检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zeng, Chunyan Ye, Jiaxiang Wang, Zhifeng Zhao, Nan Wu, Minghu Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China School of Educational Information Technology Hubei Research Center for Educational Informationization Central China Normal University Wuhan430079 China

Most Deep Learning (DL) based Compressed Sensing (DCS) algorithms adopt a single neural network for signal reconstruction, and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose unified framework, which jointly considers the sampling and reconstruction process for image compressive sensing based on welldesigned cascade neural networks. Two sub-networks, which are the sampling sub-network and the reconstruction sub-network, are included in the proposed framework. In the sampling sub-network, an adaptive full connected layer instead of the traditional random matrix is used to mimic the sampling operator. In the reconstruction sub-network, a cascade network combining stacked denoising autoencoder (SDA) and convolutional neural network (CNN) is designed to reconstruct signals. The SDA is used to solve the signal mapping problem and the signals are initially reconstructed. Furthermore, CNN is used to fully recover the structure and texture features of the image to obtain better reconstruction performance. Extensive experiments show that this framework outperforms many other state-ofthe-art methods, especially at low sampling rates. Copyright © 2022, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

A Multi-Dimensional Assessment Model and Its Application in E-learning Courses of Computer Science 20

A Multi-Dimensional Assessment Model and Its Application in ...

引用

21st Annual Conference of the Special Interest Group in Information Technology Education, SIGITE 2020

作者： Luo, Jiwen Lu, Feng Wang, Tao Key Lab. of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781450370455

Computer science is a practical discipline. It is always a great challenge to evaluate students' computer practice using computer-aided means for large scale students. We always need to address problems such as suspected plagiarism and deviation of the overall difficulty factor. In this paper, a multi-dimensional assessment model is designed for CS courses based on the detailed practice processing data in an E-learning system. The model comprehensively evaluates the students' learning process and results in three aspects of correctness, originality, and quality detection. Besides, the teacher can easily participate in the assessment according to their needs. The correctness is an essential requirement, and the originality is based on the clustering results of students' behaviors after clone detection to curb homework plagiarism. SonarQube is used to detect code quality and put forward higher requirements for codes. Manual participation intelligence has improved the flexibility and applicability of the model to a certain extent. We applied this model on the EduCoder online education platform and carried out a comprehensive analysis of 485 students in the Parallel Programming Principles and Practice Class of Huazhong University of Science and Technology. Experiment results confirm the distinction, rationality, and fairness of the model in assessing student performance. It not only gives students a credible, comprehensive score in large-scale online practical programming courses but also gives teachers and students corresponding suggestions based on the evaluation results. Furthermore, the model can be extended to other online education platforms. © 2020 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Influence of Electrical Tree Aging on the Dielectric and Trap Properties of XLPE Insulation 4

Influence of Electrical Tree Aging on the Dielectric and Tra...

引用

4th IEEE China International Electrical and Energy Conference, CIEEC 2021

作者： Xie, Kun Ren, Chengyan Lin, Tiandi Zhang, Cheng Zhang, Wei Hu, Libin Chen, Jie Hubei University of Technology Hubei Key Lab. for High-Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan China Chinese Academy of Sciences Beijing International St Cooperation Base for Plasma Science and Energy Conversion Institute of Electrical Engineering Beijing China State Grid Jiangsu Electric Power Co. Ltd. Research Institute Nanjing China

