检索结果-内蒙古大学图书馆

Protected Health Information Recognition of Unstructured Code-Mixed Electronic Health Records in Taiwan 18

Protected Health Information Recognition of Unstructured Cod...

18th World Congress on Medical and Health Informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Lee, You-Qian Wang, Bo-Hong Su, Chu-Hsien Chen, Pei-Tsz Lin, Wu-Qing Wu, Chi-Shin Dai, Hong-Jie Intelligent System Lab College of Electrical Engineering and Computer Science Department of Electrical Engineering National Kaohsiung University Science and Technology Kaohsiung Taiwan Department of Psychiatry National Taiwan University Hospital Taipei Taiwan Department of Chemical Engineering Feng Chia University Taichung Taiwan National Institute of Cancer Research National Health Research Institutes Tainan Taiwan School of Post-Baccalaureate Medicine Kaohsiung Medical University Kaohsiung Taiwan

ISBN: (纸本)9781643682648

Electronic health records (EHRs) at medical institutions provide valuable sources for research in both clinical and biomedical domains. However, before such records can be used for research purposes, protected health information (PHI) mentioned in the unstructured text must be removed. In Taiwan's EHR systems the unstructured EHR texts are usually represented in the mixing of English and Chinese languages, which brings challenges for de-identification. This paper presented the first study, to the best of our knowledge, of the construction of a code-mixed EHR de-identification corpus and the evaluation of different mature entity recognition methods applied for the code-mixed PHI recognition task. © 2022 International Medical Informatics Association (IMIA) and IOS Press.

关键词： Mixing

来源：评论

学校读者我要写书评

暂无评论

HO-FPIA: High-Order Field-Programmable Ising Arrays with In-Memory Computing

HO-FPIA: High-Order Field-Programmable Ising Arrays with In-...

引用

IEEE computer Society Annual Symposium on VLSI

作者： Tinish Bhattacharya George Higgins Hutchinson Giacomo Pedretti Dmitri Strukov Department of Electrical and Computer Engineering University of California Santa Barbara Santa Barbara CA USA Artificial Intelligence Research Lab (AIRL) Hewlett Packard Labs Milpitas CA USA

ISBN: (数字)9798350354119

ISBN: (纸本)9798350354126

High Order Ising Machines (HOIMs) are a generalization of the Ising Machine framework that can solve hard combinatorial optimization problems with higher order ( $k> 2$ ) polynomial objective functions. The area cost of a dedicated High Order Ising Machine hardware using a single In-Memory Computing (IMC) crossbar array has been shown to scale linearly with the number of variables and monomials in the Ising Hamiltonian. However, an efficient hardware implementation for large-scale problems requiring multiple crossbar arrays is lacking and thanks to the inherent sparsity in such problems, there remains significant room for further area reduction. Here, we present a Field Programmable Gate Array (FPGA)-inspired architecture for implementing large-scale High Order Ising Machines where cluster-based logic blocks are replaced by IMC-cores that are present as “islands” in a “sea” of programmable routing fabric comprising of interconnects, switches, and connection blocks. Each IMC-core comprises of pair of locally interconnected crossbar arrays for computing high-order polynomial gradients crucial to the Ising Machine's operation. We adapted an open-source FPGA pack-place-route tool to optimize sparsity and fan-in-aware packing of large problems into multiple IMC-cores and model routing overhead. Modeling results of benchmark problems for the developed architecture show up to 116x area improvement and faster operation than a baseline approach and 43x area improvement over a similarly tiled Second Order Ising Machine implementation of the same problem. Crude estimates suggest at least an order of magnitude faster and more energy efficient operation compared to other architectures when the target optimization problems are natively high order.

