检索结果-内蒙古大学图书馆

12th International Conference on Renewable Power Generation, RPG 2023

作者： Nasser Danapour, S. Mohammadi, Fazel Department of Electrical and Computer Engineering University of Tabriz Tabriz51666-67541 Iran Electrical and Computer Engineering and Computer Science Department University of New Haven West HavenCT06516 United States

The integrated wind turbine-power transmission line systems integrate wind turbines into high-voltage power transmission lines by directly interconnecting wind turbines to high-voltage power transmission lines without using high-voltage power transformers. In such systems, by considering double-circuit power transmission lines, creating a specific phase difference between two power transmission lines can lead to creating an appropriate voltage difference vector between them for injecting the power of wind turbines into power transmission lines without using high-ratio step-up power transformers. Then, a number of power transformers, which are termed receiving-end transformers, absorb the injected power of wind turbines. Such transformers increase the complexity and overall cost of the system. In this paper, an improved method for creating a voltage difference vector between two power transmission lines in an integrated wind turbine-power transmission line system is proposed. In addition, a new approach for injecting the power of wind turbines into power transmission lines and delivering to the load center without the need for receiving-end transformers is presented. The proposed method and its operation are analyzed in MATLAB/Simulink. © The Institution of engineering & Technology 2023.

关键词： Electric power transmission

来源：评论

学校读者我要写书评

暂无评论

Learning to Communicate Among Agents for Large-Scale Dynamic Path Planning With Genetic Programming Hyperheuristic

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1269-1283页

作者： Liao, Xiao-Cheng Hu, Xiao-Min Chen, Xiang-Ling Mei, Yi Jia, Ya-Hui Chen, Wei-Neng Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China Hanyang University Department of Electrical and Electronic Engineering Ansan15588 Korea Republic of South China University of Technology School of Future Technology Guangzhou510006 China Pazhou Lab Guangzhou510005 China South China University of Technology School of Computer Science and Engineering State Key Laboratory of Subtropical Building and Urban Science Guangzhou510006 China

Genetic programming hyperheuristic (GPHH) has recently become a promising methodology for large-scale dynamic path planning (LDPP) since it can produce reusable heuristics rather than disposable solutions. However, in this methodology, the extracted local and decentralized heuristic for agents that lack a global systemic view sometimes may be problematic. Therefore, a new challenge is to strike a balance between conciseness to improve generalization ability and incorporation of more global information to obtain better performance. In this work, we target the LDPP problem and propose a communication learning mechanism (ComLGP) for GPHH to address the above difficulties. In ComLGP, a communication function is introduced to serve as a communication protocol and exist in the form of an extra terminal in GPHH. Compared to the classic terminals which are fixed in genetic programing, this communication function undergoes optimization along with the evolutionary process of GPHH. In this way, the communication function can be learned which enables agents to communicate without a predefined communication protocol. Then, a caching and lazy updating mechanism for ComLGP is presented to accelerate the calculation of communication content. Last, we verified our method on 22 scenarios including two real world road networks. The experimental results demonstrate that the proposed ComLGP can successfully learn to communicate. Although in the absence of any manually designed communication features, ComLGP is capable of achieving performance competitive to the state-of-the-art method that employs a predefined communication protocol and outperforms the remaining compared methods in most scenarios. © 2020 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

DIFFAR: DENOISING DIFFUSION AUTOREGRESSIVE MODEL FOR RAW SPEECH WAVEFORM GENERATION 12

DIFFAR: DENOISING DIFFUSION AUTOREGRESSIVE MODEL FOR RAW SPE...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Benita, Roi Elad, Michael Keshet, Joseph Department of Electrical and Computer Engineering Technion - Israel Institute of Technology Haifa Israel Department of Computer Science Technion - Israel Institute of Technology Haifa Israel

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a waveform (i.e., a vocoder). This work proposes a diffusion probabilistic end-to-end model for directly generating the raw speech waveform. The proposed model is autoregressive, generating overlapping frames sequentially, where each frame is conditioned on a portion of the previously generated one. Hence, our model can effectively synthesize an unlimited speech duration while preserving high-fidelity synthesis and temporal coherence. We implemented the proposed model for unconditional and conditional speech generation, where the latter can be driven by an input sequence of phonemes, amplitudes, and pitch values. Working directly on the waveform has some empirical advantages. Specifically, it allows the creation of local acoustic behaviors, like vocal fry, which makes the overall waveform sounds more natural. Furthermore, the proposed diffusion model is stochastic and not deterministic;therefore, each inference generates a slightly different waveform variation, enabling abundance of valid realizations. Experiments show that the proposed model generates speech with superior quality compared with other state-of-the-art neural speech generation systems. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Trends in One-Shot Neural Architecture Search 15

