检索结果-内蒙古大学图书馆

6th Machine Learning for Healthcare Conference, MLHC 2021

作者： Ötleş, Erkin Oh, Jeeheh Li, Benjamin Bochinski, Michelle Joo, Hyeon Ortwine, Justin Shenoy, Erica Washer, Laraine Young, Vincent B. Rao, Krishna Wiens, Jenna Department of Industrial & Operations Engineering University of Michigan United States Medical Scientist Training Program University of Michigan Medical School United States Division of Computer Science & Engineering University of Michigan United States Nursing Informatics Michigan Medicine United States Department of Anesthesiology University of Michigan Medical School United States Department of Learning Health Sciences University of Michigan Medical School United States Infection Control Unit Division of Infectious Diseases Massachusetts General Hospital Harvard Medical School United States Department of Internal Medicine Division of Infectious Diseases University of Michigan Medical School United States Department of Microbiology & Immunology University of Michigan Medical School United States

Once integrated into clinical care, patient risk stratification models may perform worse compared to their retrospective performance. To date, it is widely accepted that performance will degrade over time due to changes in care processes and patient populations. However, the extent to which this occurs is poorly understood, in part because few researchers report prospective validation performance. In this study, we compare the 2020-2021 (’20-’21) prospective performance of a patient risk stratification model for predicting healthcare-associated infections to a 2019-2020 (’19-’20) retrospective validation of the same model. We define the difference in retrospective and prospective performance as the performance gap. We estimate how i) "temporal shift", i.e., changes in clinical workflows and patient populations, and ii) "infrastructure shift", i.e., changes in access, extraction and transformation of data, both contribute to the performance gap. Applied prospectively to 26,864 hospital encounters during a twelve-month period from July 2020 to June 2021, the model achieved an area under the receiver operating characteristic curve (AUROC) of 0.767 (95% confidence interval (CI): 0.737, 0.801) and a Brier score of 0.189 (95% CI: 0.186, 0.191). Prospective performance decreased slightly compared to’19-’20 retrospective performance, in which the model achieved an AUROC of 0.778 (95% CI: 0.744, 0.815) and a Brier score of 0.163 (95% CI: 0.161, 0.165). The resulting performance gap was primarily due to infrastructure shift and not temporal shift. So long as we continue to develop and validate models using data stored in large research data warehouses, we must consider differences in how and when data are accessed, measure how these differences may negatively affect prospective performance, and work to mitigate those differences. © 2021 E. Ötleş & J. Oh et al.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Computer Vision Techniques in Continuous Beehive Monitoring Applications: A Survey

arXiv

引用

arXiv 2022年

作者： Bilik, Simon Zemcik, Tomas Kratochvila, Lukas Ricanek, Dominik Richter, Miloslav Zambanini, Sebastian Horak, Karel Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3058/10 Brno61600 Czech Republic Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Yliopistonkatu 34 Lappeenranta53850 Finland Computer Vision Lab Institute of Visual Computing & Human-Centered Technology Faculty of Informatics TU Wien Favoritenstr. 9/193-1 ViennaA-1040 Austria

Wide use and availability of machine learning and computer vision techniques allows development of relatively complex monitoring systems in many domains. Besides the traditional industrial domain, new applications appears also in biology and agriculture, where they may be used to detect infections, parasites and weeds, but also for automated monitoring and early warning systems. This goes in concordance with the introduction of the easily accessible hardware and development kits such as the Arduino, or RaspberryPi families. In this paper, we survey 50 papers focusing on the methods of automated beehive monitoring using computer vision techniques. Particularly on the pollen and Varroa mite detection together with the bee traffic monitoring. Such systems could also be used for monitoring of honeybee colonies and for the inspection of their health state, which could potentially identify dangerous states before the situation is critical, or to better plan periodic bee colony inspections and therefore save significant costs. Further on, we also include analysis of the research trends in this application field and we outline the possible directions of new development. Our paper is also aimed at veterinary and apidology professionals and experts, who may not be familiar with machine learning to introduce them to its capabilities, hence each family of techniques is prefaced by a brief theoretical introduction and motivation related to its base method. We hope that this paper will inspire other scientists to use machine learning techniques for other applications in beehive monitoring. © 2022, CC BY.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Protocol to explain support vector machine predictions via exact Shapley value computation

引用

STAR Protocols 2024年第2期5卷 103010页

作者： Mastropietro, Andrea Bajorath, Jürgen Deparment of Computer Control and Management Engineering “Antonio Ruberti” Sapienza University of Rome Via Ariosto 25 Rome 00185 Italy Department of Life Science Informatics and Data Science B-IT LIMES Program Unit Chemical Biology and Medicinal Chemistry Rheinische Friedrich-Wilhelms-Universität Friedrich-Hirzebruch-Allee 5/6 Bonn 53115 Germany Lamarr Institute for Machine Learning and Artificial Intelligence Friedrich-Hirzebruch-Allee 5/6 Bonn 53115 Germany

Shapley values from cooperative game theory are adapted for explaining machine learning predictions. For large feature sets used in machine learning, Shapley values are approximated. We present a protocol for two techniques for explaining support vector machine predictions with exact Shapley value computation. We detail the application of these algorithms and provide ready-to-use Python scripts and custom code. The final output of the protocol includes quantitative feature analysis and mapping of important features for visualization. For complete details on the use and execution of this protocol, please refer to Feldmann and Bajorath¹ and Mastropietro et al.² © 2024 The Author(s)

关键词： Bioinformatics Chemistry Computer sciences

来源：评论

学校读者我要写书评

暂无评论

Oriented grouping-constrained spectral clustering for medical imaging segmentation

Oriented grouping-constrained spectral clustering for medica...

