检索结果-内蒙古大学图书馆

International Symposium on Applied Machine Intelligence and informatics (SAMI)

作者： Rebin Saleh Balazs Villanyi Dept. of Electronics Technology Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350379365

ISBN: (纸本)9798350379372

IIoT and Industry 4.0 have enabled, in turn, revolutionary approaches toward energy management for commercial buildings by giving way to more intelligent data-driven decision-making mechanisms. The work presented in this paper aims to discuss the role of electronic sensors and embedded systems as an enabler for real-time forecasting of energy consumption in IIoT-enabled infrastructures. The three most common machine learning algorithms, XGBoost, LightGBM, and Random Forest, were compared in comprehensive detail with all types of sensor data: electricity, chilled water, hot water, and steam. Unlike previous research, which has usually focused on a single model or limited evaluation criteria, the research compared multiple models on seven different performance metrics such as RMSE, R 2 , MAE, SMAPE, MSLE, F1 Score, and Precision. The results have shown that XGBoost has outperformed other models consistently in terms of accuracy, proving its potential in improving energy efficiency and enabling predictive maintenance schemes in smart buildings. These observations enhance overall understanding in terms of effective incorporation of machine learning models into IIoT-centric energy management systems and provide considerable guidance for further development in energy-efficient infrastructure.

关键词： Energy consumption Smart buildings Predictive models Energy efficiency Sensor systems Real-time systems Fourth Industrial Revolution Forecasting Random forests Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Gamification of Therapeutic Tools for Speech and Hearing Disorders

Gamification of Therapeutic Tools for Speech and Hearing Dis...

引用

International Conference on Emerging eLearning Technologies and Applications (ICETA)

作者： Stanislav Ondáš Zuzana Sokolová Ján Staš Adam Božek Department of Electronics and Multimedia Communications Faculty of Electrical Engineering and Informatics Technical University of Košice Slovakia

ISBN: (数字)9798331527716

ISBN: (纸本)9798331527723

The paper explores the gamification of therapeutic tools for speech and hearing disorders. The goal was to develop a web application in the form of a game to test communication development of children by the TEKOS II. The web application, game story and principles, speech and picture stimuli were designed and developed. The designed concept brings a new view of how the TEKOS test can be realized, where children are directly involved through a game-like application, which can provide additional information and which enhances the diagnostics of comprehension problems. The designed prototype can be especially useful in cases where there is no person who is able to answer questions about which words a child can understand and speak. The prototype was evaluated in short tests under laboratory conditions. The overall impression of the designed prototype is positive, where the story, speech and visual stimuli are positively assessed.

关键词： Visualization Electronic learning Prototypes Medical treatment Focusing Auditory system Games Data collection

来源：评论

学校读者我要写书评

暂无评论

Frying Oil Quality Evaluation Using UWB Impedance Spectrometer and Machine Learning Techniques

Frying Oil Quality Evaluation Using UWB Impedance Spectromet...

引用

Asia-Pacific Conference on Microwave

作者： Miroslav Soko Zuzana Sokolová Maroš Harahus Patrik Jurík Pavol Galajda Department of Electronics and Multimedia Telecommunications Faculty of Electrical Engineering and Informatics Technical University of Košice Slovakia

ISBN: (数字)9798350363548

ISBN: (纸本)9798350363555

This paper aims to streamline and accelerate the quality evaluation of vegetable oil used in fryers. We attempt to train the algorithm using several machine learning methods on the data measured by an M-Sequence Ultra-wideband impedance spectrometer, which enables wideband sensing from almost DC to 6 GHz. Using the machine learning AutoEncoder method, we achieved the best results with an Mean Absolute Error value of around 0.25 compared to other methods.

关键词： Training Vegetable oils Autoencoders Machine learning Data models Sensors Impedance Wideband Ultra wideband technology Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Investigating the Copper Peel and Solder Joint Shear Strength on Biodegradable Substrates

Investigating the Copper Peel and Solder Joint Shear Strengt...

