检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Niu, Yao Luo, Zhiming Lian, Sheng Li, Lei Li, Shaozi Song, Haixin Xiamen University Department of Artificial Intelligence Fujian China Fuzhou University College of Computer and Data Science Fujian China Xiamen University Department of Software Engineering Fujian China

ISBN: (纸本)9781665468190

Few-shot learning can potentially learn the target knowledge in extremely few data regimes. Existing few-shot medical image segmentation methods fail to consider the global anatomy correlation between the support and query sets. They generally adopt a weak one-way information transmission that can not fully explore the knowledge to segment query data. To address this problem, we propose a novel Symmetrical Supervision network based on traditional two-branch methods. We raise two main contributions: (1) The Symmetrical Supervision Mechanism is leveraged to strengthen the supervision of network training;(2) A transformer-based Global Feature Alignment module is introduced to increase the global consistency between the two branches. Experimental results on two challenging datasets (abdominal segmentation dataset CHAOS and cardiac segmentation dataset MS-CMRSeg) show a remarkable performance compared to other comparing methods. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Extending the Heatmap Matrix: Pairwise Analysis of Multivariate Categorical Data

Extending the Heatmap Matrix: Pairwise Analysis of Multivari...

引用

International Conference on Information Visualisation (IV)

作者： David Trye Mark Apperley David Bainbridge Computer Science University of Waikato Hamilton New Zealand Software Engineering University of Waikato Hamilton New Zealand

Analysts are often interested in understanding the association between variables within a dataset. This paper describes a set of techniques for augmenting the Heatmap Matrix, which represents pairwise intersections of categorical variables. The proposed extensions include adapting the design and layout of the matrix to enhance its readability, expanding the number of metrics that can be presented, displaying matching records in a coordinated table view, and embedding the Chi-square test of independence. These features are demonstrated on two datasets using the empirical prototype that has been developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Target Detection Models Based on deep Learning

Target Detection Models Based on deep Learning

引用

2022 International Conference on Cloud Computing, Performance Computing, and Deep Learning, CCPCDL 2022

作者： Fu, Haoluo Li, Yuming Wang, Weining Xu, Xuanbo P.C. Rossin College of Engineering and Applied Science Lehigh University BethlehemPA18015 United States College of Computer Science Guangdong University of Technology Guangdong Guangzhou510006 China College of software Xinjiang University Xinjiang830046 China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China

ISBN: (纸本)9781510655867

Object detection is one of the most basic and important tasks in the field of computer vision, and it is the foundation of high-level vision tasks such as behaviour recognition and human-computer interaction. With the development of deep learning technology, the accuracy and efficiency of target detection models have been greatly improved. Compared with traditional target detection algorithms, deep learning uses powerful hierarchical feature extraction and learning capabilities to make a breakthrough in the performance of target detection algorithms. At the same time, the emergence of large-scale data sets and the greatly improved computing power of graphics cards have also contributed to the vigorous development of this field. This article reviews the existing research results of target detection based on deep learning. This article first reviews the traditional target detection algorithm and its existing problems, then introduces the two-stage detection model and single-stage detection model under deep learning, and finally briefly summarizes the application scenarios of the target detection algorithm and summarizes the full text. © 2022 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A review on computer vision and machine learning techniques for automated road surface defect and distress detection

引用

Journal of Smart Cities and Society 2023年第PRE-PRESS期Pre-press卷 1-17页

作者： Chen, Xuejing Yongchareon, Sira Knoche, Martin Computer Science and Software Engineering Department Auckland University of Technology Auckland New Zealand N3T Limited Whangarei New Zealand

As the pace grows in the development of image processing techniques and the current applications rise in machine learning and deep learning techniques for visual inspections and physical assessment, this article reviews the existing literature. It provides a detailed synthesis of the overview of surface pavement conditions, computer-vision-based technologies for road damage detection, various datasets and data collection methods. We analyse and compare different machine-learning methods and models proposed in the literature and identify challenges that need to be addressed in the future in road surface defect detection.

