检索结果-内蒙古大学图书馆

13th International Conference on Educational data Mining, EDM 2020

作者： Dumbach, Philipp Aly, Alexander Zrenner, Markus Eskofier, Bjoern M. Machine Learning and Data Analytics Lab Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg Carl-Thiersch-Str. 2b Erlangen91052 Germany

ISBN: (纸本)9781733673617

The increasing complexity in software development leads to the necessity for a detailed data analysis. Literature illustrates a stronger research focus on Educational Process Mining (EPM) being applied to the fields of e-learning and professional training. In this work, the opportunities of Process Mining (PM) are further examined by the evaluation of software engineering (SE) courses. The methodology follows the five stages of the L* life cycle model for PM projects using data from software repositories. The event log data was analyzed with the PM tool Disco to examine the students’ work following an agile development process. The new tool GitLab Analyser supports supervisors to visualize educational processes and still extracts event logs for the further analysis and application of PM techniques. © 2020 Proceedings of the 13th International Conference on Educational data Mining, EDM 2020. All rights reserved.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

On Aggregation in Ensembles of Multilabel Classifiers 23rd

On Aggregation in Ensembles of Multilabel Classifiers

引用

23rd International Conference on Discovery science, DS 2020

作者： Nguyen, Vu-Linh Hüllermeier, Eyke Rapp, Michael Loza Mencía, Eneldo Fürnkranz, Johannes Heinz Nixdorf Institute and Department of Computer Science Paderborn University Paderborn Germany Knowledge Engineering Group TU Darmstadt Darmstadt Germany Computational Data Analytics Group JKU Linz Linz Austria

ISBN: (纸本)9783030615260

While a variety of ensemble methods for multilabel classification have been proposed in the literature, the question of how to aggregate the predictions of the individual members of the ensemble has received little attention so far. In this paper, we introduce a formal framework of ensemble multilabel classification, in which we distinguish two principal approaches: "predict then combine" (PTC), where the ensemble members first make loss minimizing predictions which are subsequently combined, and "combine then predict" (CTP), which first aggregates information such as marginal label probabilities from the individual ensemble members, and then derives a prediction from this aggregation. While both approaches generalize voting techniques commonly used for multilabel ensembles, they allow to explicitly take the target performance measure into account. Therefore, concrete instantiations of CTP and PTC can be tailored to concrete loss functions. Experimentally, we show that standard voting techniques are indeed outperformed by suitable instantiations of CTP and PTC, and provide some evidence that CTP performs well for decomposable loss functions, whereas PTC is the better choice for non-decomposable losses. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Implementing a Nordic-Baltic Federated Health data Network: a case report

arXiv

引用

arXiv 2024年

作者： Chomutare, Taridzo Babic, Aleksandar Peltonen, Laura-Maria Elunurm, Silja Lundberg, Peter Jönsson, Arne Eneling, Emma Gerstenberger, Ciprian-Virgil Siggaard, Troels Kolde, Raivo Jerdhaf, Oskar Hansson, Martin Makhlysheva, Alexandra Muzny, Miroslav Ylipää, Erik Brunak, Søren Dalianis, Hercules Health Data Analytics Norwegian Centre for E-health Research Tromsø Norway Department of Computer Science UiT The Arctic University of Norway Tromsø Norway Group Research and Development DNV Høvik1322 Norway Department of Health and Social Management University of Eastern Finland and Wellbeing services county of North Savo Kuopio Finland Department of Nursing Science University of Turku and Research Services Wellbeing Services County of Southwest Turku Finland Institute of Computer Science University of Tartu Tartu Estonia Department of Radiation Physics Department of Medical and Health Sciences Linköping University Linköping Sweden Linköping University Linköping Sweden Novo Nordisk Foundation Center for Protein Research Faculty of Health and Medical Sciences University of Copenhagen Copenhagen Denmark Stockholm University Stockholm Sweden Institute of Family Medicine and Public Health University of Tartu Tartu Estonia Department of Computer and Information Science Linköping University Linköping Sweden

