检索结果-内蒙古大学图书馆

Multi-routine-data driven spatio-temporal short-term predictions for surface ozone in China

Air Quality, Atmosphere and Health 2025年 1-10页

作者： Zheng, Canju Shen, Hengqing Sun, Jianan Liu, Guangliang Cao, Haowei Zhang, Jie Gong, Xiang Xu, Da Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Environment Research Institute Shandong University Shandong Qingdao 266237 China Ningbo Yonghuanyuan Environmental Engineering and Technology Co. LTD Zhejiang Ningbo 315012 China School of Mathematics and Physics Qingdao University of Science and Technology Qingdao 266061 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Qingdao Innovation Center of Artificial Intelligence Ocean Technology Qingdao 266061 China

Ozone (O3) is a major atmospheric pollutant, and accurate prediction of its concentrations remains challenging due to its complex nonlinear relationships with precursor compounds. Existing machine learning methods hav... 详细信息

Ozone (O₃) is a major atmospheric pollutant, and accurate prediction of its concentrations remains challenging due to its complex nonlinear relationships with precursor compounds. Existing machine learning methods have mainly focused on single-site or spatial predictions, lacking research on spatio-temporal short-term predictions based on simple factors. To address this gap, the MRD-O₃former, a deep learning model driven by multi-routine data, was developed to predict short-term hourly spatio–temporal surface ozone concentrations over China. The model exhibits strong spatio–temporal consistency, achieving a high correlation coefficient (r2=0.85∼0.90) and low normalized mean biases (NMBs) between -15% and 15% at the national scale compared to reanalysis ozone data. Both ablation experiments and permutation importance analysis reveal that historical ozone levels play a primary role in next-day ozone prediction, while meteorological factors such as wind speed and temperature also make significant contributions. Regional validation confirms the model’s effectiveness in the Beijing-Tianjin-Hebei region. Moreover, the study investigates the differential impact of crucial factors in urban and rural areas, revealing that historical ozone levels and meteorological factors significantly influence rural areas. However, the influence of historical ozone levels on urban ozone prediction is relatively small, especially during the summer. This suggests that urban ozone undergoes rapid formation and removal processes. These findings highlight the promising potential of deep learning techniques in accurately predicting spatiotemporal short-term ozone concentrations and interpreting the mechanism and source for ozone pollution. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Data-driven Multi-factor Ozone concentration Spatio-temporal prediction

来源：评论

学校读者我要写书评

暂无评论

Robust Watermarking Based on Multi-layer Watermark Feature Fusion

引用

IEEE Transactions on Multimedia 2025年

作者： Wu, Shaowu Lu, Wei Luo, Xiangyang Sun Yat-Sen University School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China State Key Laboratory of Mathematical Engineering and Advanced Computing Henan450002 China

The purpose of robust image watermarking is to embed a watermark into a carrier image in an invisible form and extract the watermark successfully even under noise interference conditions to achieve copyright confirmation and traceability. Although watermarking methods based on deep learning can improve the robustness by adding a noise simulation layer, few theoretical analyses of the codec structure have been conducted. Theoretical explainability is the theoretical basis for developing a network architecture, which plays a guiding role in network development. On the basis of the interpretability of convolutional networks, this paper analyzes the mathematical process of embedding and extracting watermarks in codecs and proposes a novel watermarking framework based on multi-layer watermark feature fusion. Specifically, the encoder can be a convolutional network structure of arbitrary depth, whereas the decoder needs only to adopt its corresponding deconvolution structure. To improve the quality and robustness of the generated watermarked image, the watermark is associated with an arbitrary layer feature space in the decoder. In the decoder, the network quickly converges to each original encoding feature space through the deconvolution structure, thus decoupling the watermark features. Finally, the watermark is extracted via the automatic fusion of multi-layer watermark features. The experimental results show that the proposed method is suitable for few-shot learning, and its invisibility, robustness and generalization performance on multiple datasets are significantly better than those of other advanced methods. © 2025 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

