检索结果-内蒙古大学图书馆

Monte Carlo-based Strategy for Assessing the Impact of EEG Data Uncertainty on Confidence in Convolutional Neural Network Classification

引用

IEEE Access 2025年 13卷 85342-85362页

作者： Nzakuna, Pierre Sedi Gallo, Vincenzo Paciello, Vincenzo Lay-Ekuakille, Aime Lusala, Angelo Kuti University of Salerno Dpt. of Industrial Engineering Fisciano 84084 Italy University of Salento Dpt. of Engineering for Innovation Lecce 73100 Italy ISPT-Kin Dpt. of Electronics Kinshasa Congo University of Kinshasa Dpt. of Electrical and Computer Engineering Polytechnic Faculty Kinshasa Congo

Electroencephalography (EEG) data acquisition process in Brain-computer Interfaces (BCIs) is inevitably affected by uncertainty which introduces variability in the data. This variability, often over-looked, affects the training and testing of neural network (NN) models. This study evaluates the impact of systematic bias (±2%) plus aleatoric uncertainty (2–5% random Gaussian perturbations) on the classification confidence of the EEGNet model for four class-Motor Imagery (MI) tasks using the BCI Competition IV 2a dataset. Through two Monte Carlo simulations with 100 iterations each, perturbed datasets were generated to mimic real-world EEG acquisition uncertainties. Softmax outputs served to analyze overlap in predicted probabilities and quantify model confidence in classification decisions. We introduce robust evaluation metrics, including the proportion of area under the curve (AUC) of probability density functions (PDFs) ≥ 70% accuracy, overlap coefficients, and percentile-based thresholding, which provide a more comprehensive assessment of model performance, capturing not only accuracy but also confidence and ambiguity in predictions. Results show that the robustness of EEGNet in the face of realistic measurement uncertainties is prone to inter-subject variability, with the model achieving higher confidence for Subject 1 (average 90.52%) compared to Subject 2 (62.96%). EEGNet demonstrates resilience to directional calibration shifts in the data, with model confidence varying by 0.22% for Subject 1 and by 6.24% for Subject 2, showing that aleatoric precision errors dominate over small systematic shifts. Our approach provides a rigorous framework for quantifying the impact of measurement variability on EEG-based BCI classification, thereby enhancing reliability and generalizability in practical BCI deployments. © 2013 IEEE.

关键词： Brain-computer Interface (BCI) Classification confidence Convolutional Neural Network (CNN) Digital Signal Processing (DSP) Electroencephalography (EEG) Monte Carlo simulations motor imagery uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Results From a Large-Scale IoT-based Intervention for Energy Saving and Sustainability Awareness via Behavior Change in 25 K-12 Schools in Europe

引用

IEEE Internet of Things Journal 2025年

作者： Mylonas, Georgios Amaxilatis, Dimitrios Paganelli, Federica Chatzigiannakis, Ioannis Koulouris, Pavlos Falkouskaya, Yelizaveta Markopoulos, Panos Athena Research Center Industrial Systems Institute Patras26504 Greece Comp. Tech. Institute and Press "Diophantus" 26504 Greece Spark Works Ltd GalwayH91 AHR1 Ireland Univ. of Pisa Dpt. of Computer Science Pisa56127 Italy CNIT Florence50134 Italy Sapienza University of Rome Dpt. of Computer Control and Management Engineering 00185 Italy Ellinogermaniki Agogi Athens Greece Eindhoven University of Technology AI Systems Institute Industrial Design Noord-Brabant Eindhoven5612 AE Netherlands

The unfolding climate crisis has resulted in a rising interest for increasing sustainability awareness and achieving energy savings worldwide. Several interventions within educational environments have been aimed at mobilizing younger audiences towards such goals. However, most of the interventions carried out so far are based on a subset of possible tools (e.g., IoT monitoring, gamification) and offer "all or nothing"approaches, which do not cope well with the uniqueness of schools and the need to adapt interventions to specific contexts (e.g. school size, building, curriculum, teacher involvement). We present a large-scale intervention in 25 school buildings in Europe over the course of two school years. Our intervention was based on the installation of a relatively low-cost IoT infrastructure in schools, that produced real-time energy-related data from the school buildings involved, and the application of a strategy combining, in a flexible and customizable way, educational activities, monitoring tools, gamification, and competition to motivate behavior change and achieve energy savings. Overall, 2983 students and 204 educators were directly involved to a variable degree of participation. Our results indicate a positive overall result in terms of short-term energy savings in most schools involved, with an average reduction of 20-25% in the energy that could be affected by end-users, as well as a 32.9% increase after the intervention in students self-reporting good or very good sustainability awareness. These findings suggest that such interventions can be a valuable step towards educating young students regarding sustainability and towards sustainable schools, if designed and implemented properly. © 2014 IEEE.

