检索结果-内蒙古大学图书馆

2nd International Conference on Energy Geotechnics, ICEGT 2020

作者： Rizvi, Zarghaam Haider Akhtar, Syed Jawad Sabeeh, Wurood Talib Wuttke, Frank Geomechanics and Geotechnics Kiel University Kiel24118 Germany Department of Civil and Environmental Engineering University of Waterloo WaterlooON Canada Department of Computer Engineering Aligarh Muslim University Aligarh202002 India

Soil thermal conductivity plays a critical role in the design of geo-structures and energy transportation systems. Effective thermal conductivity (ETC) of soil depends primarily on the degree of saturation, porosity and mineralogical composition. These controlling parameters have nonlinear dependencies, thus making prediction a nontrivial task. In this study, an artificial neural network (ANN) model is developed based on the deep learning (DL) algorithm to predict the effective thermal conductivity of unsaturated soil. A large dataset is constructed including porosity, degree of saturation and quartz content from literature to train and validate the developed model. The model is constructed with a different number of hidden layers and neurons in each hidden layer. The standard errors for training and testing are calculated for each variation of hidden layers and neurons. The network with the least error is adopted for prediction. Two sand types independent of training and validation data reported in the literature are considered for prediction of the ETC. Five simulation runs are performed for each sand, and the computed results are plotted against the reported experimental results. The results conclude that the developed ANN model provides an efficient, easy and straightforward way to predict soil thermal conductivity with reasonable accuracy. © The Authors, published by EDP Sciences, 2020.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Weakly Semi-supervised phenotyping using Electronic Health records

引用

Journal of Biomedical Informatics 2022年 134卷 104175页

作者： Nogues, Isabelle-Emmanuella Wen, Jun Lin, Yucong Liu, Molei Tedeschi, Sara K. Geva, Alon Cai, Tianxi Hong, Chuan Department of Biostatistics Harvard T. H. Chan School of Public Health BostonMA United States Department of Biomedical Informatics Harvard Medical School BostonMA United States Center for Statistical Science Tsinghua University Beijing China Department of Medicine Division of Rheumatology Inflammation and Immunity Brigham and Women's Hospital BostonMA United States Department of Anesthesiology Critical Care and Pain Medicine Computational Health Informatics Program Boston Children's Hospital BostonMA United States Department of Anesthesia Harvard Medical School BostonMA United States

Objective: Electronic Health Record (EHR) based phenotyping is a crucial yet challenging problem in the biomedical field. Though clinicians typically determine patient-level diagnoses via manual chart review, the sheer volume and heterogeneity of EHR data renders such tasks challenging, time-consuming, and prohibitively expensive, thus leading to a scarcity of clinical annotations in EHRs. Weakly supervised learning algorithms have been successfully applied to various EHR phenotyping problems, due to their ability to leverage information from large quantities of unlabeled samples to better inform predictions based on a far smaller number of patients. However, most weakly supervised methods are subject to the challenge to choose the right cutoff value to generate an optimal classifier. Furthermore, since they only utilize the most informative features (i.e., main ICD and NLP counts) they may fail for episodic phenotypes that cannot be consistently detected via ICD and NLP data. In this paper, we propose a label-efficient, weakly semi-supervised deep learning algorithm for EHR phenotyping (WSS-DL), which overcomes the limitations above. Materials and Methods: WSS-DL classifies patient-level disease status through a series of learning stages: 1) generating silver standard labels, 2) deriving enhanced-silver-standard labels by fitting a weakly supervised deep learning model to data with silver standard labels as outcomes and high dimensional EHR features as input, and 3) obtaining the final prediction score and classifier by fitting a supervised learning model to data with a minimal number of gold standard labels as the outcome, and the enhanced-silver-standard labels and a minimal set of most informative EHR features as input. To assess the generalizability of WSS-DL across different phenotypes and medical institutions, we apply WSS-DL to classify a total of 17 diseases, including both acute and chronic conditions, using EHR data from three healthcare systems. Addition

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Beware analyst bias when considering algorithm types

Control

引用

Control 2022年第2期35卷

作者： Risse, Michael Seeq Corp

Humans can bring their own prejudices to the practice of data analytics. There has been a spate of articles regarding unintended bias in machine learning algorithms and how these may lead to undesirable outcomes, such... 详细信息

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Multiple-Instance learning Support Vector Machine Algorithm based Pedestrian Detection 9

Multiple-Instance Learning Support Vector Machine Algorithm ...

