检索结果-内蒙古大学图书馆

International Conference on data Science and Advanced analytics (DSAA)

作者： Iman Kamkar Sunil Kumar Gupta Dinh Phung Svetha Venkatesh Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9781467382748

Feature selection is an important step in building predictive models for most real-world problems. One of the popular methods in feature selection is Lasso. However, it shows instability in selecting features when dealing with correlated features. In this work, we propose a new method that aims to increase the stability of Lasso by encouraging similarities between features based on their relatedness, which is captured via a feature covariance matrix. Besides modeling positive feature correlations, our method can also identify negative correlations between features. We propose a convex formulation for our model along with an alternating optimization algorithm that can learn the weights of the features as well as the relationship between them. Using both synthetic and real-world data, we show that the proposed method is more stable than Lasso and many state-of-the-art shrinkage and feature selection methods. Also, its predictive performance is comparable to other methods.

关键词： Stability criteria Optimization Covariance matrices Correlation Linear programming Predictive models

来源：评论

学校读者我要写书评

暂无评论

Heart rate independent QT variability component can detect subclinical cardiac autonomic neuropathy in diabetes

Heart rate independent QT variability component can detect s...

引用

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

作者： Mohammad H Imam Chandan K Karmakar Ahsan H Khandoker Herbert F Jelinek M Palaniswami Department of Electrical & Electronic Engineering The University of Melbourne Melbourne VIC Australia Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia Department of Biomedical Engineering Khalifa University of Science Technology and Research Abu Dhabi UAE School of Community Health Charles Sturt University Albury Australia

ISBN: (纸本)9781457702198

Cardiac autonomic neuropathy (CAN) may lead to life threatening arrhythmia due to denervation of both the parasympathetic and sympathetic branches of autonomic nervous system innervating the heart. CAN is a frequently under diagnosed complication of diabetes, because a patient can have asymptomatic CAN for several years before it is clinically apparent. However, detection of CAN at the early or subclinical stage leads to more effective treatment outcomes. Cardiac autonomic reflex tests (CART) (i.e. Ewing test battery) are normally used for the detection and staging of CAN. These tests have limitations with the necessity of active participation of the patients for test maneuvers, as a majority of patients will not be able to complete all five tests required due to comorbidities such as frailty, obesity or cardiorespiratory disease. CAN affects both heart rate (measured by RR interval dynamics) and ventricular repolarization function (i.e. QT interval dynamics) of the heart, which can be efficiently analyzed from surface ECG. Therefore, ECG based diagnosis techniques of CAN analysis are becoming popular as they can reduce the limitations of CARTs used traditionally for CAN detection and it complements CART results. In this study, the performance of an ECG based QTV feature derived using a model free approach, which can quantify the QTV component not affected directly by the heart rate (HR) variation, is compared with some other measures of QTV and HRV in subclinical CAN detection in diabetes. Short-term ECGs (i.e. 5 min long) of 60 diabetic subjects without CAN and 50 diabetic subjects detected with early level of CAN determined by CART were analyzed. The proposed measure for quantifying the QTV component independent of HR denoted as QTV~RR stands out to be more discriminatory than other existing variability measures of QTV and HRV in subclinical detection of CAN.

关键词： sugar blood cardiovascular system diseases electrocardiography feature extraction medical signal processing

来源：评论

学校读者我要写书评

暂无评论

Overcoming data scarcity of Twitter: Using tweets as bootstrap with application to autism-related topic content analysis

Overcoming data scarcity of Twitter: Using tweets as bootstr...

