检索结果-内蒙古大学图书馆

An Energy-Efficient Ensemble Approach for Mitigating data incompleteness in IoT Applications 20

An Energy-Efficient Ensemble Approach for Mitigating Data In...

20th Annual International Conference on Distributed Computing in Smart Sensor Systems and the Internet of Things (DCOSS-IoT)

作者： AlShehri, Yousef Ramaswamy, Lakshmish Univ Georgia Sch Comp Athens GA 30602 USA

ISBN: (纸本)9798350369458;9798350369441

The dynamic nature of many IoT ecosystems poses unique challenges to the efficacy of IoT ML-based applications. One such challenge is data incompleteness. Furthermore, most IoT systems are severely power-constrained. It is important that we build IoT-based ML systems that are robust against data incompleteness while simultaneously being energy efficient. This paper presents an empirical study of SECOE a recent technique for alleviating data incompleteness in IoT with respect to its energy bottlenecks. Towards addressing the energy bottlenecks of SECOE, we propose ENAMLE a proactive, energy-aware technique for mitigating the impact of concurrent missing data. ENAMLE is unique in the sense that it builds an energy-aware ensemble of sub-models, each trained with a subset of sensors chosen carefully based on their correlations. Furthermore, at inference time, ENAMLE adaptively alters the number of the ensemble of models based on the amount of missing data rate and the energy-accuracy trade-off. ENAMLE's design includes several novel mechanisms for minimizing energy consumption while maintaining accuracy. Through experimental studies, we demonstrate the energy efficiency of ENAMLE and its ability to alleviate sensor failures.

关键词： IoT Failure Resilience Energy-Aware Machine Learning data incompleteness Machine Learning Ensemble

来源：评论

学校读者我要写书评

暂无评论

Analyzing data incompleteness for MRI data for Quality Enhancement

引用

IEEE ACCESS 2024年 12卷 183542-183554页

作者： Shanbhag, Sanjay Raju, Supreetha Gurupur, Varadraj P. Sowmya Kamath, S. Kandala, Rajesh N. V. P. S. Trader, Elizabeth A. Lal, Shyam Univ Cent Florida Dept Comp Sci Orlando FL 32816 USA Natl Inst Technol Karnataka Dept Informat Technol Surathkal 575025 India Univ Cent Florida Ctr Decis Support Syst & Informat Orlando FL 32816 USA Univ Cent Florida Sch Global Hlth Management & Informat Orlando FL 32816 USA VIT AP Univ Sch Elect Engn Amaravati Andhra Pradesh India Univ Cent Florida Dept Elect & Comp Engn Orlando FL 32816 USA Natl Inst Technol Karnataka Dept Elect & Commun Engn Surathkal 575025 India

Magnetic resonance imaging (MRI) is a powerful medical imaging technique widely used for diagnosing various conditions because it provides detailed images of internal structures within the body. However, like any imaging modality, MRI images can be susceptible to artifacts that may arise from various sources, including hardware imperfections, patient motion, and image acquisition techniques. Detecting and mitigating these artifacts are crucial steps in ensuring MRI scans' reliability and clinical utility. In this paper, we present algorithms specifically designed to address the challenges of undersampling and motion artifacts in MR images. Our approach involves leveraging advanced image processing techniques, including line detection algorithms for undersampling detection and blur parameter estimation for motion artifact analysis. By accurately identifying and quantifying these artifacts, our algorithms aim to improve MRI data's overall quality and completeness, ultimately enhancing diagnostic accuracy and patient care.

