检索结果-内蒙古大学图书馆

5th International Conference on Science and Technology, ICST 2019

作者： Wijaya, Adi Kharis Prastuti, Wini Universitas Gadjah Mada Department of Electrical and Information Engineering Yogyakarta Indonesia Universitas Gadjah Mada Department of Public Policy Management Yogyakarta Indonesia

ISBN: (纸本)9781728123691

Parkinson's Disease (PD) is one of the most common neurodegenerative disorder with increasing prevalence in the world. Many studies have been conducted to detect or diagnose PD. Recently, voice signal based PD detection has been conducted rapidly. However, the performance of the detection still not excellent, hence the need for excellent detection still an open issue in PD detection. In this study, PD detection based on voice signal was conducted using public dataset. Since the dataset consist of many features, the proposed method combines feature selection mechanism and classification based on Gradient Boosted Tree (GBT) algorithm. Feature selection was conducted by using feature weighting from GBT. The experimental results show that the proposed method outperforms prior research with the accuracy about 0.92 with the minimum number of features. This result proves that GBT able to perform feature selection and good classifier. This concludes that the proposed method is promising as PD detection based on voice signal analysis. © 2019 IEEE.

关键词： Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Fluctuating risk of acute kidney injury-related mortality for four weeks after exposure to air pollution: A multi-country time-series study in 6 countries

引用

Environment International 2024年 183卷 108367页

作者： Min, Jieun Kang, Duk-Hee Kang, Cinoo Bell, Michelle L. Kim, Ho Yang, Juyeon Gasparrini, Antonio Lavigne, Eric Hashizume, Masahiro Kim, Yoonhee Fook Sheng Ng, Chris Honda, Yasushi das Neves Pereira da Silva, Susana Madureira, Joana Leon Guo, Yue Pan, Shih-Chun Armstrong, Ben Sera, Francesco Masselot, Pierre Schwartz, Joel Maria Vicedo-Cabrera, Ana Pyo Lee, Jung Al-Aly, Ziyad Won Lee, Jung Kwag, Youngrin Ha, Eunhee Lee, Whanhee Department of Environmental Medicine College of Medicine Ewha Womans University Seoul Korea Republic of Graduate Program in System Health Science and Engineering College of Medicine Ewha Womans University Seoul Korea Republic of Division of Nephrology Department of Internal Medicine Ewha Womans University School of Medicine Ewha Medical Research Center Seoul Korea Republic of Department of Public Health Sciences Graduate School of Public Health Seoul National University Seoul Korea Republic of Yale School of the Environment Yale University New HavenCT United States Biostatistics Collaboration Unit Yonsei University College of Medicine Seoul Korea Republic of Lab Department of Public Health Environments and Society London School of Hygiene & Tropical Medicine London United Kingdom School of Epidemiology & Public Health Faculty of Medicine University of Ottawa Ottawa Canada Department of Global Health Policy Graduate School of Medicine The University of Tokyo Tokyo Japan Department of Global Environmental Health Graduate School of Medicine University of Tokyo Tokyo Japan School of Tropical Medicine and Global Health Nagasaki University Nagasaki Japan Center for Climate Change Adaptation National Institute for Environmental Studies Tsukuba Japan Department of Epidemiology Instituto Nacional de Saúde Dr. Ricardo Jorge Lisbon Portugal EPIUnit-Institute of Public Health University of Porto Porto Portugal Porto Portugal College of Medicine and NTU Hospital Taipei Taiwan National Institute of Environmental Health Science National Health Research Institutes Zhunan Taiwan Department of Public Health Environments and Society London School of Hygiene & Tropical Medicine London United Kingdom Department of Statistics Computer Science and Applications "G. Parenti" University of Florence Florence Italy Department of Environmental Health Harvard T.H. Chan School of Public Health BostonMA United States Institute of Social and Preventive Medicine Universi

Background: Recent studies have reported that air pollution is related to kidney diseases. However, the global evidence on the risk of death from acute kidney injury (AKI) owing to air pollution is limited. Therefore, we investigated the association between short-term exposure to air pollution—particulate matter ≤ 2.5 μm (PM2.5), ozone (O3), and nitrogen dioxide (NO2)—and AKI-related mortality using a multi-country dataset. Methods: This study included 41,379 AKI-related deaths in 136 locations in six countries during 1987–2018. A novel case time-series design was applied to each air pollutant during 0–28 lag days to estimate the association between air pollution and AKI-related deaths. Moreover, we calculated AKI deaths attributable to non-compliance with the World Health Organization (WHO) air quality guidelines. Results: The relative risks (95% confidence interval) of AKI-related deaths are 1.052 (1.003, 1.103), 1.022 (0.994, 1.050), and 1.022 (0.982, 1.063) for 5, 10, and 10 µg/m3 increase in lag 0–28 days of PM2.5, warm-season O3, and NO2, respectively. The lag-distributed association showed that the risk appeared immediately on the day of exposure to air pollution, gradually decreased, and then increased again reaching the peak approximately 20 days after exposure to PM2.5 and O3. We also found that 1.9%, 6.3%, and 5.2% of AKI deaths were attributed to PM2.5, warm-season O3, and NO2 concentrations above the WHO guidelines. Conclusions: This study provides evidence that public health policies to reduce air pollution may alleviate the burden of death from AKI and suggests the need to investigate the several pathways between air pollution and AKI death. © 2023 The Author(s)

