检索结果-内蒙古大学图书馆

IEEE Symposium Series on Computational Intelligence

作者： Tayo Obafemi-Ajayi Khalid Al-Jabery Lauren Salminen David Laidlaw Ryan Cabeen Donald Wunsch Robert Paul Engineering Program Missouri State University Springfield MO Dept. of Electrical and Computer Eng. Missouri University of Science and Technology Rolla MO University of Southern California Imaging Genetics Center Los Angeles CA Dept. of Computer Science Brown University Providence RI USC Stevens Neuroimaging and Informatics Institute Los Angeles CA Dept. of Psychological Sciences University of Missouri St. Louis MO

Cognitive aging in healthy adults exhibits significant and heterogeneous variability. In this study, we apply a robust unified learning framework to cluster subgroups using neuroimaging data (brain volume and white matter), to identify neurological phenotypes that can sort out the heterogeneity in cognitive aging and help identify potential risk factors for suboptimal brain aging. Using machine learning analytics, results revealed two unique subgroups in healthy older adults with different patterns of white matter integrity and brain volumetric measures. The classification of phenotypical subgroups in healthy older adults may inform the understanding of the complexity of brain changes before the onset of clinical symptoms. The identified neuroimaging features that defined group classification are recognized as important structures that subserve cognitive performance. Further analysis of these potential biomarkers that help predict trajectory of cognitive decline in symptom free individuals could lead to the detection of early stages of neurodegenerative diseases.

关键词： Neuroimaging Feature extraction Aging Clustering algorithms Algorithm design and analysis Predictive models Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

A new solution representation for the rectilinear block packing problem

A new solution representation for the rectilinear block pack...

引用

IEEE International Conference on Industrial Engineering and Engineering Management

作者： Ken Matsushita Yannan Hu Hideki Hashimoto Shinji Imahori Mutsunori Yagiura Dept. Computer Science and Mathematical Informatics Nagoya University Nagoya Japan Dept. Logistics and Information Engineering Tokyo University of Marine Science and Technology Tokyo Japan Dept. Information and System Engineering Chuo University Tokyo Japan

ISBN: (纸本)9781509036660

The rectilinear block packing problem is a problem of packing a set of rectilinear blocks into a larger rectangular container, where a rectilinear block is a polygonal block whose interior angles are either 90° or 270°. This problem has many applications, such as VLSI design and timber cutting. In this paper, we propose a new solution representation, based on an order of items, to decide a layout of rectilinear blocks whose x-coordinates are fixed. When the shapes of given items have certain characteristics, our representation guarantees optimality. We also generalize this result to the case of general shapes. We then propose an exact algorithm that iteratively generates x-coordinates of items and finds the corresponding optimal layout. The computational results show that our algorithm obtains five exact and one heuristic solutions for six instances and it improves the running time of an existing algorithm.

关键词： Layout Containers Shape Strips Very large scale integration Heuristic algorithms IP networks

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

An Ontology-based contextual pre-filtering technique for Recommender Systems

An Ontology-based contextual pre-filtering technique for Rec...

引用

Federated Conference on computer Science and Information Systems (FedCSIS)

作者： Aleksandra Karpus Iacopo Vagliano Krzysztof Goczyła Maurizio Morisio Faculty of Electronics Telecommunication and Informatics Gdansk University of Technology Gdańsk-Wrzeszcz Poland Dept. Control and Computer Engineering Politecnico di Torino Turin Italy

Context-aware Recommender Systems aim to provide users with the most adequate recommendations for their current situation. However, an exact context obtained from a user could be too specific and may not have enough data for accurate rating prediction. This is known as the data sparsity problem. Moreover, often user preference representation depends on the domain or the specific recommendation approach used. Therefore, a big effort is required to change the method used. In this paper we present a new approach for contextual pre-filtering (i.e. using the current context to select a relevant subset of data). Our approach can be used with existing recommendation algorithms. It is based on two ontologies: Recommender System Context ontology, which represents the context, and Contextual Ontological User Profile ontology, which represents user preferences. We evaluated our approach through an offline study which showed that when used with well-known recommendation algorithms it can significantly improve the accuracy of prediction.

