检索结果-内蒙古大学图书馆

Application of Broad Learning System for Image Classification Based on Deep Features 5th

学校读者我要写书评

暂无评论

Application of Broad Learning System for Image Classificatio...

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhang, Dan Zuo, Yi Chen, Philip C. L. Wang, Chiye Li, Teishan Navigation College Dalian Maritime University Dalian116026 China Innovation and Entrepreneurship Education College Dalian Minzu University Dalian116600 China Computer Science and Engineering College South China University of Technology Guangzhou510641 China Department of Computer and Information Science Faculty of Science and Technology University of Macau 99999 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9789811623356

Due to large amount of image data, the accuracy and real-time performance of classification are difficult problems in image classification. On the one hand, the broad learning system (BLS) has achieved good results in the timeliness of classification. On the other hand, deep learning feature extraction effect is good, but its structure is complex and the training time is long. Therefore, based on the above advantages of both methods, this paper proposed BLS based on deep features for image classification. Firstly, a feature extractor is constructed based on the ResNet101 to obtain the deep features of the classification image. Then, the feature nodes and enhancement nodes of BLS are constructed based on the deep features. Through the experiment, our method has two performance on benchmark datasets: high classification accuracy, good real-time. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Image classification

Deep Learning based Performance Testing for Analog Integrated Circuits

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Cao, Jiawei Guo, Chongtao Li, Hao Wang, Zhigang Wang, Houjun Li, Geoffrey Ye School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Guangdong Shenzhen518110 China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom

In this paper, we propose a deep learning based performance testing framework to minimize the number of required test modules while guaranteeing the accuracy requirement, where a test module corresponds to a combination of one circuit and one stimulus. First, we apply a deep neural network (DNN) to establish the mapping from the response of the circuit under test (CUT) in each module to all specifications to be tested. Then, the required test modules are selected by solving a 0-1 integer programming problem. Finally, the predictions from the selected test modules are combined by a DNN to form the specification estimations. The simulation results validate the proposed approach in terms of testing accuracy and cost. Copyright © 2024, The Authors. All rights reserved.

关键词： Integrated circuit testing

Experimental Study on the Characteristics of Annular Fluid Film in a Locally Deformed Narrow Rectangular Channel

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Wang, Fenze Ren, Quanyao Liu, Haidong Xiao, Yi Chen, Deqi Key Laboratory of Low-grade Energy Utilization Technologies and Systems Chongqing University Ministry of Education Chongqing400044 China Department of Nuclear Engineering and Technology School of Energy and Power Engineering Chongqing University Chongqing400044 China Science and Technology on Reactor System Design Technology Laboratory Chengdu610041 China Liangjiang International College Chongqing University of Technology Chongqing401135 China Chongqing Research Institute of HIT Chongqing401151 China School of Flight Technology Civil Aviation Flight University of China Sichuan618307 China China

The study of the characteristics of the annular flow film in the narrow rectangular channel under the localized deformation can provide a research basis for the heat and mass transfer and the hydrodynamic characteristics of the locally deformed narrow flow channel. In this study, the annular flow liquid film characterization experiments are carried out in a narrow rectangular channel without local deformation, ellipsoidal deformation and pillow-shaped deformation, and different annular flow liquid film parameters liquid film thickness, disturbance wave height, and disturbance wave wavelength are obtained by high-speed camera acquisition system and intelligent image processing technology. Analyze the effects of flow conditions and local deformation on the liquid film parameters of each annular flow. Local deformation impact factor functions for liquid film thickness, disturbance wave height, and disturbance wave wavelength are obtained. The error of the impact factor function is within ±30%. © 2024, The Authors. All rights reserved.

