检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Pengzhong Sun Wei Wang Xiangyu Li Suyu Dong Shuo Li Kuanquan Wang Gongning Luo Faculty of Computing Harbin Institute of Technology Harbin China Faculty of Computing Harbin Institute of Technology Shenzhen China College of Computer and Control Engineering Northeast Forestry University Harbin China Case School of Engineering Case Western Reserve University Cleveland USA

The application of transformer architecture in analyzing whole slide images (WSIs) has become increasingly popular due to its remarkable ability to learn complex associations. Nevertheless, a significant drawback emerges in the multiclass analysis of WSIs. The majority of the transformer-based methods available currently rely primarily on a single, class-agnostic token. This approach might not ideally capture the subtleties of class-discriminative information. To address this challenge, we present an innovative approach tailored for multi-class WSI analysis that harnesses the power of class-specific tokens. Central to our method is a novel attention mechanism designed to foster a synergistic learning relationship between patch and class tokens, enhancing the granularity of information captured and ensuring a more comprehensive representation of the WSI. Complementing this, we introduce a dynamic class-centric training strategy designed to optimize token representation learning, ensuring each token is informatively aligned with its corresponding class. Through extensive experimentation on three challenging multi-class WSI analysis datasets, our method consistently demonstrates superior performance, underscoring its potential as a robust solution for multi-class WSI analysis tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FewFine: Few-shot Malware Traffic Classification Via Transfer Learning based on Fine-tuning Strategy

FewFine: Few-shot Malware Traffic Classification Via Transfe...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Xingtong Liu Meng Shen Laizhong Cui Ke Ye Jizhe Jia Guangchun Yue School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer Science Beijing Institute of Technology Beijing China

Malware traffic is constantly evolving and remains destructive. The detection and classification of malware traffic is crucial for maintaining cyberspace security. Only by swiftly and accurately detecting and classifying malware traffic can user privacy and cyberspace security be effectively *** this paper, we propose FewFine, an approach for few-shot malware traffic classification based on transfer learning. We initially pre-train a detection model and two classification models with substantial quantity of malware and application traffic samples. For classifying new types of malware traffic accurately and promptly, we utilize transfer learning based on fine-tuning strategy and freeze several blocks in the pre-trained model. Utilizing prior knowledge from the pre-trained models, we leverage few samples of novel classes to perform accurate malware detection and classification. We execute extensive experiments on publicly available datasets to evaluate the effectiveness of FewFine. In model pre-training, with considerable number of samples, the accuracy of malware detection and classification can reach 0.99. The pre-trained models are saved for fine-tuning. When detecting and classifying novel malware traffic, FewFine can achieve the accuracy of 0.95 leveraging only 10 samples per class through fine-tuning the pre-trained model. It outperforms methods under comparison in terms of accuracy and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D EMSU‐Net: A framework for automatic segmentation of brain tumors

3D EMSU‐Net: A framework for automatic segmentation of brai...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Luyi Qiu Ji Geng Yiling Zhang Chao Zhang Dongjie He Lingling Gao College of information and software University of electronic science and technology of China College of Computer Science and Engineering University of electronic science and technology of China

ISBN: (纸本)9781665447300

Glioma is the most common tumor in the brain's central nerve cells, which is extremely dangerous clinically. Glioma's accurate surgical localization and diagnosis both rely on the segmentation result of the tumor area in brain Magnetic Resonance Imaging (MRI) images. Recently, deep learning methods have been widely used in the tasks of semantic segmentation of brain tumor images. However, traditional 2D Convolutional Neural Networks (CNNs) only consider the feature information of images rather than the spatial features, which is hard to learn the contextual information between adjacent MRI slices of brain tumors. Simultaneously, 3D CNNs have attracted more and more attention due to their concentration on the correlation among slices. Inspired by 3D U-Net [1], this paper proposes an efficient 3D EMSU-Net to segmentation multi-modal brain tumor images with attention mechanism [2] and Efficient Multi-Scale Feature Extraction Component (EMS), which pays more attention to the feature information related to brain tumor areas to achieve over-performance segmentation of brain tumors. The proposed network is applied to brain tumor segmentation tasks and verified by BRATS 2018 dataset in experiments. The results demonstrated that 3D EMSU-Net is superior to other existing methods.