关键词： Behavior Change Education for Sustainable Development Energy Literacy Energy Saving Environmental Education Gamification Internet of Things K-12 Sustainability Sustainable Smart Schools

来源：评论

学校读者我要写书评

暂无评论

Production portfolio optimisation under uncertainty: Threats of emissions trading

引用

International Journal of Applied Decision Sciences 2017年第3期10卷 274-290页

作者： Zapletal, Frantisek Dpt. of Systems Engineering Faculty of Economics VŠB - Technical University of Ostrava Czech Republic

This study is devoted to profit margin maximisation of heavy industrial companies in Europe which are under the economic and environmental pressure caused by Emissions Trading Scheme (EU ETS). The aim of the study is to use an optimisation model maximising a company's total profit margin under uncertainty related to the duty of CO2 emissions trading in order to assess possible threats and impact of emissions trading. Two main factors, which are considered to be uncertain, are the prices of the emission permits and the demand for products of the company. Since the uncertainty is involved in the model, the fuzzy optimisation (level sets approach) is used to face it. The calibration of the model is done using real dataset of a European steel company. Based on the results of the verification, a potential impact of emissions trading on companies, their profit and sustainability, has been discovered. © 2017 Inderscience Enterprises Ltd.

关键词： Gas emissions

来源：评论

学校读者我要写书评

暂无评论

IxaMed at CLEF eHealth 2018 task 1: ICD10 coding with a sequence-to-sequence approach 19

IxaMed at CLEF eHealth 2018 task 1: ICD10 coding with a sequ...

引用

19th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2018

作者： Atutxa, A. Casillas, A. Ezeiza, N. Fresno, V. Goenaga, I. Gojenola, K. Martínez, R. Oronoz, M. Perez-De-Viñaspre, O. Dpt. Languages and Computer Systems School of Engineering UPV EHU Bilbao Spain Dpt. Electricity and Electronics Fac. of Science and Technology UPV EHU Leioa Spain Dpt. Languages and Computer Systems Faculty of Informatics UPV EHU Donostia-San Sebastian United States Dpt. Languages and Computer Systems School of Computer Engineering UNED Madrid Spain

Hospital systems routinely assign disease codes (ICD10 codes) to medical records. The challenge stands on treating natural and nonstandard language in which doctors express their diagnoses and, additionally, to solve a large-scale classification problem, as there are thousands of possible codes. In this working notes paper, we present our system and the results of the CLEF 2018 eHealth Evaluation Task 1 on Multilingual Information Extraction-ICD10 coding. This benchmark addresses information extraction in written text with focus on several languages, specifically Hungarian, Italian and French. The goal is to automatically assign ICD10 codes to diagnostic terms of death certificates. The problem can be cast in different ways, for example as a multilabel classification task or as sequence-to-sequence prediction. Our proposal follows this last approach, with promising results, well above the average results for the task. It only relies on the material provided by the task organizers, allowing the application of the same system to all datasets.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

PI+CI tuning for integrating plus deadtime systems

PI+CI tuning for integrating plus deadtime systems

引用

2012 IEEE 17th International Conference on Emerging Technologies and Factory Automation, ETFA 2012

作者： Davo, Miguel A. Banos, Alfonso University of Murcia Dpt. Computer and Systems Engineering 30071 Murcia Spain

ISBN: (纸本)9781467347372

The PI+CI is a reset compensator that has been shown to be effective in a number of practical applications. In this work, a simple PI+CI tuning method for integrating systems with time delay is proposed. It is a direct method, with only a tuning parameter to balance between closed-loop robustness and performance. A tuning rule for the reset ratio parameter of the PI+CI compensator is proposed in order to improve the disturbance rejection. Finally, the proposed compensator is compared with some well-tuned PI compensators. © 2012 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Tractability of the crisp representations of tractable fuzzy description logics

Tractability of the crisp representations of tractable fuzzy...