Background: Centralized collection and processing of healthcare data across national borders pose significant challenges, including privacy concerns, data heterogeneity and legal barriers. To address some of these challenges, we formed an interdisciplinary consortium to develop a federated health data network, comprised of six institutions across five countries, to facilitate Nordic-Baltic cooperation on secondary use of health data. The objective of this report is to offer early insights into our experiences developing this network. Methods: We used a mixed-method approach, combining both experimental design and implementation science to evaluate the factors affecting the implementation of our network. Results: Technically, our experiments indicate that the network functions without significant performance degradation compared to centralized simulation. Conclusion: While use of interdisciplinary approaches holds a potential to solve challenges associated with establishing such collaborative networks, our findings turn the spotlight on the uncertain regulatory landscape playing catch up and the significant operational costs. Copyright © 2024, The Authors. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

data driven VRP: A neural network model to learn hidden preferences for VRP

arXiv

引用

arXiv 2021年

作者： Mandi, Jayanta Canoy, Rocsildes Bucarey, Víctor Guns, Tias Data Analytics Laboratory Vrije Universiteit Brussel Belgium Institute of Engineering Sciences Universidad de o'Higgins Rancagua Chile Department of Computer Science Ku Leuven Belgium

The traditional Capacitated Vehicle Routing Problem (CVRP) minimizes the total distance of the routes under the capacity constraints of the vehicles. But more often, the objective involves multiple criteria including not only the total distance of the tour but also other factors such as travel costs, travel time, and fuel consumption. Moreover, in reality, there are numerous implicit preferences ingrained in the minds of the route planners and the drivers. Drivers, for instance, have familiarity with certain neighborhoods and knowledge of the state of roads, and often consider the best places for rest and lunch breaks. This knowledge is difficult to formulate and balance when operational routing decisions have to be made. This motivates us to learn the implicit preferences from past solutions and to incorporate these learned preferences in the optimization process. These preferences are in the form of arc probabilities, i.e., the more preferred a route is, the higher is the joint probability. The novelty of this work is the use of a neural network model to estimate the arc probabilities, which allows for additional features and automatic parameter estimation. This first requires identifying suitable features, neural architectures and loss functions, taking into account that there is typically few data available. We investigate the difference with a prior weighted Markov counting approach, and study the applicability of neural networks in this setting. © 2021, CC BY-NC-SA.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm to Classify the Mitotic Cell using Ant Colony Algorithm

An Efficient Algorithm to Classify the Mitotic Cell using An...

引用

computer, Power and Communications (ICCPC), International Conference on

作者： R.G. Vidhya J. Seetha Sudhir Ramadass S. Dilipkumar Ajith Sundaram G. Saritha Department of ECE HKBK College of Engineering Bangalore India Department of Computer science and Business systems Panimalar Engineering College Chennai India Data analyst Sterck systems Chennai Department of Analytics Scope VIT Vellore Selection grade School of Business Kochi Department of ECE Sri Sai Ram institute of technology Chennai Tamilnadu India

Cancer that originates in the breast tissue then spreads to the chest wall is called breast cancer. Doctors routinely examine mammograms for signs of cancer; however, aberrant macrocalcifications and microcalcifications might appear on mammograms when the picture quality is subpar. Always get checked out if you see anything out of the ordinary, especially if it involves your breasts, such abnormal calcium deposits. For this mammographic deposit to be properly interpreted, top-notch picture quality is necessary. Many different breast cancer screening methods and the many breast cancer phases are still the subject of active study. In order to construct effective medical image processing systems, experts use methods including the Ant Colony Algorithm (ACA), the Improved Adaptive Fuzzy C-Means (IAFCM), and TNM (the size of the breast tumor (T), the lymph nodes around the tumor, and metastasized). Classes were determined using an MPIG, or a modified Poisson inverse gradient classifier. More than five hundred picture modalities are used across all methods. Medical professionals that rely on images to establish diagnoses or treatments might find the results of this research useful.

关键词： Image segmentation Sensitivity Breast tissue Medical services Feature extraction Breast cancer Mammography

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Clan Updated Grey Wolf Optimization (CU-GWO) based Deep Ensemble Technique for Identifying Sarcasm from Social Media data

Performance Analysis of Clan Updated Grey Wolf Optimization ...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Geeta Abakash Sahu Manoj Hudnurkar Faculty of Computer Studies (FoCS) Symbiosis Center for Research and Innovation(SCRI) Symbiosis International (Deemed University)(SIU) Pune Maharashtra India Department of Information Technology and Data Science Vidyalankar School of Information Technology (VSIT) Mumbai India Operations and Analytics Symbiosis Centre for Management and Human Resource Development(SCMHRD) Symbiosis International (Deemed University) (SIU) Pune Maharashtra India