关键词： Image segmentation Three-dimensional displays Convolution Magnetic resonance imaging Semantics Surgery Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Wang, Chunyan Zhang, Dong Zhang, Liyan Tang, Jinhui The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China

Thanks to the advantages of the friendly annotations and the satisfactory performance, Weakly-Supervised Semantic Segmentation (WSSS) approaches have been extensively studied. Recently, the single-stage WSSS was awakened to alleviate problems of the expensive computational costs and the complicated training procedures in multi-stage WSSS. However, results of such an immature model suffer from problems of background incompleteness and object incompleteness. We empirically find that they are caused by the insufficiency of the global object context and the lack of the local regional contents, respectively. Under these observations, we propose a single-stage WSSS model with only the image-level class label supervisions, termed as Weakly-Supervised Feature Coupling Network (WS-FCN), which can capture the multi-scale context formed from the adjacent feature grids, and encode the fine-grained spatial information from the low-level features into the high-level ones. Specifically, a flexible context aggregation module is proposed to capture the global object context in different granular spaces. Besides, a semantically consistent feature fusion module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents. Based on these two modules, WS-FCN lies in a self-supervised end-to-end training fashion. Extensive experimental results on the challenging PASCAL VOC 2012 and MS COCO 2014 demonstrate the effectiveness and efficiency of WS-FCN, which can achieve state-of-the-art results by 65.02% and 64.22% mIoU on PASCAL VOC 2012 val set and test set, 34.12% mIoU on MS COCO 2014 val set, respectively. The code and weight have been released at: WS-FCN. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Kernel-based Class-specific Broad Learning System for software defect prediction

Kernel-based Class-specific Broad Learning System for softwa...

引用

2021 International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2021

作者： Chen, Wuxing Yang, Kaixiang Shi, Yifan Feng, Qiying Zhang, Chengxi Yu, Zhiwen Guangdong University of Technology School of Computer Science and Technology Guangzhou China Zhejiang University College of Control Science and Engineering Hangzhou China Huaqiao University School of Engineering Institute Quanzhou China South China University of Technology Computer Science and Engineering Guangzhou China Harbin Institute of Technology Shenzhen Electronic Information Engineering Shenzhen China

ISBN: (纸本)9781665402453

With the continuous expansion of the software industry, the problem of software defects is receiving more and more attention. There has been a series of machine learning methods applied to the field of software defect prediction (SDP) as a way to ensure the stability of software. However, SDP suffers from the imbalance problem. To solve this problem, we first propose a class-specific broad learning system (CSBLS), which assigns a specific penalty factor to each class in accordance with the data distribution. Then we design a class-specific kernel-based broad learning system (CSKBLS), which adopts kernel mapping instead of random projection. This additive kernel scheme takes into account both outliers and noise in the data set. Extensive experiments on the real-world NASA datasets show that CSKBLS outperforms the comparison methods on the tasks of software defect prediction. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing online industrial quality index prediction with a general deep temporal feature extraction and incremental ensemble modeling framework

引用

engineering Applications of Artificial Intelligence 2025年 156卷

作者： Zhao, Yuchen Yang, Rui Ying, Jie Wang, Song Zeng, Zhenyu College of Control Science and Engineering Zhejiang University Zheda Road 38 Hangzhou310027 China School of Automotive and Transportation Engineering Hefei University of Technology Tunxi Road 193 Hefei230000 China School of Computer Science and Engineering Nanyang Technological University Nanyang Avenue 50 Singapore639798 Singapore Alibaba Cloud Computing Co. Ltd. Alibaba Group Dengcai Road 1008 Hangzhou310030 China

