检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China JinYinHu Laboratory Wuhan China

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter-Procedural Vulnerability dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulnerability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Learner Action Patterns in the Problem-Solving Process Related to Program Code Composition Based on Tracking System Activities 7

Learner Action Patterns in the Problem-Solving Process Relat...

引用

7th International Conference on Informatics and Computing, ICIC 2022

作者： Syahidi, Aulia Akhrian Supianto, Ahmad Afif Hirashima, Tsukasa Watanobe, Yutaka Politeknik Negeri Banjarmasin Smart City Information System Applied Undergraduate Program Banjarmasin City Indonesia Research Center for Data and Information Sciences Bandung City Indonesia Graduate School of Advanced Science and Engineering Hiroshima University Kagamiyama Learning Engineering Laboratory Higashihiroshima Japan University of Aizu Division of Information Systems Department of Computer Science and Engineering Fukushima AizuWakamatsu Japan

ISBN: (纸本)9798350345711

Learning activities are an indicator of the learner's desire to learn during the learning process. The pattern of learner action is related to learning activities. In this case, in extracting the learning process, it is necessary to collect a lot of data through analysis of the learning process. The purpose of this study is to recommend and report the performance of an activity tracking system equipped with visual artifacts as an educational data mining approach to analyze action patterns when learners complete the arrangement of program code lines in each programming problem. In this study, data were taken from activity recordings when learners used interactive learning media for a basic programming subject called TOLSYASUPI-EduMed which had problem-solving learning models embedded in their interactions. Learning Analytics is used as a method of this research and data relationships from learner actions during the learning process using the 'if-then' rule. Log data is used for recording and detecting activities carried out by learners. We confirm that the results of the study are based on the findings of the data relationship that if the lines of program code are too long (more than five lines) then almost all learners experience a bottleneck condition. The completion time of each question and the number of iterations in completing the program code lines for each question have also been recorded and have a pattern of connection between the data. The information that has been obtained is then forwarded to teachers or stakeholders as key information to make appropriate feedback to learners based on the results as a means of analyzing and evaluating the programming learning process. © 2022 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

On the Effectiveness of Function-Level Vulnerability Detecto...

引用

International Conference on Software engineering (ICSE)

作者： Zhen Li Ning Wang Deqing Zou Yating Li Ruqian Zhang Shouhuai Xu Chao Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jin YinHu Laboratory Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado Springs Colorado USA Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers; and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities.

关键词： Deep learning Detectors Open source software Software engineering

来源：评论

学校读者我要写书评

暂无评论

Imaging foundation model for universal enhancement of non-ideal measurement CT

arXiv

引用

arXiv 2024年

作者： Liu, Yuxin Ge, Rongjun He, Yuting Wu, Zhan Yang, Shangwen Gao, Yuan You, Chenyu Wang, Ge Chen, Yang Li, Shuo School of Computer Science and Engineering Southeast University China School of Instrument Science and Engineering Southeast University China Department of Computer and Data Sciences Case Western Reserve University United States Department of Biomedical Engineering Case Western Reserve University United States Department of Electrical & Computer Engineering Yale University United States Department of Radiology Nanjing Drum Tower Hospital Affiliated Hospital of Medical School Nanjing University China Shandong Fundamental Research Center for Computer Science Qilu University of Technology Shandong Academy of Sciences China Department of Biomedical Engineering Rensselaer Polytechnic Institute United States

Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We propose the multi-scale integrated Transformer AMPlifier (TAMP), the first imaging foundation model for universal NICT enhancement. Pre-trained on 10.8 million physics-driven simulated NICT images, TAMP generalizes effectively across various NICT settings, defect degrees, and body regions. Moreover, a parameter-efficient fine-tuning strategy enables TAMP to adapt to specific clinical scenarios using only few slices. Extensive experiments, including radiologists and real-world validations, demonstrate that TAMP consistently improves image quality and clinical acceptability, underscoring its significant potential to advance CT imaging and broaden NICT applications in clinical practice. © 2024, CC BY-NC-SA.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Logical Relation Modeling and Mining in Hyperbolic Space for Recommendation

Logical Relation Modeling and Mining in Hyperbolic Space for...