关键词： Motion artifacts Magnetic resonance imaging Image reconstruction Accuracy Liver Fast Fourier transforms Euclidean distance Encoding data models Transfer learning data incompleteness diagnostic image quality magnetic resonance imaging under-sampling detection image processing

来源：评论

学校读者我要写书评

暂无评论

Embracing data incompleteness for Better Earthquake Forecasting

引用

JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH 2021年第12期126卷 e2021JB022379-e2021JB022379页

作者： Mizrahi, Leila Nandan, Shyam Wiemer, Stefan Swiss Fed Inst Technol Swiss Seismol Serv Zurich Switzerland

We propose two methods to calibrate the parameters of the epidemic-type aftershock sequence (ETAS) model based on expectation maximization (EM) while accounting for temporal variation of catalog completeness. The first method allows for model calibration on long-term earthquake catalogs with temporal variation of the completeness magnitude, m(c). This calibration technique is beneficial for long-term probabilistic seismic hazard assessment (PSHA), which is often based on a mixture of instrumental and historical catalogs. The second method generalizes the concept of m(c), considering rate- and magnitude-dependent detection probability, and allows for self-consistent estimation of ETAS parameters and high-frequency detection incompleteness. With this approach, we aim to address the potential biases in parameter calibration due to short-term aftershock incompleteness, embracing incompleteness instead of avoiding it. Using synthetic tests, we show that both methods can accurately invert the parameters of simulated catalogs. We then use them to estimate ETAS parameters for California using the earthquake catalog since 1932. To explore how model calibration, inclusion of small events, and accounting for short-term incompleteness affect earthquakes' predictability, we systematically compare variants of ETAS models based on the second approach in pseudo-prospective forecasting experiments for California. Our proposed model significantly outperforms the ETAS null model, with decreasing information gain for increasing target magnitude threshold. We find that the ability to include small earthquakes for simulation of future scenarios is the primary driver of the improvement and that accounting for incompleteness is necessary. Our results have significant implications for our understanding of earthquake interaction mechanisms and the future of seismicity forecasting. Plain Language Summary Our capability to detect earthquakes varies with time, on one hand because more and bette

关键词： data incompleteness model inversion ETAS earthquake forecasting

来源：评论

学校读者我要写书评

暂无评论

HGMF: Heterogeneous Graph-based Fusion for Multimodal data with incompleteness 20

HGMF: Heterogeneous Graph-based Fusion for Multimodal Data w...

引用

26th ACM SIGKDD International Conference on Knowledge Discovery and data Mining (KDD)

作者： Chen, Jiayi Zhang, Aidong Univ Virginia Charlottesville VA 22901 USA

ISBN: (纸本)9781450379984

With the advances in data collection techniques, large amounts of multimodal data collected from multiple sources are becoming available. Such multimodal data can provide complementary information that can reveal fundamental characteristics of real-world subjects. Thus, multimodal machine learning has become an active research area. Extensive works have been developed to exploit multimodal interactions and integrate multi-source information. However, multimodal data in the real world usually comes with missing modalities due to various reasons, such as sensor damage, data corruption, and human mistakes in recording. Effectively integrating and analyzing multimodal data with incompleteness remains a challenging problem. We propose a Heterogeneous Graph-based Multimodal Fusion (HGMF) approach to enable multimodal fusion of incomplete data within a heterogeneous graph structure. The proposed approach develops a unique strategy for learning on incomplete multimodal data without data deletion or data imputation. More specifically, we construct a heterogeneous hypernode graph to model the multimodal data having different combinations of missing modalities, and then we formulate a graph neural network based transductive learning framework to project the heterogeneous incomplete data onto a unified embedding space, and multi-modalities are fused along the way. The learning framework captures modality interactions from available data, and leverages the relationships between different incompleteness patterns. Our experimental results demonstrate that the proposed method outperforms existing graph-based as well as non-graph based baselines on three different datasets.

关键词： multimodal fusion data incompleteness missing modalities graph neural networks heterogeneous graph

来源：评论

学校读者我要写书评

暂无评论

A Novel Methodology to Address the Internet AS-Level data incompleteness

引用

IEEE-ACM TRANSACTIONS ON NETWORKING 2015年第4期23卷 1314-1327页

作者： Gregori, Enrico Improta, Alessandro Lenzini, Luciano Rossi, Lorenzo Sani, Luca IIT CNR I-56124 Pisa Italy Univ Pisa Dept Informat Engn I-56126 Pisa Italy

