检索结果-内蒙古大学图书馆

A multi-stages chromosome segmentation and mixed classification method for chromosome automatic karyotyping 1

17th International Conference on Web Information Systems and Applications, WISA 2020

作者： Lin, Chengchuang Zhao, Gansen Yin, Aihua Ding, Bichao Guo, Li Chen, Hanbiao School of Computer Science South China Normal University Guangzhou510631 China Guangdong Women and Children Hospital Guangzhou511400 China Key Lab on Cloud Security and Assessment technology of Guangzhou Guangzhou China SCNU & VeChina Joint Lab on BlockChain Technology and Application Guangzhou510631 China

ISBN: (数字)9783030600297

ISBN: (纸本)9783030600280

The chromosome karyotyping task is vital and indispensable but tedious work for birth defect diagnosis and biomedical research. In this work, we tackle chromosome automatic karyotyping using a multi-stages chromosome segmentation and mixed classification method. Firstly, we apply a global binary threshold-based method to segment the metaphase chromosome microscope grayscale image into several image slices, consisting of chromosome instances and chromosome clusters. Afterward, we propose a mixed chromosome classification method for identifying a given image is a chromosome cluster or corresponding instance label. After that, we use a deep learning-based approach to segment chromosome cluster images into chromosome instances and apply the mixed chromosome classification model to recognize their corresponding labels. Finally, we synthesize a chromosome karyotype from all corresponding instances and labels. In the mixed classification stage, the proposed method yields 99.53± 0.23% classification accuracy on the clinical dataset. In segmentation stages, the proposed method achieves 90.81% comprehensive segmentation accuracy and 85.00% instance segmentation accuracy with 90.63% $$AP:{50}$$ precision. The experimental results show that our proposed method is promising for solving chromosome segmentation and classification task of the clinical chromosome automatic karyotyping. © Springer Nature Switzerland AG 2020.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

Subscription-Based State Access for Cross-Chain Smart Contracts

Subscription-Based State Access for Cross-Chain Smart Contra...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Zhihao Hou Jinji Yang Ruilin Lai Yale He Zefeng Mo Gansen Zhao School of Computer Science South China Normal University Guangzhou China Key Lab on Cloud Security and Assessment Technology of Guangzhou Guangzhou China

Smart contracts play a vital role in blockchain applications, supporting an expanding array of services as the number of blockchains rises. As service requirements become increasingly complex, the need for access and collaboration among multiple smart contracts becomes more prevalent. However, achieving access between smart contracts on different blockchains presents a significant challenge in the Internet of Blockchain scenario comprising numerous heterogeneous blockchains. In this paper, we first explore the problem of smart contract access in cross-heterogeneous blockchain scenarios. Then, an Oracle gateway-based cross-chain smart contract access architecture and a subscription-based cross-chain smart contract active access mechanism are proposed. Finally, a prototype is implemented to show that our architecture and mechanism can support cross-chain smart contract access for heterogeneous blockchains and reduce the complexity and latency of cross-chain smart contract access.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Graph Feature Extraction Based on Multi-Information Contract Graph for Enhanced Smart Contract Vulnerability Detection

Hierarchical Graph Feature Extraction Based on Multi-Informa...

引用

IEEE International Conference on Trust, security and Privacy in computing and Communications (TrustCom)

作者： Tao Fang Zhihao Hou Jiahao He Junjie Zhou Gansen Zhao School of Computer Science South China Normal University Guangzhou China Key Lab on Cloud Security and Assessment Technology of Guangzhou Guangzhou China Webank Co. Ltd Shenzhen China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

With the development of deep learning, especially driven by advanced models such as Graph Neural Networks (GNN), smart contract vulnerability detection is gradually moving toward automation and intelligence. Although existing deep learning detection methods have improved the efficiency of vulnerability detection to some extent, they fail to fully explore and utilize the rich syntactic and semantic information in smart contracts and generally suffer from insufficient feature extraction. In this paper, we propose a new method for smart contract vulnerability detection that combines a Multi-Information Contract Graph (MIG) with a Hierarchical Graph Feature Extraction model (HGFE). MIG integrates key information such as control flow, data flow, and vulnerability feature flow within smart contracts, fully mining and utilizing the rich syntactic and semantic features of smart contracts, providing the model with comprehensive feature representation. HGFE applies a multilayer feature extraction strategy, combining global and local feature extraction, and comprehensively considers multiple dimensions of information within the contract graph, thereby fully extracting the features of the contract graph. The experimental results demonstrate that our method significantly enhances the ability to detect potential vulnerabilities in smart contracts, achieving a maximum accuracy and precision of 97.29% and 97.70%, respectively, outperforming other advanced methods.