关键词： Liquid films

Experimental Study on the Characteristics of Annular Fluid Film in a Locally Deformed Narrow Rectangular Channel

学校读者我要写书评

暂无评论

SSRN 2024年

The local deformation of plate fuel assembly due to neutron irradiation will lead to the deterioration of heat transfer in the flow channel. Studying the characteristics of annular flow films in narrow rectangular channels under localized deformation provides a foundation for understanding the heat and mass transfer and the hydrodynamic characteristics of the locally deformed narrow flow channel. In this study, the annular flow liquid film characterization experiments were conducted in a narrow rectangular channel under three conditions: no local deformation, ellipsoidal deformation, and pillow-shaped deformation. Various parameters of the annular flow liquid films, including liquid film thickness, disturbance wave height, and disturbance wave wavelength, were obtained using a high-speed camera acquisition system and advanced image processing techniques. The effects of flow conditions and local deformation on the liquid film parameters of each annular flow were analyzed. As the radial size of the local deformation increases relative to the liquid film thickness, the viscous bottom layer of the liquid film disintegrates, resulting in a reduction of the total liquid film thickness. When the gas-phase velocity is low, the local deformation exerts a greater shear force on the disturbance wave, prolonging the action time and increasing the likelihood of wave disintegration. Under conditions of no channel deformation, the disturbance wave wavelength is negatively correlated with the gas-phase velocity;conversely, under localized channel deformation, the wavelength is positively correlated with the gas-phase velocity. Thus, the effect of localized deformation on wavelength is bidirectional. Local deformation impact factor functions for liquid film thickness, disturbance wave height, and disturbance wave wavelength have been derived, with the error of these impact factor functions maintained within ±30%. © 2024, The Authors. All rights reserved.

关键词： Neutron irradiation

Multi-objective Optimization of Production Scheduling Using Particle Swarm Optimization Algorithm for Hybrid Renewable Power Plants with Battery Energy Storage System

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2021年第2期9卷 285-294页

作者： Jon Martinez-Rico Ekaitz Zulueta Ismael Ruiz de Argandona Unai Femandez-Gamiz Mikel Armendia The Automation and Control Unit Fundacion TeknikerBasque Research and Technology Alliance(BRTA)Ifiaki Goenaga520600 the University of the Basque Country Ing.Torres Quevedo148013 BilbaoSpain the Department of Systems Engineering and Control College of Engineering at Vitoria-GasteizUniversity of the Basque CountryNieves Cano1201006 Vitoria-GasteizSpain the Department of Nuclear and Fluid Mechanics College of Engineering at Vitoria-GasteizUniversity of the Basque CountryNieves Cano1201006 Vitoria-GasteizSpain

Considering the increasing integration of renewable energies into the power grid,batteries are expected to play a key role in the challenge of compensating the stochastic and intermittent nature of these energy ***,the deployment of batteries can increase the benefits of a renewable power *** way to increase the profits with batteries studied in this paper is performing energy *** strategy is based on storing energy at low electricity price moments and selling it when electricity price is *** this paper,a hybrid renewable energy system consisting of wind and solar power with batteries is studied,and an optimization process is conducted in order to maximize the benefits regarding the dayahead production scheduling of the plant.A multi-objective cost function is proposed,which,on the one hand,maximizes the obtained profit,and,on the other hand,reduces the loss of value of the battery.A particle swarm optimization algorithm is developed and fitted in order to solve this non-linear multi-objective *** the aim of analyzing the importance of considering both the energy efficiency of the battery and its loss of value,two more simplified cost functions are *** show the importance of including the energy efficiency in the cost function to ***,it is proven that the battery lifetime increases substantially by using the multi-objective cost function,whereas the profitability is similar to the one obtained in case the loss of value is not ***,due to the small difference in price among hours in the analyzed Iberian electricity market,it is observed that low profits can be provided to the plant by using batteries just for arbitrage purposes in the day-ahead market.

关键词： Battery energy storage system energy arbitrage hybrid renewable energy system particle swarm optimization

Understanding Two Corrosion Mechanisms of 20cr25ni2.5al Alumina - Forming Austenitic Alloy in Supercritical Carbon Dioxide

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Shu, Ming Zheng, Wenjin Zhou, Qin Wu, Bin Yu, Zhiyang Gu, Xinfu Ming, Hongliang Xiao, Jun Nuclear Power Institute of China Chengdu610213 China Institute of Nuclear and New Energy Technology Tsinghua University Beijing100084 China State Key Laboratory of Photocatalysis on Energy and Environment College of Chemistry Fuzhou University Fuzhou350002 China CAS Key Laboratory of Nuclear Materials and Safety Assessment Institute of Metal Research Chinese Academy of Sciences Shenyang110016 China School of Materials Science and Engineering University of Science and Technology Beijing Beijing100083 China School of Materials Science and Engineering