引用

9th IEEE International Conference on Communication and Signal Processing, ICCSP 2020

作者： Haritha, T. Megalingam, Rajesh Kannan Amrita Amrita Vishwa Vidyapeetham Department of Electronics and communication Engineering Amritapuri India

ISBN: (纸本)9781728149882

Pedestrian detection is one of the significant task for the intelligent transportation *** the pedestrian detection become much relevant in automotive field for improving the safety systems. Many of the existing research papers focused on efficient pedestrian detection. The challenges that are facing the existing researches are (1)Various style of clothing appearances (2)Different possible poses of pedestrian (3) Presence of hidden objects(4)Frequent occlusion. In this paper, to resolve the above challenges by formulate the pedestrian detection based on the multiple instance learning support vector machine algorithm (MILSVM).Therefore the pedestrian performing various action will be accurately detected. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Autonomous detection of malicious events using machine learning models in drone networks 2

Autonomous detection of malicious events using machine learn...

引用

2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020

作者： Moustafa, Nour Jolfaei, Alireza University of New South Wales at ADFA CanberraACT Australia Macquarie University SydneyNSW Australia

ISBN: (纸本)9781450381055

Drone systems, the so-called Unmanned Autonomous Vehicles (UAVs), have been widely employed in military and civilian sectors. Drone systems have been used for cyber warfare, warfighting and surveillance purposes of modern military and civilian applications. However, they have increasingly suffered from sophisticated malicious activities that exploit their vulnerabilities through network communications. As drones comprise a complex infrastructure as piloted aircraft but without operators, they still need a reliable security control to assert their safe operations. This paper proposes an autonomous intrusion detection scheme for discovering advanced and sophisticated cyberattacks that exploit drone networks. A testbed was configured to launch malicious events against a drone network for collecting legitimate and malicious observations and evaluate the performances of machine learning in real-time. Machine learning algorithms, including decision tree, k-nearest neighbors, naive Bayes, support vector machine and deep learning multi-layer perceptron, were trained and evaluated using the data collections, with promising results in terms of detection accuracy, false alarm rates, and processing times. © 2020 Association for Computing Machinery.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A data enhancement approach to improve machine learning performance for predicting health status using remote healthcare data 2

A data enhancement approach to improve machine learning perf...

引用

2nd International Conference on Advanced Information and Communication Technology, ICAICT 2020

作者： Tabassum, Shaira Sampa, Masuda Begum Islam, Rafiqul Yokota, Fumihiko Nakashima, Naoki Ahmed, Ashir United International University Department of Computer Science and Engineering Bangladesh Kyushu University Department of Advanced Information Technology Japan Kyushu University Medical Information Center Japan Institute of Decision Science for A Sustainable Society Kyushu University Japan

ISBN: (纸本)9780738123233

Machine learning (ML) is becoming tremendously important to improve the performance of remote healthcare systems. Portable health clinic (PHC), a remote healthcare system contains a triage function that classifies the patients in two major groups - (a)healthy and (b)unhealthy. Unhealthy patients require regular health checkups. This paper aims to predict the status of the registered patients to decide the follow-up date and frequency. Health management cost can be reduced by decreasing the number of follow-up frequency. We carried out an experiment on 271 corporate members and monitored their health status in every three months and collected four phases of data. The data records contain clinical data, socio-demographical data, dietary behavior data. However, most of the machine learning algorithms can not directly work with categorical data. Several encoding techniques are available which can also enhance the prediction performance. In this paper, We applied three encoding techniques and proposed a new encoding approach to handle categorical variables. The result shows that Random Forest Classifier performs the best with 95.33% accuracy. A comparison chart displaying the performance of eight different supervised learning algorithms in terms of three existing encoding mechanisms is reported. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Chest X-Ray Report Generation Through Fine-Grained Label learning 23rd

Chest X-Ray Report Generation Through Fine-Grained Label Lea...

