检索结果-内蒙古大学图书馆

CT perfusion parameter estimation in stroke using neural network with transformer and physical model priors

computers in Biology and Medicine 2024年 182卷 109134-109134页

作者： Luo, Luyao Liu, Pan Ye, Wanxing Chen, Fengwei Liu, Yu Liu, Ziyang Jing, Jing Xiong, Yunyun Zhu, Wanlin Jiang, Yong Cheng, Jian Wang, Yongjun Liu, Tao Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering Beihang University Beijing China Medical Big Data Research Center Chinese PLA General Hospital Beijing China China National Clinical Research Center for Neurological Diseases Beijing China Department of Neurology Beijing Tiantan Hospital Capital Medical University Beijing China School of Computer Science and Engineering Beihang University Beijing China

Objectives: CT perfusion (CTP) imaging is vital in treating acute ischemic stroke by identifying salvageable tissue and the infarcted core. CTP images allow quantitative estimation of CT perfusion parameters, which can provide information on the degree of tissue hypoperfusion and its salvage potential. Traditional methods for estimating perfusion parameters, such as singular value decomposition (SVD) and its variations, are known to be sensitive to noise and inaccuracies in the arterial input function. To our knowledge, there has been no implementation of deep learning methods for CT perfusion parameter estimation. Materials & methods: In this work, we propose a deep learning method based on the Transformer model, named CTPerformer-Net, for CT perfusion parameter estimation. In addition, our method incorporates some physical priors. We integrate physical consistency prior, smoothness prior and the physical model prior through the design of the loss function. We also generate a simulation dataset based on physical model prior for training the network model. Results: In the simulation dataset, CTPerformer-Net exhibits a 23.4 % increase in correlation coefficients, a 95.2 % decrease in system error, and a 90.7 % reduction in random error when contrasted with block-circulant SVD. CTPerformer-Net successfully identifies hypoperfused and infarcted lesions in 103 real CTP images from the ISLES 2018 challenge dataset. It achieves a mean dice score of 0.36 for the infarct core segmentation, which is slightly higher than the commercially available software (dice coefficient: 0.34) used as a reference level by the challenge. Conclusion: Experimental results on the simulation dataset demonstrate that CTPerformer-Net achieves better performance compared to block-circulant SVD. The real-world patient dataset confirms the validity of CTPerformer-Net. © 2024 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network and Deep One-Class Support Vector Machine with Imbalanced dataset for Anomaly Network Traffic Detection

Convolutional Neural Network and Deep One-Class Support Vect...

引用

International Conference on Cyber Security, Privacy and Networking, ICSPN 2022

作者： Chui, Kwok Tai Gupta, Brij B. Chi, Hao Ran Zhao, Mingbo Hong Kong International Center for AI and Cyber Security Research and Innovations & Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Lebanese American University Beirut1102 Lebanon Instituto de Telecomunicações Aveiro3810-193 Portugal School of Information Science & Technology Donghua University Shanghai200051 China

ISBN: (纸本)9783031220173

Anomaly detection of network traffic is important for real-time network monitoring and management. The research challenges for anomaly network traffic detection (ANTD) are attributable to the nature of highly imbalanced dataset of abnormal samples and poor generalization. Generating additional training data or undersampling does not perform well with highly imbalanced dataset. The drives to the common formulation of ANTD as an one-class classification problem. Convolution neural network is utilized for feature extraction. This is followed by a deep one-class support vector machine classifier with customized kernel via multiple kernel learning to address the issue of generalization and overfitting. The deep architecture leverages the performance of traditional support vector machine to a large extent. Performance evaluation reveals that the proposed algorithm achieves accuracy of 97.5%. Ablation studies show that our algorithm enhances the accuracy by 2.52–15.2%. Compared with existing work, our algorithm enhances the accuracy by 3.07%. Several future research directions are discussed for further exploration and analysis. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

