检索结果-内蒙古大学图书馆

heterogeneous data analysis: Online learning for medical-image-based diagnosis

PATTERN RECOGNITION 2017年 63卷 612-624页

作者： Motai, Yuichi Siddique, Nahian Alam Yoshida, Hiroyuki Virginia Commonwealth Univ Richmond VA 23284 USA Massachusetts Gen Hosp Harvard Med Sch Boston MA 02114 USA Virginia Commonwealth Univ Elect & Comp Engn Dept Richmond VA 23284 USA Massachusetts Gen Hosp Dept Radiol Boston MA 02114 USA Harvard Med Sch Boston MA USA

heterogeneous data analysis (HDA) is proposed to address a learning problem of medical image databases of Computed Tomographic Colonography (CTC). The databases are generated from clinical CTC images using a Computer-aided Detection (CAD) system, the goal of which is to aid radiologists' interpretation of CTC images by providing highly accurate, machine-based detection of colonic polyps. We aim to achieve a high detection accuracy in CAD in a clinically realistic context, in which additional CTC cases of new patients are added regularly to an existing database. In this context, the CAD performance can be improved by exploiting the heterogeneity information that is brought into the database through the addition of diverse and disparate patient populations. In the HDA, several quantitative criteria of data compatibility are proposed for efficient management of these online images. After an initial supervised offline learning phase, the proposed online learning method decides whether the online data are heterogeneous or homogeneous. Our previously developed Principal Composite Kernel Feature analysis (PC-KFA) is applied to the online data, managed with HDA, for iterative construction of a linear subspace of a high-dimensional feature space by maximizing the variance of the non-linearly transformed samples. The experimental results showed that significant improvements in the data compatibility were obtained when the online PC-KFA was used, based on an accuracy measure for long-term sequential online datasets. The computational time is reduced by more than 93% in online training compared with that of offline training.

关键词： Online learning Computed tomographic colonography heterogeneous data analysis Kernel feature analysis Computer-aided detection Principal composite kernel feature analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing NGBoost with dynamic sequential model-based optimization for predicting UHPC compressive strength on heterogeneous datasets

引用

MATERIALS TODAY COMMUNICATIONS 2025年 45卷

作者： Rahman, Taimur Momin, Md. Farhad Podder, Sagor Kumar Li, Hejie Zheng, Pengfei World Univ Bangladesh Dept Civil Engn Dhaka Bangladesh Zhengzhou Univ Sch Civil Engn Zhengzhou 450001 Peoples R China

Due to its outstanding performance in both strength and durability, ascertaining the compressive strength of Ultra-High-Performance Concrete (UHPC) holds critical significance. Recent trends reveal a shift towards using various Machine Learning (ML) and Deep Learning (DL) techniques to predict UHPC's compressive strength using multi-study datasets, though not all models effectively handle these diverse and heterogeneous datasets. To address this challenge, this study proposes a Natural Gradient Boosting (NGBoost) method optimized with Dynamic Sequential Model-Based Optimization (DSMBO), leveraging a probabilistic approach to manage heterogeneous datasets. A dataset of 920 instances of compressive strength of UHPC from various studies was compiled and utilized in this research, considering 14 input features. A thorough comparative and sensitivity analysis was undertaken to evaluate NGBoost's performance with different base models and Sequential Model-Based Optimization techniques, culminating in the identification of the best-performing model, which is then benchmarked against a spectrum of ML and DL models. The findings reveal that the proposed model significantly outperforms other models, yielding R2 of 0.9748 and RMSE of 3.77 MPa. More importantly, this paper provides detailed insights into the contribution of each feature to model predictions through SHAP (SHapley Additive exPlanations) values for easy user selection. Additionally, a user-friendly web-based interface was developed to promote the practical use of the proposed model in predicting UHPC's compressive strength.

关键词： Ultra-High-Performance Concrete Natural Gradient Boosting Sequential Model-Based Optimization heterogeneous data analysis Sensitivity analysis Machine Learning SHAP

来源：评论

学校读者我要写书评

暂无评论

CulturAI: Semantic Enrichment of Cultural data Leveraging Artificial Intelligence

引用

IEEE ACCESS 2022年 10卷 127328-127344页

作者： Carta, Salvatore M. Consoli, Sergio Giuliani, Alessandro Podda, Alessandro Sebastian Recupero, Diego Reforgiato Univ Cagliari Dept Math & Comp Sci I-09121 Cagliari Italy European Commiss Joint Res Ctr JRC I-21027 Ispra Italy

In this paper, we propose an innovative tool able to enrich cultural and creative spots (gems, hereinafter) extracted from the European Commission Cultural Gems portal, by suggesting relevant keywords (tags) and YouTube videos (represented with proper thumbnails). On the one hand, the system queries the YouTube search portal, selects the videos most related to the given gem, and extracts a set of meaningful thumbnails for each video. On the other hand, each tag is selected by identifying semantically related popular search queries (i.e., trends). In particular, trends are retrieved by querying the Google Trends platform. A further novelty is that our system suggests contents in a dynamic way. Indeed, as for both YouTube and Google Trends platforms the results of a given query include the most popular videos/trends, such that a gem may constantly be updated with trendy content by periodically running the tool. The system has been tested on a set of gems and evaluated with the support of human annotators. The results highlighted the effectiveness of our proposal.