The 20Cr25Ni2.5Al AFA alloy demonstrated an order of magnitude lower oxidation rate constant compared to the reference alloy in supercritical CO2 (sCO2) at 20 MPa and 650 ℃. Both alloys exhibited uniform corrosion and localized corrosion zones, but the fraction of localized corrosion zones was reduced by more than 50% in Al - modified alloy. The atomic structure of the multilayer oxide scales in both zones was precisely characterized through AC-TEM analysis. The Ni rich precipitates resulted in the disruption of continuous Al2O3 layer and localized corrosion. The corrosion mechanisms of the AFA alloy in sCO2 were schematically elucidated. © 2024, The Authors. All rights reserved.

关键词： Carbon dioxide

Nonlinear Subband Adaptive Filter Based on Andrew's Sine Estimator for Van Der Pol System Identification

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Yang, Wenxing Yin, Kai-Li Lu, Lu College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266520 China Center of Intelligent Acoustics and Immersive Communications Northwestern Polytechnical University 127 Youyi West Road Shaanxi Xi’an710072 China College of Electronics and Information Engineering Sichuan University Chengdu610065 China

Echo cancellation has been effectively achieved through the successful application of subband adaptive filtering (SAF) algorithms. However, the performance of these algorithms may significantly deteriorate when the system exhibits nonlinear distortion. The Van der Pol-Duffing oscillator (VDPDO) system is widely recognized as a complex nonlinear system that displays intricate dynamical behaviors, emphasizing the importance of identifying this nonlinear model. This paper proposes a novel SAF, termed nonlinear SAF (NLSAF) for VDPDO system identification. The NLSAF is based on the functional link artificial neural network (FLANN) to achieve superior nonlinear modeling capability. In particular, the Andrew’s sine estimator is integrated into the NLSAF, generating NLSAF-ASE algorithm for performance improvement. The simulation results provide evidence of the accurate identification of the Van der Pol system through the effective utilization of the NLSAF-ASE algorithm. © 2023, The Authors. All rights reserved.

关键词： Nonlinear systems

Rapid Identification of Living Cancer Cells Based on Label-Free Surface-Enhanced Raman Spectroscopy

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Xu, Lijia Ren, Bin Pu, Mingbo Guo, Yinghui Li, Xiong Luo, Xiangang National Key Laboratory of Optical Filed Manipulation Science and Technology Institute of Optics and Electronics Chinese Academy of Sciences Chengdu610209 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China State Key Laboratory of Physical Chemistry of Solid Surfaces MOE Key Laboratory of Spectrochemical Analysis and Instrumentation Collaborative Innovation Center of Chemistry for Energy Materials College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China

Surface-enhanced Raman spectroscopy (SERS) is a highly sensitive vibration spectroscopy technique that can obtain fingerprint information of biomolecules in cells, and it has demonstrated significant potential in the early diagnosis of cancer. Here, we propose a rapid and efficient identification method of living cancer cells (within 10 minutes), which is based on the label-free SERS detection using iodide-modified Ag nanoparticles (Ag IMNPs) and the ultra-fast Raman mapping by line illumination. The Ag IMNPs achieve a better balance between sensitivity, reproducibility, and biocompatibility when compared to conventional Au or Ag nanoparticles. Statistical analysis of Raman peak frequency and intensity across substantial SERS spectra reveals a wealth of intracellular chemical information about the three cell lines 7701/7703/Caski. This method can not only accurately identify and classify normal cells, cancer cells, and various types of cancer cells, but it can also detect fingerprint changes in the distribution of intracellular chemicals. Furthermore, we discover that, among the three cell lines, liver cancer cells 7703 had the highest level of reactive oxygen species (ROS). This rapid SERS method can provide a new optical detection method for early screening, progression monitoring and prognosis assessment of tumors. © 2024, The Authors. All rights reserved.

关键词： Cancer cells

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods ...

