检索结果-南通市图书馆

Categorizing methods for integrating machine learning with executable specifications

Science China(Information Sciences) 2024年第1期67卷 5-19页

作者： David HAREL Raz YERUSHALMI Assaf MARRON Achiya ELYASAF Department of Computer Science and Applied Mathematics Weizmann Institute of Science Department of Software and Information Systems Engineering Ben-Gurion University of the Negev

Deep learning(DL),which includes deep reinforcement learning(DRL),holds great promise for carrying out real-world tasks that human minds seem to cope with quite readily.That promise is already delivering extremely impressive results in a variety of areas.However,while DL-enabled systems achieve excellent performance,they are far from perfect.It has been demonstrated,in several domains,that DL systems can err when they encounter cases they had not hitherto encountered.Furthermore,the opacity of the produced agents makes it difficult to explain their behavior and ensure that they adhere to various requirements posed by human engineers.At the other end of the software development spectrum of methods,behavioral programming(BP) facilitates orderly system development using self-standing executable modules aligned with how humans intuitively describe desired system behavior.In this paper,we elaborate on different approaches for combining DRL with BP and,more generally,machine learning(ML) with executable specifications(ES).We begin by defining a framework for studying the various approaches,which can also be used to study new emerging approaches not covered here.We then briefly review state-of-the-art approaches to integrating ML with ES,continue with a focus on DRL,and then present the merits of integrating ML with BP.We conclude with guidelines on how this categorization can be used in decision making in system development,and outline future research challenges.

关键词： machine learning artificial intelligence grey box learning domain knowledge rules behavioral programming deep reinforcement learning survey

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

RepDNet:A re-parameterization despeckling network for autonomous underwater side-scan sonar imaging with prior-knowledge customized convolution

引用

Defence Technology（防务技术） 2024年第5期35卷 259-274页

作者： Zhuoyi Li Zhisen Wang Deshan Chen Tsz Leung Yip Angelo P.Teixeira Department of Logistics and Maritime Studies The Hong Kong Polytechnic UniversityChina State Key Laboratory of Maritime Technology and Safety Wuhan University of TechnologyChina School of Transportation and Logistics Engineering Wuhan University of TechnologyChina National Engineering Research Center for Water Transport Safety Wuhan University of TechnologyChina Centre for Marine Technology and Ocean Engineering(CENTEC) Instituto Superior TecnicoUniversidade de LisboaPortugal

Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined trajectory.However,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise suppression.Existing approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain knowledge.To address the problem,Rep DNet,a novel and effective despeckling convolutional neural network is proposed.Rep DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle noise.During training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing functions.During inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing accuracy.Rep DNet comprises three computational operations:3×3 convolution,element-wise summation and Rectified Linear Unit activation.Evaluations on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish Rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.

关键词： Side-scan sonar Sonar image despeckling domain knowledge Re-parameterization

来源：

维普期刊数据库博看期刊

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

domain knowledge enhanced deep learning for electrocardiogram arrhythmia classification

引用

Frontiers of Information Technology & Electronic Engineering 2023年第1期24卷 59-72页

作者： Jie SUN School of Cyber Science and Engineering Ningbo University of TechnologyNingbo 315211China

Deep learning provides an effective way for automatic classification of cardiac arrhythmias,but in clinical decisionmaking,pure data-driven methods working as black-boxes may lead to unsatisfactory results.A promising solution is combining domain knowledge with deep learning.This paper develops a flexible and extensible framework for integrating domain knowledge with a deep neural network.The model consists of a deep neural network to capture the statistical pattern between input data and the ground-truth label,and a knowledge module to guarantee consistency with the domain knowledge.These two components are trained interactively to bring the best of both worlds.The experiments show that the domain knowledge is valuable in refining the neural network prediction and thus improves accuracy.

关键词： domain knowledge Cardiac arrhythmia Electrocardiogram(ECG) Clinical decision-making

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

domain knowledge discovery from abstracts of scientific literature on Nickel-based single crystal superalloys

引用

Science China(Technological Sciences) 2023年第6期66卷 1815-1830页

作者： LIU Yue DING Lin YANG ZhengWei GE XianYuan LIU DaHui LIU Wei YU Tao AVDEEV Maxim SHI SiQi School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444China State Key Laboratory of Advanced Special Steel&Shanghai Key Laboratory of Advanced Ferrometallurgy&School of Materials Science and Engineering Shanghai UniversityShanghai 200444China Materials Genome Institute Shanghai UniversityShanghai 200444China Institute of Functional Materials Central Iron&Steel Research InstituteBeijing 100081China Australian Nuclear Science and Technology Organisation Locked Bag 2001Kirrawee DC NSW 2232Australia School of Chemistry The University of SydneySydney 2006Australia Zhejiang Laboratory Hangzhou 311100China

