检索结果-内蒙古大学图书馆

Enhancing building pattern recognition through multi-scale data and knowledge graph:a case study of C-shaped patterns

引用

International Journal of Digital Earth 2023年第1期16卷 3860-3881页

作者： Zhiwei Wei Wenjia Xu Yi Xiao Mi Shu Lu Cheng Yang Wang Chunbo Liu Key Laboratory of Network Information System Technology(NIST) Aerospace Information Research InstituteChinese Academy of SciencesBeijingPeople’s Republic of China The Aerospace Information Research Institute Chinese Academy of SciencesBeijingPeople’s Republic of China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijingPeople’s Republic of China School of Software Engineering Shenzhen Institute of Information TechnologyShenzhenPeople’s Republic of China Institute of Remote Sensing and GIS Peking UniversityBeijingPeople’s Republic of China School of Geography Science and Geomatics Suzhou University of Science and TechnologySuzhouPeople’s Republic of China

Building pattern recognition is important for understanding urban forms,automating map generalization,and visualizing 3D city ***,current approaches based on object-independent methods have limitations in capturing all visually aware patterns due to the part-based nature of human ***,these approaches also suffer from inefficiencies when applying proximity graph *** address these limitations,we propose a framework that leverages multi-scale data and a knowledge graph,focusing on recognizing C-shaped building *** first employ a specialized knowledge graph to represent the relationships between buildings within and across various ***,we convert the rules for C-shaped pattern recognition and enhancement into query conditions,where the enhancement refers to using patterns recognized at one scale to enhance pattern recognition at other ***,rule-based reasoning is applied within the constructed knowledge graph to recognize and enrich C-shaped building *** verify the effectiveness of our method using multi-scale data with three levels of detail(LODs)collected from AMap,and our method achieves a higher recall rate of 26.4%for LOD1,20.0%for LOD2,and 9.1%for LOD3 compared to existing methods with similar ***,also achieve recognition efficiency improvements of 0.91,1.37,and 9.35 times,respectively.

关键词： Building pattern recognition urban form knowledge graph rule-based reasoning

来源：评论

学校读者我要写书评

暂无评论

Introducing Diminutive Causal Structure into Graph Representation Learning

arXiv

引用

arXiv 2024年

作者： Gao, Hang Qiao, Peng Jin, Yifan Wu, Fengge Li, Jiangmeng Zheng, Changwen Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

When engaging in end-to-end graph representation learning with Graph Neural Networks (GNNs), the intricate causal relationships and rules inherent in graph data pose a formidable challenge for the model in accurately capturing authentic data relationships. A proposed mitigating strategy involves the direct integration of rules or relationships corresponding to the graph data into the model. However, within the domain of graph representation learning, the inherent complexity of graph data obstructs the derivation of a comprehensive causal structure that encapsulates universal rules or relationships governing the entire dataset. Instead, only specialized diminutive causal structures, delineating specific causal relationships within constrained subsets of graph data, emerge as discernible. Motivated by empirical insights, it is observed that GNN models exhibit a tendency to converge towards such specialized causal structures during the training process. Consequently, we posit that the introduction of these specific causal structures is advantageous for the training of GNN models. Building upon this proposition, we introduce a novel method that enables GNN models to glean insights from these specialized diminutive causal structures, thereby enhancing overall performance. Our method specifically extracts causal knowledge from the model representation of these diminutive causal structures and incorporates interchange intervention to optimize the learning process. Theoretical analysis serves to corroborate the efficacy of our proposed method. Furthermore, empirical experiments consistently demonstrate significant performance improvements across diverse datasets. © 2024, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Improving Smart Contract Security with Contrastive Learning-based Vulnerability Detection

arXiv

引用

arXiv 2024年

作者： Chen, Yizhou Sun, Zeyu Gong, Zhihao Hao, Dan MOE School of Computer Science Peking University Beijing China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China

