检索结果-内蒙古大学图书馆

A cloud-based deep learning model in heterogeneous data integration system for lung cancer detection in medical industry 4.0

引用

JOURNAL OF INDUSTRIAL INFORMATION integration 2022年 30卷

作者： Gu, Chang Dai, Chenyang Shi, Xin Wu, Zhiqiang Chen, Chang Tongji Univ Shanghai Pulm Hosp Sch Med Dept Thorac Surg Shanghai Peoples R China Shanghai Jiao Tong Univ Shanghai Chest Hosp Dept Cardiol Shanghai Peoples R China Wright State Univ Dept Elect Engn Dayton OH USA

Currently, lung cancer has become one of the most common and deadliest types of cancer. Due to its severity, many countries are now encouraging their at-risk citizens to test and treat lung cancer early. Lung cancer has been worse for poor regions or countries, whose citizens are more susceptible to lung cancer, as the local medical resources and healthcare provider level are inadequate. In recent years, this situation can be significantly improved by leveraging the existing datasets about lung cancer in developed countries. However, due to the poor synchronization of data collection methods, the collected data is heterogeneous, and can't be readily used. Artificial intelligence (AI), big data, cloud computing, and the internet of things accelerate the 4th revolution in the medical industry, and we called it medical industry 4.0. In the medical industry 4.0, lung cancer can be early detected by using a very intelligent approach. In this paper, using AI and cloud platform techniques in the medical industry 4.0, we propose an intelligent detection system including data integration, detection, historical cases comparison, similar cases inquiry, and retrieval for lung cancer. In this system, doctors can integrate the heterogeneous data at hand, and source a large amount of integrated data as a reference when treating the patient. A cloud-based deep learning model is integrated into this system, and then a content-based image retrieval system for similarity comparison is used. Finally, some public datasets are used to train and test this system, and results prove its performance is better than that of some baseline approaches. Then the similar case finding is evaluated with cosine similarity and all similarities reach over 0.93. The heterogeneous data integration system creates a good effect in helping doctors and patients access better diagnosis and treatment for lung cancer.

关键词： Medical industry 4.0 Lung cancer heterogeneous data integration Cloud-based deep learning Content-based image retrieval

来源：评论

学校读者我要写书评

暂无评论

heterogeneous data integration using Confidence Estimation of Unseen Visual data for Zero-shot Learning 2019

Heterogeneous Data Integration using Confidence Estimation o...

引用

2nd International Conference on Software Engineering and Information Management (ICSIM) / 2nd International Conference on Big data and Smart Computing (ICBDSC)

作者： Seo, Sanghyun Kim, Juntae Dongguk Univ 30Pildong Ro 1 Gil Seoul South Korea

ISBN: (纸本)9781450366427

Zero-shot learning is a learning methodology that can be used to recognize concepts that have never been seen during the training phase. Recently, interest in zero-shot learning has been increased by embedding multi-modal data into common vector space through heterogeneous data integration methodology. However, since the existing methodologies compare heterogeneous data focusing on the similarity between each vector, the performance of zero-shot learning decreases when the number of semantic candidates increases. We propose a heterogeneous data integration methodology using a confidence estimator for unseen visual data which estimates that whether input data is unseen data or not and output confidence measure. The proposed methodology constructs a more efficient zero-shot learning model by applying estimated confidence of input unseen visual data to the visual-semantic distance obtained from heterogeneous data integration model. Experiments have shown that the proposed methodology can improve zero-shot learning performance for unseen data despite a small performance decrease in the seen data.

关键词： Zero-shot Learning heterogeneous data integration Confidence Estimation Visual Semantic Embedding Cross Modal Retrieval

来源：评论

学校读者我要写书评

暂无评论

heterogeneous data integration by Learning to Rerank Schema Matches 18

Heterogeneous Data Integration by Learning to Rerank Schema ...