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Li, Yawei Zhang, Yulun Timofte, Radu Van Gool, Luc Yu, Lei Li, Youwei Li, Xinpeng Jiang, Ting Wu, Qi Han, Mingyan Lin, Wenjie Jiang, Chengzhi Luo, Jinting Fan, Haoqiang Liu, Shuaicheng Wang, Yucong Cai, Minjie Li, Mingxi Zhang, Yuhang Fan, Xian-Jun Sheng, Yankai Mao, Yanyu Zhang, Nihao Wang, Qian Zheng, Mingjun Sun, Long Pan, Jinshan Dong, Jiangxin Tang, Jinhui Yang, Zhongbao Wang, Yan Pan, Erlin Cai, Qixuan Dai, Xinan Zhussip, Magauiya Kalyazin, Nikolay Vyal, Dmitry Zou, Xueyi Yan, Youliang Chung, Heaseo Zhang, Jin Yu, Gaocheng Zhang, Feng Wang, Hongbin Liao, Bohao Du, Zhibo Wu, Yu-Liang Shi, Gege Peng, Long Wang, Yang Cao, Yang Zha, Zhengjun Huang, Zhi-Kai Chen, Yi-Chung Chiang, Yuan-Chun Yang, Hao-Hsiang Chen, Wei-Ting Chang, Hua-En Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Liu, Xin Pan, Jiahao Yu, Hongyuan Yu, Weichen Ge, Lin Dong, Jiahua Zou, Yajun Wu, Zhuoyuan Han, Binnan Zhang, Xiaolin Zhang, Heng Yin, Xuanwu Zuo, Kunlong Deng, Weijian Yuan, Hongjie Lu, Zengtong Ouyang, Mingyu Ma, Wenzhuo Liu, Nian Zheng, Hanyou Zhang, Yuantong Zhang, Junxi Chen, Zhenzhong Gendy, Garas Sabor, Nabil Hou, Jingchao He, Guanghui Zhu, Yurui Wang, Xi Fu, Xueyang Zha, Zheng-Jun Yin, Daheng Liu, Mengyang Chen, Baijun Li, Ao Luo, Lei Jin, Kangjun Zhu, Ce Zhang, Xiaoming Xie, Chengxing Li, Linze Meng, Haiteng Zhang, Tianlin Li, Tianrui Zhao, Xiaole Zhang, Zhao Li, Baiang Zheng, Huan Zhao, Suiyi Gao, Yangcheng Ren, Jiahuan Hu, Kang Shi, Jingpeng Wu, Zhijian Huang, Dingjiang Zhu, Jinchen Li, Hui Xv, Qianru Liu, Tianle Weng, Shizhuang Wu, Gang Jiang, Junpeng Liu, Xianming Jiang, Junjun Zhang, Mingjian Hu, Jing Wu, Chengxu Fan, Qinrui Feng, Chengming Luo, Ziwei Hu, Shu Lyu, Siwei Wu, Xi Wang, Xin Computer Vision Lab ETH Zurich Switzerland Computer Vision Lab University of Würzburg Germany Megvii Technology China MicroBT China College of Computer Science and Electronic Engineering Hunan University China Attrsense Xian University of Posts and Telecommunications Xi'an China National Engineering Laboratory for Cyber Event Warning and Control Technologies China Nanjing University of Science and Technology China Nankai University China University of Electronic Science and Technology of China China Tianjin University China Noah's Ark Lab Huawei Technologies McMaster University Canada Espresomedia Korea Republic of AntGroup China University of Science and Technology of China China Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan ServiceNow United States China Mobile Research Institute China Chongqing University of Technology China Multimedia Department Xiaomi Inc. China Institute of Automation Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences China School of Information and Communication Engineering Communication University of China China Smart Classroom Division Ruijie Networks Co. Ltd. China School of Remote Sensing and Information Engineering Wuhan University China Micro-Nano Electronics Department Shanghai Jiao Tong University Shanghai200240 China Electrical Engineering Department Faculty of Engineering Assiut University Assiut71516 Egypt Southeast University China University of Electronic Science and Technology of China Chengdu China Chongqing University of Posts and Telecommunications Chongqing China Information Technology Co. Ltd Hangzhou China Southwest Jiaotong University China National Space Science Center Chinese Academy of Science China Hefei University of Technology Hefei China Anhui University China Fried Ric

ISBN: (纸本)9798350302493

This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution. © 2023 IEEE.

关键词： Optical resolving power