CPSNet: Comprehensive Enhancement Representation for Polyp Segmentation Task

CPSNet: Comprehensive Enhancement Representation for Polyp S...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Cai, Jiati Liu, Xiaogang Yang, Hongjie Ding, Yi Zhong, Ting Qin, Zhen Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China Department of Gastroenterology and Hepatology University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

Accurately segmenting polyp regions in colonoscopy images is crucial for the diagnosis and intervention of colorectal cancer. However, the task of polyp segmentation remains challenging due to the diverse size and shape variations among polyps, their extreme similarity to the background, and frequent rotation of the lens, which further increases the diversity in polyp presentation. To address these challenges effectively, we propose a comprehensive polyp segmentation network (CPSNet). Specifically, we introduce a Comprehensive Spatial Feature Extraction Module (CFEM) that progressively and densely integrates features while forming receptive windows with various shapes. This enables enhanced perception of polyps at manifold sizes and shapes. Additionally, we propose a Fine-grained Region Strengthen Module (FGSM) to supplement uncertain areas around polyps by mitigating background noise interference. In terms of training strategy, we further introduce a Rotation-augmented Constrained Loss (RC Loss), which reinforces consistency constraints on polyp images under multiple rotation angles. Qualitative and quantitative experiments conducted on five public datasets demonstrate both the plug-and-play capability of CFEM as well as the effectiveness and excellence achieved by CPSNet. © 2025 IEEE.

关键词： colonoscopy computer vision polyp segmentation representation enhancement

来源：评论

学校读者我要写书评

暂无评论

Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding

Joint Automatic Speech Recognition And Structure Learning Fo...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hu, Jiliang Li, Zuchao Shen, Mengjia Ai, Haojun Li, Sheng Zhang, Jun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China School of Computer Science Wuhan University Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China National Institute of Information and Communications Technology Japan

ISBN: (纸本)9798350368741

Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper, we propose a joint speech recognition and structure learning framework (JSRSL), an end-to-end SLU model based on span, which can accurately transcribe speech and extract structured content simultaneously. We conduct experiments on name entity recognition and intent classification using the Chinese dataset AISHELL-NER and the English dataset SLURP. The results show that our proposed method not only outperforms the traditional sequence-to-sequence method in both transcription and extraction capabilities but also achieves state-of-the-art performance on the two datasets. © 2025 IEEE.

关键词： information Extraction Speech Recognition Spoken Language Understanding

来源：评论

学校读者我要写书评

暂无评论

A novel shilling attack on black-box recommendation systems for multiple targets

引用

Neural Computing and Applications 2025年第5期37卷 3399-3417页

作者： Liu, Shuangyu Yu, Siyang Li, Huan Yang, Zhibang Duan, Mingxing Liao, Xiangke School of Information Science and Engineering Hunan University Hunan Changsha410082 China College of Information Technology and Management Hunan University of Finance and Economics Hunan Changsha410000 China Hunan Province Key Laboratory of Industrial Internet Technology and Security Changsha University Hunan Changsha410022 China Shenzhen Institute Hunan University Guangdong Shenzhen518063 China School of Computer Science National University of Defense Technology Hunan Changsha410073 China

In the digital era, e-platforms ubiquitously deploy recommendation systems, utilizing machine learning paradigms to tailor content according to user preferences and needs. Yet, the integrity of these systems is often compromised by shilling attacks, where malicious entities inject fake user profiles to skew product exposure and sales. This vulnerability has catalyzed research efforts to bolster the robustness and security of recommendation systems, primarily through controlled attacks and reinforcement training. This paper introduces an innovative approach to combat the inefficiency of traditional single-target shilling attacks. We propose a novel multi-target shilling strategy for black-box recommendation systems, capable of generating convincing and aggressive fake user profiles. Given the complexity of the recommendation system algorithms, we employ surrogate models to replicate and understand the target system’s behavior. The surrogate model is then subjected to attacks using our proposed methodology. An attack is deemed successful when it achieves an 80% or higher success rate against the surrogate, preluding an attack on the actual recommendation system. Our model, RWA-GAN, stands out by integrating two components: a generative adversarial network (GAN) for crafting realistic fake user profiles, and a mechanism to enhance attack success rates. This dual approach not only expedites the attack process but also ensures the generation of more authentic and well-distributed fake profiles, making the model easier to migrate. Additionally, the paper delineates several defense strategies against such attacks, contributing significantly to the discourse on enhancing the robustness of recommender systems. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