In the last decade, many studies have used the Internet autonomous system (AS)-level topology to perform several analyses, from discovering its graph properties to assessing its impact on the effectiveness of worm-containment strategies. Yet, the Border Gateway Protocol (BGP) data used to reveal the topologies are far from complete. Our contribution is threefold. First, we analyze BGP data currently gathered by the most famous route collector projects, highlighting and explaining the causes of their incompleteness. We found that large areas of the Internet are not properly captured due to the geographical location of route collector feeders and due to BGP filters, such as export policies and decision processes. Second, we propose a methodology based on a new metric, named p2c-distance, which is able to: 1) identify the minimum number of ASs required to obtain an Internet AS-level topology that is closer to reality;and 2) identify a ranking list of these ASs to show that it is possible to obtain nonnegligible coverage improvements with a limited number of appropriately chosen feeding ASs. Third, we characterize the ASs that were found to be part of the solution of the above covering problems. We found that the route collectors are rarely connected to these ASs, thus highlighting that much effort is needed to devise a route collector infrastructure that ideally would be able to capture a complete view of the Internet.

关键词： AS-level topology autonomous systems Border Gateway Protocol (BGP) data incompleteness Internet

来源：评论

学校读者我要写书评

暂无评论

Effect of data incompleteness on the Approximation Properties of Nonparametric Estimation of the Two-Dimensional Probability Density of Independent Random Variables

引用

OPTOELECTRONICS INSTRUMENTATION AND data PROCESSING 2014年第1期50卷 68-74页

作者： Lapko, A. V. Lapko, V. A. Russian Acad Sci Inst Computat Modeling Siberian Branch Akademgorodok 50Bldg 44 Krasnoyarsk 660036 Russia Reshetnev Siberian State Aerosp Univ Krasnoyarsk 660014 Russia

Asymptotic properties of a nonparametric estimate of the two-dimensional probability density of independent random variables are studied. Based on these results, the dependence of its efficiency on data incompleteness... 详细信息

关键词： probability density nonparametric estimate asymptotic properties independent random variables data incompleteness

来源：评论

学校读者我要写书评

暂无评论

Method for Incomplete and Imbalanced data Based on Multivariate Imputation by Chained Equations and Ensemble Learning

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第5期28卷 3102-3113页

作者： Li, Jiaxi Wang, Zhelong Wu, Lina Qiu, Sen Zhao, Hongyu Lin, Fang Zhang, Ke Dalian Univ Technol Sch Control Sci & Engn Dalian 116024 Peoples R China Liaoning Canc Hosp & Inst Shenyang 110042 Peoples R China

The classification analysis of incomplete and imbalanced data is still a challenging task since these issues could negatively impact the training of classifiers, which were also found in our study on the physical fitness assessments of patients. And in fields such as healthcare, there are higher requirements for the accuracy of the generated imputation values. To train a high-performance classifier and pursue high accuracy, we attempted to resolve any potential negative impact by using a novel algorithmic approach based on the combination of multivariate imputation by chained equations and the ensemble learning method (MICEEN), which can solve the two problems simultaneously. We used multivariate imputation by chained equations to generate more accurate imputation values for the training set passed to ensemble learning to build a predictor. On the other hand, missing values were introduced into minority classes and used them to generate new samples belonging to the minority classes in order to balance the distribution of classes. On real-world datasets, we perform extensive experiments to assess our method and compare it to other state-of-the-art approaches. The advantages of the proposed method are demonstrated by experimental results for the benchmark datasets and self-collected datasets of physical fitness assessment of tumor patients with varying missing rates.

关键词： Training Mathematical models Ensemble learning Task analysis Costs Support vector machines data models data incompleteness class imbalance physical fitness assessment malignant tumor patients multivariate imputation by chained equations ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Robust multimodal federated learning for incomplete modalities

引用

COMPUTER COMMUNICATIONS 2024年 214卷 234-243页

作者： Yu, Songcan Wang, Junbo Hussein, Walid Hung, Patrick C. K. Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen 518107 Peoples R China Guangdong Prov Key Lab Fire Sci & Intelligent Emer Guangzhou 510006 Peoples R China British Univ Egypt Fac Informat & Comp Sci Cairo Egypt Ontario Tech Univ Fac Business & Informat Technol Oshawa ON Canada

