Graph neural networks (GNNs) excel in various graph-based tasks due to their exceptional ability to process non-Euclidean data. However, recent research indicates that their predictive performance is highly vulnerable to perturbations from intentionally manipulated data. Current node injection attack methods disrupt GNN training by injecting numerous nodes, often in excessive amounts, making them easily detectable. To address this issue, this study introduces a structure-aware node injection attack (SNIA), which enables effective and subtle attacks under extreme budget constraints. The scheme leverages the network topology to construct an attack candidate set and applies homogeneity constraints to regulate the generation of perturbed features. By eliminating the dependency on surrogate models for generating perturbed data, SNIA effectively diminishes the global classification performance of GNNs based on the network's inherent structure. We conducted attack experiments with the SNIA scheme on real-world network datasets against both general and defensive GNNs. The experimental findings reveal that it significantly surpasses the existing state-of-the-art methods in attack efficiency, while also showcasing outstanding generalization and resilience.

Accurately identifying influential nodes in complex networks is crucial for understanding their structure and dynamics. Traditional methods for measuring node centrality often struggle to capture the inherent uncertainties in node relationships and to model specific higher-order interaction patterns, limiting their reliable evaluations in hypergraph contexts. To address this challenge, we propose a novel approach called Fuzzy Multi-Hierarchical Centrality (FMHC), which integrates fuzzy theory with multi-hierarchical topological analysis for centrality assessment in hypergraphs. By synthesizing inter-node fuzzy distances, node-to-edge fuzzy membership degrees, and mutual information associations among nodes and edges, FMHC constructs a multi-hierarchical evaluation architecture to generate comprehensive and discriminative importance scores for each node. Extensive experiments on nine real-world datasets demonstrate that FMHC consistently outperforms eight classical and state-of-the-art benchmarks across three key evaluation criteria: the capacity to identify nodes with high spreading influence, alignment with the Susceptible-Infected-Recovered (SIR) epidemic model, and monotonicity in ranking discrimination. These findings validate the effectiveness, robustness, and superiority of FMHC in hypergraph environments.

Quantum image processing (QIMP) was first introduced in 2003 by Venegas-Andraca and Bose at the University of Oxford. This field attempts to overcome the limitations of classical computers and the potentially overwhelming complexity of classical algorithms by providing a more effective way to store and manipulate visual information. Over the past 20 years, QIMP has become an active area of research, experiencing rapid and vigorous development. However, these advancements have suffered from an imbalance, as inherent critical issues have been largely ignored. In this article, we review the original intentions for this field and analyze various unresolved issues from a new perspective, including QIMP algorithm design, potential advantages and limitations, technological debates, and potential directions for future development. We suggest that the 20-year milestone could serve as a new beginning and advocate for more researchers to focus their attention on this pursuit, helping to overcome bottlenecks, and achieving more practical results in the future.

Multi-modal emotion analysis, as an important direction in affective computing, has attracted increasing attention in recent years. Most existing multi-modal emotion recognition studies are targeted at a classification task that aims to assign a specific emotion category to a combination of several heterogeneous input data, including multimedia signals and physiological signals. Compared to single-class emotion recognition, a growing number of recent psychological evidence suggests that different discrete emotions may co-exist at the same time, which promotes the development of mixed-emotion recognition to identify a mixture of basic emotions. Although most current studies treat it as a multi-label classification task, in this work, we focus on a challenging situation where both positive and negative emotions are presented simultaneously, and propose a multi-modal mixed emotion recognition framework, namely EmotionDict. The key characteristics of our EmotionDict include the following. (1) Inspired by the psychological evidence that such a mixed state can be represented by combinations of basic emotions, we address mixed emotion recognition as a label distribution learning task. An emotion dictionary has been designed to disentangle the mixed emotion representations into a weighted sum of a set of basic emotion elements in a shared latent space and their corresponding weights. (2) While many existing emotion distribution studies are built on a single type of multimedia signal (such as text, image, audio, and video), we incorporate physiological and overt behavioral multi-modal signals, including electroencephalogram (EEG), peripheral physiological signals, and facial videos, which directly display the subjective emotions. These modalities have diverse characteristics given that they are related to the central or peripheral nervous system, and the motor cortex. (3) We further design auxiliary tasks to learn modality attentions for modality integration. Experiments on two datasets show that our method outperforms existing state-of-the-art approaches on mixed-emotion recognition.