引用

18th IEEE International Conference on data Mining Workshops (ICDMW)

作者： Gal, Avigdor Roitman, Haggai Shraga, Roee Technion Israel Inst Technol Haifa Israel IBM Res AI Haifa Israel

ISBN: (纸本)9781538691595

Schema matching is a task at the heart of integrating heterogeneous structured and semi-structured data with applications in data warehousing, process matching, data analysis recommendations, Web table matching, etc. Schema matching is known to be an uncertain process and a common method of overcoming this uncertainty is by introducing a human expert with a ranked list of possible schema matches from which the expert may choose, known as top-K matching. In this work we propose a learning algorithm that utilizes an innovative set of features to rerank a list of schema matches and improves upon the ranking of the best match. The proposed algorithm assists the matching process by introducing a quality set of alternative matches to a human expert. It also serves as a step towards eliminating the involvement of human experts as decision makers in a matching process altogether. A large scale empirical evaluation with real-world benchmark shows the effectiveness of the proposed algorithmic solution.

关键词： Schema Matching heterogeneous data integration Uncertainty Learning to Rerank

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies of heterogeneous data integration for Digital Campus

Research on Key Technologies of Heterogeneous Data Integrati...

引用

作者： Fan Wei Sichuan Vocational College of Chemical Industry

With the continuous improvement of information technology, the current information system has been applied in various fields. The same is true for colleges and universities. Through the construction of digital campus, multiple business systems can be integrated to provide students with better services. Especially when colleges and universities are welcoming newcomers, the integrated campus service construction can make students integrate into campus life more quickly, reduce the workload of teachers, and actively help the optimization of teaching. Based on this, this paper starts with the definition and advantages of digital campus, firstly explores the characteristics and methods of heterogeneous data integration, and then focuses on the key technologies of heterogeneous data integration for digital campus, hoping to give digital campus construction and differentiation Relevant research on the integration of the structure provides some reference.

关键词： digital campus heterogeneous data integration key technologies

来源：评论

学校读者我要写书评

暂无评论

Hadoop as a Service: integration of a Company's heterogeneous data to a Remote Hadoop Infrastructure

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2022年第4期13卷 49-55页

作者： Kalmukov, Yordan Marinov, Milko Univ Ruse Dept Comp Syst & Technol Ruse Bulgaria

data analysis is very important for the development of any business today. It helps to identify organizational bottlenecks, optimize business processes, foresee customers' demands and behavior, and provides summarized data that could help reducing costs and increase profits. Having this information when designing new products or services highly increases the chances of their success, and thus provides an additional competitive advantage over other businesses. However, having a single data analyst with a computer is far from enough in the era of big data. There are powerful data analytical software tools, but they are either expensive or hard to deploy and require multiple high-performance servers to run. Buying expensive hardware and software, and hiring highqualified IT experts, is not affordable for all companies, especially for smaller ones and start-ups. Therefore, this article proposes an architecture for integration of a company's heterogeneous data (stored within a database of any type, or in the file system) to a remote Hadoop cluster, providing powerful data analytical services on demand. This is an affordable and cost-effective cloud-based solution, suitable for a company of any size. Businesses are not required to by any hardware or software, but use the data analytical services on demand, paying a small processing fee per request or by subscription.

关键词： Hadoop integration data analytical tools heterogeneous data integration Hadoop distributed file system (HDFS) HBase hive

来源：评论

学校读者我要写书评

暂无评论

Reconsideration of in silico siRNA design from a perspective of heterogeneous data integration: problems and solutions

引用

BRIEFINGS IN BIOINFORMATICS 2014年第2期15卷 292-305页

作者： Liu, Qi Zhou, Han Zhu, Ruixin Xu, Ying Cao, Zhiwei Hong Kong Univ Sci & Technol Dept Comp Sci Hong Kong Hong Kong Peoples R China Tongji Univ Coll Life Sci & Technol Dept Bioinformat Shanghai 200092 Peoples R China Tongji Univ Bioinformat Grp Shanghai 200092 Peoples R China Univ Georgia Athens GA 30602 USA