Consumer electronics are continuously collecting multimodal data, such as audio, video, and so on. A multimodal learning mechanism can be adopted to deal with these data. Due to the consideration of privacy protection, some successful attempts at multimodal federated learning (MMFed) have been conducted. However, real-world multimodal data is usually missing modalities, which can significantly affect the accuracy of the global model in MMFed. Effectively fusing and analyzing multimodal data with incompleteness remains a challenging problem. To tackle this problem, we propose a robust Multimodal Federated Learning Framework for Incomplete Modalities (FedInMM). More specifically, we design a Long Short-Term Memory (LSTM)-based module to extract the information in the temporal sequence. We dynamically learn a weight map to rescale the feature in each modality and formulate the different contributions of features. And then the content of each modality is further fused to form a uniform representation of all modalities of data. By considering the temporal dependency and intra-relation of multi-modalities automatically through the learning stage, this MMFed framework can efficiently mitigate the effects of missing modalities. By using two multimodal datasets, DEAP and AReM, we have conducted comprehensive experiments by simulating different levels of incompleteness. Experimental results demonstrate that FedInMM outperforms other approaches and can train highly accurate models on datasets comprising different incompleteness patterns, which is more appropriate for integration into a practical multimodal application.

关键词： Multimodal fusion Federated learning data incompleteness Missing modalities

来源：评论

学校读者我要写书评

暂无评论

Optimization of missing value imputation for neural networks

引用

INFORMATION SCIENCES 2023年 649卷

作者： Han, Jongmin Kang, Seokho Sungkyunkwan Univ Dept Ind Engn 2066 Seobu Ro Suwon 16419 South Korea

To train a neural network with an incomplete dataset, missing values can be replaced with plausible substitutions using missing value imputation. Various missing value imputers are available for use, each with its own competencies. Using multiple different imputers can improve the predictive performance of neural networks. Existing methods selected the best imputer or combined multiple imputers, irrespective of the training of the neural network. In this study, we propose an Optimization of Missing Value Imputation (OptMVI) method for improved training of a neural network in the presence of missing values in a training dataset. For each instance in the training dataset, multiple imputations are obtained from different imputers. A convex combination of the imputations is then used as the input for the neural network, with the combination weights indicating the relative contribution of each imputer. We simultaneously train the combination weights and neural network. This allows the combination weights to be optimized toward improving the predictive performance of the neural network. Through experimental evaluation on benchmark datasets with varying missing rates, we demonstrate that the proposed method outperforms the existing methods.

关键词： Machine learning Neural network data incompleteness Missing value imputation

来源：评论

学校读者我要写书评

暂无评论

Real -Time Tracking of Misdiagnosis in Electronic Health Records for Improved Predictive Modeling

Real -Time Tracking of Misdiagnosis in Electronic Health Rec...

引用

IEEE SoutheastCon Conference on Engineering the Future

作者： Trader, Elizabeth Gurupur, Varadraj Univ Cent Florida Ctr Decis Support Syst & Informat Dept Elect & Comp Engn Orlando FL USA Univ Cent Florida Sch Global Hlth Management & Informat Ctr Decis Support Syst & Informat Orlando FL USA

ISBN: (纸本)9798350317107;9798350317114

Misdiagnosis, a persistent threat in healthcare, compromises patient outcomes and hinders effective treatment. Despite its prevalence, understanding and addressing misdiagnoses remains a complex challenge due to the limitations of traditional methods and fragmented data. The emergence of machine learning (ML) offers a potential game -changer, leveraging vast medical datasets to identify subtle disease signatures and personalize treatment plans with unprecedented accuracy. However, data quality remains a formidable barrier, as incompleteness, inconsistencies, and biases can distort ML models, leading to potentially detrimental misinterpretations. This paper highlights the critical role of misdiagnosis statistics in navigating this intricate landscape and creates a schema to address the problems caused by the lack of accessible misdiagnosis data.

关键词： data quality machine learning health informatics data incompleteness

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：