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

Multi-objective evolutionary algorithms used in greenhouse planning for recycling biomass into energy

引用

作者： Márquez, A.L. Gil, C. Manzano-Agugliaro, F. Montoya, F.G. Fernández, A. Baños, R. Dpt. of Computer Architecture and Electronics University of Almería Spain Dpt. of Rural Engineering University of Almería Spain

ISBN: (纸本)9783642148828

Advanced parallel Multi-Objective Evolutionary Algorithms (MOEA) have been used in order to solve a wide array of problems, including the planning of greenhouse crops. This paper shows the application of MOEA using the Island Parallel Model to solve a problem involving greenhouse crop planning in order to maximize profits and the production of biomass while reducing economic risks. The interest in maximizing biomass waste lies in the possibility of recycling it into heat and energy. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

A comprehensive evaluation of cache utilization characteristics in large scale WSN considering network driven cache replacement techniques 5

A comprehensive evaluation of cache utilization characterist...

引用

5th International Conference of engineering Against Failure, ICEAF-V 2018

作者： Panagiotou, Christos Antonopoulos, Christos Koubias, Stavros Applied Electronics Laboratory Electrical and Computer Engineering Dpt. University of Patras Greece

WSNs as adopted in current smart city deployments, must address demanding traffic factors and resilience in failures. Furthermore, caching of data in WSN can significantly benefit resource conservation and network performance. However, data sources generate data volumes that could not fit in the restricted data cache resources of the caching nodes. This unavoidably leads to data items been evicted and replaced. This paper aims to experimentally evaluate the prominent caching techniques in large scale networks that resemble the Smart city paradigm regarding network performance with respect to critical application and network parameters. Through respective result analysis valuable insights are provided concerning the behaviour of caching in typical large scale WSN scenarios. © The Authors, published by EDP Sciences, 2018.

关键词： Smart city

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

Definition System of Human Body Position in Virtual Reality 16

Definition System of Human Body Position in Virtual Reality

引用

16th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and computer engineering, TCSET 2022

作者： Diachok, Roman Klym, Halyna Vasylchyshyn, Ivanna Karbovnyk, Ivan Lviv Polytechnic National University Specialized Computer Systems Dpt. Lviv Ukraine Lviv Polytechnic National University Theoretical and General Electrical Engineering Dpt. Lviv Ukraine Ivan Franko National University of Lviv Electronics and Computer Technologies Dpt. Lviv Ukraine

ISBN: (纸本)9781665468619

System for determining the position of the human body in the virtual world has been designed, implemented and researched. The system consists of two independent subsystems: subsystem for collecting, processing and transmitting data on the position of the human body and subsystem for visualizing collected data to the virtual world. In general, the system measures the position of the human body, processes the data, generates the set of commands for the virtual world and sends these commands to the virtual reality helmet for processing. Schemes of the system and algorithm of system's functioning are offered. The system using quaternions and Euler angles was investigated. Also was shown that the system works more efficiently when using quaternions. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Physical & Chemical Water-sorption Processes in the MgAl2O4Ceramics 12

Physical & Chemical Water-sorption Processes in the MgAl2O4C...

引用

12th IEEE International Conference "Nanomaterials: Applications and Properties", NAP 2022

作者： Klym, Halyna Karbovnyk, Ivan Vasylchyshyn, Ivanna Lviv Polytechnic National University Specialized Computer Systems Dpt. Lviv Ukraine Ivan Franko Nationak University Of Lviv Electronics And Computer Technology Dpt. Lviv Ukraine Lviv Polytechnic National University Theoretical And General Electrical Engineering Dpt. Lviv Ukraine

ISBN: (数字)9781665489829

ISBN: (纸本)9781665489829

Structural properties and physical and chemical water-sorption processes were investigated in the humidity-sensitive MgAl2O4 ceramics sintered at 1300 °C for 2 h under the influence of water. It is shown that ceramics has developed the structure of grains, grain boundaries and pores with trimodal pore size distribution. It is established that absorbed water in ceramics result in more intensive trapping of positrons in extended defects near grain boundaries. Furthermore, the presence of water in the inner structure of ceramics leads to specific fragmentation of free volume in the nanopores and ortho-positronium decaying in the water. © 2022 IEEE.

关键词： Nanopores

来源：评论

学校读者我要写书评

暂无评论

Interoperability for embedded systems in JFML software: An Arduino-based implementation

Interoperability for embedded systems in JFML software: An A...

