检索结果-内蒙古大学图书馆

REAL-TIME TRACKING OF PARAMETERS OF LUNG-MECHANICS - EMPHASIS ON algorithm tuning

JOURNAL OF BIOMEDICAL ENGINEERING 1990年第6期12卷 489-495页

作者： AVANZOLINI, G BARBINI, P CAPPELLO, A CEVENINI, G UNIV SIENA IST CHIRURG TORACICA & CARDIOVASC SEZ BIOINGN VIALE BRACCI I-53100 SIENA ITALY

We consider the problem of tracking rapid changes in the viscous and elastic properties of the respiratory system by using mouth flow and transpulmonary pressure data measured during mechanical ventilation. A recursive least-squares algorithm with adjustable compensator is used for online estimation of an R-C model of the breathing mechanics. Specific simulation experiments are presented to provide guidelines to select suitable values for the key variable, which controls the compromise between tracking ability and noise sensitivity. The results obtained confirm the critical role of the optimum tuning in relation to the noise level. Experimental results obtained from data measured on mechanically-ventilated dogs, in which respiratory distress syndrome was intravenously induced by oleic acid, demonstrate that the tuned algorithm is able to track appropriately both the viscous and elastic properties of lung mechanics. Paramter estimates are consistent with those obtained by standard and robust offline algorithms and their time course is in qualitative agreement with known physiopathological behaviour.

关键词： Lung mechanics modelling online identification algorithm tuning

来源：评论

学校读者我要写书评

暂无评论

Competitive-Adaptive algorithm-tuning of Metaheuristics inspired by the Equilibrium Theory: A Case Study

Competitive-Adaptive Algorithm-Tuning of Metaheuristics insp...

引用

IEEE Congress on Evolutionary Computation (CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Nishihara, Kei Nakata, Masaya Yokohama Natl Univ Coll Engn Yokohama Kanagawa Japan

ISBN: (纸本)9781728169293

This paper proposes a competitive-adaptive algorithm-tuning framework for metaheuristic algorithms. Our proposed method, called CAT, is inspired by the Equilibrium Theory in economics, which explains competitors eventually converge to an equilibrium status, e.g. in terms of the price of products. In detail, our proposal runs multiple optimizers with different algorithmic configurations, e.g. mutation variants. Then, the configurations of inferior optimizers are adaptively tuned so that they can derive good solutions that superior ones have derived. This intends to boost the performance even with a limited number of fitness evaluations, by the following technical advantage. The CAT preliminarily validates a search capacity of tuned algorithmic configurations and then constructs an ensemble optimizer by utilizing multiple optimizers. As a case study, this paper applies the CAT to tune the differential evolution algorithms (DEs). Experimental results show that our proposal outperforms the standard DE and an alternative approach i.e. jDE, which adapts hyper-parameters of genetic operators.

关键词： self-adaptation algorithm tuning differential evolution

来源：评论

学校读者我要写书评

暂无评论

Selection and tuning of a Fast and Simple Phase-Contrast Microscopy Image Segmentation algorithm for Measuring Myoblast Growth Kinetics in an Automated Manner

引用

MICROSCOPY AND MICROANALYSIS 2013年第4期19卷 855-866页

作者： Juneau, Pierre-Marc Garnier, Alain Duchesne, Carl Univ Laval Dept Chem Engn Quebec City PQ G1V 0A6 Canada

Acquiring and processing phase-contrast microscopy images in wide-field long-term live-cell imaging and high-throughput screening applications is still a challenge as the methodology and algorithms used must be fast, simple to use and tune, and as minimally intrusive as possible. In this paper, we developed a simple and fast algorithm to compute the cell-covered surface (degree of confluence) in phase-contrast microscopy images. This segmentation algorithm is based on a range filter of a specified size, aminimum range threshold, and aminimum object size threshold. These parameters were adjusted in order to maximize the F-measure function on a calibration set of 200 hand-segmented images, and its performance was compared with other algorithms proposed in the literature. A set of one million images from 37 myoblast cell cultures under different conditions were processed to obtain their cell-covered surface against time. The data were used to fit exponential and logistic models, and the analysis showed a linear relationship between the kinetic parameters and passage number and highlighted the effect of culture medium quality on cell growth kinetics. This algorithm could be used for real-time monitoring of cell cultures and for high-throughput screening experiments upon adequate tuning.