关键词： Deep learning Privacy Smart contracts Semantics Syntactics Feature extraction Nonhomogeneous media Graph neural networks Data mining security

来源：评论

学校读者我要写书评

暂无评论

EtherGIS: A Vulnerability Detection Framework for Ethereum Smart Contracts Based on Graph Learning Features

EtherGIS: A Vulnerability Detection Framework for Ethereum S...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Qingren Zeng Jiahao He Gansen Zhao Shuangyin Li Jingji Yang Hua Tang Haoyu Luo School of Computer Science South China Normal University Guangzhou China Key Lab on Cloud Security and Assessment technology of Guangzhou Guangzhou China WeBank Co. Ltd Shenzhen China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

The financial property of Ethereum makes smart contract attacks frequently bring about tremendous economic loss. Method for effective detection of vulnerabilities in contracts imperative. Existing efforts for contract security analysis heavily rely on rigid rules defined by experts, which are labor-intensive and non-scalable. There is still a lack of effort that considers combining expert-defined security patterns with deep learning. This paper proposes EtherGIS, a vulnerability detection framework that utilizes graph neural networks (GNN) and expert knowledge to extract the graph feature from smart contract control flow graphs (CFG). To gain multi-dimensional contract information and reinforce the attention of vulnerability-related graph features, sensitive EVM instruction corpora are constructed by analyzing EVM underlying logic and diverse vulnerability triggering mechanisms. The characteristic of nodes and edges in a CFG is initially confirmed according to the corpora, generating the corresponding attribute graph. GNN is adopted to aggregate the whole graph's attribute and structure information, bridging the semantic gap between low-level graph features and high-level contract features. The feature representation of the graph is finally input into the graph classification model for vulnerability detection. Furthermore, automated machine learning (AutoML) is adopted to automate the entire deep learning process. Data for this research was collected from Ethereum to build up a dataset of six vulnerabilities for evaluation. Experimental results demonstrate that EtherGIS can productively detect vulnerabilities in Ethereum smart contracts in terms of accuracy, precision, recall, and F1-score. All aspects outperform the existing work.

关键词： Deep learning Knowledge engineering Smart contracts Semantics Feature extraction Software Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Garbage Image Classification Framework Based on Deep Learning

A Garbage Image Classification Framework Based on Deep Learn...

引用

作者： Chengchuang Lin Gansen Zhao Lei Zhao Bingchuan Chen School of Computer Science South China Normal University Key Lab on Cloud Security and Assessment Technology of Guangzhou SCNU & VeChina Joint Lab on BlockChain Technology and Application Guangdong University of Finance and Economics

In this paper, we present a garbage image classification framework to tackle the waste sorting problem which besets residents around the world every day. The proposed framework consists of two modules, a convolutional neural network backbone transferred from the ImageNet classification task and a customized network header designed for the garbage image classification *** friendly deploy into mobile devices, the proposed method makes an artful tradeoff between classification accuracy and running efficiency. The proposed framework yields 95.62% online classification accuracy on the test dataset provided by Huawei cloud with 95 ms per image inference time occupying 897 Megabytes GPU memory.

关键词： Transfer learning Garbage classification Weakly supervised learning

来源：评论

学校读者我要写书评

暂无评论

EOSIOAnalyzer: An Effective Static Analysis Vulnerability Detection Framework for EOSIO Smart Contracts

EOSIOAnalyzer: An Effective Static Analysis Vulnerability De...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Wenyuan Li Jiahao He Gansen Zhao Jinji Yang Shuangyin Li Ruilin Lai Ping Li Hua Tang Haoyu Luo Ziheng Zhou School of Computer Science South China Normal University Key Lab on Cloud Security and Assessment technology of Guangzhou WeBank Co. Ltd Shenzhen China VeChain Foundation

