检索结果-内蒙古大学图书馆

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Yawei Zhang, Kai Timofte, Radu Van Gool, Luc Kong, Fangyuan Li, Mingxi Liu, Songwei Du, Zongcai Liu, Ding Zhou, Chenhui Chen, Jingyi Han, Qingrui Li, Zheyuan Liu, Yingqi Chen, Xiangyu Cai, Haoming Qiao, Yu Dong, Chao Sun, Long Pan, Jinshan Zhu, Yi Zong, Zhikai Liu, Xiaoxiao Hui, Zheng Yang, Tao Ren, Peiran Xie, Xuansong Hua, Xian-Sheng Wang, Yanbo Ji, Xiaozhong Lin, Chuming Luo, Donghao Tai, Ying Wang, Chengjie Zhang, Zhizhong Xie, Yuan Cheng, Shen Luo, Ziwei Yu, Lei Wen, Zhihong Wu, Qi Li, Youwei Fan, Haoqiang Sun, Jian Liu, Shuaicheng Huang, Yuanfei Jin, Meiguang Huang, Hua Liu, Jing Zhang, Xinjian Wang, Yan Long, Lingshun Li, Gen Zhang, Yuanfan Cao, Zuowei Sun, Lei Alexander, Panaetov Wang, Yucong Cai, Minjie Wang, Li Tian, Lu Wang, Zheyuan Ma, Hongbing Liu, Jie Chen, Chao Cai, Yidong Tang, Jie Wu, Gangshan Wang, Weiran Huang, Shirui Lu, Honglei Liu, Huan Wang, Keyan Chen, Jun Chen, Shi Miao, Yuchun Huang, Zimo Zhang, Lefei Ayazoglu, Mustafa Xiong, Wei Xiong, Chengyi Wang, Fei Li, Hao Wen, Ruimian Yang, Zhijing Zou, Wenbin Zheng, Weixin Ye, Tian Zhang, Yuncheng Kong, Xiangzhen Arora, Aditya Zamir, Syed Waqas Khan, Salman Hayat, Munawar Khan, Fahad Shahbaz Gao, Dandan Zhou, Dengwen Ning, Qian Tang, Jingzhu Huang, Han Wang, Yufei Peng, Zhangheng Li, Haobo Guan, Wenxue Gong, Shenghua Li, Xin Liu, Jun Wang, Wanjun Zeng, Kun Lin, Hanjiang Chen, Xinyu Fang, Jinsheng Zhang, Shuhao Zhang, Yuhao Sinha, Abhishek Kumar Moorthi, S. Manthira Dhar, Debajyoti Yang, Hao-Hsiang Huang, Zhi-Kai Chen, Wei-Ting Chang, Hua-En Kuo, Sy-Yen Tan, Wei Chen, Hao Xu, Qian Narang, Pratik Singh, Usneek Sameen, Syed Khaitan, Harsh Yinghua, Liu Tianlin, Zhang Xiaoming, Zhang Meng, Dingxuan Tian, Chunwei Morshed, Mashrur M. Ahsan, Ahmad Omar Computer Vision Lab ETH Zurich Switzerland University of Würzburg Germany ByteDance Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University China ByteDance Inc China NetEase Inc. China Shenzhen Institutes of Advanced Technology CAS China University of Macau China Shanghai AI Lab Shanghai China Nanjing University of Science and Technology China Amazon Web Services United States China Alibaba DAMO Academy EFC Yuhang District Zhejiang Hangzhou China East China Normal University China Youtu Lab Tencent China Megvii Technology China University of Electronic Science and Technology of China China School of Artificial Intelligence Beijing Normal University China Alibaba Group China Bilibili AI China Nankai-Baidu Joint Lab Nankai University Tianjin China Platform Technologies Tencent Online Video China Higher School of Economics Russia Huawei Moscow Research Center Russia Hunan University China Xidian University China Xilinx Technology Beijing Limited China College of Information Science and Engineering Xinjiang University Urumqi China Department of Electronic Engineering Tsinghua University Beijing China Nanjing University China McMaster University Canada School of Telecommunication Engineering Xidian University Xi’an China School of Computer Science Wuhan University Wuhan China School of Mathematical Science University of Electronic Science and Technology of China Chengdu China School of Computer Science The University of Sydney Sydney Australia Aselsan Research Ankara Turkey School of Electronic and Information Engineering South-Central University for Nationalities Wuhan China Guangdong University of Technology China Fujian Normal University Fuzhou University Jimei University China Design Group China Abu Dhabi United Arab Emirates Monash University Melbourne Australia Mohamed bin Zayed University of AI United Arab Emirates North China Electric Power University Changping District Beijing China The School of Art

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution. © 2022, CC BY.