引用

作者： Xia, Kaijian Gu, Xiaoqing Zhang, Yudong School of Information and Control Engineering China University of Mining and Technology XuzhouJiangsu221116 China ChangshuJiangsu215500 China School of Information Science and Engineering Changzhou University ChangzhouJiangsu China Department of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

Original medical images are often inadequate for clinical diagnosis. Certain prior information can be used as an important basis for disease diagnosis and prevention. In this study, an oriented grouping-constrained spectral clustering method, OGCSC, is proposed to deal with medical image segmentation problems. OGCSC propagates the group information from the affinity matrix and subdivides the group information into two constraints. By adopting the normalized framework, OGCSC can be transformed into normalized spectral clustering. The solution of OGSCSC can be viewed as a generalized eigenvalue problem that can be solved using eigenvalue decomposition techniques. The significance of our work is that the use of group information and constraints information to analyse image data can greatly enhance the results achieved using the clustering segmentation method. The empirical experimental results reveal that the proposed method achieves robust and effective performance for medical image segmentation. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

The Use of Various Neurostimulators in Therapy of Neurodegenerative Disorders – A Survey

The Use of Various Neurostimulators in Therapy of Neurodegen...

引用

Progress in Applied Electrical engineering (PAEE)

作者： Aleksandra Kawala-Sterniuk Agata Gajos Mateusz Pawłowski Witold Libionka Władysław Piotr Duch Bartosz Pańczyszak Monika Stomal-Słowińska Michał Podpora Waldemar Bauer Adam Sudoł Mariusz Pelc Jarosław Zygarlicki Piotr Sterniuk Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland Department of Neurosurgery "Vital Medic" Hospital Kluczbork Poland Department of Extrapyramidal Diseases Medical University of Łódź Łódź Poland Faculty of Health Sciences Wroclaw Medical University Wrocław Poland Department of Automatic Control and Robotics AGH University of Science and Technology Kraków Poland Faculty of Natural Sciences and Technology University of Opole Opole Poland School Of Computing and Mathematical Sciences University of Greenwich London United Kindgom Center for Technology Transfer Opole University of Technology Opole Poland

ISBN: (数字)9781665455152

ISBN: (纸本)9781665455169

The use of neurostimulators in the treatment and therapy of neurodegenerative diseases is an alternative to pharmacological treatment. Unfortunately, most of these disorders are incurable, however, the use of neurostimulators can delay the onset of symptoms, the course of the disease and significantly improve the quality of life. Treatment with the use of neurostimulators also allows you to avoid side effects which usually accompany pharmacotherapy, or in order to replace it when prescribed medication is not working properly or not working at all. This paper focuses mainly on vagus nerve and deep brain stimulation.

关键词： Electrical engineering Deep brain stimulation Medical treatment Delays Diseases

来源：评论

学校读者我要写书评

暂无评论

Fractional-order composite control for the transient creep of a piezoelectric actuator

引用

International Journal of Nanomanufacturing 2019年第4期15卷 394-406页

作者： Zhao, Xueliang Zhang, Chengjin Liu, Hongbo School of Control Science and Engineering Shandong University Jinan Shandong250061 China Department of Informatics Beijing City University Beijing100083 China School of Mechanical Electrical and Information Engineering Shandong University at Weihai Shandong264209 China

In this study, a fractional-order composite controller is proposed to decrease the settling time and narrow the range of the transient creep of a piezoelectric actuator. The controller is composed of backlash modules and a fractional-order PIλ controller. The backlash modules reduce the effect of the transient creep and the hysteresis, while the fractional-order controller decreases the settling time. Experiments show that the settling time is decreased from 11 ms to 6 ms. The controller exhibits good performance on step creep and hysteresis when the input signal is discretised into steps, whether 10, 20, 40 or 80 steps. All standard deviations are suppressed to levels 39.3% lower than that of a standard PI controller and the range of the transient creep is reduced to 19.46%. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Piezoelectric actuators

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Adaptive Filter for Head Tracking in Augmented Reality (AR)-based Flight Simulators

引用

IEEE Transactions on Computers 2025年

作者： Nwobodo, Onyeka J. Kuaban, Godlove Suila Nkemeni, Valery Wereszczynski, Kamil Cyran, Krzysztof A. Silesian University of Technology Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Gliwice Poland Polish Academy of Sciences Institute of Theoretical and Applied Informatics Poland University of Buea Laboratory of Electrical Engineering and Computing Faculty of Engineering and Technology Buea Cameroon