The success of RNA interference (RNAi) depends on the interaction between short interference RNAs (siRNAs) and mRNAs. Design of highly efficient and specific siRNAs has become a challenging issue in applications of RNAi. Here, we present a detailed survey on the state-of-the-art siRNAs design, focusing on several key issues with the current in silico RNAi studies, including: (i) inconsistencies among the proposed guidelines for siRNAs design and the incomplete list of siRNAs features, (ii) improper integration of the heterogeneous cross-platform siRNAs data, (iii) inadequate consideration of the binding specificity of the target mRNAs and (iv) reduction in the 'off-target' effect in siRNAs design. With these considerations, the popular in silico siRNAs design rules are reexamined and several inconsistent viewpoints toward siRNAs feature identifications are clarified. In addition, novel computational models for siRNAs design using state-of-art machine learning techniques are discussed, which focus on heterogeneous data integration, joint feature selection and customized siRNAs screening toward highly specific targets. We believe that addressing such issues in siRNA study will provide new clues for further improved design of more efficient and specific siRNAs in RNAi.

关键词： siRNA RNAi machine learning heterogeneous data integration feature selection

来源：评论

学校读者我要写书评

暂无评论

Research of heterogeneous data integration based on Mediator/Wrapper

Research of heterogeneous data integration based on Mediator...

引用

2014 International Conference on Communication Technology and Application(CTA2014)

作者： P.Y.Zheng X.D.Wang F.S.Sheng School of Economics and Management Beijing Jiaotong University Tianjin Campus of Naval Engineering University

ISBN: (纸本)9781845649302

Nowadays, it is increasingly frequent to communicate and share data. However, the business data are heterogeneous and isolated in different information systems which lead to the phenomenon of information islands. In order to enhance data communications and resource sharing of heterogeneous data sources, heterogeneous multi-source data integration technologies have become the current research focus. In this paper, the architecture of data integration system is presented based on Mediator/Wrapper that can hide heterogeneities and support transparent access to all data sources. In addition, this paper focuses on metadata database in the mediation layer, and then an algorithm for conversion from relational schemas to local schemas and strategies for eliminating data heterogeneities are put forward. What’s more, this paper presents the Complex Types Manager in order to improve the local schemas’ maintenance efficiency.

关键词： heterogeneous data integration Mediator/Wrapper XML schema schema conversion

来源：评论

学校读者我要写书评

暂无评论

On using kernel integration by graphical LASSO to study partial correlations between heterogeneous data sets

引用

JOURNAL OF CHEMOMETRICS 2021年第10期35卷

作者： Norgaard, Sarah Kristine Linder-Steinlein, Kristoffer Eliasen, Anders Ulrik Stokholm, Jakob Chawes, Bo L. Bonnelykke, Klaus Bisggard, Hans Smilde, Age K. Rasmussen, Morten Arendt Univ Copenhagen Herlev & Gentofte Hosp Copenhagen Prospect Studies Asthma Childhood COPSAC Copenhagen Denmark Tech Univ Denmark Dept Hlth Technol Lyngby Denmark Swammerdam Inst Life Sci Biosyst Data Anal Sci Pk 904 NL-1098 XH Amsterdam Netherlands Univ Copenhagen Dept Food Sci Sect Chemometr & Analyt Technol Copenhagen Denmark

integration of unstructured and very diverse data is often required for a deeper understanding of the complex biological systems. In order to uncover communalities between heterogeneous data, the data are often harmonized by constructing a kernel and perform numerical integration. In this study, we propose a method for data integration in the framework of an undirected graphical model, where the nodes represent individual data sources of varying nature in terms of complexity and underlying distribution and where the edges represent the partial correlations between two blocks of data. We propose a modified GLASSO for estimation of the graph, with a combination of cross-validation and extended Bayes Information Criterion for sparsity tuning. Furthermore, hierarchical clustering on the weighted consensus kernels from a fixed network is used to partitioning the samples into different classes. Simulations show increasing ability to uncover true edges with increasing sample size and signal to noise. Likewise, identification of nonexisting edges towards disconnected nodes is feasible. The framework is demonstrated for integration of longitudinal symptom burden data, from the second and third year of life, combined with 21 diseases precursors and information of the development of asthma and eczema at the age of 6 years, from 403 children from the COPSAC2010 mother-child cohort. This suggests that maternal predisposition as well as being born preterm indirectly lead to a higher risk of asthma via an increased respiratory symptom burden.