关键词： Chemical activation

Fractional-order biological system: chaos, multistability and coexisting attractors

学校读者我要写书评

暂无评论

The European Physical Journal Special Topics 2021年第5期231卷 1061-1070页

作者： Debbouche, Nadjette Ouannas, Adel Momani, Shaher Cafagna, Donato Pham, Viet-Thanh Laboratory of Dynamical System and Control University of Larbi Ben M’hidi Oum El Bouaghi Algeria Department of Mathematics and Computer Sciences Larbi Ben M’hidi University Oum El Bouaghi Algeria Nonlinear Dynamics Research Center (NDRC) College of Humanities and Sciences Ajman University Ajman UAE Department of Mathematics Faculty of Science University of Jordan Amman Jordan Department of Innovation Engineering University of Salento Lecce Italy Nonlinear Systems and Applications Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Vietnam

In this paper, the nonlinear dynamics of the biological system modeled by the fractional incommensurate order Van der Pol equations are investigated. The stability of the proposed fractional non-autonomous system is analyzed by varying both the fractional order derivative and system parameters. Moreover, very interesting phenomena such as symmetry, multi-stability and coexistence of attractors are discovered in the considered biological system. Numerical simulations are performed by considering the Caputo fractional derivative and results are reported by means of bifurcation diagrams, computation of the largest Lyapunov exponent, phase portraits in 2D and 3D projections.

关键词：

EMDS-6: Environmental Microorganism Image Dataset Sixth Version for Image Denoising, Segmentation, Feature Extraction, Classification and Detection Methods Evaluation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Peng Li, Chen Rahaman, Md Mamunur Xu, Hao Ma, Pingli Yang, Hechen Sun, Hongzan Jiang, Tao Xu, Ning Grzegorzek, Marcin Microscopic Image and Medical Image Analysis Group MBIE College Northeastern University Shenyang110169 China School of Control Engineering Chengdu University of Information Technology Chengdu610225 China University of Lübeck Germany Department of Radiology Shengjing Hospital China Medical University Shenyang110122 China School of Arts and Design Liaoning Shihua University Fushun113001 China School of Computer Science and Engineering University of New South Wales Sydney Australia

Environmental microorganisms (EMs) are ubiquitous around us and have an important impact on the survival and development of human society. However, the high standards and strict requirements for the preparation of environmental microorganism (EM) data have led to the insufficient of existing related datasets, not to mention the datasets with ground truth (GT) images. This problem seriously affects the progress of related experiments. Therefore, This study develops the Environmental Microorganism Dataset Sixth Version (EMDS-6), which contains 21 types of EMs. Each type of EM contains 40 original and 40 GT images, in total 1680 EM images. In this study, in order to test the effectiveness of EMDS-6. We choose the classic algorithms of image processing methods such as image denoising, image segmentation and target detection. The experimental result shows that EMDS-6 can be used to evaluate the performance of image denoising, image segmentation, image feature extraction, image classification, and object detection methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

Brain structure can mediate/moderate the relationship of behavior to brain function and transcriptome: a preliminary study

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bari, Sumra Vike, Nicole L. Stetsiv, Khrystyna Blood, Anne J. Nauman, Eric A. Talavage, Thomas M. Slobounov, Semyon Breiter, Hans C. Department of Computer Science University of Cincinnati CincinnatiOH United States Warren Wright Adolescent Center Department of Psychiatry and Behavioral Sciences Feinberg School of Medicine Northwestern University ChicagoIL United States Mood and Motor Control Laboratory Departments of Neurology and Psychiatry Massachusetts General Hospital Harvard Medical School BostonMA02129 United States Laboratory of Neuroimaging and Genetics Department of Psychiatry Massachusetts General Hospital Harvard Medical School BostonMA02129 United States Martinos Center for Biomedical Imaging Department of Radiology Massachusetts General Hospital Harvard Medical School BostonMA02129 United States Department of Biomedical Engineering University of Cincinnati CincinnatiOH United States Department of Kinesiology Pennsylvania State University University ParkPA United States The Pennsylvania State University 268P Recreation Building University ParkPA16802 United States Department of Computer Science College of Engineering and Applied Science University of Cincinnati 2901 Woodside Drive CincinnatiOH45219 United States