关键词： phase-contrast microscopy live-cell imaging segmentation cell-covered surface degree of confluence myoblasts growth kinetics passage number algorithm tuning algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised tuning for Drift Detectors Using Change Detector Segmentation

引用

IEEE ACCESS 2024年 12卷 54256-54271页

作者： Silva, Ricardo Petri Junior, Sylvio Barbon Zarpelao, Bruno Bogaz De Melo, Leonimer Flavio Univ Estadual Londrina Dept Elect Engn BR-86057970 Londrina Brazil Univ Trieste Dept Engn & Architecture I-34127 Trieste Italy Univ Estadual Londrina Dept Comp Sci Londrina Brazil

Concept drifts can occur due to various factors such as changes in the environment or sensor degradation, posing significant challenges to machine learning systems by potentially skewing decision-making processes. Therefore, detecting drifts is essential to maintain the integrity and functionality of these systems. Automatic detectors based on statistical information are usually used to accomplish this task. Optimizing drift detectors through tuning is crucial for effective concept drift analysis. However, relying on user expertise or labeled data for supervised tuning can be challenging. In such cases, the use of unsupervised tuning methods becomes a suitable alternative to adapt detectors to evolving data distributions. To address this gap in the literature an unsupervised tuning method was proposed, leveraging a time series segmentation method. This innovative approach aims to alleviate the reliance on labeled data or user expertise traditionally associated with supervised methods, offering a more adaptive and automated means of tuning detectors. Our results demonstrate that our proposed approach outperforms the default configuration in most evaluated cases. Furthermore, we show that our approach can improve the hyperparameter tuning process when the type of drift is known including supervised methods such as Random Search tuning. By adopting our approach, we can achieve better performance in drift detection and improve the accuracy and reliability of systems that rely on this critical task.

关键词： algorithm tuning concept drift signal drift drift detector

来源：评论

学校读者我要写书评

暂无评论

Comparing Ellipse Detection and Deep Neural Networks for the Identification of Drinking Glasses in Images 12th

Comparing Ellipse Detection and Deep Neural Networks for the...

引用

12th International Conference on Computer Vision Systems (ICVS)

作者： Jabbar, Abdul Mendes, Alexandre Chalup, Stephan Univ Newcastle Sch Elect Engn & Comp Callaghan NSW 2308 Australia

ISBN: (纸本)9783030349950;9783030349943

This study compares a deep learning approach with the traditional computer vision method of ellipse detection on the task of detecting semi-transparent drinking glasses filled with water in images. Deep neural networks can, in principle, be trained until they exhibit excellent performance in terms of detection accuracy. However, their ability to generalise to different types of surroundings relies on large amounts of training data, while ellipse detection can work in any environment without requiring additional data or algorithm tuning. Two deep neural networks trained on different image data sets containing drinking glasses were tested in this study. Both networks achieved high levels of detection accuracy, independently of the test image resolution. In contrast, the ellipse detection method was less consistent, greatly depending on the visibility of the top and bottom of the glasses, and water levels. The method detected the top of the glasses in less than half of the cases, at lower resolutions;and detection results were even worse for the water level and bottom of the glasses, in all resolutions.

关键词： Deep learning Computer vision Ellipse detection Drinking glasses Training data algorithm tuning Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Breast Cancer Detection 7

Machine Learning Techniques for Breast Cancer Detection

引用

7th International Conference on Complexity, Future Information Systems and Risk (COMPLEXIS)

作者： Hall, Karl Chang, Victor Mitchell, Paul Teesside Univ Sch Comp Engn & Digital Technol Middlesbrough Cleveland England Aston Univ Aston Business Sch Dept Operat & Informat Management Birmingham W Midlands England

ISBN: (纸本)9789897585654

Breast cancer is the second most prevalent type of cancer overall and the most frequently occurring cancer in women. The most effective way to improve breast cancer survival rates still lies in the early detection of the disease. An increasingly popular and effective way of doing this is by using machine learning to classify and analyze patient data to help identify signs of cancer. This paper explores a variety of machine learning techniques and compares their prediction accuracy and other metrics when using the Breast Cancer Wisconsin (Original) data set using 10-fold cross-validation methods. Of the algorithms tested in this paper, a support vector machine model using the radial basis function kernel outperformed all other models we tested and those previously developed by others, achieving an accuracy of 99%.

关键词： Cancer Diagnosis Machine Learning Support Vector Machine algorithm tuning

来源：评论

学校读者我要写书评

暂无评论

Towards a Faster Incremental Packrat Parser 12

Towards a Faster Incremental Packrat Parser

引用

12th International Conference on Information and Communication Technology and System (ICTS)

作者： Guillermo, Jerwin Mark L. Fernandez, Proceso L., Jr. Ateneo Manila Univ Dept Informat Syst & Comp Sci Quezon City Philippines

ISBN: (纸本)9781728121338

This work is an extension to the research done by Dubroy and Warth [1] on incremental packrat parsing. It attempts to further decrease the parse time of the incremental parser using two techniques from experimental algorithmics: algorithm and code tuning. Two modifications were introduced to the original incremental packrat parser: reduction of copy operations, and the use of an array of overlapping entries. Initial results showed that there is a significant difference between the parse times of the original parser (mu = 15.64ms, sigma = 69.29ms) and the modified parser (mu = 4.60ms, sigma = 69.53ms), with a t-score of t(890) = 52.26 and a p-value of 9.41 x 10(-274). This means that faster parse times are achieved when using the modified parser.

