检索结果-内蒙古大学图书馆

12th Iranian Conference on Renewable Energies and Distributed Generation, ICREDG 2025

作者： Fardadidokht, Sahand Talebi, Seyedamirhossein Sadeghian, Salar Zarei, Seyed Fariborz School of Electrical Engineering Iran University of Science and Technology Tehran Iran North Carolina State University Department Electrical and Computer Engineering NC United States Department of Electrical and Computer Engineering Qom Iran

ISBN: (纸本)9798331525132

This paper presents a simple method for predicting inductance in applications of variable inductors with ferrite cores. Today, switching converters are widely used for voltage and current level conversion in renewable energy applications. The variation of inductance in switching converters improves the voltage gain range and other converter characteristics. In this paper, through the analysis of core saturation, a simple circuit model is proposed to predict inductance when the core reaches saturation. This model enables designers to predict inductance variations prior to the winding of the core and the construction of the inductor. Two approaches regarding core permeability are analyzed: the well-known Brauer relationship and a proposed alternative. Finally, the proposed method has been validated and tested on two types of cores, includes E42 and E55. © 2025 IEEE.

关键词： Electric transformers

来源：评论

学校读者我要写书评

暂无评论

Contactless Fingerprint Biometric Anti-Spoofing: An Unsupervised Deep Learning Approach 18

Contactless Fingerprint Biometric Anti-Spoofing: An Unsuperv...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Adami, Banafsheh Hosseinzadehketilateh, Mohammad Reza Karimian, Nima West Virginia University Computer Science and Electrical Engineering United States

ISBN: (纸本)9798350364132

Contactless fingerprint recognition offers a higher level of user comfort and addresses hygiene concerns more effectively. However, it is also more vulnerable to presentation attacks, such as photo-paper, paper printout, and various display attacks, making it more challenging to implement in biometric systems compared to contact-based modalities. Limited research has been conducted on presentation attacks in contactless fingerprint systems, and these studies have encountered challenges in terms of generalization and scalability since both bonafide samples and presentation attacks are utilized during the training model. Although this approach appears promising, it lacks the ability to handle unseen attacks, which is a crucial factor for developing PAD methods that can generalize effectively. We introduced an innovative anti-spoofing approach that combines an unsupervised autoencoder with a convolutional block attention module to address the limitations of existing methods. Our model is trained exclusively on bonafide images without exposure to any spoofed samples during the training phase. It is then evaluated against various types of presentation attack images in the testing phase. The scheme we proposed has achieved an average BPCER of 0.96% with an APCER of 1.6% for presentation attacks involving various types of spoofed samples. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Custom Generative AI Chatbot as a Course Resource

A Custom Generative AI Chatbot as a Course Resource

引用

2024 ASEE Annual Conference and Exposition

作者： Ai, Yutong Baveja, Maya Girdhar, Akanksha O'Dell, Melina Deorio, Andrew Department of Electrical Engineering and Computer Science University of Michigan United States

Generative AI (GenAI) chatbots have taken the world by storm with their ability to summarize information and produce complex natural language *** the same time, the demand for computer science education has grown *** developed a custom GenAI chatbot and released it to over 700 students to assist with a course programming *** tool was trained on the project specification, lecture content, lab materials, and past course forum posts relevant to the *** course is a high-enrollment upper-level computer science elective at a large public research *** project is a simple distributed system using processes, threads, and *** goal of the tool was to provide an additional course resource that supplies valuable information to students comparable to advice they would receive from course *** measured the effectiveness of our tool with a student survey, evaluation by course instructors, and comparison with a state-of-the-art general purpose *** overall survey data indicated high rates of correctness and helpfulness in the Bot *** found that hallucination was not common, and most incorrect responses were identifiable by *** Bot also performed better than general purpose bots for project-specific *** experience can provide insights for faculty using GenAI to assist students in their courses.A customized chatbot can be helpful to students and augment traditional course resources. © American Society for engineering Education, 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

ISHD:Intelligent Standing Human Detection of Video Surveillance for the Smart Examination Environment