关键词： Road condition assessment distress detection road defects analysis

来源：评论

学校读者我要写书评

暂无评论

Underwater image color correction via global and local two-step optimization

引用

Pattern Recognition Letters 2025年 196卷 38-44页

作者： Baiqiang Yu Ling Zhou Wenqiang Yu Peixian Zhuang Weidong Zhang School of Information Engineering Henan Institute of Science and Technology Xinxiang 453003 China School of Computer and Software Nanyang Institute of Technology Nanyang 473000 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing 100084 China School of Electrical and Information Engineering Zhengzhou University Zhengzhou 450001 China

Underwater images usually suffer from quality degradation due to light absorption and scattering, leading to color distortion, blurred details, and low contrast. To address these challenges, we propose a global and local two-step optimization method (GLTO). Specifically, we first analyze the statistical features of natural images in the CIELab color space. Meanwhile, we design a heuristic global optimization strategy that minimizes the feature differences between underwater and natural images to restore the color and luminance of the raw image. We develop a local optimization strategy based on luminance information, which uses guided filtering to decompose the luminance channel into large-scale and small-scale high-frequency images and weighted fusion of them to obtain a detail-enhanced luminance channel. Finally, we leverage the local illumination intensity of the image captured by the luminance channel to adjust the local color distortion. Extensive experimental evaluations have demonstrated the superiority of our proposed GLTO method in underwater image preprocessing, which substantially enhances the performance of subsequent image enhancement. The project can be found at https://***/yubaiqiang/GLTO .

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Model for Brain Tumor Recognition in MRI Images Based on Hand-Crafted Features and Deep Learning

A New Hybrid Model for Brain Tumor Recognition in MRI Images...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Yasser Nizamli Weaam Fadel Anton Filatov Yulia Shichkina Department of Software Engineering and Computer Applications Saint Petersburg Electrotechnical University Saint Petersburg Russian Federation Department of Computer Science Saint Petersburg Electrotechnical University Saint Petersburg Russian Federation

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

Brain tumors are among the most life-threatening cancers that can affect people of any gender or age. MRI scans manually evaluated by an expert are the initial diagnostic procedure that precedes an appropriate treatment plan. However, the human factor involves the possibility of error, and the process itself can be time-consuming and resourceconsuming, ultimately putting patients’ lives at risk. Therefore, efforts are being made to automate the diagnostic process through computer-aided systems, of which artificial intelligence has become the basis. This paper presents a novel system for detecting brain abnormalities in MRI images that ensures high precision without compromising the simplicity of its operational structure. In the proposed model, numerical features are extracted from grayscale MRI images using the rectangular histogram of oriented gradients method. The resulting features are fed after dimensionality reduction to a specialized sequential deep network composed of 11 learnable layers. The classification accuracy of the model reached 99.51%, outperforming many analogues, making it a promising option for supporting the diagnostic decision-making process.

关键词： Deep learning Histograms Image recognition Magnetic resonance imaging Decision making Brain tumors Feature extraction Brain modeling Numerical models Testing

来源：评论

学校读者我要写书评

暂无评论

UR4NNV: Neural Network Verification, Under-approximation Reachability Works!

arXiv

引用

arXiv 2024年

作者： Liang, Zhen Wu, Taoran Zhao, Ran Xue, Bai Wang, Ji Yang, Wenjing Deng, Shaojun Liu, Wanwei College of Computer Science and Technology National University of Defense Technology China Institute of Software Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China

Recently, formal verification of deep neural networks (DNNs) has garnered considerable attention, and over-approximation based methods have become popular due to their effectiveness and efficiency. However, these strategies face challenges in addressing the "unknown dilemma" concerning whether the exact output region or the introduced approximation error violates the property in question. To address this, this paper introduces the UR4NNV verification framework, which utilizes under-approximation reachability analysis for DNN verification for the first time. UR4NNV focuses on DNNs with Rectified Linear Unit (ReLU) activations and employs a binary tree branch-based under-approximation algorithm. In each epoch, UR4NNV under-approximates a sub-polytope of the reachable set and verifies this polytope against the given property. Through a trial-and-error approach, UR4NNV effectively falsifies DNN properties while providing confidence levels when reaching verification epoch bounds and failing falsifying properties. Experimental comparisons with existing verification methods demonstrate the effectiveness and efficiency of UR4NNV, significantly reducing the impact of the "unknown dilemma".MSC Codes 68Q60, 68T07 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

Fully Distributed Multi-Agent RL Framework for QoS Routing

Fully Distributed Multi-Agent RL Framework for QoS Routing

引用

IEEE Future Networks World Forum (FNWF)

作者： Quang Huy Duong Emil Janulewicz Brigitte Jaumard Abdelhak Bentaleb Sergio Slobodrian Department of Computer Science & Software Engineering Concordia University Montréal QC Canada Ciena Ottawa ON Canada