Sarcasm is often considered as a prevalent linguistic element in online content that conveys strongly held subjectivity and viewpoints. The detection of sarcasm is a significant consideration over the dominant NLP appliances as sentiment analysis, which is utilizing for advertising and opinion mining is a precious tool for figuring out the people sentiments and attitudes. The proposed approach describes automatic detection of sarcasm as an ease classification of text challenges. This paper aims to develop a sarcasm detection model that categorizes words into either sarcastic or non-sarcastic expressions. Initially, the text input involves processing, here the stop word removal and tokenization process are carried out. Subsequently, various features like information gain, chisquare, mutual information, and symmetrical uncertaintybased features are extracted from the preprocessed data. The curse of dimensionality is a crucial issue, thereby the selection of optimal features is conducted by employing hybrid optimization model called Clan Updated Grey Wolf Optimization (CU-GWO). The optimal features are utilized for sarcasm detection by using ensemble technique. The ensemble techniques involve the classifiers such as NN, SVM, RF and DCNN. The final output of DCNN indicates whether the sarcasm is present. The effectiveness of the proposed approach demonstrated through diverse metrices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fair and explainable Myocardial Infarction (MI) prediction: Novel strategies for feature selection and class imbalance correction

引用

computers in Biology and Medicine 2025年 184卷 109413-109413页

作者： Akter, Simon Bin Akter, Sumya Tuli, Moon Das Eisenberg, David Lotvola, Aaron Islam, Humayera Fernandez, Jorge Fresneda Hüttemann, Maik Pias, Tanmoy Sarkar Martin Tuchman School of Management New Jersey Institute of Technology Newark NJ07102 United States Greenlife Medical College & Hospital Dhaka Bangladesh Department of Computer Science Virginia Tech College of Engineering BlacksburgVA United States Institute for Data Science and Informatics University of Missouri Columbia United States Department of Biochemistry Microbiology and Immunology Wayne State University School of Medicine DetroitMI United States Department of Information Management and Business Analytics Montclair State University Feliciano School of Business NJ United States Department of Oncology Wayne State University School of Medicine DetroitMI United States Center for Molecular Medicine and Genetics Wayne State University School of Medicine DetroitMI United States

The rising incidences of myocardial infarction (MI), often affecting individuals without traditional risk factors, highlight the urgent need for improved early detection using personal health data. However, health surveys and electronic health records (EHRs) frequently suffer from class imbalances, leading to prediction biases and differences between specificity and sensitivity, which hinder reliable model development despite the valuable insights contained in these datasets. To address this, we have introduced a novel approach to enhance MI risk prediction using self-reported attributes from the Behavioral Risk Factor Surveillance System (BRFSS) and the National Health Interview Survey (NHIS) dataset. Our approach incorporates three innovative techniques: the Dual-Path Artificial Neural Network (DP-ANN) to mitigate biased decision making across imbalanced datasets, the Triple Criteria Selection (TCS) for unbiased feature selection, and Minority Weighted Sampling (MWS) to tackle challenges of uncontrolled minority class sampling. These methods collectively enhance MI prediction and feature relevance. The DP-ANN model has achieved balanced performance, with an average specificity of 80%, sensitivity of 82%, and AUC–ROC of 89.5%, improving imbalance variance by approximately 14.96% compared to prior studies. By outperforming other models across four heavily imbalanced datasets, our approach demonstrates robustness and generalizability. Additionally, SHapley Additive exPlanations (SHAP) analysis has revealed key predictors and risk factors for MI, such as coronary heart disease and bronchitis in females, and stroke among individuals aged 35–54. In conclusion, our study provides a robust model for healthcare professionals to assess MI risk through targeted factors, promoting early detection and potentially improving patient outcomes. © 2024

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Candidate selection and instance ordering for realtime algorithm configuration

Candidate selection and instance ordering for realtime algor...

引用

作者： Fitzgerald, Tadhg O'Sullivan, Barry Insight Centre for Data Analytics Department of Computer Science University College Cork Cork Ireland Insight Centre for Data Analytics Department of Computer Science University College Cork Western Road Cork Ireland

