检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Huang, Kuan-Po Feng, Tzu-Hsun Fu, Yu-Kuan Hsu, Tsu-Yuan Yen, Po-Chieh Tseng, Wei-Cheng Chang, Kai-Wei Lee, Hung-Yi National Taiwan University College of Electrical Engineering and Computer Science Taiwan Asus Intelligent Cloud Services

ISBN: (纸本)9781728163277

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble Knowledge Distillation (EKD) on various self-supervised speech models such as HuBERT, RobustHuBERT, and WavLM. We tried two different aggregation techniques, layerwise-average and layerwise-concatenation, to the representations of different teacher models and found that the former was more effective. On top of that, we proposed a multiple prediction head method for student models to predict different layer outputs of multiple teacher models simultaneously. The experimental results show that our method improves the performance of the distilled models on four downstream speech processing tasks, Phoneme Recognition, Speaker Identification, Emotion Recognition, and Automatic Speech Recognition in the hidden-set track of the SUPERB benchmark. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Distributed Information Bottleneck for a Primitive Gaussian Diamond MIMO Channel

Distributed Information Bottleneck for a Primitive Gaussian ...

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Song, Yi Xu, Hao Wong, Kai-Kit Caire, Giuseppe Shamai Shitz, Shlomo Technical University of Berlin Faculty of Electrical Engineering and Computer Science Berlin10587 Germany University College London Department of Electronic and Electrical Engineering LondonWC1E7JE United Kingdom Technion-Israel Institute of Technology Department of Electrical and Computer Engineering Haifa3200003 Israel

ISBN: (纸本)9781665475549

This paper considers the distributed information bottleneck (D-IB) problem for a primitive Gaussian diamond channel with two relays and MIMO Rayleigh fading. The channel state is an independent and identically distributed (i.i.d.) process known at the relays but unknown to the destination. The relays are oblivious, i.e., they are unaware of the codebook and treat the transmitted signal as a random process with known statistics. The bottleneck constraints prevent the relays to communicate the channel state information (CSI) perfectly to the destination. To evaluate the bottleneck rate, we provide an upper bound by assuming that the destination node knows the CSI and the relays can cooperate with each other, and also two achievable schemes with simple symbol-by-symbol relay processing and compression. Numerical results show that the lower bounds obtained by the proposed achievable schemes can come close to the upper bound on a wide range of relevant system parameters. © 2023 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Mitigation of Sub-Synchronous Oscillations to Improve Grid Stability and Efficiency Using EMT-Based Analysis and Frequency Scanning Algorithms

Mitigation of Sub-Synchronous Oscillations to Improve Grid S...

引用

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Muhammad Umar Afzaal Yuqing Dong Yilu Liu Electrical Engineering and Computer Science University of Tennessee Knoxville USA

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

Integrating inverter-based resources (IBRs) into the grid significantly alters the dynamics of modern power systems, and IBRs have been linked to sub-synchronous oscillation (SSO) events worldwide. Identifying the conditions favorable for the occurrence of SSO is essential to ensure the stability of the system and prevent adverse interactions that could damage the components of the power system or even lead to system failure. This paper investigates a specific 20 Hz oscillation event that took place at 5:30 AM on November 21, 2021, at the Kaua'i power system following the tripping of an oil power plant. Using an electromagnetic transient (EMT) model in PSCAD, we performed a sensitivity analysis to examine the conditions and scenarios that contribute to the creation of SSO's. Our findings reveal that specific Synchronous Reference Frame Phase-Locked Loop (SRF-PLL), when interacting with shunt compensation, plays a significant role in the generation of SSO's. To validate these findings, a frequency-scanning-based impedance analysis (FSBIA) is conducted. FSBIA provides a comprehensive assessment of the impedance characteristics of the system on a wide range of frequencies, which is used to identify the stability of the system. The study illustrates that precise tuning of SRF-PLL parameters can effectively mitigate SSO risks.