引用

International Symposium for Design and Technology of electronics Packages (SIITME)

作者： Oliver Krammer Gergely Hambuch Réka Bátorfi Balázs Illés Attila Géczy Department of Electronics Technology Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798331539511

ISBN: (纸本)9798331539528

The amount of electronics waste is increasing rapidly, and replacing traditional electronics materials with biodegradable alternatives is essential where possible. Four types of biodegradable substrates with $35 \mu \mathrm{~m}$ thick laminated copper layer have been analysed in this research work. All the substrates are based on polylactic acid laminates with flax reinforcement. The first type is a pure PLA laminate. The second, third and fourth types incorporate polymer interlayers (polypropylene or polyamide) to facilitate the adhesion between the copper layer and the substrate. Note that the interlayers are not biodegradable but will be swapped with biodegradable alternatives in the future. Copper peel strength was measured using a standard test pattern described in IPC-TM650. The copper layers were peeled off using an Instron 5965 test equipment, and the applied load was recorded automatically. A custom sliding sample holder was designed, allowing the vertical peeling of the copper layer. In addition to the copper peeling test, surface-mounted resistors in different sizes were assembled with low-temperature reflow soldering, and the shear strength of their solder joints was investigated.

关键词： Resistors Adhesives Copper Laminates Test equipment Polymers Substrates Standards Textiles Reflow soldering

来源：评论

学校读者我要写书评

暂无评论

Deconvolution of 3D Data Measured by FMCW LiDAR Based on Image Sensor under Influence of Spatially Inhomogeneous Frequency Modulation 13

Deconvolution of 3D Data Measured by FMCW LiDAR Based on Ima...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Yokota, Nobuhide Ohira, Masato Takahashi, Hideyuki Sugiyasu, Kazuya Inokawa, Hiroshi Yasaka, Hiroshi Tohoku University Research Institute of Electrical Communication Sendai Japan Tohoku University Graduate School of Engineering Sendai Japan Tohoku Gakuin University Faculty of Informatics Sendai Japan Iwate Prefectural University Faculty of Policy Studies Takizawa Japan Shizuoka University Research Institute of Electronics Hamamatsu Japan

ISBN: (纸本)9798350355079

We propose a deconvolution technique to mitigate influence of spatially inhomogeneous frequency modulation of a laser source for frequency-modulated continuous-wave (FMCW) light detection and ranging (LiDAR) based on an image sensor. Our technique demonstrates clarity improvement of three-dimensional data. Since conventional FMCW LiDAR without using an image sensor suffers from low spatial resolution due to coarse beam steering, our technique encourages a use of an image sensor for FMCW LiDAR and leads to application to robust and informative rescue support system. © 2024 IEEE.

关键词： Image sensors

来源：评论

学校读者我要写书评

暂无评论

Face From Voice: PyTorch Adaptation of Speech2Face Framework

引用

Procedia Computer Science 2024年 246卷 2892-2901页

作者： Kacper Pietkun Bogna Gondek Marta Browarczyk Faculty of Electronics Telecommunications and Informatics Multimedia Systems Department Gdansk University of Technology Narutowicza 11/12 80-233 Gdańsk Poland

This paper focuses on the problem of face images reconstruction from short audio segments. Built in PyTorch, the speech-to-face pipeline retains the core methodology of the others presented in the previous works, but with the introduction of a few key modifications. Leveraging a comprehensive dataset of internet audio recordings, a deep neural network undergoes training to discern correlations between voice and facial features. Through self-supervised learning, various physical attributes such as age, gender and ethnicity are captured without the need for explicit feature analysis. The evaluation process quantifies the fidelity of reconstructions, measuring the resemblance to the actual facial images solely from audio data through numerical metrics.

关键词： Speech-to-Face Encoder-Decoder Face generation Audio Spectrogram Transformer Convolutional Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Miniaturized and Lightweight ESPAR Antenna for WSN and IoT Applications

Miniaturized and Lightweight ESPAR Antenna for WSN and IoT A...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Luiza Leszkowska Mateusz Czeleń Mateusz Rzymowski Krzysztof Nyka Łukasz Kulas Department of Microwave and Antenna Engineering Faculty of Electronics Telecommunications and Informatics Gdansk University of Technology Gdansk Poland

A new compact ESPAR antenna is investigated in this paper. The proposed antenna has 12 directional radiation patterns based on 12 passive elements and can be successfully used in Wireless Sensor Network applications. In proposed antenna design, the possibilities of 3D printing were used to implement a dielectric miniaturization overlay that allowed for reducing antenna occupied area by almost 60% and antenna profile by 27% in comparison to the standard ESPAR antenna. The total dimensions of the antenna are 98 mm in diameter and 20.25 mm in height, while the weight of the antenna is only 86 g, which makes it much more suitable for potential use in UAV-based wireless communication applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of Ristretto255 Group Implementation for Cortex-M4 based Cryptographic Applications

Optimization of Ristretto255 Group Implementation for Cortex...