引用

6th International Workshop on Uncertainty Reasoning for the Semantic Web, URSW 2010 - Collocated with the 9th International Semantic Web Conference, ISWC 2010

作者： Bobillo, Fernando Delgado, Miguel Dpt. of Computer Science and Systems Engineering University of Zaragoza Spain Dpt. of Computer Science and Artificial Intelligence University of Granada Spain

An important line of research within the field of fuzzy DLs is the computation of an equivalent crisp representation of a fuzzy ontology. In this short paper, we discuss the relation between tractable fuzzy DLs and tr... 详细信息

关键词： Data description

来源：评论

学校读者我要写书评

暂无评论

Reset control of a liquid level process

Reset control of a liquid level process

引用

2013 IEEE 18th International Conference on Emerging Technologies and Factory Automation, ETFA 2013

作者： Davó, Miguel A. Baños, Alfonso University of Murcia Dpt. Computer and Systems Engineering 30071 Murcia Spain

ISBN: (纸本)9781479908622

The aim of this work is to present an experiment of liquid level process controlled by a reset PI+CI compensator. The results are compared with a well tuned linear PI compensator, showing that the reset compensator improves the performance in both setpoint tracking and disturbance rejection. The experiment validates the simulation results obtained for a tuning rule proposed in a previous work. © 2013 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Reducing the size of the optimization problems in fuzzy ontology reasoning 11

Reducing the size of the optimization problems in fuzzy onto...

引用

11th International Workshop on Uncertainty Reasoning for the Semantic Web, URSW 2015 - collocated with the 14th International Semantic Web Conference, ISWC 2015

作者： Bobillo, Fernando Straccia, Umberto Dpt. of Computer Science and Systems Engineering University of Zaragoza Spain Pisa Italy

Fuzzy ontologies allow the representation of imprecise structured knowledge, typical in many real-world application domains. A key factor in the practical success of fuzzy ontologies is the availability of highly optimized reasoners. This short paper discusses a novel optimization technique: a reduction of the size of the optimization problems obtained during the inference by the fuzzy ontology reasoner fuzzyDL.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Incremental and iterative monolingual clustering algorithms 8

Incremental and iterative monolingual clustering algorithms

引用

8th European Conference on Speech Communication and Technology, EUROSPEECH 2003

作者： Barrachina, Sergio Vilar, Juan Miguel Dpt. of Computer Engineering and Science Universidad Jaume i Spain Dpt. of Programming Languages and Computer Systems Universidad Jaume i Spain

To reduce speech recognition error rate we can use better statistical language models. These models can be improved by grouping words into word equivalence classes. Clustering algorithms can be used to automatically do this word grouping. We present an incremental clustering algorithm and two iterative clustering algorithms. Also, we compare them with previous algorithms. The experimental results show that the two iterative algorithms perform as well as previous ones. It should be pointed out that one of them, that uses the leaving one out technique, has the ability to automatically determine the optimum number of classes. These iterative algorithms are used by the incremental one. On the other hand, the proposed incremental algorithm achieves the best results of the compared algorithms, its behavior is the most regular with the variation of the number of classes and can automatically determine the optimum number of classes.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A MILP-based decision procedure for the (Fuzzy) description logic ALCB 27

A MILP-based decision procedure for the (Fuzzy) description ...

引用

27th International Workshop on Description Logics, DL 2014

作者： Bobillo, Fernando Straccia, Umberto Dpt. of Computer Science and Systems Engineering University of Zaragoza Spain Pisa Italy

To overcome the inability of Description Logics (DLs) to represent vague or imprecise information, several fuzzy extensions have been proposed in the literature. In this context, an important family of reasoning algorithms for fuzzy DLs is based on a combination of tableau algorithms and Operational Research (OR) problems, specifically using Mixed Integer Linear Programming (MILP). In this paper, we present a MILP-based tableau procedure that allows to reason within fuzzy ALCB, i.e., ALC with individual value restrictions. Interestingly, unlike classical tableau procedures, our tableau algorithm is deterministic, in the sense that it defers the inherent non-determinism in ALCB to a MILP solver.

关键词： Data description

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：