检索结果-内蒙古大学图书馆

11th International Conference on the Practice and Theory of Automated Timetabling, PATAT 2016

作者： Gogos, Christos Valouxis, Christos Alefragis, Panayiotis Xanthopoulos, Iordanis Housos, Efthymios Technological Educational Institute of Epirus Department of Computer and Informatics Engineering Laboratory of Knowledge and Intelligent Computing Arta Greece Ministry of Education Achaia Branch Office Patras Greece Technological Educational Institute of Western Greece Department of Computer and Informatics Engineering Patras Greece University of Patras Department of Electrical and Computer Engineering Patras Greece

ISBN: (纸本)9780992998417

Scheduling tasks on a set of heterogeneous machines is a problem with both theoretical and practical interest. In this paper, the problem of scheduling independent tasks while trying to optimize four different objectives is studied. These objectives are makespan, flowtime, resource utilization and matching proximity. Four mathematical models are presented that optimize each individual objective. Then, certain objectives are combined forming a weighted sum single objective in order to reach good compromise solutions. A number of experiments were undertaken that demonstrated the applicability of using a mathematical integer programming solver in solving several instances of the problem. An interesting result is that when makespan is the single objective, as a side-effect, high resource utilization is obtained also. © PATAT *** rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network Based Sperm Detection in Microscopic Videos

Deep Convolutional Neural Network Based Sperm Detection in M...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2023

作者： Ma, Shiyi Li, Jindong Zhang, Wenbo Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

In recent years, with the increasingly serious quality problems of human sperm, the performance of traditional sperm analysis methods has been unable to meet the growing demand for diagnosis and treatment. The purpose of this study was to explore the application of deep convolutional neural network microvideo in computer assisted sperm analysis (CASA). For the sperm detection task, the model structure, loss function and non-maximum suppression algorithm were optimized to improve the performance of the model, reflecting the advantages of deep learning. To avoid the impact of data differences, cross-validation test was adopted in this study, and multiple indexes such as F1-score and AP were compared with the original model after training. These improvements significantly improved the average accuracy and F1 scores of the models. The performance of the model not only has an important impact on the indicators of the target detection model, but also has an important impact on the visualization results of the model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Medical Decision Support Systems based on Soft computing techniques

引用

IFAC Proceedings Volumes 2011年第1期44卷 14115-14120页

作者： Chrysostomos D. Stylios Voula C. Georgopoulos Knowledge and Intelligent Computing Laboratory Dept. of Informatics and Telecommunications Technology Technological Educational Institute of Epirus 47100 Artas Greece (+***) Department of Speech and Language Therapy Technological Educational Institute of Patras Koukouli 26334 Patras Greece

Abstract Medical Decision Support Systems (MDSS) are very important constructions that are incorporated into intelligent Information E-Health Systems aiming to produce warnings or to consult and suggest clinical judgments either to inexperienced medical professionals or in their lighter versions to the general public through medical advisors websites. Soft computing (SC) techniques, especially those that are based on exploiting human knowledge and experience, are extremely useful to model complex decision making procedures and thus, they have a key role in development such MDSS. Such a modeling methodology is Fuzzy Cognitive Maps which is suitable to represent human reasoning and to infer conclusions and decisions in a human-like way. In order to develop an integrated stand alone MDSS, Fuzzy Cognitive Maps could be complemented by other Soft computing techniques such as Genetic Algorithms and/or Case Based Reasoning and so to construct more efficient advanced Medical Decision Support Systems. The synergism and complementary of these methodologies may pave the way to new sophisticated systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Order Conditional Random Field Based Cervical Cancer Histopathological Image Classification

High Order Conditional Random Field Based Cervical Cancer Hi...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2023

作者： Zhou, Shangqi Li, Xintong Fu, Yanyu Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Cervical cancer ranks as the fourth most frequently diagnosed cancer. This disease has an extended precancerous stage and can be completely cured and prevented through early detection. Currently, the analysis of histopathological images of cervical cancer relies on manual assessment by pathologists, a subjective and time-consuming process. Moreover, there is limited research on differentiating the severity of cervical cancer in histopathological images. To address these challenges, this study proposes a classification algorithm based on high-order conditional random field for cervical cancer histopathologic images. The algorithm effectively categorizes images into high differentiation, medium differentiation, and low differentiation stages. Three deep learning models, namely VGG-16, Inception-V3, and ResNet-50, are utilized for pre-classification at the image block level. For image-level classification, the Visual Transformer model is employed. Finally, the block-level and image-level classification components are integrated using the conditional random field model, resulting in the high-order conditional random field model. Following training and testing using the dataset, the model achieves an overall accuracy of 75.4%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Multiple Machine Learning Fusion Based Analysis of Fat Composition in CT Images

Multiple Machine Learning Fusion Based Analysis of Fat Compo...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2023