引用

International Conference on Advances in Social Network Analysis and Mining, ASONAM

作者： Adham Beykikhoshk Ognjen Arandjelović Dinh Phung Svetha Venkatesh Centre for Pattern Recognition and Data Analytics Deakin University Geelong VIC Australia

ISBN: (纸本)9781509020942

Notwithstanding recent work which has demonstrated the potential of using Twitter messages for content-specific data mining and analysis, the depth of such analysis is inherently limited by the scarcity of data imposed by the 140 character tweet limit. In this paper we describe a novel approach for targeted knowledge exploration which uses tweet content analysis as a preliminary step. This step is used to bootstrap more sophisticated data collection from directly related but much richer content sources. In particular we demonstrate that valuable information can be collected by following URLs included in tweets. We automatically extract content from the corresponding web pages and treating each web page as a document linked to the original tweet show how a temporal topic model based on a hierarchical Dirichlet process can be used to track the evolution of a complex topic structure of a Twitter community. Using autism-related tweets we demonstrate that our method is capable of capturing a much more meaningful picture of information exchange than user-chosen hashtags.

关键词： Twitter data mining Web pages Media Autism Tagging Uniform resource locators

来源：评论

学校读者我要写书评

暂无评论

Global investments in pandemic preparedness and COVID-19: development assistance and domestic spending on health between 1990 and 2026

引用

The Lancet Global Health 2023年第3期11卷 e385-e413页

作者： Micah, Angela E. Bhangdia, Kayleigh Cogswell, Ian E. Lasher, Dylan Lidral-Porter, Brendan Maddison, Emilie R. Nguyen, Trang Nhu Ngoc Patel, Nishali Pedroza, Paola Solorio, Juan Stutzman, Hayley Tsakalos, Golsum Wang, Yifeng Warriner, Wesley Zhao, Yingxi Zlavog, Bianca S. Abbafati, Cristiana Abbas, Jaffar Abbasi-Kangevari, Mohsen Abbasi-Kangevari, Zeinab Abdelmasseh, Michael Abdulah, Deldar Morad Abedi, Aidin Abegaz, Kedir Hussein Abhilash, E.S. Aboagye, Richard Gyan Abolhassani, Hassan Abrigo, Michael R.M. Abubaker Ali, Hiwa Abu-Gharbieh, Eman Adem, Mohammed Hussien Afzal, Muhammad Sohail Ahmadi, Ali Ahmed, Haroon Ahmed Rashid, Tarik Aji, Budi Akbarialiabad, Hossein Akelew, Yibeltal Al Hamad, Hanadi Alam, Khurshid Alanezi, Fahad Mashhour Alanzi, Turki M. Al-Hanawi, Mohammed Khaled Alhassan, Robert Kaba Aljunid, Syed Mohamed Almustanyir, Sami Al-Raddadi, Rajaa M. Alvis-Guzman, Nelson Alvis-Zakzuk, Nelson J. Amare, Azmeraw T. Ameyaw, Edward Kwabena Amini-Rarani, Mostafa Amu, Hubert Ancuceanu, Robert Andrei, Tudorel Anwar, Sumadi Lukman Appiah, Francis Aqeel, Muhammad Arabloo, Jalal Arab-Zozani, Morteza Aravkin, Aleksandr Y. Aremu, Olatunde Aruleba, Raphael Taiwo Athari, Seyyed Shamsadin Avila-Burgos, Leticia Ayanore, Martin Amogre Azari, Samad Baig, Atif Amin Bantie, Abere Tilahun Barrow, Amadou Baskaran, Pritish Basu, Sanjay Batiha, Abdul-Monim Mohammad Baune, Bernhard T. Berezvai, Zombor Bhardwaj, Nikha Bhardwaj, Pankaj Bhaskar, Sonu Boachie, Micheal Kofi Bodolica, Virginia Botelho, João Silva Botelho Braithwaite, Dejana Breitborde, Nicholas J.K. Busse, Reinhard Cahuana-Hurtado, Lucero Catalá-López, Ferrán Chansa, Collins Charan, Jaykaran Chattu, Vijay Kumar Chen, Simiao Chukwu, Isaac Sunday Dadras, Omid Dandona, Lalit Dandona, Rakhi Dargahi, Abdollah Debela, Sisay Abebe Denova-Gutiérrez, Edgar Desye, Belay Dharmaratne, Samath Dhamminda Diao, Nancy Doan, Linh Phuong Dodangeh, Milad dos Santos, Wendel Mombaque Doshmangir, Leila Dube, John Eini, Ebrahim El Sayed Zaki, Maysaa El Tantawi, Maha Enyew, Daniel Berhanie Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Applied Mathematics University of Washington Seattle WA United States Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States Nuffield Department of Medicine University of Oxford Oxford United Kingdom Department of Juridical and Economic Studies La Sapienza University Rome Italy Antai College of Economics Shanghai Jiao Tong University Shanghai China Non-communicable Diseases Research Center Tehran University of Medical Sciences Tehran Iran Research Center for Immunodeficiencies Tehran University of Medical Sciences Tehran Iran Multiple Sclerosis Research Center Tehran University of Medical Sciences Tehran Iran Children’s Medical Center Tehran University of Medical Sciences Tehran Iran Department of Epidemiology and Biostatistics Tehran University of Medical Sciences Tehran Iran Tehran Heart Center Tehran University of Medical Sciences Tehran Iran Faculty of Medicine Tehran University of Medical Sciences Tehran Iran National Institute for Health Research Tehran University of Medical Sciences Tehran Iran Department of Pharmacology Tehran University of Medical Sciences Tehran Iran Department of Cardiology Tehran University of Medical Sciences Tehran Iran Sina Trauma and Surgery Research Center Tehran University of Medical Sciences Tehran Iran Digestive Diseases Research Institute Tehran University of Medical Sciences Tehran Iran Department of Neurology Tehran University of Medical Sciences Tehran Iran Social Determinants of Health Research Center Shahid Beheshti University of Medical Sciences Tehran Iran Department of Epidemiology Shahid Beheshti University of Medical Sciences Tehran Iran Department of Health Economics and Statistics Shahid Beheshti University of Medical Sciences Tehran Iran Department of Neurosurgery Shahid Beheshti University of Medical Sciences Tehran Iran Ophthalmic R