When Crypto Fails: Demystifying Cryptographic Defects in Ethereum Smart Contracts

引用

IEEE Transactions on Software Engineering 2025年第5期51卷 1381-1398页

作者： Zhang, Jiashuo Chen, Jiachi Shen, Yiming Zhang, Tao Wang, Yanlin Chen, Ting Gao, Jianbo Chen, Zhong Peking University School of Computer Science Beijing100871 China Sun Yat-sen University School of Software Engineering Zhuhai510275 China Macau University of Science and Technology School of Computer Science and Engineering 999078 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Kashi Institute of Electronics and Information Industry Kashi844000 China Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China

Ethereum has officially provided a set of system-level cryptographic APIs to enhance smart contracts with cryptographic capabilities. These APIs have been utilized in over 13.8% of Ethereum transactions, motivating developers to implement various on-chain cryptographic tasks, such as digital signatures. However, since developers may not always be cryptographic experts, their ad-hoc and potentially defective implementations could compromise the theoretical guarantees of cryptography, leading to real-world security issues. To mitigate this threat, we conducted a comprehensive study aimed at demystifying and detecting cryptographic defects in smart contracts. Through the analysis of 3,762 real-world security reports, we defined 12 types of cryptographic defects in smart contracts with detailed descriptions and practical detection patterns. Based on this categorization, we proposed CryptoScan, the first static analyzer to automate the pre-deployment detection of cryptographic defects in smart contracts. CryptoScan utilizes cross-contract and inter-procedure static analysis to identify crypto-related execution paths and employs taint analysis to extract fine-grained crypto-specific semantics for defect detection. Furthermore, we collected a large-scale dataset containing 79,598 real-world crypto-related smart contracts and evaluated CryptoScan's effectiveness on it. The results demonstrated that CryptoScan achieves an overall precision of 96.1% and a recall of 93.3%. Notably, CryptoScan revealed that 19,707 (24.8%) out of 79,598 smart contracts contain at least one cryptographic defect. Although not all defects directly cause financial losses, they indicate prevalent non-standard cryptographic implementations that should be addressed in real-world practices. © 1976-2012 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Federated Learning Framework via a Server-Client Defense Mechanisms

引用

IEEE Internet of Things Journal 2025年

作者： Song, Anxiao Zhang, Tao Cheng, Ke Cao, Yang Zhu, Xinghui Shen, Yulong Xidian University School of Computer Science and Technology Xi’an China Shaanxi Key Laboratory of Network and System Security Shaanxi Xi’an710071 China Xidian University School of Computer Science and Technology Shaanxi Xi’an710071 China Xi’an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi’an710121 China Institute of Science Tokyo Department of Computer Science Tokyo Japan

Federated Learning (FL), a distributed machine learning (ML) framework, is susceptible to Byzantine attacks since the attacker can manipulate clients' local data or models to compromise the performance of the global model. There has been a wealth of defenses developed to mitigate the attacks by limiting the impact of malicious models. Nevertheless, the attacker can easily circumvent these approaches that rely solely on a single server-side defense, stemming from the high dimensionality of models and the variety of Byzantine attacks. Therefore, we propose Basalt, a Byzantine-robust federated learning framework with a server-client joint defense mechanism that enables multiple clients to train a global ML model under Byzantine attacks. On the client side, we design an efficient self-defense approach with model-level penalty loss that restricts local-benign divergence and decreases local-malicious correlation to prevent misclassification. On the server side, we present an efficient defense strategy based on the manifold and maximum clique, further strengthening the FL's resilience against Byzantine attacks. We provide theoretical guarantees for global model convergence in FL with Byzantine attacks. Our extensive experiments demonstrate that Basalt outperforms existing state-of-the-art works. Especially, it achieves nearly 100% accuracy for detecting malicious clients in nonindependent and nonidentically distributed (Non-IID) MNIST datasets under various Byzantine attacks. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Dialogue Emotion Recognition Based on Label Optimization and Coarse-Grained Assisted Fine-Grained