引用

International Conference on data engineering

作者： Yanchao Tan Hang Lv Zihao Zhou Wenzhong Guo Bo Xiong Weiming Liu Chaochao Chen Shiping Wang Carl Yang College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany College of Computer Science Zhejiang University Hangzhou China Department of Computer Science Emory University Atlanta United States

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The sparse interactions between users and items have aggravated the difficulty of their representations in recommender systems. Existing methods leverage tags to alleviate the sparsity problem but ignore prevalent logical relations among items and tags (e.g., membership, hierarchy, and exclusion), which can be leveraged to enhance the accuracy of modeling user preferences and conducting recommendations. To this end, we propose to extract logical relations among item tags from existing tag taxonomies and exploit the individual strengths of the Poincaré and the Lorentz models in hyperbolic space for logical relation modeling towards enhanced recommendations. Moreover, we find that the logical relations directly extracted from existing tag taxonomies can be inaccurate and coarse. Therefore, we further devise innovative consistency-based and granularity- based weighting mechanisms based on user behavior patterns for data-driven logical relation mining that can be jointly optimized along with recommendations in an end-to-end fashion. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed framework, which constantly achieves an average of 8.25% improvement over state-of-the-art competitors regarding both Recall and NDCG metrics. Insightful case studies further demonstrate that our automatically refined logical relations are highly accurate and interpretable.

关键词： Measurement Accuracy Taxonomy Semantics Predictive models Performance gain Linguistics

来源：评论

学校读者我要写书评

暂无评论

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding

arXiv

引用

arXiv 2024年

作者： Li, Hongkang Wang, Meng Ma, Tengfei Liu, Sijia Zhang, Zaixi Chen, Pin-Yu Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute TroyNY United States Department of Biomedical Informatics Stony Brook University Stony Brook NY United States Department of Computer Science and Engineering Michigan State University East LansingMI United States MIT-IBM Watson AI Lab IBM Research MA United States Department of Computer Science and Engineering University of Science and Technology of China Anhui Hefei China IBM Thomas J. Watson Research Center Yorktown Heights NY United States

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

GeckoDAG: Towards a Lightweight DAG-Based Blockchain via Reducing data Redundancy

GeckoDAG: Towards a Lightweight DAG-Based Blockchain via Red...

引用

International Conference on Distributed Computing Systems

作者： Xiaohai Dai Yifan Zhou Jiang Xiao Feng Cheng Xia Xie Hai Jin Bo Li National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China School of Computer Science and Technology Hainan University China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

To overcome the scaling and performance limitations, the Directed Acyclic Graph (DAG) is utilized as the underlying storage model of blockchain systems, which enables concurrent transaction processing and confirmation. However, accompanied by high performance, DAG-based blockchains still suffer from the severe challenge of constrained storage scalability, i.e., expensive storage overhead. Based on an in-depth analysis of the data, we discover that the root cause of storage overhead stems from the considerable data redundancy in the DAG-based blockchains. In this paper, we propose GeckoDAG, a lightweight DAG-based blockchain, whose design consists of two steps. First, we abstract a storage model named Basic from the existing DAG-based blockchain systems, which offers both high performance and security. On top of Basic, we then devise GeckoDAG, which merges previous transactions into Transaction Union (TU) and reduces the data redundancy in TU, thus lowering the storage overhead. To evaluate our design, we implement a prototype of GeckoDAG and conduct various experiments on it. The experimental results demonstrate that GeckoDAG can offer storage scalability while maintaining the security and efficiency of DAG-based blockchains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pretraining Conformer with ASR for Speaker Verification

Pretraining Conformer with ASR for Speaker Verification

引用

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

作者： Danwei Cai Weiqing Wang Ming Li Rui Xia Chuanzeng Huang Department of Electrical and Computer Engineering Duke University Durham USA Data Science Research Center Duke Kunshan University Kunshan China Speech Audio and Music (SAMI) Group Bytedance China