Despite the huge accumulation of scientific literature,it is inefficient and laborious to manually search it for useful information to investigate structure-activity relationships.Here,we propose an efficient text-mining framework for the discovery of credible and valuable domain knowledge from abstracts of scientific literature focusing on Nickel-based single crystal superalloys.Firstly,the credibility of abstracts is quantified in terms of source timeliness,publication authority and author’s academic standing.Next,eight entity types and domain dictionaries describing Nickel-based single crystal superalloys are predefined to realize the named entity recognition from the abstracts,achieving an accuracy of 85.10%.Thirdly,by formulating 12 naming rules for the alloy brands derived from the recognized entities,we extract the target entities and refine them as domain knowledge through the credibility analysis.Following this,we also map out the academic cooperative“Author-Literature-Institute”network,characterize the generations of Nickel-based single crystal superalloys,as well as obtain the fractions of the most important chemical elements in superalloys.The extracted rich and diverse knowledge of Nickel-based single crystal superalloys provides important insights toward understanding the structure-activity relationships for Nickel-based single crystal superalloys and is expected to accelerate the design and discovery of novel superalloys.

关键词： Nickel-based single crystal superalloys text mining named entity recognition credibility analysis domain knowledge

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Discovering a formula for the high temperature oxidation behavior of FeCrAlCoNi based high entropy alloys by domain knowledge-guided machine learning

引用

Journal of Materials Science & Technology 2023年第18期149卷 237-246页

作者： Qinghua Wei Bin Cao Lucheng Deng Ankang Sun Ziqiang Dong Tong-Yi Zhang Materials Genome Institute Shanghai UniversityShanghai 200444China Hong Kong University of Science and Technology(Guangzhou) Guangzhou 511458China

A mathematical formula of high physical interpretation,and accurate prediction and large generaliza-tion power is highly desirable for science,technology and engineering.In this study,we performed a domain knowledge-guided machine learning to discover high interpretive formula describing the high-temperature oxidation behavior of FeCrAlCoNi-based high entropy alloys(HEAs).The domain knowledge suggests that the exposure time dependent and thermally activated oxidation behavior can be described by the synergy formula of power law multiplying Arrhenius equation.The pre-factor,time exponent(m),and activation energy(Q)are dependent on the chemical compositions of eight elements in the FeCrAlCoNi-based HEAs.The Tree-Classifier for Linear Regression(TCLR)algorithm utilizes the two exper-imental features of exposure time(t)and temperature(T)to extract the spectrums of activation energy(Q)and time exponent(m)from the complex and high dimensional feature space,which automatically gives the spectrum of pre-factor.The three spectrums are assembled by using the element features,which leads to a general and interpretive formula with high prediction accuracy of the determination coefficient R^(2)=0.971.The role of each chemical element in the high-temperature oxidation behavior is analytically illustrated in the three spectrums,thereby the discovered interpretative formula provides a guidance to the inverse design of HEAs against high-temperature oxidation.The present work demonstrates the sig-nificance of domain knowledge in the development of materials informatics.

关键词： domain knowledge Interpretive formula High entropy alloys Oxidation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Incorporating domain knowledge into Data Mining Process:An Ontology Based Framework

引用

Wuhan University Journal of Natural Sciences 2006年第1期11卷 165-169页

作者： PAN Ding SHEN Jun-yi ZHOU Mu-xin Department of Computer Science and Technology Xi＇an jiaotong University Xi＇an 710049 Shaanxi China Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai 200240 China

With the explosive growth of data available, there is an urgent need to develop continuous data mining which reduces manual interaction evidently. A novel model for data mining is proposed in evolving environment. First, some valid mining task schedules are generated, and then au tonomous and local mining are executed periodically, finally, previous results are merged and refined. The framework based on the model creates a communication mechanism to in corporate domain knowledge into continuous process through ontology service. The local and merge mining are transparent to the end user and heterogeneous data ,source by ontology. Experiments suggest that the framework should be useful in guiding the continuous mining process.

关键词： continuous data mining domain knowledge ontology framework

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Necessary and Sufficient Conditions for Feasible Neighbourhood Solutions in the Local Search of the Job-Shop Scheduling Problem

引用

Chinese Journal of Mechanical Engineering 2023年第4期36卷 139-154页

作者： Lin Gui Xinyu Li Liang Gao Cuiyu Wang State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China

The meta-heuristic algorithm with local search is an excellent choice for the job-shop scheduling problem(JSP).However,due to the unique nature of the JSP,local search may generate infeasible neighbourhood solutions.In the existing literature,although some domain knowledge of the JSP can be used to avoid infeasible solutions,the constraint conditions in this domain knowledge are sufficient but not necessary.It may lose many feasible solutions and make the local search inadequate.By analysing the causes of infeasible neighbourhood solutions,this paper further explores the domain knowledge contained in the JSP and proposes the sufficient and necessary constraint conditions to find all feasible neighbourhood solutions,allowing the local search to be carried out thoroughly.With the proposed conditions,a new neighbourhood structure is designed in this paper.Then,a fast calculation method for all feasible neighbourhood solutions is provided,significantly reducing the calculation time compared with ordinary methods.A set of standard benchmark instances is used to evaluate the performance of the proposed neighbourhood structure and calculation method.The experimental results show that the calculation method is effective,and the new neighbourhood structure has more reliability and superiority than the other famous and influential neighbourhood structures,where 90%of the results are the best compared with three other well-known neighbourhood structures.Finally,the result from a tabu search algorithm with the new neighbourhood structure is compared with the current best results,demonstrating the superiority of the proposed neighbourhood structure.