Background: The COVID-19 pandemic highlighted gaps in health surveillance systems, disease prevention, and treatment globally. Among the many factors that might have led to these gaps is the issue of the financing of national health systems, especially in low-income and middle-income countries (LMICs), as well as a robust global system for pandemic preparedness. We aimed to provide a comparative assessment of global health spending at the onset of the pandemic;characterise the amount of development assistance for pandemic preparedness and response disbursed in the first 2 years of the COVID-19 pandemic;and examine expectations for future health spending and put into context the expected need for investment in pandemic preparedness. Methods: In this analysis of global health spending between 1990 and 2021, and prediction from 2021 to 2026, we estimated four sources of health spending: development assistance for health (DAH), government spending, out-of-pocket spending, and prepaid private spending across 204 countries and territories. We used the Organisation for Economic Co-operation and Development (OECD)'s Creditor Reporting System (CRS) and the WHO Global Health Expenditure database (GHED) to estimate spending. We estimated development assistance for general health, COVID-19 response, and pandemic preparedness and response using a keyword search. Health spending estimates were combined with estimates of resources needed for pandemic prevention and preparedness to analyse future health spending patterns, relative to need. Findings: In 2019, at the onset of the COVID-19 pandemic, US$9·2 trillion (95% uncertainty interval [UI] 9·1–9·3) was spent on health worldwide. We found great disparities in the amount of resources devoted to health, with high-income countries spending $7·3 trillion (95% UI 7·2–7·4) in 2019;293·7 times the $24·8 billion (95% UI 24·3–25·3) spent by low-income countries in 2019. That same year, $43·1 billion in development assistance was provided

关键词：

来源：评论

学校读者我要写书评

暂无评论

The adaptable buffer algorithm for high quantile estimation in non-stationary data streams

The adaptable buffer algorithm for high quantile estimation ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ognjen Arandjelović Duc-Son Pham Svetha Venkatesh Centre for Pattern Recognition & Data Analytics Deakin University Geelong VIC Australia Department of Computing Curtin University Perth WA Australia

