Exploring the missing values is an essential but challenging issue due to the complex latent spatio-temporal correlation and dynamic nature of time series. Owing to the outstanding performance in dealing with structure learning potentials, Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs) are often used to capture such complex spatio-temporal features in multivariate time series. However, these data-driven models often fail to capture the essential spatio-temporal relationships when significant signal corruption occurs. Additionally, calculating the high-order neighbor nodes in these models is of high computational complexity. To address these problems, we propose a novel higher-order spatio-temporal physics-incorporated GNN (HSPGNN). Firstly, the dynamic Laplacian matrix can be obtained by the spatial attention mechanism. Then, the generic inhomogeneous partial differential equation (PDE) of physical dynamic systems is used to construct the dynamic higher-order spatio-temporal GNN adaptively to obtain the missing time series values. Moreover, we estimate the missing impact by Normalizing Flows (NF) to evaluate the importance of each node in the graph for better explainability. Experimental results on four benchmark datasets demonstrate the effectiveness of HSPGNN and the superior performance when combining various order neighbor nodes. Also, graph-like optical flow, dynamic graphs, and missing impact can be obtained naturally by HSPGNN, which provides better dynamic analysis and explanation than traditional data-driven models.

Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. It faces issues of forgetting previously learned classes and overfitting on few-shot classes. An efficient strategy is to learn features that are discriminative in both base and incremental sessions. Current methods improve discriminability by manually designing inter-class margins based on empirical observations, which can be suboptimal. The emerging Neural Collapse (NC) theory provides a theoretically optimal inter-class margin for classification, serving as a basis for adaptively computing the margin. Yet, it is designed for closed, balanced data, not for sequential or few-shot imbalanced data. To address this gap, we propose a Meta-learning- and NC-based FSCIL method, MetaNC-FSCIL, to compute the optimal margin adaptively and maintain it at each incremental session. Specifically, we first compute the theoretically optimal margin based on the NC theory. Then we introduce a novel loss function to ensure that the loss value is minimized precisely when the inter-class margin reaches its theoretically best. Motivated by the intuition that “learn how to preserve the margin” matches the meta-learning’s goal of “learn how to learn”, we embed the loss function in base-session meta-training to preserve the margin for future meta-testing sessions. Experimental results demonstrate the effectiveness of MetaNC-FSCIL, achieving superior performance on multiple datasets. The code is available at https://github.com/qihangran/metaNC-FSCIL.

Recently, the rapid development of Unmanned Aerial Vehicles (UAVs) enables ecological conservation, such as low-carbon and “green” transport, which helps environmental sustainability . In order to address control issues in a given region, UAV charging infrastructure is urgently needed. To better achieve this task, an investigation into the T–S fuzzy modeling for Sustainable Hypersonic Vehicles (SHVs) with Markovian jump parameters and H ∞ attitude control in three channels was conducted. Initially, the reentry dynamics were transformed into a control–oriented affine nonlinear model . Then, the original T–S local modeling method for SHV was projected by primarily referring to Taylor's expansion and fuzzy linearization methodologies. After the estimation of precision and controller complexity was assumed, the fuzzy model for jump nonlinear systems mainly consisted of two levels: a crisp level and a fuzzy level. The former illustrates the jumps, and the latter a fuzzy level that represents the nonlinearities of the system. Then, a systematic method built in a new coupled Lyapunov function for a stochastic fuzzy controller was used to guarantee the closed–loop system for H ∞ gain in the presence of a predefined performance index. Ultimately, numerical simulations were conducted to show how the suggested controller can be successfully applied and functioned in controlling the original attitude dynamics.