关键词： Scheduling Job-shop scheduling Local search Neighbourhood structure domain knowledge

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

DG-CNN:Introducing Margin Information into Convolutional Neural Networks for Breast Cancer Diagnosis in Ultrasound Images

引用

Journal of Computer Science & Technology 2022年第2期37卷 277-294页

作者：解晓政牛建伟刘雪峰李青锋王勇韩洁唐少杰 State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityHangzhou 310051China Department of Diagnostic Ultrasound National Cancer CenterChinese Academy of Medical SciencesPeking Union Medical CollegeBeijing 100021China Naveen Jindal School of Management The University of Texas at DallasRichardsonTX 75080-3021U.S.A.

Although using convolutional neural networks(CNNs)for computer-aided diagnosis(CAD)has made tremendous progress in the last few years,the small medical datasets remain to be the major bottleneck in this area.To address this problem,researchers start looking for information out of the medical datasets.Previous efforts mainly leverage information from natural images via transfer learning.More recent research work focuses on integrating knowledge from medical practitioners,either letting networks resemble how practitioners are trained,how they view images,or using extra annotations.In this paper,we propose a scheme named domain Guided-CNN(DG-CNN)to incorporate the margin information,a feature described in the consensus for radiologists to diagnose cancer in breast ultrasound(BUS)images.In DG-CNN,attention maps that highlight margin areas of tumors are first generated,and then incorporated via different approaches into the networks.We have tested the performance of DG-CNN on our own dataset(including 1485 ultrasound images)and on a public dataset.The results show that DG-CNN can be applied to different network structures like VGG and ResNet to improve their performance.For example,experimental results on our dataset show that with a certain integrating mode,the improvement of using DG-CNN over a baseline network structure ResNet 18 is 2.17%in accuracy,1.69%in sensitivity,2.64%in specificity and 2.57%in AUC(Area Under Curve).To the best of our knowledge,this is the first time that the margin information is utilized to improve the performance of deep neural networks in diagnosing breast cancer in BUS images.

关键词： medical consensus domain knowledge breast cancer diagnosis margin map deep neural network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Design of Deep Web Search Engine Based on domain knowledge

The Design of Deep Web Search Engine Based on Domain Knowled...

引用

2010 International Conference on Remote Sensing (ICRS 2010)

作者： Deng Rong Wang Hao Zhou Xin School of Software Jiangxi Normal University Jiangxi P.R.China

A new method of search data on Deep Web is proposed in this paper based on the concept of domain knowledge and the feature of Deep Web data.First they obtain the search interfaces on the Deep Web;and then do feature analysis and domain judge on them;at last,they classify and integrate various interfaces in line with diverse domains.This method has showed up higher degree of correlation of domains from the seek result,via testing several different domains.Compared with other methods,its recall and precision are also satisfactory.

关键词： Deep Web domain knowledge interface feature analysis recall precision

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A novel spatio-temporal trajectory data-driven development approach for autonomous vehicles

引用

Frontiers of Earth Science 2021年第3期15卷 620-630页

作者： Menghan ZHANG Mingjun MA Jingying ZHANG Mingzhuo ZHANG Bo LIW Dehui DU School of Software and Engineering East China Normal UniversityShanghai 200062China Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China MOE International Joint Lab of Trustworthy Software East China Normal UniversityShanghai 200062China

Nowadays,autonomous driving has been attracted widespread attention from academia and industry.As we all know,deep learning is effective and essential for the development of AI components of Autonomous Vehicles(AVs).However,it is challenging to adopt multi-source heterogenous data in deep learning.Therefore,we propose a novel data-driven approach for the delivery of high-quality Spatio-Temporal Trajectory Data(STTD)to AVs,which can be deployed to assist the development of AI components with deep learning.The novelty of our work is that the meta-model of STTD is constructed based on the domain knowledge of autonomous driving.Our approach,including collection,preprocessing,storage and modeling of STTD as well as the training of AI components,helps to process and utilize huge amount of STTD efficiently.To further demonstrate the usability of our approach,a case study of vehicle behavior prediction using Long Short-Term Memory(LSTM)networks is discussed.Experimental results show that our approach facilitates the training process of AI components with the STTD.

关键词： spatio-temporal trajectory data data metamodeling domain knowledge LSTM vehicle behavior prediction AI component

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：