Data-driven modeling methods for industrial quality index prediction often face the challenge of limited data representation. Using process variable snapshots from a single time step is insufficient for building high-performance soft sensors. Moreover, during online prediction, the performance of soft sensors is affected by diverse operating conditions and concept drift in industrial data streams, leading to performance degradation. To address these challenges, this paper proposes a Temporal Feature Extraction and Incremental Variational Bayesian Regression Ensemble (TFE-IVBRE) framework, which provides a general solution for various online industrial quality index prediction tasks. The TFE-IVBRE framework combines the temporal feature extraction capabilities of deep neural networks, the ability of ensemble learning to handle diverse operating conditions, and the online learning features of variational Bayesian models. An incremental update strategy is also incorporated to maintain consistent prediction performance. Experiments in the Debutanizer Column and Sulfur Recovery Unit scenarios show that the prediction performance of TFE-IVBRE significantly outperforms other static and online comparison models, with the effectiveness of its components validated through ablation studies. Finally, the overall model also demonstrates good robustness. These results offer valuable insights for the advancement of industrial soft sensor development. © 2025 Elsevier Ltd

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Video Segmentation Based on Information Centroid and Optimized SaliencyCut

引用

Journal of computer Science & Technology 2020年第3期35卷 564-575页

作者： Hui-Si Wu Meng-Shu Liu Lu-Lu Yin Ping Li Zhen-Kun Wen Hon-Cheng Wong College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China Department of Computing The Hong Kong Polytechnic UniversityHong Kong 999077China Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China

We propose an automatic video segmentation method based on an optimized SaliencyCut equipped with information centroid(IC)detection according to level balance principle in physical *** the existing methods,the image information of another dimension is provided by the IC to enhance the video segmentation ***,our IC is implemented based on the information-level balance principle in the image,and denoted as the information pivot by aggregating all the image information to a *** effectively enhance the saliency value of the target object and suppress the background area,we also combine the color and the coordinate information of the image in calculating the local IC and the global IC in the *** saliency maps for all frames in the video are calculated based on the detected *** applying IC smoothing to enhance the optimized saliency detection,we can further correct the unsatisfied saliency maps,where sharp variations of colors or motions may exist in complex ***,we obtain the segmentation results based on IC-based saliency maps and optimized *** method is evaluated on the DAVIS dataset,consisting of different kinds of challenging *** with the state-of-the-art methods are also conducted to evaluate our *** visual results and statistical comparisons demonstrate its advantages and robustness for automatic video segmentation.

关键词： automatic video segmentation information centroid saliency detection optimized SaliencyCut

来源：评论

学校读者我要写书评

暂无评论

Improving WiFi Fingerprint Database With Irregular Distribution of Reference Points Using Interpolation Methods

Improving WiFi Fingerprint Database With Irregular Distribut...

引用

International Conference on Advanced Technologies for Communications, ATC

作者： Trung Vu-Thanh Jing He Ninh Duong-Bao Seon-Woo Lee Luong Nguyen Thi Khanh Nguyen-Huu College of Computer Science and Electronic Engineering Hunan University Changsha China Faculty of Mathematics and Informatics Dalat University Dalat Vietnam Division of Software Hallym University Chuncheon Korea Faculty of Information Technology Dalat University Dalat Vietnam Department of Electronics and Telecommunications Dalat University Dalat Vietnam

ISBN: (数字)9798350353983

ISBN: (纸本)9798350353990

Using WiFi Fingerprinting for indoor positioning is becoming increasingly popular due to its cost-effectiveness. However, to ensure the system can operate with high accuracy and stability, this technique requires a burden of data collection tasks from a dense distribution of reference points (RPs). To decrease the cost of data collection, as well as to improve the WiFi fingerprint database with irregular distribution of RPs, this study applies and compares different interpolation methods. Evaluating these methods in a public dataset including multiple sub-datasets with irregular distributions of RPs, the results highlight the Linear Barycentric interpolation (LB) as the most favorable method due to its low complexity and stable performance. The LB-based fingerprint database achieves an average interpolation error of less than 3 dBm compared to the original one. When applying the interpolated database to positioning tasks, it can help reduce acquisition costs by up to 50% while improving positioning accuracy by up to 11%. The study reveals the feasibility of interpolation in optimizing WiFi fingerprint data collection, especially in large and complex environments where regular distribution of RPs cannot be deployed.