Abnormalities in motor-control behavior, which have been associated with concussion and head acceleration events (HAE), can be quantified using virtual reality (VR) technologies. Motor-control behavior has been consistently mapped to the brain’s somatomotor network (SM) using both structural (sMRI) and functional MRI (fMRI). However, no studies have integrated HAE, motor-control behavior, sMRI and fMRI measures. Here, brain networks important for motor-control were hypothesized to show changes in tractography-based diffusion weighted imaging [difference in fractional anisotropy (∆FA)] and resting-state fMRI (rs-fMRI) measures in collegiate American football players across the season, and that these measures would relate to VR-based motor-control. We further tested if nine inflammation-related miRNAs were associated with behavior-structure-function variables. Using permutation-based mediation/moderation methods, we found that across-season ∆FA from the SM structural connectome (SM-∆FA) mediated the relationship between across-season VR-based Sensory-motor Reactivity (∆SR) and rs-fMRI SM fingerprint similarity (psobelperm = 0.007 and Teff = 47%). The interaction between ∆SR and SM-∆FA also predicted (pFPerm= 0.036, PB₃perm = 0.058) across-season levels of ∆miRNA-30d through permutation-based moderation analysis. These results suggest (1) that motor-control is in a feedback relationship with brain structure and function, (2) behavior-structure-function can be connected to HAE, and (3) behavior-structure might predict molecular biology measures. © 2022, CC BY.

关键词： Molecular biology

Limitations on sharing bell nonlocality between sequential pairs of observers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cheng, Shuming Liu, Lijun Baker, Travis J. Hall, Michael J.W. The Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai201804 China Institute for Advanced Study Tongji University Shanghai200092 China College of Mathematics and Computer Science Shanxi Normal University Linfen041000 China Centre for Quantum Computation and Communication Technology Australian Research Council Centre for Quantum Dynamics Griffith University BrisbaneQLD4111 Australia Department of Theoretical Physics Research School of Physics Australian National University CanberraACT0200 Australia

We give strong analytic and numerical evidence that, under mild measurement assumptions, two qubits cannot both be recycled to generate Bell nonlocality between multiple independent observers on each side. This is surprising, as under the same assumptions it is possible to recycle just one of the qubits an arbitrarily large number of times [P. J. Brown and R. Colbeck, Phys. Rev. Lett. 125, 090401 (2020)]. We derive corresponding 'one-sided monogamy relations' that rule out two-sided recycling for a wide range of parameters, based on a general tradeoff relation between the strengths and maximum reversibilities of qubit measurements. We also show if the assumptions are relaxed to allow sufficiently biased measurement selections, then there is a narrow range of measurement strengths that allows two-sided recycling for two observers on each side, and propose an experimental test. Our methods may be readily applied to other types of quantum correlations, such as steering and entanglement, and hence to general information protocols involving sequential measurements. Copyright © 2021, The Authors. All rights reserved.

关键词： Recycling

control method for EV charging and discharging in V2G/V2H scenario based on the synchronvter technology and H∞ repetitive control

学校读者我要写书评

暂无评论

Control method for EV charging and discharging in V2G/V2H sc...

作者： Liu, Dongqi Zeng, Xiangjun Liu, Guorong Hunan Province Key Laboratory of Smart Grids Operation and Control Changsha University of Science and Technology Changsha China College of Electrical and Information Engineering Hunan University Changsha China School of Computer and Communication Hunan Institute of Engineering Xiangtan China

Electric vehicles (EVs) will play a vital role in the future's transportation systems since this technology is promising for environment, energy security, and improved fuel economy. EVs have huge potential of serving as the energy storage for the power grid as well as inhabitants in vehicle-to-grid (V2G) or vehicle-to-house (V2H) scenario. In this study, a control method is proposed for EV charging and discharging by using the synchronverter technology and H∞ repetitive controller, where synchronverter technology is used to generate the reference voltage to decide the power angle and amplitude of the AC side voltage of the charging/discharging port, so that the power flow between EV and the grid is controlled. In order to ensure the power quality of EVs provided for the grid and the load while EVs are with local loads, a H∞ repetitive controller is designed to control the voltage between EVs and the grid to follow the reference voltage. Simulation results have shown that the proposed controller is not only able to realise bi-directional real power and reactive power control, but also keep the output voltage of EVs in V2G or V2H scenario stable and clear while they are with different kinds of local loads. © 2019 Institution of engineering and *** right reserved.

关键词： Fuel economy

Computational fluid dynamic and machine learning modeling of nanofluid flow for determination of temperature distribution and models comparison

学校读者我要写书评

暂无评论

Scientific Reports 2025年第1期15卷 1-9页

作者： Altalbawy, Farag M. A. Alkhayyat, Ahmad Jhala, Ramdevsinh Yadav, Anupam Ramachandran, T. Shankhyan, Aman Karthikeyan, A. Thatoi, Dhirendra Nath Sinitsin, Vladimir Vladimirovich Department of Chemistry University College of Duba University of Tabuk Tabuk Saudi Arabia Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Babylon Babylon Iraq Marwadi University Research Center Department of Mechanical Engineering Faculty of Engineering & Technology Marwadi University Gujarat Rajkot 360003 India Department of Computer Engineering and Application GLA University Mathura 281406 India Department of Mechanical Engineering School of Engineering and Technology JAIN (Deemed to be University) Karnataka Bangalore India Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Department of Mechanical Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Department of Mechanical Engineering Siksha ’O’ Anusandhan (Deemed to be University) Odisha Bhubaneswar 751030 India Research Laboratory of Technical Self-Diagnostics and Self-Control of Devices and Systems Department of Scientific and Innovative Activities Research Institute of Mechanical Engineering South Ural State University Lenin prospect 76 Chelyabinsk 454080 Russian Federation