作者： Fu, Yanyu Quanyu, E. Zhou, Shangqi Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Intra-abdominal fat is a crucial factor in determining metabolic syndrome and insulin resistance. Therefore, high levels of intra-abdominal fat are always accompanied by a series of diseases such as diabetes, ischemia, hypertension, and dyslipidemia. Although methods such as the ultrasonic method and electrical impedance method have been widely used to calculate body fat tissue in recent years, these methods only provide qualitative analysis of the overall degree of obesity. However, for quantitative analysis of abdominal fat and adipose tissue distribution in the human body, the computed tomography (CT) fat segmentation method is necessary. This paper focuses on machine learning, image segmentation, and multi-feature fusion of mean clustering as its main technical directions. In terms of application, it aims to perform a quantitative analysis of the distribution and proportion of intra-abdominal fat in the abdominal cavity of the human body. The study concluded that the quantitative analysis of fat after the fusion method is more accurate, with a subcutaneous fat accuracy rate of 84.26% and a visceral fat accuracy rate of 70.20%. It can effectively, conveniently, and objectively analyze the degree of obesity in the human body. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Develop Fuzzy Cognitive Maps based on recorded data and information

Develop Fuzzy Cognitive Maps based on recorded data and info...

引用

IEEE International Conference on Fuzzy Systems

作者： Chrysostomos Stylios Voula C. Georgopoulos Knowledge and Intelligent Computing Laboratory Computer Engineering Depart. Technological Educational Institute of Epirus INTERACT Lab School of Health & Welfare Professions Technological Educational Institute of Western Greece

ISBN: (纸本)9781467374293

This work presents a novel integrated approach on how to develop Fuzzy Cognitive Maps combining human expert knowledge with existing recorded information and historical data. The proposed approach aims to extract information from unstructured data and to transform it into knowledge in the form of a FCM. The proposed approach still is dependent on experts but providing them with more information and supportive data, in the form of particular evidence-based information available in the literature in order to better justify their selections. The proposed approach is inherit to the FCM and its structure the extracted knowledge and it can be used to model a complex system such as the Medical Decision Support Systems.

关键词： Fuzzy Cognitive Maps knowledge extraction Historical data Case based Soft computing

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Linear and non-linear features for intrapartum cardiotocography evaluation

Linear and non-linear features for intrapartum cardiotocogra...

引用

作者： Chudáček, Václav Spilka, Jiří Huptych, Michal Georgoulas, George Lhotská, Lenka Stylios, Chrysostomos Koucký, Michal Janků, Petr Department of Cybernetics Czech Technical University in Prague Technická 2 Praha 6 166 27 Czech Republic Laboratory of Knowledge and Intelligent Computing TEI of Epirus Artas Greece Obstetrics and Gynaecology Clinic Medical Faculty of Charles University Prague Czech Republic Obstetrics and Gynaecology Clinic University Hospital in Brno Czech Republic

ISBN: (纸本)9781424473182

Since 1960's obstetricians have been using cardiotocography (CTG) to detect possible ongoing hypoxia of the fetus. CTG consists of fetal heart rate (fHR) and uterine contraction (TOCO) monitoring. The evaluation of the fHR in clinical settings is ruled by FIGO guidelines, which are based on evaluation of macroscopic morphological features derived from the fHR, such as baseline variability. Although upgrades were proposed to the guidelines - none of them is taking into account results achieved by the adult heart rate variability research. In this work, almost complete set of features previously used for fHR description is investigated and the features are assessed based on their statistical significance in the task of distinguishing the records into three FIGO classes. Inter-correlation of the features is also discussed. We assess the features on a large data set and use expert signal evaluation instead of pH values with the aim to give an overall view of the potential usefulness of the features in the clinical settings. We conclude the paper by presenting the best uncorrelated feature subset according to the meta-analysis of three different ranking methods.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Principal Component Analysis Anomaly Detector for Rotor Broken Bars

Principal Component Analysis Anomaly Detector for Rotor Brok...

引用

Annual Conference of the IEEE Industrial Electronics Society

作者： Mohammed Obaid Mustafa George Georgoulas George Nikolakopoulos Control Engineering Group Department of Computer Science Electrical and Space Engineering Lulea University of Technology Laboratory of Knowledge and Intelligent Computing (KIC) Department of Computer Engineering Technological Educational Institute of Epirus

ISBN: (纸本)9781479940318

In this article a method for the detection of broken rotor bars in asynchronous machines operating under full load is presented. Unlike most Motor Current Signature Analysis (MCSA) approaches, which operate in the frequency domain, our method operates in the time domain. The scheme is based on the use of a Principal Component Analysis (PCA) fault/anomaly detector. PCA is applied on the three stator currents to subsequently calculate the Q statistic which is employed for detecting the presence/absence of a fault. The efficiency of the proposed scheme was experimentally evaluated using different fault severity levels, ranging from 1/4 of a broken bar to three broken bars. The obtained results indicate that the method can detect the caused asymmetry with a very restricted amount of data.

关键词： Principal component analysis Rotors Bars Induction motors Detectors Stators Fault 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：