Many modern combinatorial solvers have a variety of parameters through which a user can customise their behaviour. Algorithm configuration is the process of selecting good values for these parameters in order to improve performance. Time and again algorithm configuration has been shown to significantly improve the performance of many algorithms for solving challenging computational problems. Automated systems for tuning parameters regularly out-perform human experts, sometimes but orders of magnitude. Online algorithm configurators, such as ReACTR, are able to tune a solver online without incurring costly offline training. As such ReACTR's main focus is on runtime minimisation while solving combinatorial problems. To do this ReACTR adopts a one-pass methodology where each instance in a stream of instances to be solved is considered only as it arrives. As such ReACTR's performance is sensitive to the order in which instances arrive. It is still not understood which instance orderings positively or negatively effect the performance of ReACTR. This paper investigates the effect of instance ordering and grouping by empirically evaluating different instance orderings based on difficulty and feature values. Though the end use is generally unable to control the order in which instances arrive it is important to understand which orderings impact Re- ACTR's performance and to what extent. This study also has practical benefit as such orderings can occur organically. For example as business grows the problems it may encounter, such as routing or scheduling, often grow in size and difficulty. ReACTR's performance also depends strongly configuration selection procedure used. This component controls which configurations are selected to run in parallel from the internal configuration pool. This paper evaluates various ranking mechanisms and different ways of combining them to better understand how the candidate selection procedure affects realtime algorithm configuration. We show

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

An analytics-driven framework for securing industrial IoT-Enabled Supply Chain Management Systems

Supply Chain Analytics

引用

Supply Chain analytics 2025年 11卷

作者： Naveen Saran Nishtha Kesswani Department of Computer Science Central University of Rajasthan NH-8 Bandarsindri Kishangarh Ajmer 305817 Rajasthan India Department of Data Science & Analytics Central University of Rajasthan NH-8 Bandarsindri Kishangarh Ajmer 305817 Rajasthan India

In today’s dynamic technological environment, the integration of IoT into Supply Chain Management Systems (SCMS) has significantly enhanced functionality, visibility, and decision-making. However, integrating Industrial-IoT (IIoT) with Supply Chain Networks (SCN) is an equally significant security concern because of interconnected systems amplified exposure and complexity. This study proposes an original Intrusion Detection System (IDS) framework based on the Staked Ensemble Model appropriate for IIoT-Enabled SCMS. A stacked ensemble model-based IDS framework operates as a novel solution to protect IIoT-Enabled SCMS. A multilayered system unites Extreme Gradient Boosting (XGBoost) with Light Gradient Boosting Machine (LightGBM) along with Deep Neural Networks (DNN) as a stacked ensemble design to enable decentralized and secure collaborative learning across the supply chain network and protect user data and maintain system stability as well as network reliability. On the other hand, Synthetic Minority Oversampling Technique (SMOTE) and Principal Component Analysis (PCA) are established techniques, and our contribution is in optimizing the application of those for IIoT traffic. We tackle the class imbalance in intrusion data with SMOTE to better detect rare attacks and to use PCA to reduce the high dimensions of feature space for less computational effort and more efficient pattern recognition. To meet the requirements of the IIoT use cases, these preprocessing techniques are effectively embedded in the framework. Moreover, the proposed modular IDS architecture, the curation and fine tuning of the various learners, and the approach to full validation are all novel. We rigorously evaluate the model under K-Fold Cross Validation using the IoT-23 dataset and prove superior detection performance when compared to state-of-the-art approaches. Specifically, this research contributes a scalable and efficient IDS for an IIoT scenarios such as real-world IIoT enabled SCMS, whi

关键词： Supply chain security Industrial-IoT analytics Intrusion detection systems data pre-processing techniques Collaborative learning models Predictive analytics for supply chains

来源：评论

学校读者我要写书评

暂无评论

Asynchronous distributed clustering algorithm for wireless sensor networks 2019

Asynchronous distributed clustering algorithm for wireless s...

引用

4th International Conference on Machine Learning Technologies, ICMLT 2019

作者： Qiao, Cheng Brown, Kenneth N. Insight Centre for Data Analytics Department of Computer Science University College Cork Ireland

ISBN: (纸本)9781450363235

In distributed clustering problems, nodes in a wireless sensor network must learn clusters from the data sensed across the network, without centralising the raw data. This paper presents an asynchronous distributed clustering algorithm for sensors to learn the global clusters, while respecting data privacy, and balancing communication cost and clustering quality. Different clustering algorithms including k-means and Gaussian Mixture Models, and different methods of summarising clusters to exchange between nodes are considered. In experiments on randomly generated network topologies, we demonstrate that methods which do more extensive clustering in each cycle, and which exchange descriptions of cluster shape and density instead of just centroids and data counts, achieve more consistent clustering, in significantly shorter elapsed time. © 2019 ACM.

关键词： Parallel 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：