Currently, smart contract vulnerabilities (SCVs) have emerged as a major factor threatening the transaction security of blockchain. Existing state-of-the-art methods rely on deep learning to mitigate this threat. They treat each input contract as an independent entity and feed it into a deep learning model to learn vulnerability patterns by fitting vulnerability labels. It is a pity that they disregard the correlation between contracts, failing to consider the commonalities between contracts of the same type and the differences among contracts of different types. As a result, the performance of these methods falls short of the desired level. To tackle this problem, we propose a novel Contrastive Learning Enhanced Automated Recognition Approach for Smart Contract Vulnerabilities, named Clear. In particular, Clear employs a contrastive learning (CL) model to capture the fine-grained correlation information among contracts and generates correlation labels based on the relationships between contracts to guide the training process of the CL model. Finally, it combines the correlation and the semantic information of the contract to detect SCVs. Through an empirical evaluation of a large-scale real-world dataset of over 40K smart contracts and compare 13 state-of-the-art baseline methods. We show that Clear achieves (1) optimal performance over all baseline methods;(2) 9.73%-39.99% higher F1-score than existing deep learning methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

First Demonstration of Wafer-level Arrayed β-Ga2O3 Thin Films and MOSFETs on Diamond by Transfer Printing technology

First Demonstration of Wafer-level Arrayed β-Ga2O3 Thin Fil...

引用

2024 IEEE International Electron Devices Meeting, IEDM 2024

作者： Zhao, Tiancheng Yu, Xinxin Xu, Wenhui He, Yang Qu, Zhenyu Shen, Rui Wang, Ruize Guo, Huaixin Sun, Huarui Li, Zhonghui Zhou, Min You, Tiangui Ou, Xin State Key Laboratory of Materials for Integrated Circuits Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai200050 China CETC Key Laboratory of Carbon-based Electronics Nanjing Electronic Devices Institute Nanjing210016 China National Key Laboratory of Solid-State Microwave Devices and Circuits Nanjing210016 China School of Science Ministry of Industry and Information Technology Key Laboratory of Micro-Nano Optoelectronic Information System Harbin Institute of Technology Shenzhen518055 China

ISBN: (纸本)9798350365429

We, for the first time, fabricated wafer-level arrayed βGa2O3 single crystal thin films on diamond substrate using transfer printing technology. The transfer-printed β-Ga2O3 thin film possesses a thickness of 260 nm, a XRD rocking curve FWHM of ~78 arcsec, and a surface roughness of 0.36 nm. The amorphous interface layer after post-annealing is less than 2 nm. The thermal boundary resistance is extracted to 21.7 m2·K/GW, which is the lowest value reported for single-crystal β-Ga2O3 integrated with diamond. Thanks to the high thermal conductivity of diamond and the high-quality hetero-interface, the performance of β-Ga2O3-on-diamond RF MOSFETs is significantly enhanced. The maximum on-state current is 810 mA/mm, and the fmax before de-embedding reaches 61 GHz, which is the highest recorded value to date. Infrared thermal imaging shows that integrating with diamond significantly reduces the junction temperature of β-Ga2O3 devices. The Rth of β-Ga2O3-ondiamond devices is merely 5.52 K·mm/W, setting a new record for βGa2O3-based devices. These results demonstrate that hetero-integration with diamond via wafer-level transfer printing technology provides an effective thermal management platform for β-Ga2O3, facilitating its advancement in high-power and RF devices. © 2024 IEEE.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of GPS satellite-based augmentation system based on low earth orbit constellations 3

Design and analysis of GPS satellite-based augmentation syst...