关键词： Computer science in cultural heritage heterogeneous data analysis modeling interlinking and browsing semantic-aware representation of cultural data machine learning social media

来源：评论

学校读者我要写书评

暂无评论

The normalized compression distance is resistant to noise

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2007年第5期53卷 1895-1900页

作者： Cebrian, Manuel Alfonseca, Manuel Ortega, Alfonso Univ Autonoma Madrid Escuela Politecn Super E-28049 Madrid Spain

This correspondence studies the influence of noise on the normalized compression distance (NCD), a measure based on the use of compressors to compute the degree of similarity of two files. This influence is approximated by a first order differential equation which gives rise to a complex effect, which explains the fact that the NCD may give values greater than 1, observed by other authors. The model is tested experimentally with good adjustment. Finally, the influence of noise on the clustering of files of different types is explored, finding that the NCD performs well even in the presence of quite high noise levels.

关键词： clustering and noise resistance datafile corruption heterogeneous data analysis Kolmogorov complexity noisy channel normalized compression distance universal similarity distance

来源：评论

学校读者我要写书评

暂无评论

BREAKING THE CURSE OF DIMENSIONALITY FOR COUPLED MATRIX-TENSOR FACTORIZATION 8

BREAKING THE CURSE OF DIMENSIONALITY FOR COUPLED MATRIX-TENS...

引用

8th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)

作者： Boudehane, Abdelhak Zniyed, Yassine Tenenhaus, Arthur Le Brusquet, Laurent Boyer, Remy Univ Paris Sud Univ Paris Saclay CNRS Cent SupelecLab Signaux & Syst Gif Sur Yvette France Univ Lille 1 Ctr Rech Informat Signal & Automat Lille Villeneuve Dascq France

ISBN: (纸本)9781728155494

In different application fields, heterogeneous data sets are structured into either matrices or higher-order tensors. In some cases, these structures present the property of having common underlying factors, which is used to improve the efficiency of factor-matrices estimation in the process of the so-called coupled matrix-tensor factorization (CMTF). Many methods target the CMTF problem relying on alternating algorithms or gradient approaches. However, computational complexity remains a challenge when the data sets are tensors of high-order, which is linked to the well-known "curse of dimensionality". In this paper, we present a methodological approach, using the Joint dImensionality Reduction And Factors rEtrieval (JIRAFE) algorithm for joint factorization of high-order tensor and matrix. This approach reduces the high-order CMTF problem into a set of 3-order CMTF and canonical polyadic decomposition (CPD) problems. The proposed algorithm is evaluated on simulation and compared with a gradient-based method.

关键词： Coupled matrix tensor decomposition Tensor train heterogeneous data analysis Joint estimation Fast algorithms

来源：评论

学校读者我要写书评

暂无评论

Determination of the data Model for heterogeneous data Processing Based on Cost Estimation 7th

Determination of the Data Model for Heterogeneous Data Proce...

引用

7th Computer Science On-Line Conference (CSOC)

作者： Zhang, Jianping Li, Hui Zhang, Xiaoping Chen, Mei Dai, Zhenyu Zhu, Ming Guizhou Univ Coll Comp Sci & Technol Guiyang Guizhou Peoples R China Guizhou Univ ACMIS Guizhou Engineer Lab Guiyang Guizhou Peoples R China Chinese Acad Sci Natl Astron Observ Beijing Peoples R China

ISBN: (纸本)9783319911892

In heterogeneous data processing, various data model often make analytic task too hard to achieve optimal performance, it is necessary to unify heterogeneous data into the same data model. How to determine the proper intermediate data model and unify the involved heterogeneous data models for the analytical task is an urgent problem need to be solved. In this paper, we proposed a model determination method based on cost estimation. It evaluates the execution cost of query tasks on different data models, which taken as the criterion to measure the data model, and chooses a data model with the least cost as the intermediate representation during data processing. The experimental results of BigBench datasets showed that the proposed cost estimation based method could appropriately determine the data model, which made heterogeneous data processing efficiently.

