检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Chen, You Kho, Abel N. Liebovitz, David Ivory, Catherine Osmundson, Sarah Bian, Jiang Malin, Bradley A. Dept. of Biomedical Informatics School of Medicine Vanderbilt University NashvilleTN United States Institute for Public Health and Medicine Northwestern University ChicagoIL United States School of Medicine University of Chicago ChicagoIL United States School of Nursing Vanderbilt University NashvilleTN United States Dept. of Obstetrics and Gynecology School of Medicine Vanderbilt University NashvilleTN United States Dept. of Health Outcomes and Policy University of Florida GainesvilleFL United States Dept. of Biostatistics School of Medicine Vanderbilt University NashvilleTN United States Dept. of Electrical Engineering and Computer Science School of Engineering Vanderbilt University NashvilleTN United States

Objective: The traditional fee-for-service approach to healthcare leads to the management of a patient's conditions in an independent manner, inducing various negative consequences. It is recognized that a bundled care approach to healthcare-one that manages a collection of health conditions together-may enable greater efficacy and cost savings. However, it is not always evident which sets of conditions should be managed in a bundled manner. Thus, we investigated how a data-driven approach could be applied to automatically learn potential bundles and evaluate their plausibility. Methods: To accomplish this research, we designed a data-driven framework to infer clusters of health conditions, which we referred to as phenotypic patterns, via their shared clinical workflows, which we refer to as coordinating care patterns, from the data inherent in electronic medical records (EMRs). We applied the framework with approximately 16,500 inpatient stays from a large medical center. The plausibility of the inferred health condition clusters for bundled care was assessed through a survey (whose responses were analyzed via an analysis of variance (ANOVA) under a 95% confidence interval) of a panel of five experts. Furthermore, the face validity of the inferred health condition clusters was confirmed by evidence in the published literature. Results: The framework inferred four condition clusters: 1) fetal abnormalities, 2) late pregnancies, 3) prostate problems, and 4) chronic diseases (with congestive heart failure featuring prominently). Each cluster had evidence in the literature and was deemed to be plausible for bundled care via ANOVA on the survey responses under a 95% confidence interval. Conclusions: The findings suggest that data from EMRs can provide a basis for discovering new directions in bundled care. Still, translating such findings into actual care management will require further refinement, implementation, and evaluation. Copyright © 2017, The Authors. All right

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Multi-criteria optimisation design of shapers with piece-wise equally distributed time-delay

引用

IFAC-PapersOnLine 2016年第10期49卷 112-117页

作者： Pilbauer, Dan Michiels, Wim Vyhlidal, Tomas CIIRC - Czech Institute of Informatics Robotics and Cybernetics and Dept. of Instrumentation and Control Eng. Faculty of Mechanical Engineering Czech Technical University in Prague Technická 4 166 07 Praha 6 Czech Republic Department of Computer Science Katholieke Universiteit Leuven Celestijnenlaan 200A HeverleeB-3001 Belgium

The paper presents an optimisation based method to parametrize input shapers with time delays of piece-wise-equal distribution. The design respects the two key requirements on the shaper performance that are the prompt response time and the robustness represented by residual vibration functions, which are however conflicting criteria as a rule. Thus, the optimisation task is solved as a constrained multi-objective problem where the constraints respect the additional requirements on the shaper performance such as a non-decreasing step response or zero residual function at some frequency points. The result is a Pareto front that shows a trade-off between the two main requirements. Next to the presentation of the results in an example, a user friendly shaper-design tool is presented. © 2016

关键词： Multiobjective optimization computer control systems Constrained optimization Economic and social effects Time delay Timing circuits Distributed time delays Multi criteria optimisation Multi objective problem Pareto frontiers Residual functions Residual vibrations Signal shaper Vibration suppression

来源：评论

学校读者我要写书评

暂无评论

Optimal medication dosing from suboptimal clinical examples: A deep reinforcement learning approach

Optimal medication dosing from suboptimal clinical examples:...