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

EOSIO smart contracts are programs that can be collectively executed by a network of mutually untrusted nodes. As EOSIO smart contracts manage valuable assets, they become high-value targets and are subjected to more and more attacks. Tools for protecting EOSIO smart contracts are imperative. This paper proposes EOSIOAnalyzer, an effective static secu-rity analysis framework for EOSIO smart contracts to counter the three most common attacks. The framework consists of three components, the control flow graph builder, the static analyzer and the vulnerability detector. This paper implements an approach to transforming low-level Wasm bytecode into a high-level intermediate representation (Register Transfer Language). Besides, this paper also implements vulnerability detection speci-fications for three popular EOSIO smart contracts vulnerabilities, including Fake EOS Transfer, Forged Transfer Notification and Block Information Dependency. As a proof of concept, this paper conducts experiments to evaluate the effectiveness and efficiency of the EOSIOAnalyzer. The experiment results show that the detection accuracy of the three vulnerabilities is 100 %, 98.8 % and 100%, respectively.

关键词： Smart contracts Semantics Detectors Transforms Static analysis Feature extraction Software

来源：评论

学校读者我要写书评

暂无评论

A Survey on the Efficiency, Reliability, and security of Data Query in Blockchain Systems

SSRN

引用

SSRN 2022年

作者： Zhang, Qizhi He, Yale Lai, Ruilin Hou, Zhihao Zhao, Gansen School of Computer Science South China Normal University Shipai Campus Guangdong Guangzhou51063 China Key Lab on Cloud Security and Assessment technology of Guangzhou Guangdong Guangzhou51063 China SCNU & VeChina Joint Lab on BlockChain Technology and Application Guangdong Guangzhou51063 China

With the rise of digital currencies, blockchain systems work for storing data efficiently and securely, creating a decentralized and tamper-proof digital platform. However, less works focus on data backtracking and supporting for many complex query functions. Therefore, we explore blockchain queries from both a technical and an application standpoint. Current methods to deliver are based on using distributed databases, data indexing structures, and various cryptographic algorithms to implement rich, verifiable, and secure query functions. As a result, the purpose of this survey is to provide some guidance on blockchain-related query technology. We analyze the issues of query efficiency, query reliability, and privacy protection of queries in blockchain. In addition we summarize some classic scenarios of query schemes in blockchain and discuss future research challenges that still need to be addressed by blockchain query technology. © 2022, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Traditional Chinese Medicine Clinical Herb Modeling and Herb Pair Recommendation

Data-Driven Traditional Chinese Medicine Clinical Herb Model...

引用

International Conference on Digital Home (ICDH)

作者： Gansen Zhao Xutian Zhuang Xinming Wang Weimin Ning Zijing Li Jianfei Wang Qiang Chen Zefeng Mo Bingchuan Chen Huiyan Chen School of Computer Science Guangzhou Key Laboratory of Cloud Computing Security and Assessment Technology Dongguan Hospital of Traditional Chinese Medicine Guangdong University of Education School of Mathematical Sciences South China Normal University School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou Flaming Interactive Information Technology Co. LTD Guangdong China

As an important branch of medical field, Traditional Chinese Medicine(TCM) continues to be explored in data mining research. Taking advantage of machine learning models and deep learning methods, researchers dive into symptom analysis, disease prediction and medicine law. The combination of TCM herbs is the essential basis for compatibility of clinical prescriptions and its research has attracted plenty of attention. However, literature on herb recommendation for clinical diagnosis, to our best knowledge, is slightly lacking. The clinical herbs collocation will be chosen by doctors in consideration of not only the characteristics and pharmacodynamics of the herbs, but also the mutual effects formed with other herbs. Based on the real clinical prescription data, this paper constructs an analytical model to represent the relationship between prescription herbs and syndromes, and develops herb recommendation model. Firstly, by constructing a modeling process based on the LDA topic model, this paper shows the analysis model and presentation method for prescription herbs. Then, based on the mentioned modeling, we propose a double-end fusion recommendation framework, including methods of adjusting weight proportion and similarity remapping. This research conducts experiments on relevant outpatient medical record data, which confirm that the proposed model can reflect the basic principles of herb combination in clinical diagnosis and the proposed fusion recommendation model has good performance in evaluation metrics.