关键词： dual‐ primal optimization GLASSO heterogeneous data integration kernelization undirected graphical models

来源：评论

学校读者我要写书评

暂无评论

A regional electricity price prediction method based on Transformer and Graph Neural Networks

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 128卷 52-64页

作者： Han, Lincheng Wang, Jianguo Northeast Elect Power Univ Sch Automat Engn Jilin 132012 Peoples R China

Electricity price prediction plays a crucial role in optimizing energy trading and improving market efficiency. However, existing models struggle to simultaneously capture the complex temporal and spatial dependencies of electricity prices in power markets. To address this, we propose TransGraph-Opt, a novel model that integrates Transformer for temporal feature extraction, Graph Neural Networks (GNN) for spatial dependency modeling, and PCGrad optimization to alleviate gradient conflicts in multi-modal data. Experimental results on the PJM Interconnection Market data and PMU Measurements of IEEE 39-Bus Power System Model datasets demonstrate that TransGraph-Opt outperforms traditional models in terms of MSE (0.3121 vs. 0.3783), MAE (0.2483 vs. 0.2554), and RMSE (0.5592 vs. 0.6132), highlighting its superior predictive accuracy. This work provides a robust framework for integrating heterogeneous data sources, offering promising applications in large-scale electricity market prediction and further advancements in smart grid technologies.

关键词： Deep learning Regional electricity price prediction heterogeneous data integration Electricity market Transformer Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Infrastructure-User heterogeneous data Interaction and Fusion of Mobile-IoT Sensing Networks in a Smart City: Application to a Footbridge

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第11期12卷 17844-17853页

作者： Li, Yixian Xia, Qi Guo, Tong Zhang, Yuxuan Wu, Wanglin Xia, Yong Hong Kong Polytech Univ Dept Civil & Environm Engn Hung Hom Hong Kong Peoples R China Southeast Univ Sch Civil Engn Nanjing 210093 Peoples R China Hong Kong Polytech Univ Joint Res Ctr Marine Infrastructure Hung Hom Hong Kong Peoples R China

Abundant data are collected in the daily operation of infrastructures via structural health monitoring (SHM) systems. Meanwhile, user information is measured through the popularized mobile smartphones nowadays. However, these data types are insufficiently integrated or fused to extract valuable information to improve user comfort or enhance infrastructure safety. In this study, a bidirectional data interaction framework is developed to facilitate information sharing and fusion among users and the infrastructure through wired and wireless communications. The framework is applied to an overpass footbridge equipped with an SHM system. The walking patterns and dynamic information of pedestrians are extracted from the acceleration, orientation, and GPS data of smartphones. On this basis, the pedestrian load is generated and applied to the numerical model of the footbridge, and the full-field bridge responses can be calculated to realize a virtual holographic sensing. Simultaneously, the micro-environment and vibration data of the footbridge are collected from the SHM system, smartphones, and online databases. These data are formulated as the pedestrian comfort indexes, which directly determine the behavior and perception of pedestrians to their surroundings. The in-field data in a week are used to verify the applicability and performance of the developed approach. Results show that the data integration framework can improve the volume and diversity of data for infrastructures and users with satisfactory accuracy.

关键词： Smart phones Sensors Pedestrians Accelerometers Bridges Vibrations Global Positioning System data mining Monitoring Gyroscopes heterogeneous data integration Internet of Things (IoT) network micro-environment comfort mobile sensing structural health monitoring (SHM) user-infrastructure interaction

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：