ISBN: (纸本)9781728171494

The dielectric and charge properties of XLPE insulation with different service periods are important to estimate the aging state of high voltage cables. The accelerated aging experiment was carried out to obtain the aged XLPE samples with the needle-plate electrodes using power frequency AC source. The surface composition and dielectric parameters of XLPE samples were measured and analyzed with the Fourier Transform Infrared Spectroscopy (FTIR) and impedance analyzer. The surface potential and trap distribution of XLPE samples were measured by the isothermal surface potential decay (ISPD) method. The tested objects include the new XLPE sample, the samples with different electrical tree lengths, and the one with electrical tree breakdown. The results show that the aging of the electrical tree changes the dielectric parameters and trap distribution of XLPE samples. The dielectric constant increases with the length of electrical tree. The deeper and shallower traps appear simultaneously in the surface layer of XLPE insulation after electrical tree aging, and the trap density increases with the length of electrical tree. The trap energy level is the lowest and the trap density is the largest in the sample with electrical tree breakdown. The FTIR result shows that the absorption peaks of XLPE backbone structure decline obviously after electrical tree aging. The fracture of molecular chain and formation of low density area in XLPE sample are the main reasons for the change of dielectric and trap after electrical tree aging. © 2021 IEEE.

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Experimental study on thermal catalytic degradation of SF6 waste gas by phosphate and metal oxides 7

Experimental study on thermal catalytic degradation of SF6 w...

引用

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

作者： Hao, Xiong Wenjiang, Li Hang, Liu Yi, Wang Xiaoxing, Zhang Maintenance Branch State Grid Chongqing Electric Power Company Chongqing China Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan China

ISBN: (纸本)9781728155111

The SF6 abatement strategies had received special attention due to the fact that SF6has very high global warming potentials and long atmospheric lifetime. The use of degradation method can effectively eliminate the greenhouse effect caused by SF6 exhaust gas. In this paper, Zr(PO4)4, AlPO4, NiO and FeO4 were used as catalysts to degrade SF6 gas (the volume ratio of SF6 was 15% and the background gas was air) at 800 ?. The concentration of SF6 gas was detected by gas chromatograph to obtain degradation rate, the partial degradation products of SF6 gas were quantitatively analyzed by gaschromatograph-mass spectrometer, and the main products detected were SOF, SOF and SO gas. Comparing the product formation characteristics of four groups of test products when phosphate and metal oxide were used as catalysts, the gas production of SO was the most at the same temperature. When Zr(PO4)4 and AlPO4 were used as catalyst, the SOF gas production reached dynamic equilibrium at 31300ppm and 2385ppm respectively after heating for 4h, and the generated SOF gas presented a linear growth. When NiO and Fe3O4 were used as catalyst, SOF and SOF gases were both linearly increased. When Zr(PO4)4 was used as catalyst, compared with other catalysts, the amount of SOF produced was the largest. NiO had a good catalytic effect, and the degradation rate of SF6 gas reached 27.07% within 12h. The main decomposition products were SOF, SOF and SO gas, which could be filtered out by lye, which was of great significance for reducing greenhouse gas caused by SF6 exhaust gas emissions. © 2020 IEEE.

关键词： Sulfur hexafluoride

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Design of Multi-Disc Coreless Axial Magnetic Flux Permanent Magnet Motor

Electromagnetic Design of Multi-Disc Coreless Axial Magnetic...

引用

2020 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2020

作者： Wang, Xiaoguang Zhao, Meng Wan, Ziwei Xu, Wei Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan430068 China

ISBN: (纸本)9781728152158

In this paper, a multi-disc coreless axial magnetic flux permanent magnet (AFPM) motor is presented. This motor takes the advantage of single-phase winding and H-bridge drive topology, which improve the fault-tolerant performance of the motor and greatly simplify the winding process. According to the performance requirement of the motor, the size, permanent magnet (PM) structure, yoke structure and the winding are designed. The model of the motor is built by the three-dimensional finite element analysis (FEA) method. The air gap magnetic flux density, back EMF and the torque of the motor are investigated. Also, the stress of the motor is studied to verify the reliability of the motor. © 2020 IEEE.

关键词： Bridge circuits

来源：评论

学校读者我要写书评

暂无评论

Performance of an Axial Flux Hybrid Excitation Motor with SMC for HEVs

Performance of an Axial Flux Hybrid Excitation Motor with SM...

