Cerebral aneurysm is a cerebrovascular disorder caused by a weakness in the wall of an artery or vein, which causes a localized dilation or ballooning of the blood vessel. It is life-threatening; hence, an early and accurate diagnosis would be a great aid to medical professionals in making the correct choice of treatment. HemeLB is a massively parallel Lattice-Boltzmann simulation software, which is designed to provide the radiologist with estimates of flow rates, pressures, and shear stresses throughout the relevant vascular structures, intended to eventually permit greater precision in the choice of therapeutic intervention. However, in order to allow surgeries and doctors to view and visualize the results in real-time at medical environments, a cost-efficient, practical platform is needed. In this article, we have developed and evaluated a version of HemeLB on various heterogeneous system-on-chip platforms, allowing users to run HemeLB on a low-cost embedded platform and to visualize the simulation results in real-time. A comprehensive evaluation of implementation on the Zynq SoC and Jetson TX1 embedded graphic processing unit platforms are reported. The achieved results show that the proposed Jetson TX1 implementation outperforms the Zynq implementation by a factor of 19 in terms of site updates per second.

The mechanical performance of biological tissues is underpinned by a complex and finely balanced structure. Central to this is collagen, the most abundant protein in our bodies, which plays a dominant role in the functioning of tissues, and also in disease. Based on the collagen meshwork of articular cartilage, we have developed a bottom-up spring-node model of collagen and examined the effect of fibril connectivity, implemented by crosslinking, on mechanical behaviour. Although changing individual crosslink stiffness within an order of magnitude had no significant effect on modelling predictions, the density of crosslinks in a meshwork had a substantial impact on its behaviour. Highly crosslinked meshworks maintained a 'normal' configuration under loading, with stronger resistance to deformation and improved recovery relative to sparsely crosslinked meshwork. Stress on individual fibrils, however, was higher in highly crosslinked meshworks. Meshworks with low numbers of crosslinks reconfigured to disease-like states upon deformation and recovery. The importance of collagen interconnectivity may provide insight into the role of ultrastructure and its mechanics in the initiation, and early stages, of diseases such as osteoarthritis.

This paper presents a novel real‐time facial feature extraction algorithm, producing a small feature set, suitable for implementing emotion recognition with online game and metaverse avatars. The algorithm aims to reduce data transmission and storage requirements, hurdles in the adoption of emotion recognition in these mediums. The early results presented show a facial emotion recognition accuracy of up to 92% on one benchmark dataset, with an overall accuracy of 77.2% across a wide range of datasets, demonstrating the early promise of the research.

Energy is at the center of human society and drives the technologies and overall human well-being. Today, artificial intelligence (AI) technologies are widely used for system modeling, prediction, control, and optimization in the energy sector. The internet of things (IoT) is the core of the third wave of the information industry revolution and AI. In the energy sector, tens of billions of IoT appliances are linked to the Internet, and these appliances generate massive amounts of data every day. Extracting useful information from the massive amount of data will be a very meaningful thing. Complex event processing (CEP) is a stream-based technique that can extract beneficial information from real-time data through pre-establishing pattern rules. The formulation of pattern rules requires strong domain expertise. Therefore, at present, the pattern rules of CEP still need to be manually formulated by domain experts. However, in the face of complex, massive amounts of IoT data, manually setting rules will be a very difficult task. To address the issue, this paper proposes a CEP rule auto-extraction framework by combining deep learning methods with data mining algorithms. The framework can automatically extract pattern rules from unlabeled air pollution data. The deep learning model we presented is a two-layer LSTM (long short-term memory) with an attention mechanism. The framework has two phases: in the first phase, the anomalous data is filtered out and labeled from the IoT data through the deep learning model we proposed, and then the pattern rules are mined from the labeled data through the decision tree data mining algorithm in the second phase. We compare other deep learning models to evaluate the feasibility of the framework. In addition, in the rule extraction stage, we use a decision tree data mining algorithm, which can achieve high accuracy. Experiments have shown that the framework we proposed can effectively extract meaningful and accurate CEP rules. The research work in this paper will help support the advancement of the sector of air pollution prediction, assist in the establishment of air pollution regulatory strategies, and further contribute to the development of a green energy structure.

Human action recognition has drawn significant attention because of its importance in computer vision-based applications. Action recognition based on skeleton sequences has rapidly advanced in the last decade. Conventional deep learning-based approaches are based on extracting skeleton sequences through convolutional operations. Most of these architectures are implemented by learning spatial and temporal features through multiple streams. These studies have enlightened the action recognition endeavor from various algorithmic angles. However, three common issues are observed: (1) The models are usually complicated; therefore, they have a correspondingly higher computational complexity. (2) For supervised learning models, the reliance on labels during training is always a drawback. (3) Implementing large models is not beneficial to real-time applications. To address the above issues, in this paper, we propose a multi-layer perceptron (MLP)-based self-supervised learning framework with a contrastive learning loss function (ConMLP). ConMLP does not require a massive computational setup; it can effectively reduce the consumption of computational resources. Compared with supervised learning frameworks, ConMLP is friendly to the huge amount of unlabeled training data. In addition, it has low requirements for system configuration and is more conducive to being embedded in real-world applications. Extensive experiments show that ConMLP achieves the top one inference result of 96.9% on the NTU RGB+D dataset. This accuracy is higher than the state-of-the-art self-supervised learning method. Meanwhile, ConMLP is also evaluated in a supervised learning manner, which has achieved comparable performance to the state of the art of recognition accuracy.