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Assessing Gender Fairness in EEG-Based Machine Learning Detection of Parkinson's Disease: A Multi-Center Study

Assessing Gender Fairness in EEG-Based Machine Learning Dete...

引用

European Signal Processing Conference (EUSIPCO)

作者： Anna Kurbatskaya Alberto Jaramillo-Jimenez John Fredy Ochoa-Gomez Kolbjørn Brønnick Alvaro Fernandez-Quilez Department of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Centre for Age-Related Medicine (SESAM) Stavanger University Hospital Stavanger Norway Department of Public Health Faculty of Health Sciences University of Stavanger Stavanger Norway Grupo de Neurociencias de Antioquia Universidad de Antioquia School of Medicine Medellin Colombia Grupo Neuropsicologia y Conducta Universidad de Antioquia School of Medicine Medellin Colombia Department of Radiology Stavanger Medical Imaging Laboratory (SMIL) Stavanger University Hospital Stavanger Norway

As the number of automatic tools based on machine learning (ML) and resting-state electroencephalography (rs-EEG) for Parkinson's disease (PD) detection keeps growing, the assessment of possible exacerbation of health disparities by means of fairness and bias analysis becomes more relevant. Protected attributes, such as gender, play an important role in PD diagnosis development. However, analysis of sub-group populations stemming from different genders is seldom taken into consideration in ML models' development or the performance assessment for PD detection. In this work, we perform a systematic analysis of the detection ability for gender sub-groups in a multi-center setting of a previously developed ML algorithm based on power spectral density (PSD) features of rs-EEG. We find significant differences in the PD detection ability for males and females at testing time (80.5% vs. 63.7% accuracy) and significantly higher activity for a set of parietal and frontal EEG channels and frequency sub-bands for PD and non-PD males that might explain the differences in the PD detection ability for the gender sub-groups.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Detection of Parkinson’s Disease From Resting-State EEG: A Multi-Center Study

Machine Learning-Based Detection of Parkinson’s Disease Fro...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Anna Kurbatskaya Alberto Jaramillo-Jimenez John Fredy Ochoa-Gomez Kolbjørn Brønnick Alvaro Fernandez-Quilez Department of Electrical Engineering and Computer Science Faculty of Science and Technology University of Stavanger Stavanger Norway Department of Psychiatry Stavanger University Hospital and the Department of Public Health Faculty of Health Sciences Centre for Age-Related Medicine (SESAM) University of Stavanger Stavanger Norway Grupo de Neurociencias de Antioquia Universidad de Antioquia School of Medicine Medellín Colombia Grupo Neuropsicología y Conducta Universidad de Antioquia School of Medicine Medellín Colombia Department of Radiology Stavanger Medical Imaging Laboratory (SMIL) Stavanger University Hospital Stavanger Norway

Resting-state EEG (rs-EEG) has been demonstrated to aid in Parkinson’s disease (PD) diagnosis. In particular, the power spectral density (PSD) of low-frequency bands (δ and θ) and high-frequency bands (α and β) has been shown to be significantly different in patients with PD as compared to subjects without PD (non-PD). However, rs-EEG feature extraction and the interpretation thereof can be time-intensive and prone to examiner variability. Machine learning (ML) has the potential to automatize the analysis of rs-EEG recordings and provides a supportive tool for clinicians to ease their workload. In this work, we use rs-EEG recordings of 84 PD and 85 non-PD subjects pooled from four datasets obtained at different centers. We propose an end-to-end pipeline consisting of preprocessing, extraction of PSD features from clinically-validated frequency bands, and feature selection. Following, we assess the classification ability of the features via ML algorithms to stratify between PD and non-PD subjects. Further, we evaluate the effect of feature harmonization, given the multi-center nature of the datasets. Our validation results show, on average, an improvement in PD detection ability (69.6% vs. 75.5% accuracy) by logistic regression when harmonizing the features and performing univariate feature selection (k = 202 features). Our final results show an average global accuracy of 72.2% with balanced accuracy results for all the centers included in the study: 60.6%, 68.7%, 77.7%, and 82.2%, *** relevance— We present an end-to-end pipeline to extract clinically relevant features from rs-EEG recordings that can facilitate the analysis and detection of PD. Further, we provide an ML system that shows a good performance in detecting PD, even in the presence of centers with different acquisition protocols. Our results show the relevance of harmonizing features and provide a good starting point for future studies focusing on rs-EEG analysis and multi-center data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Undersampling with Ensemble Learning to Identify Factors Contributing to Preterm Birth 19

Using Undersampling with Ensemble Learning to Identify Facto...