This paper introduces an approach to temperature prediction by employing three distinct machine learning models: K-Nearest Neighbors (KNN), Gaussian Process Regression (GPR), and Multi-layer Perceptron (MLP) which are integrated into Computational Fluid Dynamics (CFD). The dataset consists of inputs, represented by the features x and y, and the corresponding output, which is the temperature. The case study is fluid flow of nanofluid through a pipe and the nanofluid contains CuO particles. To enhance model efficacy, the Political Optimizer (PO) algorithm was utilized for fine-tuning purposes. The findings substantiate the capability of the optimized frameworks in delivering precise temperature estimations. GPR yielded a notable R² value of 0.998, reflecting a strong concordance between the estimated and actual measurements. In a comparable manner, the KNN approach exhibited outstanding predictive performance, also attaining an R² value of 0.998. MLP, although slightly lower in performance compared to the other models, still proves to be a reliable predictor of temperature values, with an R-squared score of 0.984. Overall, the combination of the PO algorithm and the machine learning models showcases promising results in temperature prediction. The study’s findings offer valuable insights for decision-making processes in a variety of domains that rely on accurate temperature forecasting. © The Author(s) 2025.

关键词： Gaussian process regression Heat transfer K-Nearest neighbors Multi-layer perceptron Nanofluid

RETRACTED ARTICLE: Google’s new AI technology detects cardiac issues using retinal scan

学校读者我要写书评

暂无评论

Applied Nanoscience 2022年第4期13卷 3137-3137页

作者： Borra, Surya Prasada Rao Sumathy, B. Ismail, B. Mohammed Kumar, S. Naresh Phasinam, Khongdet Ramesh, R. Prasad V. Potluri Siddhartha Institute of Technology Vijayawada India Instrumentation and Control Engineering Srisairam Engineering College Chennai India Department of Information Technology Kannur University Kannur India School of Computer Science and Artificial Intelligence SR University Warangal India School of Agricultural and Food Engineering Faculty of Food and Agricultural Technology Pibulsongkram Rajabhat University Phitsanulok Thailand Department of Science and Humanities Sri Krishna College of Engineering and Technology Coimbatore India

A New Approach for Face Anti-Spoofing Using Handcrafted and Deep Network Features

学校读者我要写书评

暂无评论

A New Approach for Face Anti-Spoofing Using Handcrafted and ...

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Das, Polash Kumar Hu, Bin Liu, Chang Cui, Kaixin Ranjan, Prabhat Xiong, Gang School of Electronic and Information Engineering South China University of Technology Guangzhou China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China College of Computer Science Sichuan University Chengdu China Cloud Computing Center Chinese Academy of Science Dongguan China

ISBN: (纸本)9781728128535

In biometrics, face recognition methods are achieving momentum with recent progress in the computer vision(CV). Face recognition is widely used in the identification of an individual's identity. Unfortunately, in recent research work has revealed this face biometrics system is unprotected to spoofing attacks using by very low price instrument such as printed 2D photos attack, 3D masking attack and taking videos using smart devices (reply attack). Therefore, a Liveness Attack Detection (LAD) approach is needed to improve the high-quality security of face recognition system. Most of the earlier worked LAD methods for face anti-spoofing methods have highlight on using the handcrafted features, which are developed by expert knowledge of researcher. As example Gabor filter, Histogram of Oriented Gradients, local ternary pattern, and the Local Binary Pattern. Because of that, the extracted features consider limited factors of the problem, yielding a capture accuracy that is very low and changes with the point of presentation in attack face images. The deep learning method has developed in the computer vision research community, which is proven to be suitable for automatically training. In this article, we approach to mix or combine the handcrafted features and deep neural network features to design the discriminant face spoofing detection. The handcrafted features were based on LBP analysis. We examine the features information from the brightness and the chrominance channels using LBP descriptor. In deep features, we present an approach based on pre-trained convolutional neural network VGG-16 model using static features to recognize video and printed(2D) photo attacks. By attaching this two types of image features on our dataset and public databases, we get good results to identify real and attack images feature, called hybrid features, which has better discrimination ability to understand spoofing image feature. © 2019 IEEE.

关键词： Local binary pattern