检索结果-内蒙古大学图书馆

MIA-Mind: A Multidimensional Interactive Attention Mechanism Based on MindSpore

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qin, Zhenkai Liang, Jiaquan Fang, Qiao Network Security Research Center Guangxi Police College Guangxi Nanning China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China School of Information Technology Guangxi Police College Guangxi Nanning China

Attention mechanisms have significantly advanced deep learning by enhancing feature representation through selective focus. However, existing approaches often independently model channel importance and spatial saliency, overlooking their inherent interdependence and limiting their effectiveness. To address this limitation, we propose MIA-Mind, a lightweight and modular Multidimensional Interactive Attention Mechanism, built upon the MindSpore framework. MIA-Mind jointly models spatial and channel features through a unified cross-attentive fusion strategy, enabling fine-grained feature recalibration with minimal computational overhead. Extensive experiments are conducted on three representative datasets: on CIFAR-10, MIA-Mind achieves an accuracy of 82.9%;on ISBI2012, it achieves an accuracy of 78.7%;and on CIC-IDS2017, it achieves an accuracy of 91.9%. These results validate the versatility, lightweight design, and generalization ability of MIA-Mind across heterogeneous tasks. Future work will explore the extension of MIA-Mind to large-scale datasets, the development of adaptive attention fusion strategies, and distributed deployment to further enhance scalability and robustness. © 2025, CC0.

关键词： Deep learning

FEW-SHOT HATE SPEECH DETECTION BASED ON THE MINDSPORE FRAMEWORK

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qin, Zhenkai Wu, Dongze Liu, Yuxin Yang, Guifang School of Computing and Information China Network Security Research Center China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China Institute of Software Chinese Academy of Sciences 100190 China School of Information Technology Guangxi Police College 530028 China

The proliferation of hate speech on social media poses a significant threat to online communities, requiring effective detection systems. While deep learning models have shown promise, their performance often deteriorates in few-shot or low-resource settings due to reliance on large annotated corpora. To address this, we propose MS-FSLHate, a prompt-enhanced neural framework for few-shot hate speech detection implemented on the MindSpore deep learning platform. The model integrates learnable prompt embeddings, a CNN-BiLSTM backbone with attention pooling, and synonym-based adversarial data augmentation to improve generalization. Experimental results on two benchmark datasets—HateXplain and HSOL—demonstrate that our approach outperforms competitive baselines in precision, recall, and F1-score. Additionally, the framework shows high efficiency and scalability, suggesting its suitability for deployment in resource-constrained environments. These findings highlight the potential of combining prompt-based learning with adversarial augmentation for robust and adaptable hate speech detection in few-shot scenarios. © 2025, CC0.

关键词： Deep learning

MAAM:A LIGHTWEIGHT MULTI-AGENT AGGREGATION MODULE FOR EFFICIENT IMAGE CLASSIFICATION BASED ON THE MINDSPORE FRAMEWORK

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qin, Zhenkai Zhu, Feng Zeng, Huan Nong, Xunyi School of Computing and Information Guangxi Police College Guangxi Nanning China Network Security Research Center Guangxi Police College Guangxi Nanning China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China Institute of Software Chinese Academy of Sciences Beijing China

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite their strong feature modeling capability, often struggle with high computational complexity and structural rigidity, limiting their applicability in scenarios with limited computational resources (e.g., edge devices or real-time systems). To address this, we propose the Multi-Agent Aggregation Module (MAAM), a lightweight attention architecture integrated with the MindSpore framework. MAAM employs three parallel agent branches with independently parameterized operations to extract heterogeneous features, adaptively fused via learnable scalar weights, and refined through a convolutional compression layer. Leveraging MindSpore’s dynamic computational graph and operator fusion, MAAM achieves 87.0% accuracy on the CIFAR-10 dataset, significantly outperforming conventional CNN (58.3%) and MLP (49.6%) models, while improving training efficiency by 30%. Ablation studies confirm the critical role of agent attention (accuracy drops to 32.0% if removed) and compression modules (25.5% if omitted), validating their necessity for maintaining discriminative feature learning. The framework’s hardware acceleration capabilities and minimal memory footprint further demonstrate its practicality, offering a deployable solution for image classification in resource-constrained scenarios without compromising accuracy. © 2025, CC0.

关键词： Image classification

MINDFLOW: A NETWORK TRAFFIC ANOMALY DETECTION MODEL BASED ON MINDSPORE

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xiang, Qiuyan Wu, Shuang Wu, Dongze Liu, Yuxin Qin, Zhenkai School of Information Technology Guangxi Police College 530028 China College of Computer Science and AI Southwest Minzu University 610213 China Institute of Software Chinese Academy of Sciences 100190 China School of Computing and Information China Network Security Research Center China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China

With the wide application of IoT and industrial IoT technologies, the network structure is becoming more and more complex, and the traffic scale is growing rapidly, which makes the traditional security protection mechanism face serious challenges in dealing with high-frequency, diversified, and stealthy cyber-attacks. To address this problem, this study proposes MindFlow, a multi-dimensional dynamic traffic prediction and anomaly detection system combining convolutional neural network (CNN) and bi-directional long and short-term memory network (BiLSTM) architectures based on the MindSpore framework, and conducts systematic experiments on the NF-BoT-IoT dataset. The experimental results show that the proposed model achieves 99% in key metrics such as accuracy, precision, recall and F1 score, effectively verifying its accuracy and robustness in network intrusion detection. © 2025, CC0.