The advent of the fourth industrial revolution along with developments in other emerging technologies, such as Internet of Things, big data, artificial intelligence as well as cloud and quantum computing, smart healthcare systems (SHS) are becoming ubiquitous in our daily lives. Meanwhile, patients, doctors, and other medical personnel rely on the safe and efficient storage, transmission, and analysis of medical images and electronic health records for successful diagnosis, treatment, and management of different ailments. Moreover since, for various reasons, medical images are always the target of different illicit criminal activities, studies to utilise advanced information technologies to safeguard the confidentiality, integrity, and availability of such data have become a major priority in all SHS platforms. Our study evaluates recent efforts to deploy emerging technologies to design, secure, and enhance the efficiency of SHS that are based on medical images. It is hoped that this work will stimulate further interest aimed at the pursuit of more advanced algorithms and frameworks covering all aspects of security and privacy in emerging and future smart healthcare applications.

With the advent of a fifth-generation mobile network and developments in technologies such as the Internet of Medical Things, smart healthcare systems are becoming ubiquitous in our daily lives. Patients, doctors, and other medical personnel rely on the safe and efficient storage, transmission, and analysis of electronic health records, particularly medical images, for successful diagnosis, treatment, and management of different ailments. In this study, a multiwatermarking scheme is proposed for medical images based on quantum random walk and the brain storm optimization algorithm. A logo image used to verify medical image integrity is embedded in regions of interest, and text data are embedded in regions of non-interest to conceal private hospital and patient information. This process improves the accuracy of medical image verification and helps to ensure authenticity. A series of experiments were conducted to validate the capacity, security, robustness, and imperceptibility of the proposed multiwatermarking scheme.

Loneliness and isolation are on the rise worldwide, threatening human well-being and the wellness of different age groups and backgrounds. Notably, global social distancing measures during the COVID-19 crisis have exacerbated this problem, resulting in various psychological and physiological ailments. Within both the categories of social and medical robots, companion robots are capable of engaging emotionally with users and providing continuous monitoring and assessment of their health. In this study, we propose a framework for modeling the emotion space of companion robots to facilitate their emotion generation and transition based on Plutchik’s wheel of emotions and reversible quantum circuit schemes. Superposition encodings allow fewer computing resources for the generation and storage of emotional states, and by using unitary operations, they facilitate easier emotion transition and recovery over different intervals. Further, an encryption strategy is designed based on the emotion communication architecture to secure the emotion-related data in human-robot interaction. It is hoped that such an integrative framework and research agenda exploring the role of companion robots will be useful to care for users’ social health by mitigating their negative emotions, especially during difficult times.

A method to analyze the similarity between two quantum images of the same size is proposed based on a representation for the quantum images. The similarity value is estimated according to the probability distribution of the results from quantum measurements. The proposed method is fast because a single operation can transform the entire information encoded in two images simultaneously. Two simulation-based experiments, which provide a reasonable estimation to the quantum images' similarity, are implemented using Matlab on a classical computer by means of linear algebra with complex vectors as quantum states and unitary matrices as unitary transformations. It also opens the door towards image searching from a database on quantum computers.

A multimodal gesture recognition method is proposed based on Choquet integral by fusing information from camera and 3D accelerometer data. By calculating the optimal fuzzy measures for the camera recognition module and the accelerometer recognition module, the proposal obtains enough recognition rate 92.7% in average for 8 types of gestures by improving the recognition rate approximate 20% compared to that of each module. The proposed method aims to realize the casual communication from humans to robots by integrating nonverbal gesture messages and verbal messages.