检索结果-内蒙古大学图书馆

5th IEEE Conference on Energy Internet and Energy system Integration, EI2 2021

作者： Guo, Dongxin Wang, Panbao Kong, Jiansheng Tian, Jinjie Ren, Chunguang Meng, Xiangqi Jia, Yanbing Qin, Yue Wang, Zeqi Shanxi Key Lab. of Power System Operation and Control Taiyuan University of Technology Taiyuan China Department of Electrical Engineering Harbin Institute ofTechnology Harbin China Datong Power Supply Company State Grid Shanxi Electric Power Company Datong China School of Electrical and Power Engineering Taiyuan University of Technology Taiyuan China

ISBN: (纸本)9781665434256

This paper proposes an advanced control strategy consisting of current stress optimization based on triple-phase-shifting (TPS) modulation for front-end DAB converter and 33% PWM method for back-end three-phase full bridge inverter. Compared with the traditional phase shift control, the control strategy proposed for the front-end DAB converter achieves linear control and significantly reduces current stress. In addition, it reduces the DC-Link capacitance, which improves the safety of the equipment. The 33% modulation method adopted by the full bridge inverter at the back-end reduces the switching loss of semiconductor devices. The principle, derivation and realization of the proposed control strategy are described in detail. Simulation results are presented to validate the effectiveness of the proposed strategy. © 2021 IEEE

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification

arXiv

引用

arXiv 2022年

作者： Wang, Jiabao Li, Yang Wei, Xiu-Shen Li, Hang Miao, Zhuang Zhang, Rui Army Engineering University of PLA Nanjing210007 China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Lab. for Novel Software Technology Nanjing University Nanjing210023 China

Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose a simple, effective, and practical method, termed as UFCL, to alleviate the gap. Three key issues are concerned and improved: First, we introduce a robust and powerful backbone, ResNet50-IBN, which has an ability of domain adaptation when we transfer ImageNet pre-trained models to FGVC tasks. Next, we propose to introduce HDBSCAN instead of DBSCAN to do clustering, which can generate better clusters for adjacent categories with fewer hyper-parameters. Finally, we propose a weighted feature agent and its updating mechanism to do contrastive learning by using the pseudo lab.ls with inevitable noise, which can improve the optimization process of learning the parameters of the network. The effectiveness of our UFCL is verified on CUB-200-2011, Oxford-Flowers, Oxford-Pets, Stanford-Dogs, Stanford-Cars and FGVC-Aircraft datasets. Under the unsupervised FGVC setting, we achieve state-of-the-art results, and analyze the key factors and the important parameters to provide a practical guidance. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Detecting SO2 and CF4 under high concentration SF6 Using V-shaped Cavity Enhanced Raman Spectroscopy 7

Detecting SO2 and CF4 under high concentration SF6 Using V-s...

引用

7th IEEE International Conference on High Voltage Engineering and Application, ICHVE 2020

作者： Hu, Jin Wan, Fu Chen, Weigen Mao, Hangyin Wang, Pinyi Wang, Jianxin Zhou, Feng Zhu, Chengzhi State Key Lab. of Transmission and Distribution Equipment and System Security and New Technology Chongqing University Chongqing China State Grid Zhejiang Elect Power Co Ltd Zhejiang China

ISBN: (纸本)9781728155111

As an important and widely used electrical equipment, GIS (gas insulated switchgear) greatly affects the stability and safety of the entire power grid. By detecting the concentration of SF6decomposed component gases in GIS, we can judge the faults existing in the GIS, and prevent the corrosive decomposed gases from damaging the insulation. However, existing SF6 decomposition component detection methods can are difficult to achieve relatively accurate simultaneous detection of multi-component gases. In this paper, a method using cavity enhanced Raman spectroscopy was developed to simultaneously detect SO and CF4 under high concentration SF6. Based on frequency-locking cavity enhancement technology, we coupled laser light with a wavelength of 642 nm and a power of about 50 mW into a V-shaped resonant cavity, and realized three orders of power enhancement. Due to the special V-shaped structure of the resonant cavity, the direct reflected light from the cavity mirror will not feedback to the laser, thereby avoiding false locking. Under 1 atmosphere pressure, Raman spectroscopy of CF4 and SO with a concentration of 1% was obtained. The characteristic Raman spectral lines of CF4 and SO were determined as 909 cm-1 and 1151 cm-1, respectively. responding to their v1 transition. And the Raman spectrum of CF4 and SO under the pressure of gradient distribution was obtained, it was found that the Raman characteristic peak intensity of CF4 and SO was highly linear between pressure relationship. Besides, the mixed gas of CF4 and SO under high concentration SF6was detected simultaneously without any interference. This study laid the foundation for Raman spectroscopy for the detection and quantitative analysis of SF6 decomposed gas components, indicating that Raman spectroscopy has great potential in the field of SF6 decomposed gas component detection. © 2020 IEEE.