引用

2018 IEEE International Conference on Fuzzy Systems, FUZZ 2018

作者： Arcos, Francisco Jesús Soto-Hidalgo, José Manuel Vitiello, Autilia Acampora, Giovanni Alcalá-Fdez, Jesús Dpt. of Computer Science and A.I. University of Granada Granada18071 Spain Dpt. of Electronics and Computer Engineering University of Córdoba Córdoba Spain Department of Computer Science University of Salerno Salerno Italy Dpt. of Physics Ettore Pancini University of Naples Federico II Naples Italy

ISBN: (纸本)9781509060207

Fuzzy Logic Systems have been successfully used in a wide range of real-world problems. They can include a priori expert knowledge and represent systems for which it is not possible to obtain a mathematical model. The standard IEEE Std 1855TM-2016 was established to provide the fuzzy community with a unique and well-defined tool allowing a fuzzy logic system design completely independent from the specific hardware/software. Recently, the library Java Fuzzy Markup Language (JFML) offers a complete implementation of the standard, however, the actual version of the JFML does not support the development of fuzzy inference systems on specific types of hardware. The aim of this paper is to develop an interoperability module to design and running FLS for embedded systems in JFML, concretely for Arduino boards. In addition, a communication protocol between JFML and Arduino boards is also defined, removing the limited computing capacity usually offered by embedded systems. A case study with a wall-following fuzzy controller to manage a mobile robotic in two environments is developed in order to illustrate the potential of the new interoperability module. © 2018 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Configurable baseband digital transceiver for Gbps wireless 60 GHz communications

Configurable baseband digital transceiver for Gbps wireless ...

引用

2011 18th IEEE International Conference on electronics, Circuits and Systems, ICECS 2011

作者： Diamantopoulos, D. Galiatsatos, P. Karachalios, A. Lentaris, G. Reisis, D. Soudris, D. Department of Physics Electronics Laboratory National and Kapodistrian University of Athens Panepistimiopolis 157-84 Athens Greece School of Electrical and Computer Engineering Dpt. of Computer Science National Technical University of Athens Zografos 157-80 Athens Greece

ISBN: (纸本)9781457718458

The evolution of 60 GHz wireless networks using Orthogonal Frequency Division Multiplexing (OFDM) technique imposed requirements of increased processing in the baseband implementations. The current paper focuses on the design of a pipelined architecture realizing the baseband functions. The design bases on using parallel paths to achieve a throughput of 1.6 Gbps. The number of paths is configured at compile time to be 4, 8 or 16, for achieving maximal throughput by either using cutting edge technology FPGA platforms or target implementations with low cost devices. FPGA implementations validate the results. © 2011 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Detection of greedy nodes in wireless LAN through comparing of probability distributions of transmission intervals

International Journal of Multimedia and Ubiquitous Engineeri...

引用

International Journal of Multimedia and Ubiquitous engineering 2013年第1期8卷 175-184页

作者： Han, Yuhun Seok, Seung-Joon Song, Wang-Cheol Choi, Duckae Huh, Jee-Wan Dpt. of Computer Engineering Kyungnam University Korea Republic of Dpt. of Computer Engineering Jeju Nat'l University Korea Republic of School of Electronics and Computer Engineering Chonnam Nat'l University Korea Republic of Future Internet Research Team Nat'l Institute for Mathematical Sciences Korea Republic of

IEEE 802.11x CSMA/CA DCF MAC protocol supports that wireless nodes have statistically impartial probabilities of wireless channel access through fair competition. However, there is greedy node problem that maliciously increasing the transmission rates of mobile nodes altering their MAC operation disturbs fair transmissions between wireless nodes. This paper addresses how to find misbehavior greedy nodes. Previous works inspect the operation of DCF MAC protocol by the MAC frame to detect greedy nodes. In this paper, a greedy node detection algorithm using Kolmogorov-Smirnov test is proposed. The algorithm classifies wireless nodes with similar probability distributions of transmission intervals and draws a comparison between groups to find a group of greedy nodes. This paper evaluates the proposed algorithm through simulation and the simulation results shows that the algorithm can accurately detect greedy nodes in the congestion condition.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Different approach to build an uninterruptible power supply system with power factor correction

International Power Electronics Congress - CIEP

引用

International Power electronics Congress - CIEP 1998年 119-124页

作者： Vázquez, N. Aguilar, C. Alvarez, J. Cáceres, R. Barbi, I. Arau, J. Inst. Tecnológico de Celaya Computer Science Dpt. Celaya Mexico CENIDET Electronics Engineering Dpt. Cuernavaca Mexico CINVESTAV-IPN Electrical Engineering Dpt. Mexico D.F. Mexico Federal University of Santa Catarina Power Electronics Institute Florianópolis -SC Brazil

In this paper a different approach to build an uninterruptible power supply (UPS) system is presented. The proposed scheme includes features such as high power factor, low total harmonic distortion and good dynamic response at the output voltage. This scheme has the desirable features of high efficiency, simple circuit and low cost compared to a traditional standalone multiple stages UPS with power factor correction. The circuit operation, analysis and experimental results of the proposed UPS scheme are presented. The UPS approach is a good solution for low power applications (&le 500 W).

关键词： Uninterruptible power systems

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：