引用

2024 3rd International Conference on Aerospace and Control Engineering, ICoACE 2024

作者： Yang, Jianlei Jin, Zhengzhen Zheng, Shuaiyong Huang, Shiyong Ma, Guoyu Ji, Shiran Key Laboratory of Satellite Navigation System and Equipment Technology Shijiazhuang050081 China The 54 Research Institute China Electronics Technology Group Shijiazhuang050081 China School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China College of Software Tianjin Normal University Tianjin300387 China

Addressing the need for improved GPS accuracy, especially for low-dynamic users, this study introduces a GPS augmentation system employing Low Earth Orbit (LEO) satellites. We detail the principles of satellite navigation and augmentation and simulate the GPS-LEO constellation to analyse its performance in terms of satellite visibility and Position Dilution of Precision (PDOP). The results demonstrate substantial augmentation in navigation accuracy with the integrated system, as verified by UAV flight experiments. The integration of LEO satellites is anticipated to advance global navigation capabilities, with implications for intelligent transportation, logistics, and precision agriculture. © 2025 institute of Physics Publishing. All rights reserved.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models

arXiv

引用

arXiv 2024年

作者： Yang, Junjie Jiang, Jiajun Sun, Zeyu Chen, Junjie College of Intelligence and Computing Tianjin University Tianjin China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China

Fairness has been a critical issue that affects the adoption of deep learning models in real practice. To improve model fairness, many existing methods have been proposed and evaluated to be effective in their own contexts. However, there is still no systematic evaluation among them for a comprehensive comparison under the same context, which makes it hard to understand the performance distinction among them, hindering the research progress and practical adoption of them. To fill this gap, this paper endeavours to conduct the first large-scale empirical study to comprehensively compare the performance of existing state-of-the-art fairness improving techniques. Specifically, we target the widely-used application scenario of image classification, and utilized three different datasets and five commonly-used performance metrics to assess in total 13 methods from diverse categories. Our findings reveal substantial variations in the performance of each method across different datasets and sensitive attributes, indicating over-fitting on specific datasets by many existing methods. Furthermore, different fairness evaluation metrics, due to their distinct focuses, yield significantly different assessment results. Overall, we observe that pre-processing methods and in-processing methods outperform post-processing methods, with pre-processing methods exhibiting the best performance. Our empirical study offers comprehensive recommendations for enhancing fairness in deep learning models. We approach the problem from multiple dimensions, aiming to provide a uniform evaluation platform and inspire researchers to explore more effective fairness solutions via a set of implications. © 2024, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

VEglue: Testing Visual Entailment systems via Object-Aligned Joint Erasing

arXiv

引用

arXiv 2024年

作者： Chang, Zhiyuan Li, Mingyang Wang, Junjie Li, Cheng Wang, Qing Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences State Key Laboratory of Intelligent Game University of Chinese Academy of Sciences Beijing China

Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence. The goal is to predict whether the image semantically entails the sentence. VE systems have been widely adopted in many downstream tasks. Metamorphic testing is the commonest technique for AI algorithms, but it poses a significant challenge for VE testing. They either only consider perturbations on single modality which would result in ineffective tests due to the destruction of the relationship of image-text pair, or just conduct shallow perturbations on the inputs which can hardly detect the decision error made by VE systems. Motivated by the fact that objects in the image are the fundamental element for reasoning, we propose VEglue, an object-aligned joint erasing approach for VE systems testing. It first aligns the object regions in the premise and object descriptions in the hypothesis to identify linked and un-linked objects. Then, based on the alignment information, three Metamorphic Relations are designed to jointly erase the objects of the two modalities. We evaluate VEglue on four widely-used VE systems involving two public datasets. Results show that VEglue could detect 11,609 issues on average, which is 194%-2,846% more than the baselines. In addition, VEglue could reach 52.5% Issue Finding Rate (IFR) on average, and significantly outperform the baselines by 17.1%-38.2%. Furthermore, we leverage the tests generated by VEglue to retrain the VE systems, which largely improves model performance (50.8% increase in accuracy) on newly generated tests without sacrificing the accuracy on the original test set. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trusted Polarimetric Feature Fusion for Polsar Image Classification

Trusted Polarimetric Feature Fusion for Polsar Image Classif...