TOWARDS FaiTHFUL Xai EVALUATION VIA GENERALIZATION-LIMITED BACKDOOR WATERMARK 12

TOWARDS FAITHFUL XAI EVALUATION VIA GENERALIZATION-LIMITED B...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Ya, Mengxi Li, Yiming Dai, Tao Wang, Bin Jiang, Yong Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China The State Key Laboratory of Blockchain and Data Security Zhejiang University China ZJU-Hangzhou Global Scientific and Technological Innovation Center China College of Computer Science and Software Engineering Shenzhen University China Guangzhou Intelligence Communications Technology Co. Ltd. China

Saliency-based representation visualization (SRV) (e.g., Grad-CAM) is one of the most classical and widely adopted explainable artificial intelligence (Xai) methods for its simplicity and efficiency. It can be used to interpret deep neural networks by locating saliency areas contributing the most to their predictions. However, it is difficult to automatically measure and evaluate the performance of SRV methods due to the lack of ground-truth salience areas of samples. In this paper, we revisit the backdoor-based SRV evaluation, which is currently the only feasible method to alleviate the previous problem. We first reveal its implementation limitations and unreliable nature due to the trigger generalization of existing backdoor watermarks. Given these findings, we propose a generalization-limited backdoor watermark (GLBW), based on which we design a more faithful Xai evaluation. Specifically, we formulate the training of watermarked DNNs as a min-max problem, where we find the 'worst' potential trigger (with the highest attack effectiveness and differences from the ground-truth trigger) via inner maximization and minimize its effects and the loss over benign and poisoned samples via outer minimization in each iteration. In particular, we design an adaptive optimization method to find desired potential triggers in each inner maximization. Extensive experiments on benchmark datasets are conducted, verifying the effectiveness of our generalization-limited watermark. Our codes are available at https://***/yamengxi/GLBW. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

DarkFed: A data-Free Backdoor Attack in Federated Learning

arXiv

引用

arXiv 2024年

作者： Li, Minghui Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Zhang, Leo Yu Wang, Yichen School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Correction of Read Biases Induced by Complex Reference Genome Regions for Improving Copy Number Variation Detection Using a Gaussian Mixture Model

Correction of Read Biases Induced by Complex Reference Genom...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Xuwen Chang, Zhili Wang, Shenjie Liu, Ruoyu Liu, Yuqian Zhu, Xiaoyan Shao, Yang Lai, Xin Yang, Shuanying Wang, Jiayin Second Affiliated Hospital Xi'an Jiaotong University Department of Respiratory Medicine Xi'an710003 China Xi'an Jiaotong University School of Computer Science and Technology Xi'an710049 China Xi'an Jiaotong University Shaanxi Engineering Research Center of Medical and Health Big Data Xi'an710049 China Nanjing Geneseeq Technology INC. China

ISBN: (纸本)9798350386226

Copy number variations are crucial in cancer research, but their detection through next-generation sequencing is often hindered by read biases, particularly in complex genomic regions. Existing bias-correction methods address common issues like GC content but often fail in regions with repetitive sequences or segmental duplications, leading to false-positive CNVs. We propose refMask, a hybrid Gaussian model-based method that dynamically identifies low-confidence regions in the reference genome, correcting read biases and improving CNV detection accuracy. By integrating features from hg38 and T2T genomes, refMask tailors a custom blacklist for each sequencing sample, enhancing the reliability of CNV detection across diverse conditions. Our method provides a more accurate and flexible solution compared to current fixed blacklists, offering improved performance in challenging genomic regions. © 2024 IEEE.

关键词： Copy number variation Gaussian model Next-generation sequencing Read biase

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning for Improved Sentiment Analysis in Natural Language Processing 3

Leveraging Deep Learning for Improved Sentiment Analysis in ...