关键词： Sulfur hexafluoride

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptive Road Perception Network of Autonomous Vehicles

Domain Adaptive Road Perception Network of Autonomous Vehicl...

引用

International Conference on intelligent Transportation

作者： Rui Wang Shichun Yang Yuyi Chen Runwu Shi Zhuoyang Li Jiayi Lu Xinjie Feng Fan Zhou Xiaoyu Yan Yaoguang Cao Department of Transportation Science and Engineering Beihang University Beijing China Innovation Center of New Energy Vehicle Digital Supervision Technology and Application for State Market Regulation Beijing China Research Institue of Aero-Engine Beihang University Beijing China Research Institute for Frontier Science Beihang University Beijing China State Key Lab of Intelligent Transportation System Beijing China

Road conditions can significantly influence the safety of autonomous vehicles (AV). Existing sensors of AV are usually less effective in recognizing road conditions during night and inclement weather. While intelligent tire systems, can identify different road conditions accurately and hardly be affected by weather or illumination conditions. However, data collected under different working conditions differ from each other with significant shifts and are hard to collect due to the tremendous field experiments. To this end, we propose a domain-adaptive model that can extract invariant features to different driving speeds. The proposed method contains two modules: a) a data pre-processing module to extract variable period signals and b) an adversarial transfer learning module for learning invariant features cross working conditions. The field tests have demonstrated that the proposed method performs better on road condition perception than other transfer learning methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

arXiv

引用

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Knowledge-aware Multi-Interest intelligent Model for Sequential Recommendation

Attention-Based Knowledge-aware Multi-Interest Intelligent M...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yang Li Qianmu Li Shunmei Meng Jun Hou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Intelligent Manufacturing Department Wuyi University Jiangmen China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Social Science Nanjing Vocational University of Industry Technology Nanjing China

As a fundamental means of intelligent service, recommender systems have shown a trend of diversification. Sequential recommendation, a class of time-aware methods, aims to predict the user’s next click. Multi-interest representation is a hot topic in recommender systems, but the research on how to apply multi-interest into sequences is still in the minority. And many methods will introduce knowledge graph to improve the representation of items, but how to consider both knowledge graph and user’s multi-interest in sequential recommendation has become a temporary blank. In this paper, we propose an attentive sequential recommendation with knowledge-aware multi-interest module (AKAMI). Items are embedded from the sequence’s structure and user’s interests. Specifically, we represent items by stacking self-attention layers to mine the internal correlation of the sequence. Meanwhile, we segment the sequence via the common neighbors in the knowledge graph and cast the user’s multi-interest based on the aggregation of subsequences. Multi-interests are integrated into item representation by the gating network adaptively. Comprehensive experiments on two real-world datasets show that the proposed model performs better than various representative methods under different evaluation metrics. Additionally, we also visually explain the model through a case study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved UAV Path Optimization Algorithm for Target Accurately and Quickly Localization

An Improved UAV Path Optimization Algorithm for Target Accur...

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Liang, Rui Wu, Kai Xu, Sheng Xu, Tiantian Ma, Xiaoyi Fu, Lianyu City West Power Supply Branch State Grid Tianjin Electric Power Company Tianjin China Shenzhen Institute of Advanced Technology Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen China Shenzhen Institute of Advanced Technology Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China State Grid Tianjin Information Telecommunication Company Tianjin China

ISBN: (纸本)9781665402453

Angle-of-arrival (AOA) target localization using the unmanned aerial vehicle (UAV) has been widely applied in many practical applications. To localize an invasive target quickly and accurately, both the estimation and UAV path optimization algorithms are required. This paper focuses on developing a path optimization method to improve the target estimation performance. Firstly, the problem formulation of AOA target localization is introduced. Secondly, the classical pseudolinear Kalman filter (PLKF) and the gradient-based path optimization are presented. Thirdly, we analyze the problems that existed in the previous methods and propose an improved gradient-descent path optimization algorithm combined with a simple grid search method. Finally, the simulation examples verify the effectiveness of the proposed methods. © 2021 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

Extrinsic Fabry-Perot Sensor for Partial Discharge Acoustic Detection in Liquid 7

Extrinsic Fabry-Perot Sensor for Partial Discharge Acoustic ...