引用

19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020

作者： Dong, Shi Feric, Zlatan Li, Guangyu Wu, Chieh Gu, April Z. Dy, Jennifer Meeker, John Padilla, Ingrid Y. Cordero, Jose Velez Vega, Carmen Rosario, Zaira Alshawabkeh, Akram Kaeli, David Dept. of Electrical and Computer Engineering Northeastern University United States Dept. of Civil and Environmental Engineering Northeastern University United States Department of Civil and Environmental Engineering Cornell University United States University of Michigan United States University of Puerto Rico Mayaguez Puerto Rico University of Georgia Graduate School of Public Health University of Puerto Rico Medical Campus Puerto Rico

ISBN: (纸本)9781728184708

In this paper, we propose Ensemble Learning models to identify factors contributing to preterm birth. Our work leverages a rich dataset collected by a NIEHS P42 Center that is trying to identify the dominant factors responsible for the high rate of premature births in northern Puerto Rico. We investigate analytical models addressing two major challenges present in the dataset: 1) the significant amount of incomplete data in the dataset, and 2) class imbalance in the dataset. First, we leverage and compare two types of missing data imputation methods: 1) mean-based and 2) similarity-based, increasing the completeness of this dataset. Second, we propose a feature selection and evaluation model based on using undersampling with Ensemble Learning to address class imbalance present in the dataset. We leverage and compare multiple Ensemble Feature selection methods, including Complete Linear Aggregation (CLA), Weighted Mean Aggregation (WMA), Feature Occurrence Frequency (OFA) and Classification Accuracy Based Aggregation (CAA). To further address missing data present in each feature, we propose two novel methods: 1) Missing Data Rate and Accuracy Based Aggregation (MAA), and 2) Entropy and Accuracy Based Aggregation (EAA). Both proposed models balance the degree of data variance introduced by the missing data handling during the feature selection process, while maintaining model performance. Our results show a 42% improvement in sensitivity versus fallout over previous state-of-the-art methods. © 2020 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era

arXiv

引用

arXiv 2024年

作者： Restrepo, David Wu, Chenwei Vásquez-Venegas, Constanza Nakayama, Luis Filipe Celi, Leo Anthony López, Diego M. Laboratory for Computational Physiology Massachusetts Institute of Technology CambridgeMA United States Departamento de Telemática Universidad del Cauca Cauca Popayán Colombia Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States Scientific Image Analysis Lab Universidad de Chile Santiago Santiago Chile Department of Ophthalmology São Paulo Federal University São Paulo São Paulo Brazil Department of Biostatistics Harvard TH Chan School of Public Health BostonMA United States Department of Medicine Beth Israel Deaconess Medical Center BostonMA United States

In the big data era, integrating diverse data modalities poses significant challenges, particularly in complex fields like healthcare. This paper introduces a new process model for multimodal Data Fusion for Data Mining, integrating embeddings and the Cross-Industry Standard Process for Data Mining with the existing Data Fusion Information Group model. Our model aims to decrease computational costs, complexity, and bias while improving efficiency and reliability. We also propose"disentangled dense fusion," a novel embedding fusion method designed to optimize mutual information and facilitate dense inter-modality feature interaction, thereby minimizing redundant information. We demonstrate the model’s efficacy through three use cases: predicting diabetic retinopathy using retinal images and patient metadata, domestic violence prediction employing satellite imagery, internet, and census data, and identifying clinical and demographic features from radiography images and clinical notes. The model achieved a Macro F1 score of 0.92 in diabetic retinopathy prediction, an R-squared of 0.854 and sMAPE of 24.868 in domestic violence prediction, and a macro AUC of 0.92 and 0.99 for disease prediction and sex classification, respectively, in radiological analysis. These results underscore the Data Fusion for Data Mining model’s potential to significantly impact multimodal data processing, promoting its adoption in diverse, resource-constrained *** Codes 68T30 © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Data discovery using lossless compression-based sparse representation

arXiv

引用

arXiv 2021年

作者： Sabeti, Elyas Song, Peter X.K. Hero, Alfred O. Michigan Institute for Data Science University of Michigan Ann Arbor United States Department of Biostatistics School of Public Health University of Michigan Ann Arbor United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States