关键词： Context Ontologies Context modeling Vocabulary Recommender systems Motion pictures Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Satellite Image Edge Detection for Population Distribution Pattern Identification using Levelset with Morphological Filtering Process

引用

IOP Conference Series: Materials Science and Engineering 2017年第1期180卷

作者： Harsiti T A Munandar A Suhendar A G Abdullah D Rohendi Information System Dept. Information Technology Faculty Universitas Serang Raya Banten – INDONESIA Informatics Engineering Dept. Information Technology Faculty Universitas Serang Raya Banten – INDONESIA Electrical and Electronic Engineering Dept. - Faculty of Technology and Vocational Education Universitas Pendidikan Indonesia Bandung INDONESIA Computer Scince Education Dept. – Math. and Naturan Science Faculty Universitas Pendidikan Indonesia Bandung INDONESIA

Population distribution pattern is directly related with economic gap of a region. Analysis of population distribution pattern is usually performed by studying statistical data on population. This study aimed to analyze population distribution pattern using image analysis concept, i.e. using satellite images. Levelset and morphological image filtering methods were used to analyze images to see distribution pattern. The research result showed that Levelset and morphological image filtering could remove a lot of noises in analysis result images and form object edge contours very clearly. The detected object contours were used as references to recognize population distribution pattern based on satellite image analysis. The pattern made based on the research result didn't show optimal result because Levelset performed image segmentation based on the contours of the analyzed objects. Other segmentation methods should be combined with it to produce clearer population distribution pattern.

关键词：

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

Sensitivity Analysis of Small Cells and DAS Techno-economic Models in Mobile 5G

Sensitivity Analysis of Small Cells and DAS Techno-economic ...

引用

IEEE Wireless Communications and Networking Conference

作者： Christos Bouras Anastasia Kollia Andreas Papazois Computer Technology Institute & Press "Diophantus" Computer Engineering & Informatics Dept. University of Patras

ISBN: (纸本)9781467398152

Next generation of mobile technologies demands high date rates and low round trip times. Therefore, we analyze deployments that offer these performance capabilities. We consider the fundamental issue of the expenses of the network's installation, maintenance and operation. We calculate the costs of Distributed Antenna Systems (DAS) and small cells by describing updated cost models for each one. We present a Sensitivity Analysis of certain types of cost variables and parameters including the existing bandwidth, the running costs, the interest rate, the base station, the equipment, the power consumption, the backhaul, the implementation costs and Throughput Density. We include a variable cost provision for the year 2016 and beyond, and conduce several experiments, based on the upper analysis, by considering many different parameter prices and introducing the Throughput Density. We calculate the Total Cost of Ownership (TCO), the Capital (CAPEX) and the Operational (OPEX) expenditures. Finally, we are led to important conclusions by comparing the two main technologies costs and evaluating the cost parameters and variables that will lead future researchers to suggest ways to reduce the higher costs.

关键词： Small cell Ultra-dense DAS Techno-economics Sensitivity analysis 5G

来源：评论

学校读者我要写书评

暂无评论

Real-time 3D tumor tracking based on 2D projections of implanted markers 31

Real-time 3D tumor tracking based on 2D projections of impla...

引用

31st International Conference on computers and Their Applications, CATA 2016

作者： Mao, Songan Wu, Huanmei Lu, Minghui Cheng, Chee-Wai Dept. of Electrical and Computer Engineering Purdue University IndianapolisIN46202 United States School of Engineering and Technology IUPUI School of Informatics and Computing IUPUI IndianapolisIN46202 United States PerkinElmer Medical Imaging Inc. Santa ClaraCA95054 United States UH Case Medical Center 11100 Euclid Ave ClevelandOH44106 United States