引用

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

作者： Shamim Nemati Mohammad M. Ghassemi Gari D. Clifford Emory University Atlanta GA US Dept. of Electrical Engineering and Computer Science MIT Cambrige MA Dept. of Biomedical Informatics Emory University Atlanta GA Dept. of Biomedical Engineering Georgia Institute of Technology Atlanta GA

Misdosing medications with sensitive therapeutic windows, such as heparin, can place patients at unnecessary risk, increase length of hospital stay, and lead to wasted hospital resources. In this work, we present a clinician-in-the-loop sequential decision making framework, which provides an individualized dosing policy adapted to each patient's evolving clinical phenotype. We employed retrospective data from the publicly available MIMIC II intensive care unit database, and developed a deep reinforcement learning algorithm that learns an optimal heparin dosing policy from sample dosing trails and their associated outcomes in large electronic medical records. Using separate training and testing datasets, our model was observed to be effective in proposing heparin doses that resulted in better expected outcomes than the clinical guidelines. Our results demonstrate that a sequential modeling approach, learned from retrospective data, could potentially be used at the bedside to derive individualized patient dosing policies.

关键词： Hospitals Training Time series analysis Learning (artificial intelligence) Drugs Feature extraction Cost function

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition using dept. body part histograms and Hidden Markov Models

Human Activity Recognition using depth body part histograms ...

引用

International Conference on Innovations in science, engineering and Technology (ICISET)

作者： Md. Zia Uddin Jim Torresen Taskeed Jabid Department of Computer Education Sungkyunkwan University Seoul Republic of Korea Dept. of Informatics University of Oslo Oslo Norway Dept. of Computer Science and Engineering Sogang University Seoul Republic of Korea

ISBN: (纸本)9781509061235

This paper proposes a novel approach for human activity recognition based on body part histograms and Hidden Markov Models. From a dept. video frame, body parts are segmented first using a trained random forest. Then, a histogram for each body part is combined to represent histogram features for a dept. image. The dept. video activity features are then applied on hidden Markov models for training and recognition. The proposed method was superior when compared with other conventional approaches.

关键词： Hidden Markov models Shape Histograms Legged locomotion Image segmentation Activity recognition Training

来源：评论

学校读者我要写书评

暂无评论

ACTR-20. A SMALL MOLECULE AXL INHIBITOR, BGB324 – FIRST-IN-HUMAN GBM SURGICAL PK TRIAL FOR RECURRENT TUMORS

引用

Neuro-Oncology 2018年第SUPPL_6期20卷 vi15-vi15页

作者： Ghosh, Sadashib Sadahiro, Hirokazu Kang, Kyung-Don Gibson, Justin T Minata, Mutsuko Yu, Hai Shi, Junfeng Chhipa, Rishi Chen, Zhihong Lu, Songjian Simoni, Yannick Furuta, Takuya Sabit, Hemragul Zhang, Suojun Bastola, Soniya Yamaguchi, Shinobu Alsheikh, Heba Allah Komarova, Svetlana Wang, Jun Kim, Sung-Hak Hambardzumyan, Dolores Lu, Xinghua Newell, Evan W Dasgupta, Biplab Nakada, Mitsutoshi Lee, L James Nabors, L Burt A. Norian, Lyse Nakano, Ichiro Department of Neurosurgery The University of Alabama at Birmingham Birmingham AL USA Dept. of Neurosurgery University of Alabama at Birmingham Birmingham AL USA Dept. of Nutrition Sciences University of Alabama at Birmingham Birmingham AL USA Dept. of Chemical and Biomolecular Engineering The Ohio State University Columbus OH USA Division of Oncology Cincinnati Children’s Hospital Medical Center Cincinnati OH USA Dept. of Pediatrics Aflac Cancer and Blood Disorders Center Children’s Healthcare of Atlanta Emory University School of Medicine Atlanta GA USA University of Pittsburgh Pittsburgh PA USA Singapore Immunology Network Agency for Science Technology and Research Singapore Dept. of Pathology Kurume University School of Medicine Kurume Fukuoka Japan Department of Neurosurgery Graduate School of Medical Science Kanazawa University Kanazawa Ishikawa Japan Dept. of Animal Science College of Africulture and Life Sciences Chonnam National University Gwangju Cholla-namdo Republic of Korea Emory University Atlanta GA USA Dept. of Biomedical Informatics University of Pittsburgh Pittsburgh PA USA Department of Neurosurgery Kanazawa University Kanazawa Ishikawa Japan Department of Neurology The University of Alabama at Birmingham Birmingham AL USA