关键词： Sensitivity analysis Prevention and mitigation Power system dynamics Power system stability Stability analysis Power grids Impedance Phase locked loops Oscillators Tuning

来源：评论

学校读者我要写书评

暂无评论

Twitter sentiment analysis using conditional generative adversarial network

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 161-169页

作者： Mahalakshmi, V. Shenbagavalli, P. Raguvaran, S. Rajakumareswaran, V. Sivaraman, E. Department of Information Technology Sengunthar College of Engineering Tiruchengode Tiruchengode637205 India Assistant Professor Karunya Institute of Technology and Sciences Coimbatore India Assistant Professor Department of Computational Intelligence School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Kanchipuram Chennai Tamil Nadu 603203 India Assistant Professor Department of Computer Science and Design Erode Sengunthar Engineering College Tamil Nadu Thuduppathi India Department of Electrical and Computer Engineering Curtin University Miri Malaysia

Sentiment analysis, which aims to extract information from textual data indicating people's ideas or attitudes about a particular problem, has developed into one of the most exciting study issues in natural language processing (NLP) with the development of social media. Twitter is a social network with an extensive audience that expresses their thoughts and opinions clearly and readily. Due to the prevalence of slang phrases and incorrect spellings in short phrase styles, Twitter data analysis is more challenging than data analysis from other social networks. Automated feature selection still has several limitations, such as higher computing costs that rise with the number of characteristics. Deep learning, which is self-learned and more accurate at processing vast amounts of data, is utilized to overcome these challenges. This paper introduces a conditional generative adversarial network (GAN) for Twitter sentiment analysis, whereas a convolutional neural network (CNN) has been used to extract traits from Twitter data. Compared to existing works, the proposed work has outperformed in accuracy, recall, precision, and F1 score. The suggested method is the most accurate, with a classification accuracy of 93.33 %. © 2024

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Generating synthetic wind speed scenarios using artificial neural networks for probabilistic analysis of hybrid energy systems

Generating synthetic wind speed scenarios using artificial n...

引用

作者： Chen, Jun Zhao, Junhui Department of Electrical and Computer Engineering Oakland University RochesterMI48309 United States Department of Electrical Computer Engineering and Computer Science University of New Haven West HavenCT06516 United States

Hybrid energy systems (HESs) have been proposed to include and co-optimise multiple energy inputs and multiple energy outputs to enable increasing penetration of clean energy such as wind power. To optimise the system design, extensive datasets of renewable resources for the given location are required, whose availability may be limited. To address this limitation, this paper proposes an innovative methodology to generate synthetic wind speed data. Specifically, artificial neural networks are adopted to characterise historical wind speed data and to generate synthetic scenarios. In addition, Fourier transformation is used to capture the characteristics of the low frequency components in historical data, allowing the synthetic scenarios to preserve seasonal trends. The proposed methodology enables the possibility of Monte Carlo simulation of HES for probabilistic analysis using large volumes of heterogeneous scenarios. Case study of probabilistic analysis is then performed on a particular HES configuration, which includes nuclear power plant, wind farm, battery storage, electric vehicle charging station, and desalination plant. Wind power availability and requirements on component ramping rate are then investigated. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Quality of Control Based Resource Dimensioning for Collaborative Edge Robotics 22

Quality of Control Based Resource Dimensioning for Collabora...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Roy, Neelabhro Dhullipalla, Mani H. Sharma, Gourav Prateek Dimarogonas, Dimos V. Gross, James School of Electrical Engineering and Computer Science Digital Futures Research Center Kth Royal Institute of Technology Stockholm Sweden

ISBN: (纸本)9798331508050

With the increasing focus on flexible automation, which emphasizes systems capable of adapting to varied tasks and conditions, exploring future deployments of cloud and edge-based network infrastructures in robotic systems becomes crucial. This work, examines how wireless solutions could support the shift from rigid, wired setups toward more adaptive, flexible automation in industrial environments. We provide a quality of control (QoC) based abstraction for robotic workloads, parameterized on loop latency and reliability, and jointly optimize system performance. The setup involves collaborative robots working on distributed tasks, underscoring how wireless communication can enable more dynamic coordination in flexible automation systems. We use our abstraction to optimally maximize the QoC ensuring efficient operation even under varying network conditions. Additionally, our solution allocates the communication resources in time slots, optimizing the balance between communication and control costs. Our simulation results highlight that minimizing the delay in the system may not always ensure the best QoC but can lead to substantial gains in QoC if delays are sometimes relaxed, allowing more packets to be delivered reliably. © 2025 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Colonic Pressure Signal Denoising Based on Improved Threshold Function and Threshold Optimization 24

Colonic Pressure Signal Denoising Based on Improved Threshol...