关键词： heterogeneous data analysis data model determination Cost estimation BigBench datasets

来源：评论

学校读者我要写书评

暂无评论

Cloud-Edge Collaboration Framework for IoT data analytics 9

Cloud-Edge Collaboration Framework for IoT data analytics

引用

9th International Conference on Information and Communication Technology Convergence (ICTC)

作者： Moon, Jaewon Cho, Sangyeon Kum, Seungweoo Lee, Sangwon Korea Elect Technol Inst Smart Media Res Ctr Seoul South Korea Sungkyunkwan Univ Dept Interact Sci Seoul South Korea

ISBN: (纸本)9781538650417

In recent years, big data analysis from Internet of Things (IoT) has been getting more attention. Several cloud platforms have provided machine learning service with a pre-trained model to understand IoT data. However, it is necessary to transfer personal data in order to use the cloud service, and network problems might be preventing the customer from getting analysis results at an appropriate time. To overcome these problems, data and analysis task are moving to the edge platform. However, most edge devices do not have enough capacity to process and train large amounts of data. In this paper, we propose a new framework structure that can analyze IoT data by distributing analysis role. The proposed framework is designed to maximize the resources of the cloud to generate the model and to use the model at the edge to enable immediate and instantaneous actuator operation. And we also present a case study to verify this framework.

关键词： Edge Computing Machine Learning heterogeneous data analysis

来源：评论

学校读者我要写书评

暂无评论

CoRAST: Towards Foundation Model-Powered Correlated data analysis in Resource-Constrained CPS and IoT

CoRAST: Towards Foundation Model-Powered Correlated Data Ana...

引用

IEEE International Workshop on Foundation Models for Cyber-Physical Systems and Internet of Things (FMSys)

作者： Hu, Yi Zuo, Jinhang Zhao, Alanis Iannucci, Bob Joe-Wong, Carlee Carnegie Mellon Univ Pittsburgh PA 15213 USA CALTECH Pasadena CA 91125 USA UMass Amherst Amherst MA USA Google Mountain View CA 94043 USA

ISBN: (纸本)9798350363456;9798350363463

Foundation models (FMs) emerge as a promising solution to harness distributed and diverse environmental data by leveraging prior knowledge to understand the complicated temporal and spatial correlations within heterogeneous datasets. Unlike distributed learning frameworks such as federated learning, which often struggle with multimodal data, FMs can transform diverse inputs into embeddings. This process facilitates the integration of information from various modalities and the application of prior learning to new domains. However, deploying FMs in resource-constrained edge systems poses significant challenges. To this end, we introduce CoRAST, a novel learning framework that utilizes FMs for enhanced analysis of distributed, correlated heterogeneous data. Utilizing a server-based FM, CoRAST exploits existing environment information to extract temporal, and cross-feature correlations among sensor data. This enables CoRAST to offer context-aware insights for localized client tasks through FM-powered global representation learning. Our evaluation on real-world weather dataset demonstrates CoRAST's ability to exploit correlated heterogeneous data through environmental representation learning to reduce the forecast errors by up to 50.3% compared to the baselines.

关键词： Cyber-physical systems foundation models heterogeneous data analysis Internet of Things (IoT) time series

来源：评论

学校读者我要写书评

暂无评论

Static and adaptive subspace information fusion for indefinite heterogeneous proximity data

引用

NEUROCOMPUTING 2023年第1期555卷

作者： Muench, Maximilian Roeder, Manuel Heilig, Simon Raab, Christoph Schleif, Frank-Michael Univ Appl Sci Wurzburg Schweinfurt Ctr Artificial Intelligence & Robot CAIRO Wurzburg Germany Univ Groningen Bernoulli Inst Math Comp Sci & Artificial Intellig Groningen Netherlands Friedrich Alexander Univ Erlangen Nurnberg Erlangen Germany IAV GmbH Berlin Germany

heterogeneous data is common in many real-world machine learning applications, such as healthcare, market analysis, environmental sciences, and social media analysis. In these domains, data is often represented in different modalities and, most of the time, in non-vectorial formats, like text, images, and video. Traditional machine learning algorithms are often limited in their ability to effectively analyze and learn from such diverse data types. In this paper, we propose two approaches for such heterogeneous data analysis: static and adaptive subspace kernel fusion. The first approach is a kernel-based method extracting the essential parts of the subspace of each input modality and creating one single fused representation of the data. The second approach utilizes an adaptation step by integrating the weighting of spectral properties into the fusion process in order to improve the data's representation with respect to a given classification task. Our proposed methods are evaluated on several multi-modal, heterogeneous data sets and demonstrate significant performance improvement compared to other methods in the field. Our results highlight the importance of fusing the underlying subspace information of heterogeneous data for achieving superior performance in machine learning tasks.

关键词： Indefinite learning Multi-modal data heterogeneous data analysis Multiple kernel learning Kernel fusion Proximity learning

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：