Sparse representation has been widely used in data compression, signal and image denoising, dimensionality reduction and computer vision. While overcomplete dictionaries are required for sparse representation of multidimensional data, orthogonal bases represent one-dimensional data well. In this paper, we propose a data-driven sparse representation using orthonormal bases under the lossless compression constraint. We show that imposing such constraint under the Minimum Description Length (MDL) principle leads to a unique and optimal sparse representation for one-dimensional data, which results in discriminative features useful for data discovery. © 2021, CC BY.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Cross-sector energy system resilience and interdependence in a changing climate

引用

Joule 2025年

作者： Xu, Luo Lin, Ning Perera, A.T.D. Poor, H. Vincent Guo, Qinglai Sun, Hongbin Oppenheimer, Michael Department of Civil and Environmental Engineering Princeton University PrincetonNJ United States Center for Policy Research on Energy and the Environment Princeton University PrincetonNJ United States Andlinger Center for Energy and the Environment Princeton University PrincetonNJ United States Department of Electrical and Computer Engineering Princeton University PrincetonNJ United States Department of Electrical Engineering Tsinghua University Beijing China School of Public and International Affairs Princeton University PrincetonNJ United States Department of Geosciences Princeton University PrincetonNJ United States High Meadows Environmental Institute Princeton University PrincetonNJ United States

Rapid global electrification is deepening cross-sector interdependence, fundamentally reshaping the resilience of energy systems in the face of intensifying climate extremes. While increased integration across energy generation, transmission, and consumption sectors can significantly enhance operational flexibility, it can also amplify the risk of cross-sector cascading failures under extreme weather events, giving rise to an emerging resilience paradox that remains insufficiently understood. This study examines evolving cross-sector interactions and their implications for climate resilience by analyzing global electrification trends and regional cases in Texas, integrated with global and downscaled projections of climate extremes. By identifying critical vulnerabilities and flexibility associated with increasing sectoral interdependence, this study highlights the necessity of adopting resilience-oriented, system-level strategies for system operators and policymakers to mitigate cross-sector cascading risks and maximize the benefits of electrification in a changing climate. © 2025 Elsevier Inc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Field Study to Capture Events of Interest (EoI) from Living Labs Using Wearables for Spatiotemporal Monitoring Towards a Framework of Smart Health (sHealth)

A Field Study to Capture Events of Interest (EoI) from Livin...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Md Juber Rahman Bashir I. Morshed Brook Harmon Electrical and Computer Engineering Department University of Memphis Memphis TN USA School of Public Health University of Memphis TN Memphis

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Everyday wearables such as smartwatches or smart bands can play a pivotal role in the field of fitness and wellness and hold the prospect to be used for early disease detection and monitoring towards Smart Health (sHealth). One of the challenges is the extraction of reliable biomarkers from data collected using these devices in the real world (Living Labs). In this yearlong field study, we collected the nocturnal instantaneous heart rate from 9 participants using wrist-worn commercial smart bands and extracted heart rate variability features (HRV). In addition, we measured core body temperature using our custom-designed flexible Inkjet-Printed (IJP) temperature sensor and SpO2 with a finger pulse oximeter. The core body temperature along with user-reported symptoms have been used for automated spatiotemporal monitoring of flu symptoms severity in real-time. The extracted HRV feature values are within the 95% confidence interval of normative values and shows an anticipated trend for gender and age. The resulting dataset from this study is a novel addition and may be used for future *** Relevance- The findings of this study shows usability of wearables in detection and monitoring of diseases such as obstructive sleep apnea reducing the prevalence of undiagnosed cases. This framework also has potentials to monitor outbreaks of flu and other diseases with spatiotemporal distribution.

关键词： Heart rate variability Feature extraction Temperature sensors Diseases Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Generalizability of splint therapy for temporomandibular joint disorders in the era of precision medicine

引用

International journal of rheumatic diseases 2023年第1期26卷 170-171页

作者： Shu-Hao Hsu Wei-Wei Liu Yung-Heng Lee Kevin Sheng-Kai Ma School of Medicine Chung Shan Medical University Taichung Taiwan Republic of China. Department of Orthopedics Cishan Hospital Ministry of Health and Welfare Kaohsiung Taiwan Republic of China. Center for Global Health Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA. Graduate Institute of Biomedical Electronics and Bioinformatics College of Electrical Engineering and Computer Science National Taiwan University Taipei Taiwan Republic of China. Department of Epidemiology Harvard T.H. Chan School of Public Health Boston Massachusetts USA. Department of Dermatology Massachusetts General Hospital Boston Massachusetts USA.

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：