引用

computer Modeling in engineering & sciences 2023年第10期137卷 509-526页

作者： Wu Song Yayuan Tang Wenxue Tan Sheng Ren School of Computer and Electrical Engineering Hunan University of Arts and SciencesChangde415000China School of Information Engineering Hunan University of Science and TechnologyYongzhou425119China School of Computer Science and Engineering Central South UniversityChangsha410083China

In the environment of smart examination rooms, it is important to quickly and accurately detect abnormal behavior(human standing) for the construction of a smart campus. Based on deep learning, we propose an intelligentstanding human detection (ISHD) method based on an improved single shot multibox detector to detect thetarget of standing human posture in the scene frame of exam room video surveillance at a specific examinationstage. ISHD combines the MobileNet network in a single shot multibox detector network, improves the posturefeature extractor of a standing person, merges prior knowledge, and introduces transfer learning in the trainingstrategy, which greatly reduces the computation amount, improves the detection accuracy, and reduces the trainingdifficulty. The experiment proves that the model proposed in this paper has a better detection ability for the smalland medium-sized standing human body posture in video test scenes on the EMV-2 dataset.

关键词： Deep learning object detection video surveillance of exam room smart examination environment

来源：评论

学校读者我要写书评

暂无评论

Improving TRISAT-R Satellite Attitude Prediction by Incorporating a High-Resolution Optical Sensor to Kalman Filtering 15

Improving TRISAT-R Satellite Attitude Prediction by Incorpor...

引用

15th International Conference Elektro, ELEKTRO 2024

作者： Kramberger, Iztok Kosanic, Nejc University of Maribor Faculty of Electrical Engineering and Computer Science Maribor Slovenia

ISBN: (纸本)9798350372359

When flying a satellite, various operations on-board the satellite require determining quite a precise orientation to properly function, such as Earth or Sun observation, downlink communication and similar. This results in satellite attitude estimation posing a crucial problem to be solved, using a wide array of spacecraft control systems and sensor readings. Due to the noise in magnetic sensor measurements and drift in gyro meters, auxiliary (optical) subsystems are widely used to add reference measurements and correct the noise and the drift. Since the star-trackers, most widely used optical subsystem for attitude estimation, can be relatively large and high energy consuming, a smaller alternative is found in photodiodes and small CMOS cameras, both of which are being currently used on board TRISAT-R. Even with additional optical filters, there is error present in all measurements and error estimation is necessary. Recently the development and use of Unscented Kalman Filter (UKF) has shown greater potential for use in space related estimation, due to UKF not using classic Kalman linearization but employing a set of sigma points to calculate the systems mean and covariance more accurately. TRISAT-R use of on-board systems to tackle the problem of attitude estimation is described. UKF filtering is briefly discussed, and the simulation model for UKF of TRISAT-R orbiting is proposed. The results show an increase in accuracy of attitude prediction when using CMOS cameras for prediction instead of photodiodes, which confirms the idea that small cameras can be used for in-orbit photodiode calibration. © 2024 IEEE.

关键词： Photodiodes

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Aviation Materials Surface Defection Classification: From Non-Standardized Image Acquisitions 4

Few-Shot Aviation Materials Surface Defection Classification...

引用

4th International Symposium on Intelligent Robotics and Systems, ISoIRS 2024

作者： Wu, Zewei Peng, Chengbin Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798350364798

Defect classification in the aviation industry plays a crucial role in manufacturing. However, in non-standardized captured scenes, the object to be inspected and the background are often complex and variable, e.g., lighting, angle, occlusion, etc., which can affect the core features of the image data. Therefore, achieving accurate classification using a limited number of defect samples from products photographed in non-standardized environments has emerged as a challenging yet promising research focus. To address this issue, this study proposes a learning approach that can be trained using standardized industrial defect datasets to detect defects in few-shot, non-standardized industrial defect production. Specifically, this approach initially utilizes the knowledge acquired from a standardized pre-training dataset to crop the data within the query set. Subsequently, an embedding extraction is employed to obtain feature embedding and classification results. Our practice demonstrates a performance improvement of roughly 5% on non-standard datasets compared to few-shot classification methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Closed form Solution of Moving Source Localization Using TDOA and FDOA Measurements Under Sensor Location Errors 16

Closed form Solution of Moving Source Localization Using TDO...