Trends in One-Shot Neural Architecture Search

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Bin Son, Seok Park, Soohyun Kim, Joongheon Korea University Department of Electrical and Computer Engineering Seoul Korea Republic of Sookmyung Women's University Division of Computer Science Seoul Korea Republic of

ISBN: (纸本)9798350364637

Recent advances in neural architecture search (NAS) techniques have provided effective solutions for managing high-dimensional data. These methods algorithmically automate the design process of NAS, aiming to identify an optimized structure that meets target performance criteria with reduced time and resource expenditure. This paper introduces the One-shot NAS method, which offers a computationally efficient approach to exploring NAS while minimizing the associated computational costs. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object Detection Enhancement Based on Super-Resolution Mapping 31

Object Detection Enhancement Based on Super-Resolution Mappi...

引用

31st International Conference on electrical engineering, ICEE 2023

作者： Abyazi, Danial Abyazi, Dadfar Yazdi, Mehran Institute for Advanced Studies in Basic Science University Department of Computer Engineering Zanjan Iran Shiraz University Department of Electrical and Computer Engineering Shiraz Iran School of Electrical and Computer Engineering Shiraz Uniersity Shiraz Iran

ISBN: (纸本)9798350312560

Object detection, while being a key step in many applications, has remained challenging, mainly due to the different resolutions of objects in an image. On the other hand, Super-Resolution (SR) approaches have recently been developed to improve the resolution of an image. In this paper, we utilize SR to enhance the quality of images before applying them to a detection model and propose a structure where the detection performance is improved. Furthermore, we remove the image noises by SR methods. Comparisons depict the superior visual performance of the proposed method compared to the conventional detection models. We evaluate our proposed method for detection of solar panels in two countries. To this aim, we created a dataset of satellite images needed for implementing detection models. As a result, we can simply evaluate the usage of solar panels in countries. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Introduction to Quantum Multi-Agent Reinforcement Learning: Concepts and Applications 15

Introduction to Quantum Multi-Agent Reinforcement Learning: ...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Cho, Yeryeong Bin Son, Seok Park, Soohyun Kim, Joongheon Korea University Department of Electrical and Computer Engineering Seoul Korea Republic of Sookmyung Women's University Division of Computer Science Seoul Korea Republic of

ISBN: (纸本)9798350364637

Advancements in quantum computer hardware and software have paved the way for the application of quantum computing across various fields. With the development of computers with thousands of qubits, the power of quantum is increasing. Because of efficiency in high action dimensions, quantum computing has advantages in multi-agent fields where the amount of data is huge. At the same time, reinforcement learning (RL) has gained prominence for its potential in unknown environments. Consequently, the integration of quantum computing and multi-agent reinforcement learning (MARL), known as quantum multi-agent reinforcement learning (QMARL), is proposed. This paper introduces the overall concept and applications of quantum computing, MARL, and QMARL. It also shows the current technology trends depending on the application. In conclusion, the paper presents challenges and future research directions for QMARL and shows that QMARL can be utilized in various applications for excellent performance. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a 4-element Wideband MIMO Antenna for THz Applications 2

Design and Analysis of a 4-element Wideband MIMO Antenna for...

引用

2nd International Conference on Power, electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Jafor, Md. Shakiul Paul, Liton Chandra Mimi, Afsana Hossain, Md. Sadik Al Mamun, Md. Shajol Rahman, Md. Hasibur Department of Electrical and Electronic Engineering Pabna University of Science & Technology Electronic and Communication Engineering Department of Electrical Pabna Bangladesh Pundra University of Science & Technology Department of Computer Science & Engineering Bogura Bangladesh