The need to estimate a particular quantile of a distribution is an important problem which frequently arises in many computer vision and signal processing applications. For example, our work was motivated by the requirements of many semi-automatic surveillance analytics systems which detect abnormalities in close-circuit television (CCTV) footage using statistical models of low-level motion features. In this paper we specifically address the problem of estimating the running quantile of a data stream with non-stationary stochasticity when the memory for storing observations is limited. We make several major contributions: (i) we derive an important theoretical result which shows that the change in the quantile of a stream is constrained regardless of the stochastic properties of data, (ii) we describe a set of high-level design goals for an effective estimation algorithm that emerge as a consequence of our theoretical findings, (iii) we introduce a novel algorithm which implements the aforementioned design goals by retaining a sample of data values in a manner adaptive to changes in the distribution of data and progressively narrowing down its focus in the periods of quasi-stationary stochasticity, and (iv) we present a comprehensive evaluation of the proposed algorithm and compare it with the existing methods in the literature on both synthetic data sets and three large `real-world' streams acquired in the course of operation of an existing commercial surveillance system. Our findings convincingly demonstrate that the proposed method is highly successful and vastly outperforms the existing alternatives, especially when the target quantile is high valued and the available buffer capacity severely limited.

关键词： Australia Indexes Entropy

来源：评论

学校读者我要写书评

暂无评论

Unsupervised inference of significant locations from WiFi data for understanding human dynamics 14

Unsupervised inference of significant locations from WiFi da...

引用

13th International Conference on Mobile and Ubiquitous Multimedia, MUM 2014

作者： Nguyen, Thanh-Binh Nguyen, Thuong Luo, Wei Venkatesh, Svetha Phung, Dinh Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9781450334013

Motion and location activities are essential to understanding human dynamics. This paper presents a method for discovering significant locations and individuals' daily routines from WiFi data, a data source considered more suitable for analyzing human dynamics than GPS data. Our method determines significant locations by clustering access points in close proximity using the Affinity Propagation algorithm. We demonstrate the method on the MDC dataset that includes more than 30 million WiFi scans. The experimental results show a high clustering performance for most of the users. The discovered location trajectories revealed interesting mobility patterns of mobile phone users. The human dynamics of participants is reflected through the entropy of the location distributions which shows interesting correlation with the age and occupations of users. Quantitative results are presented to support our proposed approach. Copyright © 2014 ACM 978-1-4503-3304-7/14/11 $15.00.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Bayesian nonparametric extraction of hidden contexts from pervasive honest signals

Bayesian nonparametric extraction of hidden contexts from pe...

引用

2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014

作者： Nguyen, Thuong Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9781479927364

Hidden patterns and contexts play an important part in intelligent pervasive systems. Most of the existing works have focused on simple forms of contexts derived directly from raw signals. High-level constructs and patterns have been largely neglected or remained under-explored in pervasive computing, mainly due to the growing complexity over time and the lack of efficient principal methods to extract them. Traditional parametric modeling approaches from machine learning find it difficult to discover new, unseen patterns and contexts arising from continuous growth of data streams due to its practice of training-then-prediction paradigm. In this work, we propose to apply Bayesian nonparametric models as a systematic and rigorous paradigm to continuously learn hidden patterns and contexts from raw social signals to provide basic building blocks for context-aware applications. Bayesian nonparametric models allow the model complexity to grow with data, fitting naturally to several problems encountered in pervasive computing. Under this framework, we use nonparametric prior distributions to model the data generative process, which helps towards learning the number of latent patterns automatically, adapting to changes in data and discovering never-seen-before patterns, contexts and activities. The proposed methods are agnostic to data types, however our work shall demonstrate to two types of signals: accelerometer activity data and Bluetooth proximal data. © 2014 IEEE.

关键词： Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Fixed-lag particle filter for continuous context discovery using Indian Buffet Process

Fixed-lag particle filter for continuous context discovery u...

