INTRODUCTION: Generative artificial intelligence (AI) has implications for foreign language education, necessitating careful consideration of how the technology should be addressed. This should be based on the perspectives of different stakeholders, not least the students.OBJECTIVES: The paper explores foreign language students’ use of and perspectives on generative AI in foreign language education.METHODS: The paper employs a survey design and analyses responses from 106 students collected over a three-year period.RESULTS: The study documents increasing, frequent and varied use of generative AI. The students’ evaluation of AI output quality has grown more moderate over the years. The study suggests benefits may arise from even limited integration of the technology into language education.CONCLUSION: The study has highlighted a need for integrating generative AI into foreign language education. We need to continue the dialogue with students to inform future pedagogical choices.

While human factors are important in cyber security, the discipline has largely not explored incorporating indigenous perspectives—or, more specifically, in an Australian context, Aboriginal perspectives—in its curricula. In this paper, we introduce a promising approach for aligning Aboriginal perspectives with the needs of cyber security graduates and incorporating diverse perspectives into cyber degrees. The approach advocates for the centrality of good curriculum design fundamentals: backward design, constructive alignment, and student outcomes. The paper ends by reflecting on challenges and lessons from the first implementation and review of the material. It provides recommendations for other cyber practitioners exploring ways of incorporating indigenous perspectives in their teaching.

Semantic segmentation is a key research topic in the field of computer vision, aiming to assign each pixel to the corresponding category based on the semantic information in the image. This technology has significant application value in fields such as virtual reality and autonomous driving.With the rapid development of deep learning, particularly with the advent of FCN, image semantic segmentation has made substantial progress. Fully supervised learning, which trains deep learning models using labeled data, has demonstrated excellent performance in semantic segmentation tasks. This paper provides a comprehensive discussion and analysis of fully supervised semantic segmentation algorithms for 2D data in deep learning. First, it introduces the concept of semantic segmentation, its development, and its application scenarios. Next, it systematically reviews and categorizes current real-time semantic segmentation algorithms, analyzing the characteristics and limitations of each. Additionally, this paper presents a complete evaluation framework for real-time semantic segmentation, including relevant datasets and evaluation metrics. Based on this foundation, it identifies several challenges currently facing the field and suggests potential directions for future research. Through this summary and analysis, the paper aims to provide valuable insights for researchers conducting studies on image semantic segmentation.

A brain tumor is a serious neurological condition caused by the growth of abnormal cells in various regions of the brain, leading to a variety of health issues. Although the specific causes of brain tumors are not yet fully understood, known risk factors include genetic predisposition, ionizing radiation, viral infections, and exposure to certain chemicals. With the advancement of deep learning technology, computer-aided diagnosis systems can offer crucial support for the early diagnosis of brain tumors. Brain tumor image classification using deep learning has emerged as a prominent area of research. This article begins by summarizing the publicly available datasets frequently utilized in brain tumor classification tasks. It then provides an overview of the models commonly applied for diagnosing brain tumors. Following this, the paper reviews the advancements made in the field of brain tumor classification research to date. Finally, it highlights the future trends and challenges in brain tumor classification.

Convolutional Neural Networks (CNNs) have emerged as a prominent research area in deep learning in recent years. U-Net, an essential model within CNNs, has gradually become a research focus in the field of medical image segmentation due to its remarkable segmentation performance. This paper presents a comprehensive overview of brain tumor segmentation methods based on CNNs. Firstly, it introduces common medical image datasets in the field of brain tumor segmentation. Secondly, it offers detailed reviews on the common improvements to 2D U-Net, 3D U-Net, and improvements based on other CNNs for brain tumor segmentation. Finally, it discusses the future development directions of CNNs for brain tumor segmentation.

In recent years, Graph Neural Networks (GNNs) have seen notable success in fields such as recommendation systems and natural language processing, largely due to the availability of vast amounts of data and powerful computational resources. GNNs are primarily designed to work with graph data that involve pairwise relationships. However, in many real-world networks, the relationships between entities are complex and go beyond simple pairwise connections, as seen in scientific collaboration networks, protein networks, and similar domains. If these complex relationships are directly represented as pairwise relationships using graph structures, it can lead to information loss. A hypergraph, as a special kind of graph-structured data, can represent higher-order relationships that cannot be fully captured by graphs, thereby addressing the limitations of graphs. In light of this, researchers have begun to focus on how to design neural networks on hypergraphs, leading to the proposal of hypergraph neural network (HGNN) models for downstream tasks. Therefore, this paper reviews the existing hypergraph neural network models. The review is conducted from two perspectives: spectral analysis methods and neural network methods on hypergraphs, discussing both unfolded and non-unfolded methods, and further subdividing them based on their algorithm characteristics and application scenarios. Subsequently, the design concepts of various algorithms are analyzed and compared, and the advantages and disadvantages of each type of algorithm are summarized based on experimental results. Finally, potential future research directions in hypergraph learning are discussed.