ISBN: (纸本)9798331517984

In this work, initially a rectangular microstrip patch antenna measuring (94.8 × 110 × 10) μm3 with a polyamide substrate has been analyzed and developed. The antenna has a bandwidth of 170 GHz (1.98 - 2.15 THz) and is tuned to resonate at a frequency of 2.08 THz. Its return loss is -26.733 dB, radiation efficiency is 92%, and maximum gain is 6.35 dB. In addition, the MIMO technology has been implemented to improve performance. Its bandwidth is 210 GHz (1.98-2.19 THz), and it offers a reflection coefficient of -37.75 dB, a radiation efficiency of 95%, and a peak gain of 6.01 dB. The substrate of the four-element MIMO antenna measures (154.8x170x10) μm3. The HFSS platform has been used to perform the modelling and simulation. © 2024 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

IoT in Agriculture: A Review 1

引用

International Conference on Recent Evolutions in Energy, Drives and E-Vehicles, REED-EV 2022

作者： Gupta, S.K. Thakur, Pragya Kumar, Ritik Bharadwaj, Prakhar Department of Electrical Engineering Chandigarh University Mohali India Department of Computer Science Engineering Chandigarh University Mohali India

ISBN: (数字)9789819707638

ISBN: (纸本)9789819707621

Internet of Things technique is being accepted in all the important domains of human existence such as Medical, Defense, e-governance, services, education, pollution, agriculture, and many more. This paper has reviewed the role of IoT in Agriculture domain. Different applications in the domain of agriculture such as automatic water feeding, determining soil composition, crop selection, and the user interface have been studied considering the technologies offered by IoT and its effects. The paper is a complete package for a user who wants to optimize the crop yield and the profit with the help of IoT technology.... © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

LG-FAL: Locality-customized GSA Federated Active Learning 15

LG-FAL: Locality-customized GSA Federated Active Learning

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Wang, Shuwen Zhu, Xingquan Portland State University Department of Computer Science Portland United States Florida Atlantic University Dept. of Electrical Engineering & Computer Science Boca Raton United States

ISBN: (纸本)9798331508821

Federated Learning (FL) is a learning paradigm which constructs machine learning models using decentralized datasets, with the goal of training a globally optimized model while preserving data privacy. In practice, annotating training data for FL is expensive and time-consuming. To solve this problem, researchers proposed to integrate active Learning (AL) strategy as Federated Active Learning (FAL) framework. However, existing research on FAL has two main limitations: (1) In the active learning part, more attention is paid to the global model, while ignoring the local information;(2) In the federated learning part, the popular Federated averaging (FedAvg) method relies on the assumption that the corresponding nodes in distributed neural networks share the same importance when averaging. In this paper, in order to tackle the two limitations, we propose a locality-customized GSA federated active learning (LG-FAL) method. Specifically, (i) both local and global information are taken into consideration to evaluate and select informative data samples to annotate for active learning;(ii) we integrate Gravitational Search Algorithm (GSA) to dynamically average local network parameters into the global parameter, by mimicking the principles of gravity and motion in the universe, for effective federated learning. As a result, LG-FAL can select a small subset of informative samples considering both local and global information, and at the same time, provide an improved trade-off between communication cost and learning accuracy. Experimental results show that LG-FAL significantly outperforms the current state-of-the-art baselines in terms of performance and effectiveness. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Natural Approach for Synthetic Short-Form Text Analysis 30

A Natural Approach for Synthetic Short-Form Text Analysis

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Shao, Ruiting Schwarz, Ryan Clifton, Christopher Delp, Edward J. School of Electrical and Computer Engineering Purdue University West LafayetteIN United States Department of Computer Science Purdue University West LafayetteIN United States

ISBN: (纸本)9782493814104

Detecting synthetically generated text in the wild has become increasingly difficult with advances in Natural Language Generation techniques and the proliferation of freely available Large Language Models (LLMs). Social media and news sites can be flooded with synthetically generated misinformation via tweets and posts while authentic users can inadvertently spread this text via shares and retweets. Most modern natural language processing techniques designed to detect synthetically generated text focus primarily on long-form content, such as news articles, or incorporate stylometric characteristics and metadata during their analysis. Unfortunately, for short form text like tweets, this information is often unavailable, usually detached from its original source, displayed out of context, and is often too short or informal to yield significant information from stylometry. This paper proposes a method of detecting synthetically generated tweets via a Transformer architecture and incorporating unique style-based features. Additionally, we have created a new dataset consisting of human-generated and Large Language Model generated tweets for 4 topics and another dataset consisting of tweets paraphrased by 3 different paraphrase models. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Large datasets

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：