关键词： Convolutional neural networks

A topic detection method based on KM-LSH Fusion algorithm and improved BTM model

学校读者我要写书评

暂无评论

Soft Computing 2024年第19期28卷 11421-11438页

作者： Liu, Wenjun Guo, Huan Gan, Jiaxin Wang, Hai Wang, Hailan Zhang, Chao Peng, Qingcheng Sun, Yuyan Yu, Bao Hou, Mengshu Li, Bo Li, Xiaolei School of Computer and Software Engineering XiHua University Chengdu610039 China Chengdu611731 China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou646000 China School of Big Data and Artificial Intelligence Chengdu Technological University Chengdu611730 China Sichuan Provincial Engineering Research Center of Hydroelectric Energy Power Equipment Technology Chengdu610039 China

Topic detection is an information processing technology designed to help people deal with the growing problem of data information on the Internet. In the research literature, topic detection methods are used for topic classification through word embedding, supervised-based and unsupervised-based approaches. However, most methods for topic detection only address the problem of clustering and do not focus on the problem of topic detection accuracy reduction due to the cohesiveness of topics. Also, the sequence of biterm during topic detection can cause substantial deviations in the detected topic content. To solve the above problems, this paper proposes a topic detection method based on KM-LSH fusion algorithm and improved BTM model. KM-LSH fusion algorithm is a fusion algorithm that combines K-means clustering and LSH refinement clustering. The proposed method can solve the problem of cohesiveness of topic detection, and the improved BTM model can solve the influence of the sequence of biterm on topic detection. First, the text vector is constructed by processing the collected set of microblog texts using text preprocessing methods. Secondly, the KM-LSH fusion algorithm is used to calculate text similarity and perform topic clustering and refinement. Finally, the improved BTM model is used to model the texts, which is combined with the word position and the improved TF-IDF weight calculation algorithm to adjust the microblogging texts in clustering. The experiment results indicate that the proposed KM-LSH-IBTM method improves the evaluation indexes compared with the other three topic detection methods. In conclusion, the proposed KM-LSH-IBTM method promotes the processing capability of topic detection in terms of cohesiveness and the sequence of biterm. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： K-means clustering

AN INNOVATIVE CGL-MHA MODEL FOR SARCASM SENTIMENT RECOGNITION USING THE MINDSPORE FRAMEWORK

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qin, Zhenkai Luo, Qining Nong, Xunyi School of Information Technology Guangxi Police College Guangxi Nanning China Network Security Research Center China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China

The pervasive use of the Internet and social media has introduced significant challenges to automated sentiment analysis, particularly with regard to sarcastic expressions found in user-generated content. Sarcasm conveys negative emotions through ostensibly positive or exaggerated language, complicating its detection within natural language processing tasks. To address this issue, this paper presents an innovative sarcasm detection model that integrates Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Long Short-Term Memory networks (LSTM), and Multi-Head Attention mechanisms. The CNN component captures local n-gram features, while GRU and LSTM layers model sequential dependencies and contextual information. The Multi-Head Attention mechanism enhances the model’s ability to focus on relevant parts of the input, providing better interpretability. Experiments conducted on two datasets for sarcasm detection—Headlines and Riloff—demonstrate that the proposed model achieves an accuracy of 81.20% and an F1 score of 80.77% on the Headlines dataset, and an accuracy of 79.72% with an F1 score of 61.39% on the Riloff dataset, significantly outperforming traditional models. These results validate the effectiveness of our hybrid approach in enhancing sarcasm detection performance in social media texts. © 2024, CC BY.

关键词： Convolutional neural networks

RF Sign: Signature Anticounterfeiting Real-Time Monitoring System Based on Single Tag

学校读者我要写书评

暂无评论

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Zhu, Biaokai Wei, Qing Li, Lu Yang, Zejiao Liu, Wei You, Zirong Zhou, Jiangfan Li, Ping Song, Jie Liu, Sanman Li, Deng-Ao Network Security Department Shanxi Police College No. 799 Qingdong Rd Qingxu County Taiyuan China Intelligent Policing Key Laboratory of Sichuan Province No. 34 Jiangyang West Road Jiangyang District Luzhou China School of Computer Science and Technology Anhui University No. 111 Jiulong Road Hefei China Big Data College Taiyuan University of Technology No. 209 University Street Jinzhong China

Signatures are one of the most important means to ensure the authenticity of documents and are commonly used in life and work. In identifying imitation handwriting, it is easy to make mistakes that cannot correctly identify and evaluate different writing characteristics. In this paper, from the perspective of dynamic handwriting detection, we propose RF sign, a signature anticounterfeiting real-time monitoring model, which achieves passive recognition of signature behavior using only a single antenna with a single tag. The RF sign identifies different users by extracting fine-grained reflection features from the original RF signal. We introduced a dynamic time regularization and neural network technique for similarity calculation and signature recognition matching to achieve template matching and classification. We compiled a real-time signature handwriting detection system. The system effectively identifies the person's signature by checking real-time spatial and temporal information. Comprehensive experiments show that the recognition accuracy of my signature can reach over 93% and is robust to input location, environmental changes, and user diversity. © 2023 Biaokai Zhu et al.

关键词： Template matching