引用

International Conference on Radioelektronika

作者： Eva Kupcova Patrik Zelenak Matus Pleva Milos Drutarovsky Department of Electronics and Multimedia Telecommunications Faculty of Electrical Engineering and Informatics Technical University of Kosice Kosice Slovakia

This article focuses on specifying and optimizing one primary order group, Ristretto255, which is suitable for securely implementing higher and more complex modern cryptographic protocols. The Ristretto255 Group is employed across a spectrum of modern cryptographic applications, spanning zero-knowledge protocols, elliptic curve cryptography, key exchange protocols, etc. In this article, we present the principles and optimization of Ristretto255 Group implementation for embedded cryptographic applications based on the Bernstein elliptic curve Curve25519. In our implementation, with a combination of the C programming language and Assembler, we achieved a faster and more compact result on a microcontroller built on 32-bit ARM Cortex-M4 core. We have prepared our Ristretto255 Group transformation implementation that serves as a compliant building block for cryptographic protocols operating at the 128-bit security level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3-D Image-to-Image Fusion in Lightsheet Microscopy by Two-Step Adversarial Network: Contribution to the Fusemycells Challenge 22

3-D Image-to-Image Fusion in Lightsheet Microscopy by Two-St...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Wodzinski, Marek Müller, Henning Agh University of Krakow Department of Measurement and Electronics Krakow Poland Institute of Informatics University of Applied Sciences Western Switzerland Sierre Switzerland University of Geneva Medical Faculty Geneva Switzerland

ISBN: (纸本)9798331520526

Lightsheet microscopy is a powerful 3-D imaging technique that addresses limitations of traditional optical and confocal microscopy but suffers from a low penetration depth and re-duced image quality at greater depths. Multiview lightsheet microscopy improves 3-D resolution by combining multiple views but simultaneously increasing the complexity and the photon budget, leading to potential photobleaching and pho-totoxicity. The FuseMyCells challenge, organized in conjunction with the IEEE ISBI 2025 conference, aims to benchmark deep learning-based solutions for fusing high-quality 3-D vol-umes from single 3-D views, potentially simplifying procedures and conserving the photon budget. In this work, we propose a contribution to the FuseMyCells challenge based on a two-step procedure. The first step processes a down-sampled version of the image to capture the entire region of interest, while the second step uses a patch-based approach for high-resolution inference, incorporating adversarial loss to enhance visual outcomes. This method addresses chal-lenges related to high data resolution, the necessity of global context, and the preservation of high-frequency details. Ex-perimental results demonstrate the effectiveness of our approach, highlighting its potential to improve 3-D image fusion quality and extend the capabilities of lightsheet microscopy. The average SSIM for the nucleus and membranes is greater than 0.85 and 0.91, respectively. © 2025 IEEE.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Measuring and Mitigating Stereotype Bias in Language Models: An Overview of Debiasing Techniques

Measuring and Mitigating Stereotype Bias in Language Models:...

引用

International Symposium on electronics in Marine (ELMAR)

作者： Zuzana Sokolová Maroš Harahus Ján Staš Eva Kupcová Miroslav Sokol Marianna Koctúrová Jozef Juhár Department of Electronics and Multimedia Communications Faculty of Electrical Engineering and Informatics Technical University of Košice Slovakia

ISBN: (数字)9798350375428

ISBN: (纸本)9798350375435

This paper provides an overview of methods for measuring the stereotype bias of pre-trained language models. It explains the term ‘stereotype bias’ and its measurement. A comprehensive review of language model debiasing techniques, including Dropout, Counterfactual Data Augmentation, Iterative Nullspace Projection, Sent-Debias, Self-Debias, Context-Debias, FairFil, and Auto-Debias, is provided. Subsequently, these techniques are compared, and their advantages and disadvantages are highlighted. In addition, there is an explanation of how these techniques work simply. In the future, debiasing techniques will be tested on pre-trained models for the Slovak language, focusing on the task of toxic language detection.

关键词： Measurement Ethics Reviews Scalability Focusing Data augmentation Robustness Data models Iterative methods Testing

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：