引用

3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024

作者： Cui, Liu Du, Yupeng Zhao, Kai Shi, Yanjiao Yang, Fan Shanghai Institute of Technology Department of Computer Science and Information Engineering Shanghai201418 China Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai201418 China

ISBN: (纸本)9798400716416

Wavelet threshold noise reduction is widely used because of its simple algorithm and small computation. The properties of the threshold function are studied and a new two-parameter adjustable threshold function is designed to solve the problems of signal loss and local oscillations caused by soft and hard threshold function noise reduction. The threshold function has the properties of continuity, small constant deviation and high order differentiability. Meanwhile, an artificial hummingbird algorithm based on a mixture of Cubic chaotic mapping, global Cauchy variation and golden sine strategy is used for optimization of thresholds and adjustment factors. Applying this algorithm in noise reduction of colonic pressure signals, most of the noise can be filtered out and the details of colonic peristaltic signals are preserved. © 2024 ACM.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Identifying and Addressing Security Vulnerabilities in Hybrid Network Security Algorithms

Identifying and Addressing Security Vulnerabilities in Hybri...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Pipersenia, Arun Kumar Nidhya, M.S. Jain, Sandeep Kumar College of Engineering Teerthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India Electrical Engineering Vivekananda Global University Jaipur India

ISBN: (纸本)9798350383348

Hybrid network protection algorithms represent a critical vicinity in facts safety techniques. Inside the computation of networking environments, such algorithms provide a cozy and dependable mechanism for site visitor management, records storage, entry to manipulation, and so on. The security of this mechanism is, but suffering from the presence of certain safety vulnerabilities within the gadget. To ensure the powerful operation of modern-day networks, these vulnerabilities need to be identified and addressed. This paper explores some of the procedures to be had for the identification and addressing of the safety vulnerabilities in hybrid community security algorithms: The security goals the ones want to be worked on, consisting of authentication, authorization, records integrity, and confidentiality, are mentioned. Several assault fashions, consisting of insider attacks, man-in-the-center assaults, and brute-pressure assaults, are also stated to detail the vulnerabilities in hybrid protection algorithms. Modern practices for figuring out and addressing safety vulnerabilities in hybrid community security algorithms are supplied. Those consist of techniques which include reading network site visitors, assessing the trustworthiness of customers, enforcing encryption techniques, and applying community entry to controls. Several protection models, in addition to protocols for reaching secure verbal exchange in hybrid networks, are examined. © 2024 IEEE.

关键词： Algorithms Critical Examined Network Protection Vicinity

来源：评论

学校读者我要写书评

暂无评论

Literature Review of Quantum-dot Cellular Automata (QCA) Technology used in Cryptography 5

Literature Review of Quantum-dot Cellular Automata (QCA) Tec...

引用

5th College of science International Conference on Recent Trends in Information Technology, CSCTIT 2022

作者： Sayal, Maha A. Albermany, S.A. Alkaldy, Esam Al College of Computer and Mathematics Science University of Thi-Qar Computer Science Department Thi-Qar Iraq University of Kufa Faculty of Computer Science and Mathematics Computer Department Kufa Iraq Collage of Engineering University of Kufa Electrical Engineering Kufa Iraq

ISBN: (纸本)9798350334920

Cellular quantum dot (QCA) technology is a recent technology. It is used to get rid of the limitations of complementary metal semiconductor (CMOS). This is why high-speed QCA circuits, ultra-low consumption, and less space are designed. to encrypt securely, the purpose is the continuous development of the encryption and decryption process. Therefore, we use electronic circuits and gates such as the majority gate, inverter gate, and MUX circuit in this paper. The cipher used here is stream. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Computational Fabrication and Assembly for In Situ Manufacturing

arXiv

引用

arXiv 2024年

作者： Nisser, Martin Eric William Department of Electrical Engineering and Computer Science United States

Fabrication today relies on disparate, large machines spread across industrial facilities. These are operated by domain experts to construct and assemble artefacts in sequential steps from large numbers of parts. This traditional, centralized mass manufacturing paradigm is characterized by large capital costs and inflexibility to changing needs, complex global supply chains hinged on economic and political stability, and waste and over-manufacturing of uniform artefacts that fail to meet the technical and personal needs of today’s diverse individuals and use cases. Today, these challenges are particularly severe at points of need, such as the space environment. The space environment is remote and unpredictable, and the ability to manufacture in situ offers unique opportunities to address new challenges as they arise. However, the challenges faced in space are often mirrored on Earth. In hospitals, disaster zones, low resource environments and laboratories, the ability to manufacture customized artefacts at points of need can significantly enhance our ability to respond rapidly to unforeseen events. In this thesis, I introduce digital fabrication platforms with co-developed hardware and software that draw on tools from robotics and human-computer interaction to automate manufacturing of customized artefacts at the point of need. Highlighting three research themes across fabrication machines, modular assembly, and programmable materials, the thesis will cover a digital fabrication platform for producing functional robots, a modular robotic platform for in-space assembly deployed in microgravity, and a method for programming magnetic material to selectively assemble. © 2024, CC BY-NC-ND.

关键词： Supply chains

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：