引用

2014 12th IEEE International Conference on Pervasive Computing and Communications, PerCom 2014

作者： Nguyen, Thuong Gupta, Sunil Venkatesh, Svetha Phung, Dinh Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9781479934454

Exploiting context from stream data in pervasive environments remains a challenge. We aim to extract proximal context from Bluetooth stream data, using an incremental, Bayesian nonparametric framework that estimates the number of contexts automatically. Unlike current approaches that can only provide final proximal grouping, our method provides proximal grouping and membership of users over time. Additionally, it provides an efficient online inference. We construct co-location matrix over time using Bluetooth data. A Poisson-exponential model is used to factorize this matrix into a factor matrix, interpreted as proximal groups, and a coefficient matrix that indicates factor usage. The coefficient matrix follows the Indian Buffet Process prior, which estimates the number of factors automatically. The non-negativity and sparsity of factors are enforced by using the exponential distribution to generate the factors. We propose a fixed-lag particle filter algorithm to process data incrementally. We compare the incremental inference (particle filter) with full batch inference (Gibbs sampling) in terms of normalized factorization error and execution time. The normalized error obtained through our incremental inference is comparable to that of full batch inference, whilst the execution time is more than 100 times faster. The discovered factors have similar meaning to the results of the popular Louvain method for community detection. © 2014 IEEE.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Individualized arrhythmia detection with ECG signals from wearable devices

Individualized arrhythmia detection with ECG signals from we...

引用

2014 IEEE International Conference on data Science and Advanced analytics, DSAA 2014

作者： Nguyen, Thanh-Binh Lou, Wei Caelli, Terry Venkatesh, Svetha Phung, Dinh Centre for Pattern Recognition and Data Analytics Deakin University Australia National ICT Australia Australia

ISBN: (纸本)9781479969913

Low cost pervasive electrocardiogram (ECG) monitors is changing how sinus arrhythmia are diagnosed among patients with mild symptoms. With the large amount of data generated from long-term monitoring, come new data science and analytical challenges. Although traditional rule-based detection algorithms still work on relatively short clinical quality ECG, they are not optimal for pervasive signals collected from wearable devices - they don't adapt to individual difference and assume accurate identification of ECG fiducial points. To overcome these short-comings of the rule-based methods, this paper introduces an arrhythmia detection approach for low quality pervasive ECG signals. To achieve the robustness needed, two techniques were applied. First, a set of ECG features with minimal reliance on fiducial point identification were selected. Next, the features were normalized using robust statistics to factors out baseline individual differences and clinically irrelevant temporal drift that is common in pervasive ECG. The proposed method was evaluated using pervasive ECG signals we collected, in combination with clinician validated ECG signals from Physiobank. Empirical evaluation confirms accuracy improvements of the proposed approach over the traditional clinical rules. © 2014 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Analysing effect of heart rate and age on radial artery pressure derived systolic and diastolic durations in healthy adults

Analysing effect of heart rate and age on radial artery pres...

引用

Computers in Cardiology (CinC)

作者： Peng Li Chandan Karmakar Chengyu Liu Changchun Liu School of Control Science and Engineering Shandong University Jinan China Centre of Pattern Recognition and Data Analytics (PRaDA) Deakin University Geelong Australia Electrical & Electronic Engineering Department University of Melbourne Melbourne Australia

The measurements of cardiac systolic duration (SD) and diastolic duration (DD) have been well accepted as helpful tools for evaluating the cardiac functionality. In clinical practice, SD and DD are generally measured using echocardiography or heart sound signals. Recent studies have seen the attempts of approximating SD and DD by electrocardiogram (ECG) derived QT and TQ intervals, as well as radial artery pressure (RAP) derived foot-to-notch and notch-to-foot intervals. However, to the best of knowledge, there lacks deep elucidations on their performance when used as surrogate SD and DD data. We investigated the RAP-derived SD, DD, and ratio of SD to DD (S/D), to heart rate (HR) and age in healthy adults. Sixty healthy subjects were enrolled and their ECG and RAP signals were simultaneously recorded. The SD and DD were extracted automatically from RAP with the aid of the acceleration RAP. The HR was calculated using the RR interval extracted from ECG. Their mean values of 10 cardiac cycles were used in the analysis. Results demonstrated a negative linear relationship between SD and HR, a negative nonlinear relationship between DD and HR, and a positive linear relationship between S/D and HR (all p

关键词： Heart rate Pediatrics Wrist Electrocardiography Fitting Hafnium

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：