关键词： Interpolation Costs Accuracy Databases Fingerprint recognition Data collection Reliability Computational complexity Wireless fidelity Floors

来源：评论

学校读者我要写书评

暂无评论

dugMatting: Decomposed-Uncertainty-Guided Matting

arXiv

引用

arXiv 2023年

作者： Wu, Jiawei Zhang, Changqing Li, Zuoyong Fu, Huazhu Peng, Xi Zhou, Joey Tianyi College of Mechanical and Electrical Engineering Fujian Agriculture and Forestry University Fuzhou China College of Intelligence and Computing Tianjin University Tianjin China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China Institute of High Performance Computing Agency for Science Technology and Research Singapore College of Computer Science Sichuan University Chengdu China Singapore

Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typically user-defined trimaps or scribbles, are usually needed to reduce the uncertainty. Although effective, it is either time consuming or only suitable for experienced users who know where to place the strokes. In this work, we propose a decomposed-uncertainty-guided matting (dugMatting) algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results. Basing on the characteristic of these uncertainties, the epistemic uncertainty is reduced in the process of guiding interaction (which introduces prior knowledge), while the aleatoric uncertainty is reduced in modeling data distribution (which introduces statistics for both data and possible noise). The proposed matting framework relieves the requirement for users to determine the interaction areas by using simple and efficient labeling. Extensively quantitative and qualitative results validate that the proposed method significantly improves the original matting algorithms in terms of both efficiency and efficacy. Copyright © 2023, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Multimodal graph representation learning for robust surgical workflow recognition with adversarial feature disentanglement

引用

Information Fusion 2025年 123卷

作者： Bai, Long Ma, Boyi Wang, Ruohan Wang, Guankun Cui, Beilei Jiang, Zhongliang Islam, Mobarakol Min, Zhe Lai, Jiewen Navab, Nassir Ren, Hongliang Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Chair for Computer Aided Medical Procedures Technical University of Munich Munich Germany Department of Biomedical Engineering University of Toronto Toronto Canada Center for Computational and Molecular Biology Brown University Providence United States UCL Hawkes Institute University College London London United Kingdom School of Control Science and Engineering Shandong University Jinan China

Surgical workflow recognition is vital for automating tasks, supporting decision-making, and training novice surgeons, ultimately improving patient safety and standardizing procedures. However, data corruption can lead to performance degradation due to issues like occlusion from bleeding or smoke in surgical scenes and problems with data storage and transmission. Therefore, a robust workflow recognition model is urgently needed. In this case, we explore a robust graph-based multimodal approach to integrating vision and kinematic data to enhance accuracy and reliability. Vision data captures dynamic surgical scenes, while kinematic data provides precise movement information, overcoming limitations of visual recognition under adverse conditions. We propose a multimodal Graph Representation network with Adversarial feature Disentanglement (GRAD) for robust surgical workflow recognition in challenging scenarios with domain shifts or corrupted data. Specifically, we introduce a Multimodal Disentanglement Graph Network (MDGNet) that captures fine-grained visual information while explicitly modeling the complex relationships between vision and kinematic embeddings through graph-based message modeling. To align feature spaces across modalities, we propose a Vision-Kinematic Adversarial (VKA) framework that leverages adversarial training to reduce modality gaps and improve feature consistency. Furthermore, we design a Contextual Calibrated Decoder, incorporating temporal and contextual priors to enhance robustness against domain shifts and corrupted data. Extensive comparative and ablation experiments demonstrate the effectiveness of our model and proposed modules. Specifically, we achieved an accuracy of 86.87% and 92.38% on two public datasets, respectively. Moreover, our robustness experiments show that our method effectively handles data corruption during storage and transmission, exhibiting excellent stability and robustness. Our approach aims to advance automated surgi

关键词： Transplantation (surgical)

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：