检索结果-内蒙古大学图书馆

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Al-Olimat, Khalid S. Ohio Northern University Department of Electrical & Computer Engineering and Computer Science AdaOH45810 United States

ISBN: (纸本)9798350336429

Utilizing student-led case studies as an innovative educational tool can effectively introduce real-world practices into the power engineering classroom. By assigning students to draft a story around a case study, they are given ownership and agency to hone their problem-solving, self-directed learning, and team skills. These case studies are grounded in real-world situations, providing students with opportunities to enhance their domain knowledge in power engineering. The use of case studies offers several advantages, including promoting active and engaged learning, encouraging critical thinking and problem-solving, enhancing the relevance and applicability of course content, facilitating teamwork and collaboration, promoting diversity, and encouraging the use of real-world examples and data. The interactive learning strategy of case studies shifts the emphasis from teacher-centered to more student-centered activities, resulting in a more engaging and immersive learning experience. Evaluation of students' perception and attitude toward this teaching method showed that students have better understanding of the course materials and an appreciation of the method for promoting diversity and entrepreneurial mindset. © 2023 IEEE.

关键词： Case studies diversity entrepreneurial mindset student perception and attitudes

来源：评论

学校读者我要写书评

暂无评论

4D Structured Tensor Decomposition-Based Channel Estimation for RIS-Aided mmWave MIMO-NOMA System in Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第12期12卷 22298-22310页

作者： Cai, Wanyuan Li, Youming Wu, Yonghong Sheng, Menglei Qi, Qinke Guo, Qiang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China China Research Institute of Radiowave Propagation Qingdao266107 China Harbin Engineering University College of Information and Communication Engineering Harbin150000 China

Severe Doppler shift and the obstruction of the line-of-sight (LoS) path significantly decrease the communication performance. This article considers a downlink channel estimation problem for reconfigurable intelligent surface (RIS)-aided millimeter-wave (mmWave) multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) system in Internet of Vehicles (IoVs) with high-mobility scenarios. By introducing the concept of aggregated slot and half slot, a 5G subframe partitioning scheme without changing the standard 5G frame structure is first proposed to facilitate the formulation of the received signal. Then, the received signal is modeled as a quadrilinear tensor, meeting with a canonical polyadic decomposition (CPD) form, which separates angle of arrival (AoA), angle of departure (AoD), time delay, and Doppler shift into four corresponding factor matrices and avoids parameters coupling. Subsequently, by leveraging the Vandermonde structure of the factor matrix and the low-rank property of the mmWave channel, we design a four-dimension (4D) structured tensor decomposition-based method to decompose the tensor into four factor matrices in a closed-form solution, which can avoid initialization and iteration. Accordingly, the channel parameters can be extracted by a simple correlation-based estimator. After obtaining the channel parameters, we construct a least squares problem to obtain the channel path gain, which can avoid solving the scaling matrix. Finally, numerical experiments are conducted to confirm the effectiveness of the proposed algorithm, in which the Cramér-Rao bound (CRB) results for channel parameters are derived as the benchmark. © 2014 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Tackling System Induced Bias in Federated Learning: Stratification and Convergence Analysis 42

Tackling System Induced Bias in Federated Learning: Stratifi...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Tang, Ming Wong, Vincent W. S. Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350334142

In federated learning, clients cooperatively train a global model by training local models over their datasets under the coordination of a central server. However, clients may sometimes be unavailable for training due to their network connections and energy levels. Considering the highly non-independent and identically distributed (non-IID) degree of the clients' datasets, the local models of the available clients being sampled for training may not represent those of all other clients. This is referred as system induced bias. In this work, we quantify the system induced bias due to time-varying client availability. The theoretical result shows that this bias occurs independently of the number of available clients and the number of clients being sampled in each training round. To address system induced bias, we propose a FedSS algorithm by incorporating stratified sampling and prove that the proposed algorithm is unbiased. We quantify the impact of system parameters on the algorithm performance and derive the performance guarantee of our proposed FedSS algorithm. Theoretical and experimental results on CIFAR-10 and MNIST datasets show that our proposed FedSS algorithm outperforms several benchmark algorithms by up to 5.1 times in terms of the algorithm convergence rate. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Integrating cycleGAN and BERT for Chinese text style transfer

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Chou, Chien-Hsing Chou, Cheng-Hou Hsieh, Yi-Zeng Yang, Tzu-Shien Department of Mathematics and Information Education National Taipei University of Education Taipei Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Electrical and Computer Engineering Tamkang University New Taipei Taiwan

In this study, we integrate the Bidirectional Encoder Representations from Transformers (BERT) model with the Cycle Generative Adversarial Network (CycleGAN) to create a system for Chinese text style transfer. Natural language processing (NLP) involves converting human languages into data interpretable by computers, enabling applications like text classification, chatbots, and dialogue systems. Recent advancements, such as Google's transformer model and the BERT technique, have significantly improved NLP capabilities through self-attention mechanisms and unsupervised pretraining. Text style transfer modifies the style of texts without altering their semantics. Previous methods like StyIns and models based on disentangled representation learning highlight the challenges of retaining text meaning during style transfer. Our system leverages CycleGAN’s unsupervised learning to convert unpaired data between wuxia and fantasy styles while preserving semantics. Using the pretrained BERT model from the Chinese Knowledge and Information Processing (CKIP) Lab, our experimental results demonstrate successful style conversion, maintaining the original meanings of texts. This integration of BERT and CycleGAN shows promise for further advancements in NLP applications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Assessing LWIR and Visual Sensor Modalities for UAV Detection and Tracking

Assessing LWIR and Visual Sensor Modalities for UAV Detectio...