This paper presents a novel approach for head tracking in augmented reality (AR) flight simulators using an adaptive fusion of Kalman and particle filters. This fusion dynamically balances the strengths of both algorithms, leveraging Kalman filters for computational efficiency and particle filters for handling non-linearities based on real-time factors such as sensor noise and head movement patterns. Our method demonstrates superior tracking precision and reduced latency, making it particularly effective for immersive pilot training in AR-based flight simulations. While focused on flight simulation, our approach holds high potential for broader applications in other AR and virtual reality (VR) environments where precise, real-time head tracking is crucial. These results provide actionable design guidance for developers optimizing tracking systems in environments that require fast response times and high accuracy. Future extensions of this research could explore the generalization of our approach across diverse AR applications, including human-computer interaction (HCI), medical simulations, and gaming. © 1968-2012 IEEE.

关键词： Flight simulators

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling of hyper-elastic soft robots using spatial curves

引用

IFAC-PapersOnLine 2020年第2期53卷 9238-9243页

作者： Brandon J. Caasenbrood Alexander Y. Pogromsky Henk Nijmeijer Mechanical Engineering Department Eindhoven University of Technology Eindhoven The Netherlands Department of Control Systems and Informatics Saint-Petersburg National Research University of Information Technologies Mechanics and Optics (ITMO) Russian Federation

Soft robots differ fundamentally from traditional robotics. Due to their composition of soft materials, soft robots are inherently compliant and allow for large continuum-bodied motion. Although some frameworks exist for describing the kinematics, the development of dynamic models intended for control-oriented applications is relatively scarce and, to some extent, underdeveloped. This paper provides a modeling framework to describe the nonlinear dynamics of a soft robot using differential geometry of spatial curves. Furthermore, we include the geometrically nonlinear and time-variant mechanical nature imposed by these soft materials into our modeling framework. Numerical simulations of the dynamic model are presented, as well as experimental validations of a study case soft robot to illustrate the accuracy. The proposed modeling framework can be used to simulate the nonlinear dynamics of soft robots but also to calculate the inverse dynamics required for model-based control.

关键词： Modeling Robots manipulators Robotics technology

来源：评论

学校读者我要写书评

暂无评论

Hidden attractors in a new fractional-order discrete system: Chaos, complexity, entropy, and control

引用

Chinese Physics B 2020年第5期29卷 174-181页

作者： Adel Ouannas Amina Aicha Khennaoui Shaher Momani Viet-Thanh Pham Reyad El-Khazali Laboratory of Mathematics Informatics and Systems(LAMIS)University of Laarbi TebessiTebessa12002Algeria College of Humanities and Sciences Ajman UniversityAjmanUAE Laboratory of Dynamical Systems and Control University of Larbi Ben M’hidiOum El BouaghiAlgeria Department of Mathematics Faculty of ScienceUniversity of JordanAmman 11942Jordan Nonlinear Systems and Applications Faculty of Electrical and Electronics EngineeringTon Duc Thang UniversityHo Chi Minh CityVietnam ECCE Department Khalifa UniversityAbu-Dhabi 127788United Arab Emirates

This paper studies the dynamics of a new fractional-order discrete system based on the Caputo-like difference *** is the first study to explore a three-dimensional fractional-order discrete chaotic system without *** phase portrait,bifurcation diagrams,and largest Lyapunov exponents,it is shown that the proposed fractional-order discrete system exhibits a range of different dynamical ***,different tests are used to confirm the existence of chaos,such as 0-1 test and C0 *** addition,the quantification of the level of chaos in the new fractional-order discrete system is measured by the approximate entropy ***,based on the fractional linearization method,a one-dimensional controller to stabilize the new system is *** results are presented to validate the findings of the paper.

关键词： discrete chaos discrete fractional calculus hidden attractor

来源：评论

学校读者我要写书评

暂无评论

Hard hat wearing detection based on head keypoint localization

arXiv

引用

arXiv 2021年

作者： Wójcik, Bartosz Zarski, Mateusz Ksiązek, Kamil Miszczak, Jaroslaw A. Skibniewski, Miroslaw J. Faculty of Civil Engineering Silesian University of Technology Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Poland Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Poland Department of Civil & Environmental Engineering University of Maryland College Park United States

In recent years, a lot of attention is paid to deep learning methods in the context of vision-based construction site safety systems. However, still there is no reliable way to establish the relationship between supervised construction workers and their basic personal protective equipment, like hard hats. To address this problem, a novel deep learning method combining object detection, keypoint localization, and simple rule-based reasoning is proposed in this article. In tests, this solution surpassed the previous methods based on the relative bounding box position of different instances, as well as direct detection of hard hat wearers and non-wearers. Achieving MS COCO style overall AP of 67.5% compared to 66.4% and 66.3% achieved by the above-mentioned approaches, with class specific AP for hard hat non-wearers of 64.1% compared to 63.0% and 60.3%. The results show that the conjunction of deep learning methods with humanly-interpretable rule-based algorithm is better suited for detection of hard hat non-wearers. Code is available at barwojcik/hard-hats. © 2021, CC BY.

关键词： Object detection

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：