关键词： Computational modeling computer architecture Logic gates Routing In-memory computing Polynomials Hardware

来源：评论

学校读者我要写书评

暂无评论

Simulation-informed learning for time-resolved angiographic contrast agent concentration reconstruction

引用

computers in Biology and Medicine 2024年 182卷 109178-109178页

作者： Maul, Noah Birkhold, Annette Wagner, Fabian Thies, Mareike Rohleder, Maximilian Berg, Philipp Kowarschik, Markus Maier, Andreas Pattern Recognition Lab Department of Computer Science Friedrich-Alexander Universität Erlangen-Nürnberg Germany Siemens Healthineers AG Forchheim Germany Research Campus STIMULATE University of Magdeburg Germany Department of Medical Engineering University of Magdeburg Germany

Three-dimensional Digital Subtraction Angiography (3D-DSA) is a well-established X-ray-based technique for visualizing vascular anatomy. Recently, four-dimensional DSA (4D-DSA) reconstruction algorithms have been developed to enable the visualization of volumetric contrast flow dynamics through time-series of volumes. This reconstruction problem is ill-posed mainly due to vessel overlap in the projection direction and geometric vessel foreshortening, which leads to information loss in the recorded projection images. However, knowledge about the underlying fluid dynamics can be leveraged to constrain the solution space. In our work, we implicitly include this information in a neural network-based model that is trained on a dataset of image-based blood flow simulations. The model predicts the spatially averaged contrast agent concentration for each centerline point of the vasculature over time, lowering the overall computational demand. The trained network enables the reconstruction of relative contrast agent concentrations with a mean absolute error of 0.02±0.02 and a mean absolute percentage error of 5.31±9.25 %. Moreover, the network is robust to varying degrees of vessel overlap and vessel foreshortening. Our approach demonstrates the potential of the integration of machine learning and blood flow simulations in time-resolved angiographic contrast agent concentration reconstruction. © 2024 The Authors

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging

arXiv

引用

arXiv 2024年

作者： Kim, Jinuk El Halabi, Marwa Ji, Mingi Song, Hyun Oh Department of Computer Science and Engineering Seoul National University Korea Republic of Neural Processing Research Center Samsung SAIT AI Lab Montreal Canada Google. United States

Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation functions and merge the consecutive convolution layers into a single layer. However, these methods suffer from a critical drawback;the kernel size of the merged layers becomes larger, significantly undermining the latency reduction gained from reducing the depth of the network. We show that this problem can be addressed by jointly pruning convolution layers and activation functions. To this end, we propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speedup while minimizing performance loss. Since the corresponding selection problem involves an exponential search space, we formulate a novel surrogate optimization problem and efficiently solve it via dynamic programming. Empirical results demonstrate that our method consistently outperforms existing depth compression and layer pruning methods on various network architectures, both on image classification and generation tasks. We release the code at https://***/snu-mllab/LayerMerge. Copyright © 2024, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Leveraging Service Supply Dynamics in Senselife: Building an Explainable Recommender System for Tailored Frailty Prevention 21

Leveraging Service Supply Dynamics in Senselife: Building an...

引用

2024 IEEE/ACS 21st International Conference on computer Systems and Applications, AICCSA 2024

作者： Frikha, Ghassen Lorca, Xavier Pingaud, Herve Taweel, Adel Bortolaso, Christophe Borgiel, Katarzyna Lamine, Elyes IMT Mines Albi Industrial Engineering Center University of Toulouse Albi France Champollion National University Institute University of Toulouse CNRS-LGC Albi France Birzeit University Department of Computer Science Birzeit Palestine Research and Innovation Division Berger-Levrault Labège France ISIS Champollion National University Institute University of Toulouse Castres France

ISBN: (纸本)9798331518240

The growing elderly population in developed countries highlights the critical need for preventing frailty, which poses significant challenges to health systems due to increased risks of severe health issues. This paper introduces Senselife, a framework that provides explainable service recommendations specifically tailored for frailty prevention. It begins by outlining the medical context and challenges associated with aging, followed by an overview of existing recommender systems with similar objectives. We detail the integration of three key resources-ROR, RNA, and Data Laregion-within the Senselife framework to represent service supply. The paper explains how service supply is structured and the transformation of available data for use within our recommender engine. We introduce the concept of operational activities derived from the ROR and leverage the capabilities of LLMs to incorporate RNA data into Senselife. Additionally, we illustrate how these services are ultimately compiled into recommended service packages. Finally, the paper concludes by summarizing key findings and suggesting potential directions for future research. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Robust triboelectric information-mat enhanced by multi-modality deep learning for smart home