引用

2024 Intermountain engineering, Technology and Computing, IETC 2024

作者： Wadsworth, Emma Brinton, Jacob Vannoy, Trevor C. Whitaker, Bradley M. Computer Engineering University of Utah Salt Lake CityUT United States Computer Science Boston University BostonMA United States Montana State University Electrical and Computer Engineering BozemanMT United States Montana State University Electrical and Computer Engineering and Optical Technology Center BozemanMT United States

ISBN: (纸本)9798350373073

The development of unmanned aerial vehicles has led to a proliferation of drones being used for many different tasks. This necessitates systems for preventing collisions and other accidents, as well as malicious activities that could be carried out by drone operators. A vital part of that task is detecting and tracking drones. Different sensors have different strengths and weaknesses, so it is likely that a combination of sensors will be used in future systems. In order to facilitate the design of such systems, the limitations of current sensors and methods should be assessed. Here, the limitations of single-frame LWIR and RGB camera data are analyzed. Deep learning methods are applied to data at different ranges of pixels-on-target. The given results document the relative success of current single-frame detection methods on these drone targets. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Novel Complexity Scoring Model for Non-Functional Requirements in Request for Proposal in Housing Industry Using FURPS Quality and Moscow Priority Model

引用

International Journal for Housing science and Its Applications 2024年第4期45卷 30-40页

作者： Rashid, Ekbal Mastorakis, Nikos E. Technical University of Sofia Sofia Bulgaria Sector of Electrical Engineering and Computer Science Hellenic Naval Academy Piraeus Greece English Language Faculty of Engineering Technical University of Sofia Sofia Bulgaria

In this research paper we have attempted to elicit Non-Functional Requirements (NFR) which may or not have been explicitly added to the Request for Proposal (RFP) in housing industry but is important for the success of the program. We have used real time RFPs for the elicitation of NFRs. The sales proposal process, also known as response to RFP process, refers to the methodical steps a vendor takes when developing a proposal in response to a buyer’s RFP which will have details of integrating systems, Software platforms, users, business outcomes, limitations, functional requirements, and may be nonfunctional requirements (NFR). There is some work done by researchers on assessing opaqueness of NFRs and traceability of NFR. But there has been no work on a complexity scoring model for NFRs which enables a vendor to respond to an RFP with best price and schedule. The paper proposes a novel complexity scoring model for NFRs in RFP in Housing industry by using FURPS (Functionality, Usability, Reliability, Performance, Supportability) quality attribute model in conjunction with MoSCoW(Must Have, Should Have, Could Have, Won’t Have) priority model by using mathematical formula. The working model is broken down in steps for Sales and pre-Sales teams of the Vendor and is ready for adoption. © 2024 International Association for Housing science. All rights reserved.

关键词： complexity scoring model construction cost FURPS housing linear regression MoSCoW NFR RFP scatter plot

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Unmixing-Based Anomaly Detection 7

Hyperspectral Unmixing-Based Anomaly Detection

引用

Computational Imaging VII 2023

作者： Younis, Mohammed Hossain, Mazharul Robinson, Aaron Wang, Lan Preza, Chrysanthe Electrical and Computer Engineering Department China Computer Science Department The University of Memphis MemphisTN United States

ISBN: (数字)9781510661615

ISBN: (纸本)9781510661608

Research supporting improved anomaly detection performance benefits a wide range of technical applications. Thus, the definition of anomalies and the subsequent means to detect them are wide-ranging. This treatment presents an overview of the development of an anomaly detection approach based on spectral signatures obtained with hyperspectral unmixing. Anomaly Detection is a binary classification that does not require prior information about the anomaly. For example, an anomaly detector applied to hyperspectral imaging (HSI) would take a hyperspectral image with hundreds of channels as an input and output a two-dimensional image map of pixel intensities based on a threshold procedure applied to the probability of that pixel being an anomaly. There have been many advancements in the field of HSI Anomaly Detection. Our ensemble method algorithm, presented here, addresses some of the shortcomings of current state-of-the-art techniques. We present details about the extracted end-members and use them for effective anomaly detection. Our current ensemble method opens the path for future machine-learning processes. We evaluated our method on multiple datasets and reported the F1-macro score. We suggest that the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve should not be used in Hyperspectral anomaly detection as an evaluation metric. © 2023 SPIE. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Efficient Scene Reconstruction for Unmanned Aerial Vehicles 5