引用

SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA)

作者： Fangzhou Han Lamei Zhang Hongwei Dong Department of Information Engineering Harbin Institute of Technology Harbin China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China

Benefiting from the rapid advancements in Deep Learning (DL), data-driven features exhibit remarkable separability in PolSAR image classification. However, data-driven features are challenging to interpret and susceptible to resolution and noise. On the contrary, polarimetric features based on the target decomposition not only have high robustness, but also has physical interpretability. Consequently, researchers have begun to explore ways to integrate both types of features to achieve enhanced performance, which typically concat the data-driven features and polarimetric features directly. However, polarimetric features are not stable in separability, which is because the inherent defects of the target decomposition algorithm. To mitigate the adverse effects of low-quality features, this paper proposes a trusted polarimetric feature fusion (TPFF). The new paradigm calculates the confidence of features and employs a novel feature fusion method. The proposed method has been tested on the EMISAR Foulum dataset, with experimental results demonstrating improved classification performance and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Less Yet Robust: Crucial Region Selection for Scene Recognition

Less Yet Robust: Crucial Region Selection for Scene Recognit...

引用

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

作者： Zhang, Jianqi Wang, Mengxuan Wang, Jingyao Si, Lingyu Zheng, Changwen Xu, Fanjiang National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Shien-Ming Wu School of Intelligent Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene recognition tasks. However, low-quality images still impede model performance due to the inappropriate use of high-level semantic features. To address these challenges, we propose an adaptive selection mechanism to identify the most important and robust regions with high-level features. Thus, the model can perform learning via these regions to avoid interference. implement a learnable mask in the neural network, which can filter high-level features by assigning weights to different regions of the feature matrix. We also introduce a regularization term to further enhance the significance of key high-level feature regions. Different from previous methods, our learnable matrix pays extra attention to regions that are important to multiple categories but may cause misclassification and sets constraints to reduce the influence of such regions. This is a plug-and-play architecture that can be easily extended to other methods. Additionally, we construct an Underwater Geological Scene Classification dataset to assess the effectiveness of our model. Extensive experimental results demonstrate the superiority and robustness of our proposed method over state-of-the-art techniques on two datasets. © 2025 IEEE.

关键词： high-level semantic features remote sensing robust method Scene recognition underwater images

来源：评论

学校读者我要写书评

暂无评论

Testing the Limits: Unusual Text Inputs Generation for Mobile App Crash Detection with Large Language Model 24

Testing the Limits: Unusual Text Inputs Generation for Mobil...

引用

44th ACM/IEEE International Conference on software Engineering, ICSE 2024

作者： Liu, Zhe Chen, Chunyang Wang, Junjie Chen, Mengzhuo Wu, Boyu Tian, Zhilin Huang, Yuekai Hu, Jun Wang, Qing State Key Laboratory of Intelligent Game Beijing China Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Technical University of Munich Munich Germany DiDi Global Inc The Pennsylvania State University Work Done during the Internship at Iscas United States Science & Technology on Integrated Information System Laboratory China

ISBN: (纸本)9798400702174

Mobile applications have become a ubiquitous part of our daily life, providing users with access to various services and utilities. Text input, as an important interaction channel between users and applications, plays an important role in core functionality such as search queries, authentication, messaging, etc. However, certain special text (e.g., -18 for Font Size) can cause the app to crash, and generating diversified unusual inputs for fully testing the app is highly demanded. Nevertheless, this is also challenging due to the combination of explosion dilemma, high context sensitivity, and complex constraint relations. This paper proposes InputBlaster which leverages the LLM to automatically generate unusual text inputs for mobile app crash detection. It formulates the unusual inputs generation problem as a task of producing a set of test generators, each of which can yield a batch of unusual text inputs under the same mutation rule. In detail, InputBlaster leverages LLM to produce the test generators together with the mutation rules serving as the reasoning chain, and utilizes the in-context learning schema to demonstrate the LLM with examples for boosting the performance. InputBlaster is evaluated on 36 text input widgets with cash bugs involving 31 popular Android apps, and results show that it achieves 78% bug detection rate, with 136% higher than the best baseline. Besides, we integrate it with the automated GUI testing tool and detect 37 unseen crashes in real-world apps. © 2024 ACM.

关键词： Android (operating system)

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：