引用

InfoMat 2023年第1期5卷 139-160页

作者： Yanqin Yang Qiongfeng Shi Zixuan Zhang Xuechuan Shan Budiman Salam Chengkuo Lee Department of Electrical and Computer Engineering National University of SingaporeSingaporeSingapore Center for Intelligent Sensors and MEMS(CISM) National University of SingaporeSingaporeSingapore National University of Singapore Suzhou Research Institute(NUSRI) SuzhouPeople's Republic of China Singapore Institute of Manufacturing Technology and National University of Singapore(SIMTech-NUS)Joint Lab on Large-area Flexible Hybrid Electronics National University of SingaporeSingaporeSingapore Printed Intelligent Device Group Singapore Institute of Manufacturing TechnologyAgency for ScienceTechnology and Research(A*STAR)SingaporeSingapore NUS Graduate School-Integrative Sciences and Engineering Programme(ISEP) National University of SingaporeSingaporeSingapore

In metaverse,a digital-twin smart home is a vital platform for immersive communication between the physical and virtual *** nanogenerators(TENGs)sensors contribute substantially to providing smart-home ***,TENG deployment is hindered by its unstable out-put under environment ***,we develop a digital-twin smart home using a robust all-TENG based information mat(InfoMat),which consists of an in-home mat array and an entry *** interdigital electrodes design allows environment-insensitive ratiometric readout from the mat array to can-cel the commonly experienced environmental *** position sensing is also achieved because of the interval arrangement of the mat ***,the two-channel entry mat generates multi-modality informa-tion to aid the 10-user identification accuracy to increase from 93% to 99% compared to the one-channel ***,a digital-twin smart home is visualized by real-time projecting the information in smart home to virtual reality,including access authorization,position,walking trajectory,dynamic activities/sports,and so on.

关键词： digital twin environment-insensitive multi-modality deep learning scalability smart home triboelectric information-mat

来源：评论

学校读者我要写书评

暂无评论

UTMobileNetTraffic2021: A labeled Public Network Traffic Dataset

IEEE Networking Letters

引用

IEEE Networking Letters 2021年第3期3卷 156-160页

作者： Heng, Yuqiang Chandrasekhar, Vikram Andrews, Jeffrey G. Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78712 United States Standard and Mobility Innovation Lab Samsung Research America Mountain ViewCA94043 United States

A high-quality network traffic dataset is essential to the development of accurate network traffic classification algorithms. In this work, we present a new labeled public network traffic dataset with realistic mobile traffic from a wide range of popular applications. An automated platform is constructed to generate and collect data traffic from specified applications in a controlled environment. The dataset contains over 21 million packets from more than 29 hours of mobile traffic with application and activity-level labels. We provide an application classification example using machine learning (ML) models trained on the proposed dataset. © 2019 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Integrated Analysis of Remote Sensing Imagery for Geological Characterization of Volcanic Terrain: A Focus on Lithology, Geomorphology, and Structure