INTRODUCTION: Accurate tumor segmentation is a prerequisite for reliable diagnosis and treatment of brain cancer. Gliomas, a highly prevalent and life-threatening type of brain tumor, pose a challenge for segmentation due to the intricate nature of brain structures and unpredictable appearances on brain MRI images.OBJECTIVES: Current methods for brain tumor segmentation mostly rely on deep convolutional neural networks, which suffer from significant loss of feature information during encoding and decoding and the inability to capture tumor contours in detail.METHODS: To address these challenges, this study rethinks the network architecture for MRI brain tumor segmentation. It proposes ARM-Net: an improved method for MRI brain tumor segmentation based on attention mechanisms and residual modules. Firstly, inverted external attention and dilated gated attention are employed in the last two layers of the encoder to enable the network to interact with both lesion areas and global information, facilitating better interaction among the four modalities. Secondly, different numbers of Res-Paths are added in the encoder's first two layers and the decoder's last two layers to effectively mitigate the semantic gap issues caused by traditional skip connections.RESULTS: Experiments on the BraTS 2019 dataset demonstrate that ARM-Net outperforms other similar models in terms of segmentation performance.CONCLUSION: The experiment showed that the ARM-Net model could segment the contour structure of the tumor better than other methods.

Image segmentation is an important research direction in medical image processing tasks, and it is also a challenging task in the field of computer vision. At present, there have been many image segmentation methods, including traditional segmentation methods and deep learning-based segmentation methods. Through the understanding and learning of the current situation in the field of medical image segmentation, this paper systematically combs it. Firstly, it briefly introduces the traditional image segmentation methods such as threshold method, region method and graph cut method, and focuses on the commonly used network architectures based on deep learning such as CNN, FCN, U-Net, SegNet, PSPNet, Mask R-CNN. At the same time, the application in medical image segmentation is expounded. Finally, the challenges and development opportunities of medical image segmentation technology based on deep learning are discussed.

OBJECTIVES: In conventional label propagation algorithms, the randomness inherent in the selection order of nodes and subsequent label propagation frequently leads to instability and reduces the accuracy of community detection outcomes.METHODS: First, select the initial node according to the node importance and assign different labels to each initial node, aiming to reduce the number of iterations of the algorithm and improve the efficiency and stability of the algorithm; second, identify the neighbor node with the largest connection to each initial node for the pre-propagation of the labels; then, the algorithm traverses the nodes in descending order of the node importance for the propagation of labels to reduce the randomness of the label propagation process; finally, the final community is formed through the rapid merging of small communities.RESULTS: The experimental results on multiple real datasets and artificially generated networks show that the stability and accuracy are all improved.CONCLUSION: The proposed community detection algorithm based on balanced label propagation is better than the other four advanced algorithms on Q and NMI values of community division results.

This article introduces artificial intelligence techniques in mathematical modelling of complex systems and their applications. Mathematical modelling of complex systems is a method of studying the structure and behaviour of complex systems, aiming to understand interactions and nonlinear effects in the system. Commonly used modelling methods include system dynamics, network theory, and algebraic methods. Artificial intelligence technologies include machine learning and deep learning, which can be used for tasks such as prediction and classification, anomaly detection, optimization and decision-making. In mathematical modelling of complex systems, artificial intelligence technology can learn system patterns and laws from large amounts of data, and can be applied to image and speech recognition, time series analysis and other fields. Deep learning and machine learning are important branches of artificial intelligence. They realize the modelling and analysis of complex systems by building neural network models. Data-driven modelling is a modelling method based on actual data that, combined with traditional theoretical modelling, can better describe and predict the behaviour of complex systems. Self-control of complex systems means that the system realizes its own optimization and adjustment through adaptive control algorithms and feedback mechanisms. In summary, artificial intelligence technology has broad application prospects in mathematical modelling of complex systems and will provide new tools and methods for in-depth understanding and solving problems in complex systems.