关键词： Data models Medical diagnostic imaging Analytical models Hidden Markov models Diseases Data mining

来源：评论

学校读者我要写书评

暂无评论

Detection of High-Low Risk Lung Tumors Using Semi-Supervised and Selective labeling Techniques

Detection of High-Low Risk Lung Tumors Using Semi-Supervised...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jinping Lao Hongwei Lin Haiyu Zhou Chengchuang Lin Zhaoliang Zheng Gansen Zhao Hua Tang Key Lab on Cloud Security and Assessment Technology of Guangzhou and SCNU VeChina Joint Lab on BlockChain Technology and Application South China Normal University Guangzhou China The First School of Clinical Medicine Guangdong Medical University Zhanjiang China Department of Thoracic Surgery Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The accurate identification of low-risk and high-risk lung tumors is essential for clinicians to develop lung cancer treatment strategies during surgery. Despite the achievements in deep learning, most medical image analysis applications are still hampered by the difficulty of obtaining large amounts of labeled data. In this paper, a semi-supervised deep learning framework, DS-FixMatch, is proposed for identifying lung tumors intra-operatively while alleviating the issue of sparse annotations. DS-FixMatch combines selective labeling and semi-supervised training: (1) For the acquired unlabeled images, a subset that best represents the distribution of the entire dataset is selected by an unsupervised algorithm. Compared to the traditional random labeling strategy, this method can avoid introducing samples that are highly influenced by the intraoperative environment for labeling. This subset is then sent to a human expert for labeling. (2) Supervised training is performed using labeled images. For the remaining unlabeled samples, DS-FixMatch utilizes model predictions to generate pseudo-labels for consistency regularization, further enhancing the model’s generalization ability. A dataset consisting of 2221 natural images, each capturing the Region of Interest (ROI) in lung tumors, is constructed to evaluate the effectiveness of the designed framework. Experiments show that DS-FixMatch leads in performance for the task of lung tumor recognition compared to other baselines.

关键词： Training Deep learning Annotations Neural networks Lung cancer Surgery Predictive models

来源：评论

学校读者我要写书评

暂无评论

EDSNet: A deep supervision-based classification framework for non-standard medical images of lung cancer

EDSNet: A deep supervision-based classification framework fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziming Lin Zekai Huang Chengchuang Lin Zhaoliang Zheng Youqun Wang Hongwei Lin Gansen Zhao Haiyu Zhou School of Computer Science South China Normal University Guangzhou China Key Lab on Cloud Security and Assessment Technology of Guangzhou Guangzhou China The First School of Clinical Medicine Guangdong Medical University Zhanjiang China Department of Thoracic Surgery Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Lung cancer is a most prevalent and deadly type of cancer worldwide. In clinical practice, it is crucial to accurately identify the risk level of lung cancer for diagnosing and treating lung lesions. Current AI methods for lung cancer image diagnosis mainly rely on CT images, histopathological images, and a few methods based on surgical lesion section images. However, there is a great need for methods for surgical lesion section images that can help surgeons quickly decide the surgical plan during the operation. Deep learning methods among them often supervise only the output layer of the network, while ignoring the constraints on the intermediate hidden layers, resulting in insufficient accuracy of high-risk and low-risk classification. This paper aims to design a method for the task of classifying surgical lesion section of lung tumours into high-risk and low-risk categories. The EDSNet model based on deep supervision is proposed, which enhances the performance of the hidden layer through deep supervision. Moreover, the MBConv module of baseline model is replaced with the SimAM-MBConv module proposed in this paper, which further enhances the representation of pathological features by deriving 3D attention weights for feature maps within one layer. Several experiments had been conducted on a clinical lung tumour surgical lesion section image dataset, achieving the classification accuracy of EDSNet is 95.90% with an AUC of 0.9935. Compared with most existing methods for similar tasks, our method is optimal in most of the evaluation metrics. The experimental results demonstrate the effectiveness and sophistication of our method for high-risk and low-risk classification of surgical section images of lung tumours, which can serve as a reference for doctors to determine the subsequent surgical plans and treatment strategies.

关键词： Solid modeling Pathology Accuracy Three-dimensional displays Neural networks Surgery Lung cancer

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：