Glioblastoma (GBM) remains the deadliest of all primary brain tumors with very few effective treatment options. Recently, we reported that high AXL expression is correlated with poor prognosis in GBM patients and demonstrated the therapeutic benefits of targeting AXL, a member of TAM receptor tyrosine kinase family using a novel small molecule inhibitor, BGB324 in immunocompetent mouse GBM models and xenografts of patient-derived glioma stem cells(GSCs). The promise of BGB324 in tumor burden management prompted us to develop a clinical trial with BGB324 as a single agent therapeutic with the goal to extend it as a combinatorial therapy in the future. Our surgical PK/PD clinical trial with BGB324 in recurrent GBM has been approved by the Brain Malignancy Steering Committee at the National Cancer Institute. Study treatment will consist of 2 cohorts of adult GBM patients, one (Group A) receiving the treatment pre-operatively and the other (Group B) receiving no treatment at all prior to surgery. First 5 patients recruited to Group A will be checked for the desired intra-tumoral drug concentration achieved to continue the trial. Group A will be supplemented by an additional 5 patients bringing the number to n=10 in each arm of the trial. Following surgical resection, patients in both cohorts will receive BGB324 daily in 21-day cycles. Treatment will be continued unless patients exhibit significant toxicity or substantial tumor progression. Our preclinical findings show the upregulation of AXL and its role in apoptosis induction in mesenchymal GBM as well as its association with MLK4, a serine threonine kinase we previously characterized as a mesenchymal GSC molecular target. Inhibition of phosphorylation of AXL and concomitant NF-kB activation in mesenchymal GSCs was found to be the nodal target of the drug action. An up-to-date information of the trial will be presented in detail.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Security issues in cloud computing for healthcare

Security issues in cloud computing for healthcare

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Repu Daman Manish M. Tripathi Saroj K. Mishra School of Telemedicine & Biomedical Informatics Sanjay Gandhi Post Graduate Institute of Medical Sciences Lucknow UP INDIA Dept. of Computer Science & Engineering Integral University Lucknow UP India

ISBN: (纸本)9781467394178

ICT infrastructure in healthcare domain is improved with the advancement of technology. Health data consist multi-format data as it has text reports, MRI, CT-SCAN images, & pathological slides. Healthcare domain has a large volume of data which is archived as Electronic Health Record (EHR) and it has to be updated frequently. The data of the patients has to be available whenever and wherever necessary in the future course of treatment as patient history. Such a huge archival of data in the hospital needs Skilled manpower, Information and Communication Technology (ICT) and Civil infrastructure and its recurring maintenance cost. Cloud technology thus provides the necessary infrastructure as pay per usage model and when used in healthcare sector lowers the cost of storage, processing and updating infrastructure with minimum cost. Data of patients which are confidential and private in nature can be stored in cloud by selecting appropriate deployment models as different models have different levels of security.

关键词： Handheld computers Decision support systems Conferences

来源：评论

学校读者我要写书评

暂无评论

DEBS grand challenge: Pimp my taxi ride 9

DEBS grand challenge: Pimp my taxi ride

引用

9th ACM International Conference on Distributed Event-Based Systems, DEBS 2015

作者： Galeos, Aimylos Gryllos, Prokopis Leventis, Nikolaos Mavrikis, Konstantinos Voulgaris, Spyros Computer Engineering and Informatics Department University of Patras Greece Dept. of Computer Science VU University Netherlands

ISBN: (纸本)9781450332866

The DEBS 2015 Grand Challenge [2] defined a stream-processing problem on data collected through the FOILing NYC's Taxi Trip Data project [1]. These data include itinerary information on all rides of over 10,000 taxis in a wide area of 150km×150km around New York City over the whole year of 2013. The collected information includes the (anonymized) taxi ID, (anonymized) taxi license ID, pickup and dropoff coordinates, pickup and dropoff times, and the total cost of the ride divided in basic fare, tax, tolls, and tip.

关键词： Pickups

来源：评论

学校读者我要写书评

暂无评论

Monitoring and detecting atrial fibrillation using wearable technology

Monitoring and detecting atrial fibrillation using wearable ...

引用

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

作者： Shamim Nemati Mohammad M. Ghassemi Vaidehi Ambai Nino Isakadze Oleksiy Levantsevych Amit Shah Gari D. Clifford Dept of Biomedical Informatics Emory University Atlanta GA Dept. of Electrical Engineering and Computer Science MIT Cambrige MA Philadelnhia Collece of Osteonathic Medicine Suwanee GA Dept of Medicine School of Medicine Atlanta GA Division of Cardiolosv Veterans Affairs Hosoital Atlanta GA Dept of Epidemiology Emory University Atlanta GA Dept of Biomedical Engineering Georgia Institute of Technology Atlanta GA

