Images are widely used in social networks, necessitating efficient and secure transmission, especially in bandwidth-constrained environments. This article aims to develop a color image encryption algorithm that enhances security while optimizing computational efficiency. A novel parallel color image encryption algorithm based on the 2-D logistic-Rulkov neuron map (2D-LRNM) is proposed. In this approach, the three channels of the color image are first separated. Cross-channel information interaction is introduced to form three new channels, which are then processed in parallel. During the encryption process of each channel, a block-wise parallel encryption mechanism is applied, ensuring simultaneous encryption of each block. This block-wise strategy effectively leverages parallel computing resources and balances the task load. To meet the demand for a large number of keystreams during encryption, the 2D-LRNM is introduced. It combines the simplicity and chaotic properties of the Logistic map with the multitimescale dynamics and neurodynamic behaviors of the Rulkov map. By overcoming the dimensional limitations inherent in the single Logistic map, this approach extends the system to a 2-D framework, significantly increasing the complexity of chaotic behavior and improving its unpredictability. Experimental results demonstrate that the proposed encryption algorithm achieves high security and reduces computation time by approximately 83.3%.

Traditional video encryption methods protect video content by encrypting each frame individually. However, in resource-constrained environments, this approach consumes significant computational resources. To overcome this challenge, this paper proposes a novel method called “Encrypt a story (EAS)”, which aims to enhance encryption efficiency by focusing on encrypting specific segments of the video rather than encrypting each frame. The EAS refers to selecting segments in the time dimension of the video that contain important information or key events for encryption. This method leverages video segmentation techniques to focus encryption efforts on continuous key frames, significantly reducing the consumption of computational resources. To address the need for a large number of key streams during the encryption process, this paper proposes a discrete sinusoidal memristive Rulkov neuron map (DSM-RNM). Through attractor analysis, complexity comparison, Lyapunov exponent, and NIST tests, we validated its ability to generate high-performance pseudorandom sequences, which significantly enhances the security of the encryption algorithm. Notably, the DSM-RNM is shown to exhibit a phenomenon of infinitely coexisting attractors. Furthermore, by constructing a digital circuit to capture the attractors of the DSM-RNM, its potential for industrial applications is demonstrated. Evaluation results show that the EAS saves approximately 90% of the time while ensuring security, exhibiting strong practicality and efficiency

In multi-view environment, it would yield missing observations due to the limitation of the observation process. The most current representation learning methods struggle to explore complete information by lacking either cross-generative via simply filling in missing view data, or solidative via inferring a consistent representation among the existing views. To address this problem, we propose a deep generative model to learn a complete generative latent representation, namely Complete Multi-view Variational Auto-Encoders (CMVAE), which models the generation of the multiple views from a complete latent variable represented by a mixture of Gaussian distributions. Thus, the missing view can be fully characterized by the latent variables and is resolved by estimating its posterior distribution. Accordingly, a novel variational lower bound is introduced to integrate view-invariant information into posterior inference to enhance the solidative of the learned latent representation. The intrinsic correlations between views are mined to seek cross-view generality, and information leading to missing views is fused by view weights to reach solidity. Benchmark experimental results in clustering, classification, and cross-view image generation tasks demonstrate the superiority of CMVAE, while time complexity and parameter sensitivity analyses illustrate the efficiency and robustness. Additionally, application to bioinformatics data exemplifies its practical significance.

The knowledge graph (KG) is a highly needed basis to support the high-fidelity and high-interpretability modeling of various tasks in healthcare artificial intelligence. In this work, we focus on constructing an oncology knowledge graph that will be used in downstream cancer research and solution development. Modern supervised learning for knowledge graph construction requires a large amount of manually labeled data, which makes the process time-consuming and labor-intensive. Although there exists multiple research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from a general domain (biomedical in our case) to a fine-defined domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domain-specific named entities and triplets. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graphs efficiently.

Given the increasing number of building collapse tragedies nowadays (e.g., Florida condo collapse), people gradually recognize that long-term and persistent structural health monitoring (SHM) becomes indispensable for civilian buildings. However, current SHM techniques suffer from high cost and deployment difficulty caused by the wired connection. Traditional wireless sensor networks fail to serve in-concrete communication for SHM because of the complexity of battery replacement and the concrete Faraday cage. In this work, we collaborate with experts from civil engineering to create a type of promising self-sensing concrete by introducing a novel functional filler, called EcoCapsule- a battery-free and miniature piezoelectric backscatter node. We overcome the fundamental challenges in in-concrete energy harvesting and wireless communication to achieve SHM via EcoCapsules. We prototype EcoCapsules and mix them with other raw materials (such as cement, sand, water, etc) to cast the self-sensing concrete, into which EcoCapsules are implanted permanently. We tested EcoCapsules regarding real-world buildings comprehensively. Our results demonstrate single link throughputs of up to 13 kbps and power-up ranges of up to 6 m. Finally, we demonstrate a long-term pilot study on the structural health monitoring of a real-life footbridge.