This paper proposes to pretrain Conformer with automatic speech recognition (ASR) task for speaker verification. Conformer combines convolution neural network (CNN) and Transformer model for modeling local and global features, respectively. Recently, multi-scale feature aggregation Conformer (MFA-Conformer) has been proposed for automatic speaker verification. MFA-Conformer concatenates frame-level outputs from all Conformer blocks for further pooling. However, our experiments show that Conformer can be easily overfitted with limited speaker recognition training data. To avoid overfitting, we propose to transfer the knowledge learned from ASR to speaker verification. Specifically, an ASR pretrained Conformer is used to initialize the training of MFA-Conformer for speaker verification. Our experiments show that pretraining Conformer with ASR leads to significant performance gains across model sizes. The best model achieves 0.48%, 0.71% and 1.54% EER on Voxceleb1-O, Voxceleb1-E, and Voxceleb1-H, respectively.

关键词： Training Convolution Neural networks Training data Performance gain Transformers Speaker recognition

来源：评论

学校读者我要写书评

暂无评论

applications of Machine Learning in Medicine: Current Trends and Prospects

Applications of Machine Learning in Medicine: Current Trends...

引用

Wireless and Optical Technologies (GCWOT), 2020 Global Conference on

作者： Muhammad Aamir Sibghatullah Bazai Uzair Aslam Bhatti Zaheer Ahmed Dayo Jing Liu Kun Zhang College of Computer Science Huanggang Normal Univeristy Huanggang China Department of Computer Engineering Balochistan University of Information Technology Engineering and Management Sciences Quetta Pakistan School of Information and Communication Engineering Hainan University Haikou China Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China

With the continuous development of information technology and medical data information, more and more clinicians recognize artificial intelligence or will completely change medical practice by using advanced machine learning methods. The potential of using machine learning and predictive analysis to customize specific treatments for individuals is currently under research. Machine learning can learn a large number of medical data and explore the dependencies in data concentration, forming a corresponding medical model that can quickly and accurately predict new data, which is conducive to the early diagnosis of diseases and assisted clinical decisions. Clinical medicine faces the status quo of the relative shortage of medical resources and the identification and rapid diagnosis and treatment of critically ill emergency patients. In the era of big data, clinical demand is driven by clinical needs, and intelligent medical care provided by machines is the key to tackling the aforementioned issues.

关键词： Industries Wireless communication Sociology Machine learning Medical services Big data Predictive models

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Preoperative Early Recurrence Prediction of Hepatocellular Carcinoma with Multi-phase CT Images 10th

A Unified Framework for Preoperative Early Recurrence Predic...

引用

10th KES International Conference on Innovation in Medicine and Healthcare, KES-InMed 2022

作者： Ouyang, Shuyi Xu, Yingying Wang, Weibin Li, Yinhao Wang, Fang Chen, Qingqing Lin, Lanfen Chen, Yen-Wei Hu, Hongjie College of Computer Science and Technology Zhejiang University Hangzhou310000 China Research Center for Healthcare Data Science Zhejiang Lab Hangzhou311121 China College of Information Science and Engineering Ritsumeikan University Shiga Kusatsu525-8577 Japan Department of Radiology Sir Run Run Shaw Hospital Zhejiang University Hangzhou310000 China

ISBN: (纸本)9789811934391

Early recurrence (ER) after surgery is one of the main causes of death in Hepatocellular Carcinoma (HCC). Making an effective prediction of the risk of ER is important in developing treatment strategies. The existing methods generally use radiomic features or simple deep learning features, which have insufficient feature representation capabilities. Here, we present a deep learning-based strategy for obtaining enriched multi-phase fusion features that can effectively represent feature information. We present an effective preoperative prediction model that uses multi-phase CT scans as input. Our proposed framework significantly utilizes and enhances multi-phase contextual information by effectively performing multi-phase feature fusion. We also present a novel backbone network with attention mechanisms called Inv-ResNet, that can extract more discriminative features from each CT phase using ResNet block and involution operator. Further, we design a Multi-Phase Feature Fusion Module that allows for global-Squeeze and phase-Excitation of important feature weights across all CT phases to selectively fuse features. In comparison to existing methods of preoperative prediction of ER of HCC, our method achieves 72.70% accuracy and a value of 0.7478 area under the ROC curve (AUC), which is the highest accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computerized tomography

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：