检索结果-内蒙古大学图书馆

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Lin, Kaicheng Jin, Ming He, Ming Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798350312201

Underlay dynamic spectrum access (DSA) has powerful effectiveness and efficiency for sharing radio spectrum among DSA users. But two fundamental issues have to be addressed: 1) avoiding harmful interference to Primary User (PU), 2) enabling effective transmission and coordinating interference with other Secondly User (SU). To solve the aforementioned issues, we propose a novel channel access and power control algorithm, which named Parallel Action Network Structure (PANS) Deep Double Dueling Q-Network (D3QN). Additionally, We enable SUs flexibly determine whether to perform single-channel transmission or have the opportunity for dual-channel transmission based on the current state. With the support of the two innovations mentioned above, SUs can independently select channels and control transmission power, further more improve their *** numerous simulation results demonstrate the effectiveness and reliability of the proposed algorithm. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Adaptive-SpEx: Local and Global Perceptual Modeling with Speaker Adaptation for Target Speaker Extraction

Adaptive-SpEx: Local and Global Perceptual Modeling with Spe...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Xu, Xianbo Yan, Diqun Dong, Li Ningbo University Faculty of Electrical Engineering and Computer Science NingBo China

ISBN: (纸本)9798350337020

Target speaker extraction aims to extract a target speaker's speech from a multi-talker environment with the help of the target speaker's reference speech. However, the simple fusion of different features and local perceptual modeling lead to limited extraction performance. In this work, we propose a new speaker extraction model called Adaptive-SpEx. The correlation between mixed speech features and speaker embedding is fully exploited, and a dual-path structure is used for local and global perceptual modeling. We evaluate the model on the WSJ0-2mix-extr dataset in terms of its ability to reconstruct signal quality. Experimental results show that the proposed model outperforms other baseline systems on WSJ0-2mix-extr and achieves better generalizability on the Libri-2talker dataset. Furthermore, the proposed model can significantly reduce the word error rate of mixed speech on speech recognition from 79.49% to 32.73%. © 2023 IEEE.

关键词： dual-path structure speaker embedding speech recognition Target speaker extraction

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Compact and Modular SFCW GPR Systems for Detecting Buried Objects 30

Evaluation of Compact and Modular SFCW GPR Systems for Detec...

引用

30th International Conference on Systems, Signals and Image Processing, IWSSIP 2023

作者： Smogavec, Primoz Pongrac, Blaz Gleich, Dusan University of Maribor Faculty of Electrical Engineering and Computer Science Maribor Slovenia

ISBN: (纸本)9798350337297

Ground Penetrating Radar (GPR) systems have emerged as a reliable and non-destructive tool for subsurface object detection and characterization. In this paper, we present a comprehensive performance evaluation of two different stepped-frequency continuous wave (SFCW) GPR radars in application for detecting buried objects. Radars have the same structure, one is implemented on a single substrate with more than 300 elements and the second one is a modular implementation of radar using separately designed transmitter, receiver, and processing unit. The paper presents the design of both radars and their performances evaluation. The same TEM horn antennas were used for detecting subsurface objects using both these radars. The study focuses on two specific objects, an anti-tank mine and an anti-personal. The radar platforms have different output power and have different processing speeds, because they use different sets of electronic chips and FPGAs. The performance of GPR radars is assessed based on their ability to accurately detect and locate these objects. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Influence of Geometry Effects on Thermo-Mechanical Reliability of Aluminum Bond Wires in Discrete SiC MOSFETs 25

Influence of Geometry Effects on Thermo-Mechanical Reliabili...