Atrial fibrillation (AFib) is diagnosed by analysis of the morphological and rhythmic properties of the electrocardiogram. It was recently shown that accurate detection of AFib is possible using beat-to-beat interval variations. This raises the question of whether AFib detection can be performed using a pulsatile waveform such as the Photoplethysmogram (PPG). The recent explosion in use of recreational and professional ambulatory wrist-based pulse monitoring devices means that an accurate pulse-based AFib screening algorithm would enable large scale screening for silent or undiagnosed AFib, a significant risk factor for multiple diseases. We propose a noise-resistant machine learning approach to detecting AFib from noisy ambulatory PPG recorded from the wrist using a modern research watch-based wearable device (the Samsung Simband). Ambulatory pulsatile and movement data were recorded from 46 subjects, 15 with AFib and 31 non symptomatic. Single channel electrocardiogram (ECG), multi-wavelength PPG and tri-axial accelerometry were recorded simultaneously at 128 Hz from the non-dominant wrist using the Simband. Recording lengths varied from 3.5 to 8.5 minutes. Pulse (beat) detection was performed on the PPG waveforms, and eleven features were extracted based on beat-to-beat variability and waveform signal quality. Using 10-fold cross validation, an accuracy of 95 % on out-of-sample data was achieved, with a sensitivity of 97%, specificity of 94%, and an area under the receiver operating curve (AUROC) of 0.99. The described approach provides a noise-resistant, accurate screening tool for AFib from PPG sensors located in an ambulatory wrist watch. To our knowledge this is the first study to demonstrate an algorithm with a high enough accuracy to be used in general population studies that does not require an ambulatory Holter electrocardiographic monitor.

关键词： biomedical monitoring Electrocardiography Feature extraction Hospitals Monitoring Sensitivity Standards

来源：评论

学校读者我要写书评

暂无评论

A survey on network resiliency methodologies against weather-based disruptions 8

A survey on network resiliency methodologies against weather...

引用

8th International Workshop on Resilient Networks Design and Modeling, RNDM 2016

作者： Tornatore, Massimo Andre, Joao Babarczi, Peter Braun, Torsten Folstad, Eirik Heegaard, Poul Hmaity, Ali Furdek, Marija Jorge, Luisa Kmiecik, Wojciech Mas MacHuca, Carmen Martins, Lucia Medeiros, Carmo Musumeci, Francesco Pasic, Alija Rak, Jacek Simpson, Steven Travanca, Rui Voyiatzis, Artemios Politecnico di Milano Department of Electronics Information and Bioengineering Milan Italy Lisbon Portugal Hungary University of Bern Bern Switzerland Norwegian University of Science and Technology Trondheim Norway Universidade de Aveiro Dept. of Electronics Information and Bioengineering Milan Portugal KTH Royal Institute of Technology Stockholm Sweden Instituto Politécnico de Bragancą INESC Coimbra Portugal Wroclaw University of Technology Poland Technical University Munich Germany Dept. of Electrical and Computer Engineering INESC University of Coimbra Portugal Dept. of Electrical and Computer Engineering and INESC University of Coimbra Coimbra Portugal Politecnico di Milano Department of Electron. Information and Bioengineering Milan Italy MTA-BME Future Internet Research Group Budapest Uni. of Technology and Economics Hungary Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Poland Lancaster University United Kingdom Dept. of Civil Engineering Universidade de Aveiro 3810-193 Portugal SBA Research Vienna Austria

ISBN: (纸本)9781467390231

Due to the increasing dependence on network services of our society, research has recently been concentrating on enhancing traditional protection strategies to withstand large-scale failures, as in case of disaster events. The recently-formed EU-funded RECODIS project aims at coordinating and fostering research collaboration in Europe on disaster resiliency in communication networks. In particular, the Working Group (WG) 2 of the RECODIS project focuses on developing new network-resiliency strategies to survive weather-based disruptions. As a first step, WG2 members have conducted a comprehensive literature survey on existing studies on this topic. This paper classifies and summarizes the most relevant studies collected by WG2 members in this first phase of the project. While the majority of studies regarding weather-based disruptions deals with wireless network (as wireless channel is directly affected by weather conditions), in this survey we cover also disaster-resiliency approaches designed for wired network if they leverage network reconfiguration based on disaster 'alerts', considering that many weather-based disruptions grant an 'alert' thanks to weather forecast. © 2016 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