引用

7th IEEE International Conference on High Voltage Engineering and Application, ICHVE 2020

作者： Lei, Jiali Chen, Weigen Zhang, Zhixian Xiang, Shiyezi Li, Zhengqi Liu, Fan State Key Lab. of Transmission and Distribution Equipment and System Security and New Technology Chongqing University Chongqing China State Grid Hubei Electric Power Research Institute Wuhan Hubei China

ISBN: (纸本)9781728155111

Partial discharge online detection technology can reflect the insulation status of electrical equipment. The extrinsic fiber Fabry-Perot sensor uses a diaphragm cavity to sense the changes in interference intensity caused by the sound waves generated by partial discharge. It has stronger resistance to electromagnetic interference, longer transmission distance, and smaller structure, comparing with traditional ultrasonic sensors. With so many advantages, it undoubtedly becomes the focus of research on partial discharge ultrasonic detection. This paper first explores the sensitivity mechanism of optical fiber Fabry-Perot sensors to acoustic signals. Then, according to the change laws of the resonance frequency of the diaphragm with the size parameters, a fiber optic Fabry-Perot partial discharge sensor based on the structure of the nickel circular diaphragm and the quartz tube is developed. The fabricated Fabry-Perot sensor is placed in water, and the acoustic signals from the piezoelectric ceramic transducer driven by the signal generator are detected;the partial discharge ultrasonic signals generated by the pin-plate electrode model in transformer oil are also tested. And the tests have achieved the desired results. © 2020 IEEE.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Controllab.e Electrical Characteristic of Ti3c2t2/Mos2 (T=Oh, F, O) Interfaces for High Performance Electronics: Insights from First-Principles

SSRN

引用

SSRN 2023年

作者： Zhang, Qiang Liu, Yan Zhang, Riguang Lv, Bohan Hao, Runfang Sang, Shengbo Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Electronic Information and Optical Engineering Taiyuan University of Technology Shanxi Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System of The Ministry of Education Taiyuan University of Technology Shanxi Taiyuan030024 China School of Software Taiyuan University of Technology Shanxi Taiyuan030024 China State Key Laboratory of Clean and Efficient Coal Utilization China Laboratory of Aerospace Servo Actuation and Transmission Beijing Institute of Precision Mechatronics and Controls Beijing100000 China

Two-dimensional (2D) semiconductors have shown competitive potential for applications into beyond-silicon electronics. However, the controllab.e electrical characteristic of metal-semiconductor interfaces is still a challenge for high performance electronics due to Fermi level pinning. To explore Ti3C2T2/MoS2 (T= OH, F, O) for high performance electronics, the vertical electric field and interlayer distance are adopted here to regulate the electrical characteristic of interfaces based on the first-principles calculations. Though this, the electrical characteristic of Ti3C2O2/MoS2 and Ti3C2F2/MoS2 are more sensitive to electric field or interlayer distance than that of Ti3C2(OH)2/MoS2. Especially, the negative electric field with larger than -0.2 V/Å makes Ti3C2O2/MoS2 interface change from p-type Schottky to n-type Schottky contact. Furthermore, the Ti3C2O2/MoS2 interface can not only switch from p-type Schottky to n-type Schottky contact, but also from p-type Schottky to n-type Ohmic contact by varying interlayer distance. Moreover, the tunneling barriers of all interfaces are more sensitive to interlayer distance than to electric field. This work provides vital insights for high-performance electronics of Ti3C2T2/MoS2 (T=OH, F, O) in experiments. © 2023, The Authors. All rights reserved.

关键词： Electric fields

来源：评论

学校读者我要写书评

暂无评论

An Application of Auxiliary Operation of Power Dispatching based on Semantic Analysis 12

An Application of Auxiliary Operation of Power Dispatching b...

引用

12th IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2020

作者： Zhang, Tao Li, Hao Lu, Jixiang Jun, Lu Jin Li, Hong Xie, Feng Technology Research Center Nari Group Corporation Nanjing China State Key Lab. of Intelligent Power Grid Protection and Operation Control Nari Group Corporation Technology Research Center Nanjing China

ISBN: (数字)9781728157481

ISBN: (纸本)9781728157481

Power dispatching plays quite an important role in power grid operation in terms of safety and stability. Structured data has been well managed in the real-time power dispatching and controlling system. However, the management of unstructured data such as text data has not received enough attention. In this paper, we accomplish an application of auxiliary operation of power dispatching by doing semantic analysis on operation procedures, which belong to an important category of power dispatching text data for fault disposal. The method that we proposed in our application is achieved based on Natural Language Processing (NLP) technologies. Our contributions are mainly two-fold: 1) we accurately extract key information from text data through our proposed method, and 2) we help power dispatching operators reduce their work and improve efficiency by providing auxiliary operation advice. © 2020 IEEE.

关键词： Semantics

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：