ISBN: (纸本)9781943436026

In cancer radiation therapy, the treatment effectiveness is degraded greatly by the tumor respiratory motion during treatment delivery, induced by patient free breathing and organ motions. Advance treatment delivery techniques with image guidance helps to address the tumor motion challenges. However, real-time tumor localization is still a big concern as the respiratory motion dynamically changes its motion velocities, directions, and amplitude during treatment delivery. In this project, an optimized internal marker 3D localization method was proposed by combining the use of onboard kiovoltage (kV) beam and megavoltage (MV) imaging systems. Two sets of 2D projection images from any pair of kV-kV, kV-MV or MV-MV with different gantry rotation angles will be utilized to derive the 3D tumor positions. This approach transforms the projection 2D images to the original 3D location without requirements of the two imaging systems to be orthogonal. The accuracy of the proposed method was validated by several evaluation metrics. The average 3D Euclidean difference is between 0.21 mm to 0.56 mm, which is within the range of clinical applications. Further study will be carried out to evaluate the system comprehensively and integrate to the existing treatment delivery system for better communications among different systems. It potentially will improve the treatment accuracy and provide better health care to cancer patients. Copyright ISCA.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Wear-aware adaptive routing for networks-on-chips 15

Wear-aware adaptive routing for networks-on-chips

引用

9th IEEE/ACM International Symposium on Networks-on-Chip, NOCS 2015

作者： Vitkovskiy, Arseniy Soteriou, Vassos Gratz, Paul V. Dept. of Electrical Eng. Computer Eng. and Informatics Cyprus University of Technology Cyprus Dept. of Electrical and Computer Engineering Texas A and M University United States

ISBN: (纸本)9781450333962

Chip-multiprocessors are facing worsening reliability due to prolonged operational stresses, with their tile-interconnecting Network-on-Chip (NoC) being especially vulnerable to wearout-induced failure. To tackle this ominous threat we present a novel wear-aware routing algorithm that continuously considers the stresses the NoC experiences at runtime, along with temperature and fabrication process variation metrics, steering traffic away from locations that are most prone to Electromigration (EM)- and Hot-Carrier Injection (HCI)-induced wear. Under realistic applications our wear-aware algorithm yields 66% and 8% average increases in mean-time-to-failure for EM and HCI, respectively. Copyright is held by the owner/author(s).

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

A Supervisory Approach to Microgrid Demand Response and Climate Control

A Supervisory Approach to Microgrid Demand Response and Clim...

引用

Mediterranean Conference on Control and Automation

作者： Christos D. Korkas Simone Baldi Iakovos Michailidis Yiannis Boutalis Elias B. Kosmatopoulos Dept. of Electrical and Computer Engineering Democritus University of Thrace Xanthi 67100 Greece and Informatics & Telematics Institute Center for Research and Technology Hellas (ITI-CERTH) Thessaloniki 57001 Greece Delft Center for Systems and Control Delft University of Technology Delft 2628CD The Netherlands Dept. of Electrical and Computer Engineering Democritus University of Thrace Xanthi 67100 Greece

ISBN: (纸本)9781467383479

Microgrids equipped with small-scale renewable-energy generation systems and energy storage units offer challenging opportunity from a control point of view. In fact, in order to improve resilience and enable islanded mode, microgrid energy management systems must dynamically manage controllable loads by considering not only matching energy generation and consumption, but also thermal comfort of the occupants. Thermal comfort, which is often neglected or oversimplified, plays a major role in dynamic demand response, especially in front of intermittent behavior of the renewable energy sources. This paper presents a novel control algorithm for joint demand response management and thermal comfort optimization in a microgrid composed of a block of buildings, a photovoltaic array, a wind turbine, and an energy storage unit. In order to address the large-scale nature of the problem, the proposed control strategy adopt a two-level supervisory strategy: at the lower level, each building employs a local controller that processes only local measurements;at the upper level, a centralized unit supervises and updates the three controllers with the aim of minimizing the aggregate energy cost and thermal discomfort of the microgrid. Comparisons with alternative strategies reveal that the proposed supervisory strategy efficiently manages the demand response so as to sensibly improve independence of the microgrid with respect to the main grid, and guarantees at the same time thermal comfort of the occupants.

关键词： Buildings Microgrids Mathematical model Meteorology Optimization Load management Renewable energy sources

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：