引用

25th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems, EuroSimE 2024

作者： Kilian, Borja Maniar, Youssef Gleichauf, Jonas Wittler, Olaf Schneider-Ramelow, Martin Robert Bosch GmbH Corporate Sector Research and Advance Engineering Renningen Germany Fraunhofer IZM Department Environmental and Reliability Engineering Berlin Germany Technical University Berlin Faculty IV-Electrical Engineering and Computer Science Berlin Germany

ISBN: (纸本)9798350393637

Bond wire reliability remains as one of the major challenges in power electronics as device miniaturization progresses and demands on performance increase. Physics-of-failure models are commonly formulated to determine the lifetime of wire bonding interconnects. Such approach relies on damage metrics derived from finite element models, often based on simplified geometries and modeling *** paper addresses the influence of various bond wire geometry features on the thermo-mechanical reliability of PCB-mounted discrete SiC power devices. For this purpose, the bond wire geometry is characterized and the component is subjected to active power cycling until failure occurs due to bond wire lift-off. Finite element models are solved using a two-stage simulation approach: First, an upstream wire bonding simulation is performed to obtain a realistic bond foot geometry, and then the active power cycling tests are simulated. A physics-of-failure lifetime model is calibrated using damage quantities derived from the simulation results. Finally, geometry variations of the bond foot and different bond wire positions and rotations are evaluated to determine their significance for the thermo-mechanical reliability of thick Al bond wires. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attitudes of Slovenian Upper Secondary School Students towards Online Education 47

Attitudes of Slovenian Upper Secondary School Students towar...

引用

47th ICT and Electronics Convention, MIPRO 2024

作者： Šorgo, Andrej Merdaus, Mihaela University Of Maribor Faculty Of Natural Sciences And Mathematics Maribor Slovenia Faculty Of Electrical Engineering And Computer Science Maribor Slovenia

ISBN: (纸本)9798350382495

Online teaching and learning is seen by many as a way to not only improve the learning outcomes of traditional courses, but also to give participants the opportunity to learn anytime, anywhere. During the COVID-19 pandemic, when educational institutions were forced to offer online courses to students, a critical reflection on the sometimes overly optimistic predictions about the possibilities of such education was possible. Based on the assumption that knowledge and skills acquired in the classroom only form competences in connection with attitudes, we were interested in the attitudes of Slovenian upper secondary school students in connection with online teaching. We were able to collect data from 1081 students from different secondary schools. The main findings were that the majority of students, regardless of their gender: (1) would prefer to fulfil their duties at school rather than learning online;(2) do not find working in online environments challenging;and (3) do not think that this work is more productive or efficient compared to face-to-face teaching. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An efficient cloud based face recognition system for e-health secured login using steerable pyramid transform and local directional pattern

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1017-1027页

作者： Dosaj, Ayush Satapathy, Suresh Chandra Soundrapandiyan, Rajkumar Kaur, Mannat Hannoon, Naeem School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Kalinga Institute of Industrial Technology Deemed to be University Odisha Bhubaneswar India Faculty of Electrical Engineering Universiti Teknologi MARA Shah Alam Malaysia

This paper proposes a face recognition system based on steerable pyramid transform (SPT) and local directional pattern (LDP) for e-health secured login in cloud domain. In an e-health login, patients periodically forget their self-made login username and password. This face recognition system can replace the traditional login system. In the proposed system, SPT can decompose a face image into several sub-bands of different scales and orientations, and LDP can encode the sub-bands in binary texture pattern. The LDP binary pattern was obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. Therefore, SPT–LDP design represents a face image in a robust way which includes multiple information sources from different scales and orientations. The proposed system is tested on standard benchmark facial recognition technology (FERET) and extended Yale-B databases. Further, the efficiency of the proposed system is proved by comparing recognition rates with other existing descriptor based methods. From the experimental results it is observed that the proposed system achieves 99.79% recognition in fb set, 90.72% in fc set, 84.97% in dup I set, and 87.69% in dup II set for FERET database and 100% in sub2 set, 100% in sub3 set, 96% in sub4 set and 95% in sub5 set for extended Yale-B database which is better than the existing methods. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Graph Topology Identification Based on Covariance Matching

Graph Topology Identification Based on Covariance Matching

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Han, Yongsheng Natali, Alberto Leus, Geert Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

ISBN: (纸本)9798350368741

This paper addresses graph topology identification for applications where the underlying structure of systems like brain and social networks is not directly observable. Traditional approaches based on signal matching and spectral templates have limitations, particularly in handling scale issues and sparsity assumptions. We introduce a novel covariance matching methodology that efficiently reconstructs the graph topology using observable data. For the structural equation model (SEM) using an undirected graph, we demonstrate that our method can converge to the correct result under relatively soft conditions. Furthermore, we extend our methodology to polynomial models and any known distribution of latent variables, broadening its applicability and utility in diverse graph-based systems. © 2025 IEEE.