引用

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Syeda-Mahmood, Tanveer Wong, Ken C. L. Gur, Yaniv Wu, Joy T. Jadhav, Ashutosh Kashyap, Satyananda Karargyris, Alexandros Pillai, Anup Sharma, Arjun Syed, Ali Bin Boyko, Orest Moradi, Mehdi IBM Almaden Research Center San JoseCA United States

ISBN: (纸本)9783030597122

Obtaining automated preliminary read reports for common exams such as chest X-rays will expedite clinical workflows and improve operational efficiencies in hospitals. However, the quality of reports generated by current automated approaches is not yet clinically acceptable as they cannot ensure the correct detection of a broad spectrum of radiographic findings nor describe them accurately in terms of laterality, anatomical location, severity, etc. In this work, we present a domain-aware automatic chest X-ray radiology report generation algorithm that learns fine-grained description of findings from images and uses their pattern of occurrences to retrieve and customize similar reports from a large report database. We also develop an automatic labeling algorithm for assigning such descriptors to images and build a novel deep learning network that recognizes both coarse and fine-grained descriptions of findings. The resulting report generation algorithm significantly outperforms the state of the art using established metrics. © 2020, Springer Nature Switzerland AG.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Independent learning in Cooperative Markov Games 1

引用

2nd International Conference on Distributed Artificial Intelligence, DAI 2020

作者： Yehoshua, Roi Amato, Christopher Northeastern University BostonMA02115 United States

ISBN: (数字)9783030640965

ISBN: (纸本)9783030640958

Independent agents learning by reinforcement must overcome several difficulties, including non-stationarity, miscoordination, and relative overgeneralization. An independent learner may receive different rewards for the same state and action at different time steps, depending on the actions of the other agents in that state. Existing multi-agent learning methods try to overcome these issues by using various techniques, such as hysteresis or leniency. However, they all use the latest reward signal to update the Q function. Instead, we propose to keep track of the rewards received for each state-action pair, and use a hybrid approach for updating the Q values: the agents initially adopt an optimistic disposition by using the maximum reward observed, and then transform into average reward learners. We show both analytically and empirically that this technique can improve the convergence and stability of the learning, and is able to deal robustly with overgeneralization, miscoordination, and high degree of stochasticity in the reward and transition functions. Our method outperforms state-of-the-art multi-agent learning algorithms across a spectrum of stochastic and partially observable games, while requiring little parameter tuning. © 2020, Springer Nature Switzerland AG.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Transfer learning via l1 regularization 34

Transfer learning via l1 regularization

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Takada, Masaaki Fujisawa, Hironori Toshiba Corporation Tokyo105-0023 Japan The Institute of Statistical Mathematics Tokyo190-8562 Japan

Machine learning algorithms typically require abundant data under a stationary environment. However, environments are nonstationary in many real-world applications. Critical issues lie in how to effectively adapt models under an ever-changing environment. We propose a method for transferring knowledge from a source domain to a target domain via l1 regularization in high dimension. We incorporate l1 regularization of differences between source parameters and target parameters, in addition to an ordinary l1 regularization. Hence, our method yields sparsity for both the estimates themselves and changes of the estimates. The proposed method has a tight estimation error bound under a stationary environment, and the estimate remains unchanged from the source estimate under small residuals. Moreover, the estimate is consistent with the underlying function, even when the source estimate is mistaken due to nonstationarity. Empirical results demonstrate that the proposed method effectively balances stability and plasticity. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Procedure Completion by learning from Partial Summaries 31

Procedure Completion by Learning from Partial Summaries

引用

31st British Machine Vision Conference, BMVC 2020

作者： Naing, Zwe Elhamifar, Ehsan MCADS Lab Khoury College of Computer Sciences Northeastern University BostonMA United States

We address the problem of procedure completion in videos, which is to find and localize all key-steps of a task given only a small observed subset of key-steps. We cast the problem as learning summarization from partial summaries that allows to incorporate prior knowledge and learn from incomplete key-steps. Given multiple pairs of (video, subset of key-steps), we address the problem by learning representations of input data and finding the remaining key-steps that generalizes well to key-step discovery in new videos. We propose a loss function on the parameters of a network that promotes to recover unseen key-steps that together with the observed key-steps optimize a desired subset selection criterion. To tackle the highly non-convex learning problem, involving both discrete and continuous variables, we develop an efficient learning algorithm that alternates between representation learning and recovering unseen key-steps while incorporating prior knowledge, via a greedy algorithm. By extensive experiments on two instructional video datasets, we show the effectiveness of our framework. © 2020. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： learning algorithms

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：