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Kulkarni, Aniket Gollavilli, Venkata Surya Bhavana Harish Alsalami, Zaid Bhatia, Manpreet Kaur Jovanovska, Sashka Absur, Md Nurul Drata Inc San DiegoCA United States Under Armour MD United States College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Asian School of Media Studies Department of Data Science Noida India Goce Delcev University Faculty of Philology Department of English Language and Literature Stip Macedonia Cuny Graduate Center Computer Science New York United States

ISBN: (纸本)9798350354379

Sentiment analysis is viewed as quite possibly of the main works in mental science and normal language handling. To work on the productivity of sentiment analysis techniques, it is crucial for separate the useful words that add to the grouping choice as well as characterize the sentences as indicated by their profound names. Profound brain networks that depend on the consideration component have taken huge steps toward this path as of late. Reads up on consideration processes for message arrangement, and especially sentiment analysis, are as yet not many, in any case. This research fills this gap by presenting a Convolution Neural Network (CNN) combined with an attention layer that can extract relevant words and give them greater weights according to the context. The suggested model uses a context vector at the attention layer and attempts to gauge a word's relevance based on how similar the word vector and context vector are to one another. New vectors from the consideration layer are incorporated into sentence vectors and utilised for organization once they have been supplied. The suggested model was validated using a small number of tests on the Stanford datasets. The trial discoveries show that the recommended model works far superior to past research studies and can separate significant expressions from setting that have an incentive for analysis and application. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Application of TimeMachine Model in Predicting Operational Parameters of Wastewater Treatment Plants

Application of TimeMachine Model in Predicting Operational P...

引用

computers and Artificial Intelligence Technologies (CaiT), International Conference on

作者： Bailing Zhang Shuchang Zheng Kai Meng Kexuan Zhou School of Computer and Data Engineering NingboTech University Ningbo China Digital Technology Center China Water Environment Group Beijing China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9798331530891

ISBN: (纸本)9798331530907

Efficient operation of wastewater treatment plants is crucial for environmental protection and public health. However, accurately predicting key operational parameters has been a challenging task due to the complexity and dynamism of the wastewater treatment process. This study proposes an innovative time series prediction model, TimeMachine, based on the Mamba state space model, for long-term prediction of wastewater treatment plant operational parameters. The model effectively captures short-term fluctuations and long-term trends in wastewater treatment data, providing important data support for optimizing the operational management of wastewater treatment plants. We conducted extensive experiments on real wastewater treatment plant datasets, and the results show that the TimeMachine model outperforms existing state-of-the-art methods in terms of prediction accuracy, scalability, and computational efficiency. In particular, TimeMachine demonstrates significant advantages in predicting key parameters such as PAC dosing rate and effluent water quality. This study provides new insights into the application of advanced time series prediction models in the wastewater treatment field, contributing to improved operational efficiency, ensuring compliance with discharge standards, and optimizing resource utilization in wastewater treatment plants.

关键词： Fluctuations Computational modeling Scalability Time series analysis Water quality Effluents Predictive models Market research Picture archiving and communication systems Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

AegonKV: a high bandwidth, low tail latency, and low storage cost KV-separated LSM store with SmartSSD-based GC offloading 25

AegonKV: a high bandwidth, low tail latency, and low storage...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Zhuohui Duan Hao Feng Haikun Liu Xiaofei Liao Hai Jin Bangyu Li National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world *** this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/ software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

arXiv

引用

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation

arXiv

引用

arXiv 2024年

作者： Hong, Lingyi Liu, Zhongying Chen, Wenchao Tan, Chenzhi Feng, Yuang Zhou, Xinyu Guo, Pinxue Li, Jinglun Chen, Zhaoyu Gao, Shuyong Zhang, Wei Zhang, Wenqiang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Shanghai Engineering Research Center of AI&Robotics Academy for Engineering&Technology Fudan University Shanghai China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan University Shanghai China The Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5 seconds, where objects remain visible most of the time. However, these benchmarks poorly represent practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average, approximately 5 times longer than videos in existing datasets. Each video includes various attributes, especially challenges deriving from the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models' performance in real scenarios. Based on LVOS, we evaluate 20 existing VOS models under 4 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that key factor to accuracy decline is the increased video length, emphasizing LVOS's crucial role. We hope our LVOS can advance development of VOS in real scenes. data and code are available at https://***/lvos. ***/. © 2024, CC BY.

关键词： Benchmarking

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：