关键词： covariance matching graph topology identification polynomial model structural equation model

来源：评论

学校读者我要写书评

暂无评论

Relationship of IQ with Causal Connections Between Brain Salient Network Regions 31

Relationship of IQ with Causal Connections Between Brain Sal...

引用

31st National and 9th International Iranian Conference on Biomedical engineering, ICBME 2024

作者： Ghoorchian, Mina Soltanian-Zadeh, Hamid Pedram, Mir Mohsen Sadeghi, Mohsen Mir Mohammad Institute for Cognitive Science Studies Department of Cognitive Science Tehran Iran University of Tehran School of Electrical and Computer Engineering Tehran Iran Kharazmi University Department of Electrical and Computer Engineering Faculty of Engineering Tehran Iran

ISBN: (纸本)9798331529710

IQ is one of the indicators that has always been of interest to psychiatrists, doctors and cognitive science researchers. Since this index plays a key role in people's lives and also in the occurrence of brain abnormalities, many studies have been conducted on it. In this paper, we used the resting state magnetic resonance imaging data available in the HCP database to classify people into three groups with low, medium, and high IQ and applied machine learning methods on the matrix of causal connections between related network regions. We applied brain highlights. We calculated the matrix of causal relationships in this network by the spDCM algorithm and then obtained the differences of the three groups using the ANOVA statistical test and 6 edges out of 169 edges with p-value © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

AggreMark: Efficient Watermarking in Federated Learning via Weighted Averaging 17

AggreMark: Efficient Watermarking in Federated Learning via ...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Lian, Zhuotao Wang, Weiyu Su, Chunhua Sakurai, Kouichi Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka Japan University of Aizu School of Computer Science and Engineering Aizuwakamatsu Japan

ISBN: (纸本)9798350351637

Federated learning has rapidly advanced as a privacy-preserving, distributed machine learning methodology. Protecting the intellectual property rights of federated models, however, poses significant challenges. Existing backdoor-based watermarking techniques suffer from complexity, inefficiency, and implementation challenges. In this paper, we present AggreMark, a novel watermarking approach that incorporates parallel server-side training and watermark embedding during the weighted averaging phase of federated learning. This method does not alter the original model structure or parameters related to the original learning task and adds no additional time overhead, ensuring its practicality for real-world applications. AggreMark is easy to implement and maintain, and it robustly preserves the model's high performance. We validate the method's effectiveness and robustness against pruning-based watermark removal attacks through experiments on CIFAR-10. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid In-Vehicle Background Noise Reduction for Robust Speech Recognition:The Possibilities of Next Generation 5G Data Networks

引用

computers, Materials & Continua 2022年第6期71卷 4659-4676页

作者： Radek Martinek Jan Baros Rene Jaros Lukas Danys Jan Nedoma VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer ScienceDepartment of Cybernetics and Biomedical Engineering70800Ostrava-PorubaCzechia VSB Technical University of Ostrava Faculty of Electrical Engineering and Computer ScienceDepartment of Telecommunications70800Ostrava-PorubaCzechia

This pilot study focuses on employment of hybrid LMS-ICA system for in-vehicle background noise *** vehicles are nowadays increasingly supporting voice commands,which are one of the pillars of autonomous and SMART *** speaker recognition for context-aware in-vehicle applications is limited to a certain extent by in-vehicle back-ground *** article presents the new concept of a hybrid system which is implemented as a virtual *** highly modular concept of the virtual car used in combination with real recordings of various driving scenarios enables effective testing of the investigated methods of in-vehicle background noise *** study also presents a unique concept of an adaptive system using intelligent clusters of distributed next generation 5G data networks,which allows the exchange of interference information and/or optimal hybrid algorithm settings between individual *** average,the unfiltered voice commands were successfully recognized in 29.34%of all scenarios,while the LMS reached up to 71.81%,and LMS-ICA hybrid improved the performance further to 73.03%.

关键词： 5G noise reduction hybrid algorithms speech recognition 5G data networks in-vehicle background noise

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：