Integrated Analysis of Remote Sensing Imagery for Geological...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Somalin Nath Sushant Shekhar Raj Gusain Anurag Vidyarthi Rishi Prakash R. Gowri National Centre for Geodesy Indian Institute of Technology Kanpur India Department of Electronics & Communication Engineering Propagation Research Lab Graphic Era (Deemed to be University) Dehradun India Department of Computer Science Engineering Graphic Era Hill University Dehradun India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This study employs advanced radar imaging techniques to conduct a comprehensive analysis of a volcanic terrain, unraveling its geological intricacies through the lenses of lithology, geomorphology, and structural features. The research harnesses the power of synthetic aperture radar (SAR) data to provide unprecedented insights into the Earth’s surface, facilitating a holistic understanding of the volcanic landscape. The investigation begins with the utilization of radar backscatter data to discern lithological variations within the volcanic terrain. By correlating radar signatures with known lithological compositions, the study aims to delineate distinct geomorphological units and unveil the spatial distribution of volcanic materials. Additionally, the analysis extends to geomorphological features, employing radar imagery to delineate landforms associated with volcanic activity such as lava flows, calderas, and volcanic cones. Furthermore, the study delves into the structural characteristics of the volcanic terrain, employing radar interferometry techniques to detect and quantify ground deformation associated with identification of fault lines, fractures, and other structural anomalies that contribute to the overall geological context. The integration of these diverse datasets results in a multidimensional understanding of the volcanic landscape, offering valuable insights for geological mapping, hazard assessment, and resource management. The findings of this research contribute to advancing the field of remote sensing and geological exploration, highlighting the efficacy of radar imagery in unraveling the geological complexity of volcanic terrains. Such knowledge is crucial for informed decision-making in areas prone to volcanic activity, ultimately enhancing our ability to mitigate geological risks and promote sustainable development in volcanic regions.

关键词： Radar remote sensing Geology Volcanic activity Radar imaging Radar interferometry Resource management Sustainable development Synthetic aperture radar Remote sensing Lenses

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Graph Modeling based Safety Classifier Algorithm for Smart Transportation

引用

Procedia computer Science 2024年 236卷 502-507页

作者： Najib El Karkouri Smail Tigani Rachid Saadane Abdelah Chehri Samuel Pierre Noureddine Neya Mathematics and Informatics Lab Faculty of Sciences University Ibno Toufial Kenitra Morocco Research and Development Unit Accsellium LLC Fez Morocco SIRC-LaGeS Hassania School of Public Labors 20250 Casablanca Morocco Department of Mathematics and Computer Science Royal Military College of Canada Kingston Canada Department of Computer and Software Engineering Polytechnique Montreal Canada

This research introduces a novel Probabilistic Graph Modeling-based Safety Classifier Algorithm designed for the purpose of classifying road safety in smart transportation systems. Leveraging a combination of numerical integration methods and Gaussian kernel density estimation models, the proposed algorithm offers an effective approach to assess and categorizing the safety levels of roads. The integration of these techniques enables a comprehensive analysis, allowing for a more nuanced understanding of the complex interactions within transportation networks. The algorithm's efficacy in road safety classification holds promising implications for enhancing traffic management and promoting safer urban environments.

关键词： Probabilistic Graph Numerical Computation Smart Transportation Classification Road Safety

来源：评论

学校读者我要写书评

暂无评论

GraphBLAS: C++ Iterators for Sparse Matrices 36

GraphBLAS: C++ Iterators for Sparse Matrices

引用

36th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2022

作者： Brock, Benjamin McMillan, Scott Buluc, Aydin Mattson, Timothy G. Moreira, Jose E. University of California Eecs Department BerkeleyCA United States Software Engineering Institute Carnegie Mellon University PittsburghPA United States Lawrence Berkeley National Laboratory Computational Research Department BerkeleyCA United States Parallel Computing Lab Intel Ocean ParkWA United States Ibm Thomas J. Watson Research Center Yorktown HeightsNY United States

ISBN: (纸本)9781665497473

Iteration over opaque, generic data structures is an important feature of many C++ libraries. Aggressive compiler optimization and inlining enables generic C++ iterators to iterate over complex data structures with performance comparable to that of hand-tuned code with C-language (raw) pointers. In this paper, we describe the sparse matrix iterators in the current draft of the C++ GraphBLAS API, their support for a variety of backend data formats, and implementation strategies we have considered. We compare performance of these iterators to that of hand-tuned iteration with raw pointers, showing that our iterators introduce minimal overhead. We consider extensions to our iterator design for interoperability with the draft C++ Graph Library proposal and to support different semantics for iterating over sparse matrices (by row, by column, by specific diagonals, etc.). © 2022 IEEE.

关键词： Semantics

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：