引用

2020 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2020

作者： Wang, Xiaoguang Wan, Ziwei Zhao, Meng Xu, Wei Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan430068 China

ISBN: (纸本)9781728152158

Axial flux permanent magnet (AFPM) motors are used as drive motors for hybrid vehicles due to their high torque/power density and high efficiency. This technology makes the use of soft magnetic composites (SMC) attractive for both manufacturing and performance. SMC has the characteristics of low eddy current loss, convenient processing, low magnetic permeability, low mechanical strength. An additional dc magnetic field excitation coil is added to the motor to overcome the shortcomings of the low torque density of the SMC, which ensures the high performance of the motor. The performance of axial flux hybrid excitation motor (AFHEM) is evaluated based on finite element analysis (FEA) method. The analysis results show that the proposed motor is able to achieve high torque density and wide speed range, which are suitable for hybrid electric vehicles. © 2020 IEEE.

关键词： Hybrid vehicles

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

Optimization on Weighting Factors of Model Predictive Control Based on Fuzzy Technique for Linear Induction Machine

Optimization on Weighting Factors of Model Predictive Contro...

引用

2020 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2020

作者： Tang, Lei Wang, Xiaoguang Xu, Wei School of Electrical Engineering Southwest Jiaotong University Chengdu611756 China Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China State Key Laboratory of Advanced Electromagnetic Engineering and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781728152158

Compared with direct thrust control and vector control methods, the model predictive control (MPC) is recognized as a more effective approach. However, the weighting factors in the objective function must be tuned, which greatly increases the computation burden. In this work, based on the fuzzy technique, one weighting factor optimization method is proposed to identify the suitable control action for the linear induction machine (LIM), which can effectively simplify the selection process. At last, comprehensive simulation results have demonstrated the excellent performance of the proposed method. © 2020 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Battery state-of-charge estimation based on fuzzy dual kalman filter algorithm 3

Battery state-of-charge estimation based on fuzzy dual kalma...

引用

3rd IEEE International Conference on Electronic Information Technology and Computer Engineering, EITCE 2019

作者： DIng, Wen-Fang Fu, Xiao-Guang Zhang, Xuan-Hao Hubei University of Technology Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan China

ISBN: (数字)9781728135847

ISBN: (纸本)9781728135847

Extended Kalman filter (EKF) algorithm can be used as a model-based approach to estimate the state of charge (SOC) of batteries, and the accuracy of SOC estimation can be affected by the error of battery model. Moreover, a large current or current change leads to a large model error. A fuzzy dual Kalman filter (Fuzzy-DKF) algorithm was proposed to estimate SOC in this paper. Specifically, Thevenin equivalent circuit model was established, and was transformed to autoregressive exogenous (ARX) model, the parameters of ARX model were identified by Kalman filter (KF) algorithm;current and current change were monitored in real time and a fuzzy control system was built to reduce the impact of model error by modifying Kalman gain;EKF algorithm was adopted to estimate SOC. The results indicate that the accuracy of SOC estimation based on Fuzzy-DKF algorithm is better than the accuracy of SOC estimation based on EKF algorithm or dual Kalman filter (DKF) algorithm. © 2019 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Circulation suppression control method based on dynamic droop coefficient adjustment 3

Circulation suppression control method based on dynamic droo...

引用

3rd IEEE International Conference on Electronic Information Technology and Computer Engineering, EITCE 2019

作者： Qiang, Fu Jie, Zhang Meng-Xiang, Wang Hubei University of Technology Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan China

ISBN: (纸本)9781728135847

This paper investigates problem of circulating current between the output terminals of parallel converters in DC microgrid system. The dynamic regulation droop control proposes a drooping coefficient with real-time variation to minimize the circulating current. By monitoring the voltage deviation of the converter output port, the dynamic droop coefficient is accurately corrected so that the circulating current in the parallel converter system can be stably and well controlled. Matlab.simulation results analysis, compared with the traditional control method, the circulating current problem has been improved. © 2019 IEEE.

关键词： MATlab

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：