Multimodal Dialogue Emotion Recognition Based on Label Optim...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhibo Zhang Zhenyu Yang Yan Huang Baojie Xu Wenyue Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal dialogue emotion recognition integrates data from multiple modalities to accurately identify emotional states in conversations. However, differences in expression and information density across modalities complicate the fusion of features. Traditional methods may introduce redundant information from other utterances, reducing the accuracy of emotion recognition. Existing one-hot labels often fail to capture the full range of emotional expressions, leading to biased results. To address these issues, we propose a model that fuses different modalities within the same utterance to avoid redundancy. It employs a progressive classification process, refining emotion recognition from coarse to fine granularity. Additionally, we use emotion polarity probabilities as weights for fine-grained classification and introduce a multimodal information-rich label that considers both the data and their interactions. Experiments on IEMOCAP and MELD datasets demonstrate the model’s effectiveness, significantly improving dialog emotion recognition accuracy. Our code is available at https://***/r/LOCG-188E.

关键词： Emotion recognition Accuracy Fuses Refining Termination of employment Speech recognition Signal processing Speech processing Optimization Faces

来源：评论

学校读者我要写书评

暂无评论

Forgery-Aware Adaptive Learning With Vision Transformer for Generalized Face Forgery Detection

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第5期35卷 4116-4129页

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Nanchang330013 China Laboratory School of Electrical and Electronic Engineering Jurong West 639798 Singapore Sun Yat-sen University Guangdong Key Laboratory of Information Security School of Computer Science and Engineering Guangzhou510006 China Shenzhen MSU-BIT University Guangdong Laboratory of Machine Perception and Intelligent Computing Faculty of Engineering Shenzhen518116 China China-Singapore International Joint Research Institute Guangzhou China

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. To this end, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm for generalized face forgery detection, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. © 1991-2012 IEEE.

关键词： Forgery Faces Adaptation models Transformers Feature extraction Adaptive learning computer vision Face recognition Deepfakes Visualization

来源：评论

学校读者我要写书评

暂无评论

Image Compression Algorithm Based on Region of Interest Extraction for Unmanned Aerial Vehicles Communication

Image Compression Algorithm Based on Region of Interest Extr...

引用

IEEE information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Yanxia Liang Tong Jia Xin Liu Huanhuan Zhang Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts and Telecommunications Xi’an China College of Information Engineering Xi’an Eurasia University Xi’an China

ISBN: (数字)9798331529482

ISBN: (纸本)9798331529499

The flexibility and maneuverability of unmanned aerial vehicles (UAVs) have led to their widespread use, but the challenge of limited storage space and bandwidth in emergency scenarios necessitates efficient image compression techniques. In this research, we propose an image compression algorithm tailored for UAV communication, termed ROIE-UC (Region of Interest Extraction for UAV Communication). Firstly, image pixels are clustered into super pixel blocks using the Simple Linear Iterative Clustering (SLIC). Secondly, these super pixels are grouped into regions of interest (ROI) using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN). The image is then segmented into ROI and non-ROI areas based on these clusters. Lossless compression is applied to the ROI, while lossy compression with a high ratio is used for non-ROI regions. At the receiving end, the image is decompressed and reconstructed. Experimental results show that the ROIE-UC achieves a Peak Signal-to-Noise Ratio (PSNR) of 46.37 dB and a Structural Similarity Index (SSIM) of 99.94% for the ROI part, with compression ratios of 27, 25, and 14 for the whole image. Compared to the JPEG, PSNR improved by up to 28.52% and SSIM by 1.51%, with a compression ratio increase from 14.52 to 27.56. The ROIE-UC also provides up to a 49.44% increase in PSNR over other methods. These results demonstrate that ROIE-UC is an efficient and effective solution for image processing and data compression in UAV applications.

关键词： Image segmentation Visualization Image coding PSNR Wireless networks Bandwidth Autonomous aerial vehicles Real-time systems Image reconstruction Videos

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：