Classical routing heuristics, e.g., Open Shortest Path First, have several significant issues, such as they are not able to generalize or adapt to heterogeneous environments including dynamics of topology, traffic patterns, and Quality of Service (QoS) requirements. To generalize solutions, network operators recently utilized machine learning algorithms at centralized controllers. However, centralized machine learning solutions are not scalable due to many reasons, such as slow data transfer to the central controller in a large network. Distributed multi-agent systems do not require a tedious and complex central controller while reducing data storage and computation burden as tasks are divided and handled at local servers/computers. In this paper, we present a fully distributed multi-agent system named MADQN, addressing the request provisioning problem, i.e., provisioning a request on a dedicated path satisfying latency and bandwidth requirements. MADQN applies a Deep Q-Network reinforcement learning algorithm to train the agents. Although each agent has its data and policy locally, they can still cooperate with other agents to finish a common routing task that maximizes the total reward. We evaluate the effectiveness of the MADQN with a benchmark network that consists of 100 nodes and 432 directed links, and a dynamic set of thousands of requests. The results show that the agents in MADQN can learn to cooperate and provision 99% of the requests, which is about a 9% improvement against the centralized single agent scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Crime Based Evaluation of GPS Network Using Machine Learning Techniques 4

Crime Based Evaluation of GPS Network Using Machine Learning...

引用

4th International Conference on Smart Systems and Inventive Technology, ICSSIT 2022

作者： Rahul Monika Durgapal, Vartika Hari Department Of Software Engineering Delhi Technological University Delhi India Department of Computer Science Shaheed Rajguru College of Applied Sciences for Women University of Delhi Delhi110096 India

ISBN: (纸本)9781665401180

With the increased usage of data transmission, data leakage and privacy protection are becoming increasingly critical. Data comes in a variety of forms, and the amount of protection required for each one differs. With the rapid development and demand of Global Positioning S ystem (GPS) networks in every of big data technology, the vulnerability of the transportation system to unintentional and intentional GPS disruption is also increasing. The GPS signal is degraded and lost as a result of opposing interests' attacks. Potential assaults vary from GPS signal jamming and spoofing to GPS ground stations and satellite disruption. S ecurity issues with respect to data increases during data transmission. Data travelling across an organization's network is frequently sensitive and internet being the storehouse of every kind of data with methods for accessing the precise information serves as an auspicious medium for the hackers [19]. Network security solutions must deal with complicated data in this setting in order to detect and minimize any threats in real time. There are several techniques to the problem of data security such as cryptographic algorithms, classification-based models, and block-chain methods [1]-[6]. Through this research, crime rates are evaluated in a GPS network data with different other parameters using machine learning (ML) algorithms. Moreover, the inferred features effecting the crimes during data transmission are extracted. S ome of the techniques used includes techniques such as 'Decision Tree (DT)', 'K Nearest Neighbors (KNN)', 'Random Forest (RF)', 'Multivariable Regression (MR)' and 'Naïve Bayes (NB)'. It was seen that the best accuracy was given by RF - of approximately 84.25%. © 2022 IEEE

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Fast Super-Resolution Network via Dynamic Path Selection

Fast Super-Resolution Network via Dynamic Path Selection

引用

Image Processing, computer Vision and Machine Learning (ICICML), International Conference on

作者： Longfei Jia Yuguo Hu Xianlong Tian Wenwei Luo School of Computer Science and Engineering 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

In the context of edge computing environments, where the storage space and computational resources are constrained, complex super-resolution network models face significant challenges during inference. In this paper, we propose a Fast Super-Resolution Network (FSRN) based on the dynamic path selection mechanism. This method employs a policy network to boost the inference process of super-resolution network models, enabling efficient super-resolution tasks under resource limitations. The primary function of the policy network is to intelligently select appropriate inference paths based on input data and available computational resources. Its key objective is to minimize the degradation in super-resolution quality while reducing the computational burden as much as possible. In view of this objective, we designed a reward function to guide the policy network in discovering the optimal strategies. With the guidance of the policy network, we successfully enhanced the inference speed of super-resolution network models on edge devices while efficiently reducing computational overhead. Extensive experiments verify that the proposed method can significantly reduce the inference time at the cost of slight or even no performance degradation.

关键词：

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：