prognosis. To elucidate the distinct molecular alterations in ESCC and investigate therapeutic targets, we performed a comprehensive analysis of transcriptomic, proteomic, and phosphoproteomic data derived from 60 paired treatment-naive ESCC and adjacent non-tumor tissue samples. Additionally, we conducted a correlation analysis to describe the regulatory relationship between transcriptomic and proteomic processes, revealing alterations in key metabolic pathways...

RATIONALE: The shift toward virtual academic detailing (AD) was accelerated by the COVID-19 pandemic. AIMS AND OBJECTIVES: We aimed to examine the role of external, contextual, and intrinsic programme-specific factors in virtual engagement of healthcare providers (HCPs) and delivery of AD. METHODS: AD groups throughout North America were contacted to participate in semistructured interviews. An interview guide was constructed by adapting the Consolidated Framework for Implementation Research (CFIR)...

BACKGROUNDPersistent cough and dyspnea are prominent features of post-acute sequelae of SARS-CoV-2 (also termed 'Long COVID'); however, physiologic measures and clinical features associated with these pulmonary symptoms remain poorly defined. Using longitudinal pulmonary function testing (PFTs) and CT imaging, this study aimed to identify the characteristics and determinants of pulmonary Long COVID.METHODSThis single-center retrospective study included 1,097 patients with clinically defined Long COVID characterized by persistent pulmonary symptoms (dyspnea, cough, and chest discomfort) lasting for ≥1 month after resolution of primary COVID infection...

No abstract text is available yet for this article.

IMPORTANCE: Postoperative delirium is a common and impactful neuropsychiatric complication in patients undergoing coronary artery bypass grafting surgery. Cognitive training may enhance cognitive reserve, thereby reducing postoperative delirium. OBJECTIVE: To determine whether preoperative cognitive training reduces the incidence of delirium in patients undergoing coronary artery bypass grafting. DESIGN, SETTING, AND PARTICIPANTS: This prospective, single-blind, randomized clinical trial was conducted at 3 university teaching hospitals in southeastern China with enrollment between April 2022 and May 2023...

IMPORTANCE: Self-report surveys suggest that long-lasting taste deficits may occur after SARS-CoV-2 infection, influencing nutrition, safety, and quality of life. However, self-reports of taste dysfunction are inaccurate, commonly reflecting deficits due to olfactory not taste system pathology; hence, quantitative testing is needed to verify the association of post-COVID-19 condition with taste function. OBJECTIVE: To use well-validated self-administered psychophysical tests to investigate the association of COVID-19 with long-term outcomes in taste and smell function...