Efficient Scene Reconstruction for Unmanned Aerial Vehicles

引用

5th International Conference on Transdisciplinary AI, TransAI 2023

作者： Bond, Yeana L. Ledwell, Spencer Osornio, Esmeralda Cruz, Alberto C. California State University Bakersfield Department of Computer & Electrical Engineering & Computer Science Bakersfield93311 United States

ISBN: (纸本)9798350358018

There is demand for small, cost-effective Unmanned Aerial Vehicles (U A V s) in industrial applications. These machines are expected to perform autonomous decision-making tasks. Recent work shows promise for systems based on images or video. We are motivated to study Structure From Motion (SFM), a three-dimensional (3D) reconstruction technique from two-dimensional images. It uses low-cost cameras rather than expensive LIDAR such as laser scanning sensors. The goal of this work is to seek an efficient way to improve accuracy and performance of SFM on small UAVs that lack the computation needed to perform costly algorithms such as neural networks. A major step of SFM is to estimate the homography between two views of the same scene by matching pairs of distinct features in an image (also known as geometric verification). Accurate estimation of pairs leads to better 3D models. We study feature-based homography estimation with various Random Sample Consensus (RANSAC) algorithms. Specifically, pre-sampling is one of the most common strategies utilized to improve the original RANSAC algorithm. Inspired by the work of others, we implement a new pre-sampling RANSAC method. Our adaptation, Blur and Contrast RANSAC (BC-RANSAC), has state-of-the-art performance while reducing run-time by a factor of 6.78. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Integrated On-Board Battery Charger with Galvanic Isolation based on 6-Phase SPM Synchronous Machine for Electric Aircraft 50

Integrated On-Board Battery Charger with Galvanic Isolation ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Metwly, Mohamed Y. He, JiangBiao Abdel-Khalik, Ayman S. Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN United States Department of Electrical Engineering Alexandria University Alexandria Egypt

ISBN: (纸本)9781665464543

Aircraft electrification has received increasing attention due to the significant benefits, such as low carbon emissions, high energy efficiency, low operation cost, and reduced acoustic noise. Limitations on both the low energy density with the present battery technologies and slow battery charging speed highly affect the widespread adoption of electric aircraft, especially for megawatt-scale large aircraft. Thus, this paper presents an isolated integrated on-board battery charger (IOBC) using an existing six-phase surface-mounted permanent magnet (SPM) synchronous propulsion machine for MW-scale electric aircraft. Besides exploiting the existing powertrain apparatuses, i.e., the six-phase motor and inverter, in the propulsion and charging modes of operation, the proposed charger offers galvanic isolation to meet safety standards and code compliance. Moreover, zero average torque production during charging and unity power factor operation at the grid side can be simultaneously achieved. The proposed charger concept entails simple hardware reconfiguration to switch between the propulsion and charging modes of operation. Furthermore, this paper adopts a 36-slot/34-pole fractional slot concentrated winding (FSCW)-based SPM machine, which is designed and optimized based on the magnetic equivalent circuit (MEC) model and the multi-objective genetic algorithm (MOGA) design optimization approach, respectively. Eventually, theoretical findings are verified based on 2D and 3D finite element (FE) simulations. © 2024 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Transforming Sustainable Aquaculture: Synergizing Fuzzy Systems and Deep Learning Innovations

引用

International Journal of Fuzzy Systems 2024年第8期26卷 2536-2552页

作者： Haobijam, Basanta Huang, Yo-Ping Chang, Yue-Shan Chang, Tsun-Wei Department of Electrical Engineering National Taipei University New Taipei City23741 Taiwan Department of Electrical Engineering National Penghu University of Science and Technology Penghu88046 Taiwan Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Computer Science and Information Engineering National Taipei University New Taipei City23741 Taiwan Department of Information and Communication Engineering Chaoyang University of Technology Taichung41349 Taiwan Department of Computer Science and Information Engineering HungKuo Delin University of Technology New Taipei City236302 Taiwan

Pisciculture encounters an array of intricate challenges that span disease management, preservation of water quality, prevention of genetic hybridization, ensuring the integrity of net systems, sourcing sustainable aquatic feed, and comprehending fish growth and reproductive dynamics. Addressing these multifaceted challenges necessitates a comprehensive research approach. This study employs an innovative synergy of fuzzy logic and deep learning techniques, resulting in a robust strategy to tackle these obstacles effectively. Fuzzy logic excels in assessing stressed fish conditions by handling inherent uncertainties. Simultaneously, YOLOv7 with fuzzy color enhancement (YOLOv7FCE) is used to detect damaged fish nets, thereby mitigating losses and upholding the integrity of the net infrastructure. This approach also leverages YOLOv7FCE for identifying Cobia fish within shoals, streamlining the identification process. Subsequently, DeepLabv3 is implemented to meticulously segment the recognized Cobia fish, facilitating precise measurements of their physical attributes. This comprehensive methodology yields profound insights into growth patterns and feeding tendencies within the confined aquatic environment. By embracing this approach, the research presents a versatile and adaptive framework that not only enhances our comprehension of piscine dynamics but also holds the potential to revolutionize the aquaculture industry. © The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association 2024.

关键词： Fish

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：