PennyLane: Automatic differentiation of hybrid quantum-classical computations

arXiv

引用

arXiv 2018年

作者： Bergholm, Ville Izaac, Josh Schuld, Maria Gogolin, Christian Ahmed, Shahnawaz Ajith, Vishnu Alam, M. Sohaib Alonso-Linaje, Guillermo AkashNarayanan, B. Asadi, Ali Arrazola, Juan Miguel Azad, Utkarsh Banning, Sam Blank, Carsten Bromley, Thomas R. Cordier, Benjamin A. Ceroni, Jack Delgado, Alain Matteo, Olivia Di Dusko, Amintor Garg, Tanya Guala, Diego Hayes, Anthony Hill, Ryan Ijaz, Aroosa Isacsson, Theodor Ittah, David Jahangiri, Soran Jain, Prateek Jiang, Edward Khandelwal, Ankit Kottmann, Korbinian Lang, Robert A. Lee, Christina Loke, Thomas Lowe, Angus McKiernan, Keri Meyer, Johannes Jakob Montañez-Barrera, J.A. Moyard, Romain Niu, Zeyue O’Riordan, Lee James Oud, Steven Panigrahi, Ashish Park, Chae-Yeun Polatajko, Daniel Quesada, Nicolás Roberts, Chase Sá, Nahum Schoch, Isidor Shi, Borun Shu, Shuli Sim, Sukin Singh, Arshpreet Strandberg, Ingrid Soni, Jay Száva, Antal Thabet, Slimane Vargas-Hernández, Rodrigo A. Vincent, Trevor Vitucci, Nicola Weber, Maurice Wierichs, David Wiersema, Roeland Willmann, Moritz Wong, Vincent Zhang, Shaoming Killoran, Nathan Xanadu 777 Bay Street Toronto Canada Wallenberg Centre for Quantum Technology Department of Microtechnology and Nanoscience Chalmers University of Technology Gothenburg412 96 Sweden Indian Institute of Information Technology Kottayam India NASA Ames Research Center Moffett FieldCA94035 United States Mountain ViewCA94043 United States data cybernetics Martin-Kolmsperger-Str 26 Landsberg86899 Germany Department of Medical Informatics and Clinical Epidemiology Oregon Health and Science University PortlandOR97202 United States Dept. of Electrical and Computer Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada Department of Physics Indian Institute of Technology Roorkee Uttarakhand Roorkee India qBraid 5235 South Harper Court ChicagoIL60615 United States Factal Analytics Level 2 Chimes Building Plot 61 Sector - 44 Haryana Gurgaon122003 India Centre for High Energy Physics Indian Institute of Science Karnataka Bengaluru560012 India ICFO - Institut de Ciencies Fotoniques The Barcelona Institute of Science and Technology Av. Carl Friedrich Gauss 3 Castelldefels Barcelona08860 Spain Chemical Physics Theory Group Department of Chemistry University of Toronto Canada DUG Technology 76 Kings Park Rd West PerthWA6005 Australia Rigetti Computing 2919 Seventh Street BerkeleyCA94710 United States Dahlem Center for Complex Quantum Systems Freie Universität Berlin Berlin14195 Germany Institute for Advanced Simulation Jülich Supercomputing Centre Forschungszentrum Jülich Jülich52425 Germany University of Amsterdam Netherlands School of Physical Sciences National Institute of Science Education and Research HBNI Odisha Jatni752 050 India Cervest United Kingdom Centro Brasileiro de Pesquisas Físicas Rua Dr. Xavier Sigaud 150 Rio de Janeiro22290-180 Brazil Zurich8092 Switzerland Neo4j UK Ltd United Kingdom Zapata Computing Inc. United States ITC Infotech Bangalore India Department of Microtechnology and Nanoscienc

PennyLane is a Python 3 software framework for differentiable programming of quantum computers. The library provides a unified architecture for near-term quantum computing devices, supporting both qubit and continuous-variable paradigms. PennyLane’s core feature is the ability to compute gradients of variational quantum circuits in a way that is compatible with classical techniques such as backpropagation. PennyLane thus extends the automatic differentiation algorithms common in optimization and machine learning to include quantum and hybrid computations. A plugin system makes the framework compatible with any gate-based quantum simulator or hardware. We provide plugins for hardware providers including the Xanadu Cloud, Amazon Braket, and IBM Quantum, allowing PennyLane optimizations to be run on publicly accessible quantum devices. On the classical front, PennyLane interfaces with accelerated machine learning libraries such as TensorFlow, PyTorch, JAX, and Autograd. PennyLane can be used for the optimization of variational quantum eigensolvers, quantum approximate optimization, quantum machine learning models, and many other applications. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine 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：