No system entity within a contemporary distributed cyber system can be entirely trusted. Hence, the classic centralized trust management method cannot be directly applied to it. Blockchain technology is essential to achieving decentralized trust management, its consensus mechanism is useful in addressing large-scale data sharing and data consensus challenges. Herein, an n-party quantum detectable Byzantine agreement (DBA) based on the GHZ state to realize the data consensus in a quantum blockchain is proposed, considering the threat posed by the growth of quantum information technology on the traditional blockchain. Relying on the nonlocality of the GHZ state, the proposed protocol detects the honesty of nodes by allocating the entanglement resources between different nodes. The GHZ state is notably simpler to prepare than other multi-particle entangled states, thus reducing preparation consumption and increasing practicality. When the number of network nodes increases, the proposed protocol provides better scalability and stronger practicability than the current quantum DBA. In addition, the proposed protocol has the optimal fault-tolerant found and does not rely on any other presumptions. A consensus can be reached even when there are n−2 traitors. The performance analysis confirms viability and effectiveness through exemplification. The security analysis also demonstrates that the quantum DBA protocol is unconditionally secure, effectively ensuring the security of data and realizing data consistency in the quantum blockchain.

Abstract An adverse drug event (ADE) is defined as an adverse reaction resulting from improper drug use, reported in various documents such as biomedical literature, drug reviews, and user posts on social media. The recent advances in natural language processing techniques have facilitated automated ADE detection from documents. However, the contextualized information and relations among text pieces are less explored. This paper investigates contextualized language models and heterogeneous graph representations. It builds a contextualized graph embedding model for adverse drug event detection. We employ different convolutional graph neural networks and pre-trained contextualized embeddings as the building blocks. Experimental results show that our methods can improve the performance by comparing recent ADE detection models, suggesting that a text graph can capture causal relationships and dependency between different entities in a document.

As a mental disorder, depression has affected people's lives, works, and so on. Researchers have proposed various industrial intelligent systems in the pattern recognition field for audiovisual depression detection. This paper presents an end-to-end trainable intelligent system to generate high-level representations over the entire video clip. Specifically, a three-dimensional (3D) convolutional neural network equipped with a module spatiotemporal feature aggregation module (STFAM) is trained from scratch on audio/visual emotion challenge (AVEC)2013 and AVEC2014 data, which can model the discriminative patterns closely related to depression. In the STFAM, channel and spatial attention mechanism and an aggregation method, namely 3D DEP-NetVLAD, are integrated to learn the compact characteristic based on the feature maps. Extensive experiments on the two databases (i.e., AVEC2013 and AVEC2014) are illustrated that the proposed intelligent system can efficiently model the underlying depression patterns and obtain better performances over the most video-based depression recognition approaches. Case studies are presented to describes the applicability of the proposed intelligent system for industrial intelligence.

As a common mental disorder, depression has attracted many researchers from affective computing field to estimate the depression severity. However, existing approaches based on Deep Learning (DL) are mainly focused on single facial image without considering the sequence information for predicting the depression scale. In this paper, an integrated framework, termed DepNet, for automatic diagnosis of depression that adopts facial images sequence from videos is proposed. Specifically, several pretrained models are adopted to represent the low-level features, and Feature Aggregation Module is proposed to capture the high-level characteristic information for depression analysis. More importantly, the discriminative characteristic of depression on faces can be mined to assist the clinicians to diagnose the severity of the depressed subjects. Multiscale experiments carried out on AVEC2013 and AVEC2014 databases have shown the excellent performance of the intelligent approach. The root mean-square error between the predicted values and the Beck Depression Inventory-II scores is 9.17 and 9.01 on the two databases, respectively, which are lower than those of the state-of-the-art video-based depression recognition methods.

Machine Learning models learn the relationship between input and output by examples and then apply the learned models to relate unseen input. Although ML has successfully been used in almost every field, there is always room for improvement. To this end, researchers have recently been trying to implement Quantum Mechanics(QM) in ML, since it is believed that quantum-inspired ML can enhance learning rate and effectiveness. In this paper, we address a specific task of ML and present a binary classification model inspired by the quantum detection framework. We compared the model to the state of the art. Our experimental results suggest that the use of the quantum detection framework in binary classification can improve effectiveness for a number of topics of the RCV-1 test collection and that it may still provide ways to improve effectiveness for the other topics.