关键词： software engineering packrat parsing incremental packrat parsing experimental algorithmics code tuning algorithm tuning

来源：评论

学校读者我要写书评

暂无评论

Can We Use Small/Easy Problems to Tune algorithms for Large/Difficult Problems? 3

Can We Use Small/Easy Problems to Tune Algorithms for Large/...

引用

3rd International Conference on Intelligent Computing in Data Sciences (ICDS)

作者： Alkhalifah, Mashal Corne, David Heriot Watt Univ Dept Comp Sci Edinburgh EH14 4AS Midlothian Scotland

ISBN: (纸本)9781728100036

algorithm tuning is a thriving area of current research. tuning an algorithm involves a set of problem instances, called the 'training set', together with a procedure that modifies the parameters of the algorithm to improve its overall performance on the training set. tuning is invariably successful, improving subsequent performance on new problem instances. However, very little research has looked at the relationship between the composition of the training set and the algorithm's generalization performance. For example, if an algorithm is targeted at problems of a certain type, then we would expect that the training set should contain instances of the same type. Similarly, we would expect that to perform well on (say) large-scale problems, an algorithm needs to be tuned on large-scale instances. We explore such expectations, using subspaces of Traveling Salesperson Problem (TSP) instances as our testbed. In one experiment, we create TSP instances that vary in terms of a single parameter of spatial structure;in another experiment, the instances only vary in problem size (number of cities). In both experiments, a suite of algorithms is generated by tuning on each subspace, and each trained algorithm is then tested on every subspace. We find, in both experiments, that the prior expectations are clearly refuted. In particular, the difficulty of the training set (estimated by fitness-distance-correlation) seems to have no influence on the relationship between the training set and generalization performance (or, any such influence is swamped by other factors). Meanwhile, the best tuned algorithm for a given subspace is often one that was tuned on a different subspace;this includes several cases where the best algorithm for a given problem size was one tuned on a subspace of smaller problems. We conclude with consideration of the limitations of the current work, and speculate on the potential implications.

关键词： algorithm tuning parameter tuning combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of Optimization algorithms with R 12

Statistical Analysis of Optimization Algorithms with R

引用

14th International Conference on Genetic and Evolutionary Computation Conference (GECCO)

作者： Bartz-Beielstein, T. Preuss, Mike Zaefferer, Martin Clplus Cologne Univ Appl Sci Cologne Germany Tu Dortmund Algorithm Engn Dortmund Germany

ISBN: (纸本)9781450311786

Based on experiences from several (rather theoretical) tutorials and workshops devoted to the experimental analysis of algorithms at the world's leading conferences in the field of Computational Intelligence, a practical, hands-on tutorial for the statistical analysis of optimization algorithms is presented. This tutorial -demonstrates how to analyze results from real experimental studies, e.g., experimental studies in EC -item gives a comprehensive introduction in the R language -item introduces the powerful GUI "rstudio" (http://***) -exemplifies the analysis using SPOT (http://***/web/packages/SPOT/)R is the most attractive and fastest growing open source computer language for statistical computing and graphics in the world. It provides a wide variety of statistical and graphical techniques: linear and nonlinear modeling, statistical tests, time series analysis, classification, clustering, etc. R is distributed over CRAN (http://***), which is a network of ftp and web servers around the world that store identical, up-to-date, versions of code and documentation for R.

关键词： statistics optimization algorithm tuning

来源：评论

学校读者我要写书评

暂无评论

A Self-Aware tuning and Self-Aware Evaluation Method for Finite-Difference Applications in Reconfigurable Systems

引用

ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS 2014年第2期7卷 15-15页

作者： Niu, Xinyu Jin, Qiwei Luk, Wayne Weston, Stephen Univ London Imperial Coll Sci Technol & Med Dept Comp London SW7 2AZ England Maxeler Technol London England

Finite-difference methods are computationally intensive and required by many applications. Parameters of a finite-difference algorithm, such as grid size, can be varied to generate design space which contains algorithm instances with different constant coefficients. An algorithm instance with specific coefficients can either be mapped into general operators to construct static designs, or be implemented as constant-specific operators to form dynamic designs, which require runtime reconfiguration to update algorithm coefficients. This article proposes a tuning method to explore the design space to optimise both the static and the dynamic designs, and an evaluation method to select the design with maximum overall throughput, based on algorithm characteristics, design properties, available resources and runtime data size. For benchmark applications option pricing and Reverse-Time Migration (RTM), over 50% reduction in resource consumption has been achieved for both static designs and dynamic designs, while meeting precision requirements. For a single hardware implementation, the RTM design optimised with the proposed approach is expected to run 1.8 times faster than the best published design. The tuned static designs run thousands of times faster than the dynamic designs for algorithms with small data size, while the tuned dynamic designs achieve up to 5.9 times speedup over the corresponding static designs for large-scale finite-difference algorithms.

关键词： algorithm tuning finite-difference methods reconfigurable computing

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：