引用

16th International Conference on Communication Software and Networks, ICCSN 2024

作者： Sheng, Menglei Li, Youming Zhou, Yapeng Cai, Wanyuan Qi, Qinke Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China

ISBN: (纸本)9798331506322

The moving source localization is very sensitive to the knowledge of sensor locations. In this paper, we propose a two-stage closed-form method for locating a moving source by using Time Difference of Arrival (TDOA) and Frequency Difference of Arrival (FDOA) measurements in the presence of random errors in sensor locations. In the first stage, we establish a series of pseudo-linear equations by introducing the auxiliary variables and obtain an initial location estimation based on the bias reduced criteria and the Lagrange multiplier theory. In the second stage,we propose a modified weighted least squares method to obtain the final estimation by exploring the relationship between the auxiliary variables and the moving source location and velocity. The proposed method is in closed form and therefore computationally efficient as well as free from the divergence problem unlike iterative techniques. Simulations show the better performance of the proposed method. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Searching for Benchmark Problem Instances from Data-Driven Optimisation

Searching for Benchmark Problem Instances from Data-Driven O...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Hajari, Sara Gallagher, Marcus School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia

ISBN: (纸本)9798400704956

Given the large number of existing metaheuristic optimisation algorithms, there has been an increasing focus on improving benchmarking practices, to gain an improved understanding empirical performance, as well as matching algorithms and problems. One important aspect of this more diversity in test problem sets so that algorithms are evaluated on a wider range of problem instances, including problems that are more real-world *** this paper, we explore data-driven benchmarking problems. By perturbing the data, we perform meta-search over this space of problem instances. Specifically, we consider sum of squares clustering problems and find instances that test CMA-ES. This approach can be effective, even when the dataset is very simple. In addition, we show that simple clustering instances have interesting properties, including neutrality (missing from many commonly-used benchmarks). We argue that data-driven optimisation can provide useful insights into problem structure and algorithm behaviour. © 2024 Copyright held by the owner/author(s).

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Solid-if-IoT: An Internet of Things Client Bridge to Interface with Solid Backend Infrastructure

Solid-if-IoT: An Internet of Things Client Bridge to Interfa...

引用

2024 IEEE Green Technologies Conference, GreenTech 2024

作者： Grider, Zachary Nelson, Alexander H. University of Arkansas Electrical Engineering and Computer Science Fayetteville United States

ISBN: (纸本)9798350308587

Web decentralization has the potential to radically change the way we produce, store, and manage data. Much of the focus of decentralization has been on blockchain tech-nologies which have high energy requirements. An alternative and potentially complementary decentralization technology exists in the form of the Solid project. Solid primarily exists for the decentralization of online social data that is prevalent in social media. However, many of the key challenges to realizing a decentralized social web exist in the current Internet of Things (IoT). IoT-especially industrial IoT-is currently a collection of many intranets of things rather than an interconnected network of machines. Those devices that are public facing produce data and consume commands often devoid of context. Devices at the edge are resource constrained and the overhead of many decentralization technologies may be technologically infeasible or would result in performance degradation. It is our hypothesis that a mechanism to overcome some of these challenges can exist in the form of a client bridge to integrate IoT devices with the Solid infrastructure, which would in turn enable finer access control and improved context that are necessary to realize a more interconnected Internet of Things. This work demonstrates the feasibility of this paradigm, and plots future directions to bring this technology to fruition. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

The Analysis and Design of a Resonant Capacitively-Isolated Cockcroft-Walton Converter 14

The Analysis and Design of a Resonant Capacitively-Isolated ...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Rabenold, Elizabeth Jerez, Raiphy Coday, Samantha Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798331516116

Capacitive isolation is a potential alternative to magnetics-based isolation in emerging applications, such as in partial power processing converter topologies, and in applications where weight and component volume are limiting factors. This work presents a capacitively-isolated Cockcroft-Walton converter capable of isolation through the flying capacitors. Generalized equations for mid-range flying capacitor voltages and switch voltages for converters of even level count are detailed. Experimental results validate the topology and analysis with a hardware prototype demonstrating 120 V input, 93.87% efficiency, and up to 60 V of isolation. © 2025 IEEE.

关键词： Topology

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：