Wang Xinyue, You Liandong, Li Ming, Li Ming
Mothers, particularly human mothers, exhibit exceptional sensitivity to the unique acoustic features, emotional valence, and survival cues embedded in infant cries and laughter. This article evaluates various cognitive experimental paradigms developed using infant cry materials and investigates mate…
Zhai Shuyi, Zhai Shuyi, Shi Xingcheng, Xingcheng Shi, Liang Ying, Liang Ying, Xia Dingling, Xia Dingling, He Jie, He Jie, He Jie, He Jie
Against the backdrop of building a fertility-friendly society, family well-being and scientific parenting have attracted increasing attention. Based on 5-day intensive longitudinal data from 370 mothers of early school-age children in China, this study employs dynamic structural equation modeling to…
Shi Hao, Yu Guopei, Shi Hao
This study employs the Shouchang Wastewater Treatment Plant in Jiande City, Hangzhou as an empirical case study to investigate the energy conservation and carbon reduction effects of county-level environmental protection projects. The paper commences with a theoretical and methodological framework, …
Zhong Jiawei, Zheng Jun, Zhang Mingyue
Developing agricultural socialized services constitutes an important component of agricultural modernization construction. Under the "dual security" framework for grain and ecology, investigating its contribution to grain ecological efficiency holds significant importance for achieving sustainable a…
Luo, Yinfang, Lv, Jiahao, Dr. Yuan-ming Xing, Zhang, Prof. Yuhu, Mr. Min Zhang, Wang, Prof. Meng, Litvinov, Prof. Yuri, Zhou, Prof. Xiaohong 周小红, Xing, Yuan-Ming
The technique of Bρ-defined isochronous mass spectrometry (Bρ-IMS), established at a storage ring, serves as a valuable tool for determining the masses of short-lived nuclei. In the previous Bρ-IMS experiments, the effects of magnetic field drifts have to be corrected in order to improve the mass re…
Zeng, Yujie, Song, Ms. Tianzi, Xuesen Wang, Zhang, Prof. Yumei, Dr. Tao Lin, You, Prof. Zhengyun, You, Prof. Zhengyun
In high-energy physics~(HEP) experiments, visualization software plays a pivotal role in detector design, offline software development, and event data analysis. The visualization tools integrate detailed detector geometry with complex event data models, providing the researchers with invaluable insi…
Zhang Zijian, Chen Jiwen, Peng Shun, Jiahui Wu, Wang Siqian, Chen Jiwen
This study adopts a sociocultural perspective on learning engagement, integrated with human capital theory, and employs two sub-studies anchored in three categories of social factors to analyze the longitudinal evolution of learning engagement among students in mainland China, examining the influenc…
Feng Tingyong, Wang Xueke, Deng Fang, Feng Tingyong
Effective coping and management of negative emotions is an essential competency for children with Autism Spectrum Disorder (ASD) to adapt to society; however, previous research has predominantly focused on emotion recognition and emotion understanding, with less attention devoted to the emotion regu…
Zeng Haitao, Hu Longfei, Yao Tao
X-ray Absorption Fine Structure (XAFS) is an important structural analysis technique widely applied to investigate the oxidation state, coordination environment, and neighboring atomic properties of amorphous materials and disordered systems. However, due to the complexity of XAFS spectra, their int…
Peng Jiang, Dr. Yangchun Chen, Deng, Prof. Huiqiu, Deng, Prof. Huiqiu
The anisotropic diffusion of irradiation defects in α-uranium (α-U) has been investigated using classical and nonequilibrium molecular dynamics methods, with the aim of better understanding the complex response of the microstructure to irradiation damage, which depends on temperature and internal st…
Peiyu Zhang, Dr. Lei Wang, Tan, Mr. Yifan, Li, Dr. Haoxuan, Wang, Mr. Zexi, Ms. Yan Li, WANG, Dr. Lei
Accurate measurement of the activities of α/β radionuclides in environmental samples is critical for environmental radiation monitoring. Traditional α/β discrimination methods for dualscintillator detectors primarily rely on the amplitude, width, and rise time of the pulse from the detector, often l…
Choi, Yongseok, Lee, Dr. Changwoo, Lee, Dr. Hyeon-Geun, Kang, Mr. Seongmin, Park, Mr. Kyeongryeol, Jeong, Prof. Jae-Ho, Lee, Prof. Kyungjun, Lee, Prof. Kyungjun
The next-generation Molten Salt Reactor (MSR) utilizes a liquid-fuel system, in which fissile material is dissolved in high-temperature molten salts. This dual-purpose medium acts as both fuel and primary coolant, offering exceptional thermal stability and inherent safety features. However, MSR pose…
Chen Lijun, Jin Yuexin, Zeng Hanhan, Jiang Xiaoliu, Jiang Xiaoliu
Daily social verbal communication contains both semantic and prosodic cues. Do children with autism spectrum disorder rely on prosody or semantics to judge a speaker's emotion in social interactions? Investigating this question facilitates understanding of the disorder's etiology and provides direct…
Han, Mr. Yang, Han, Mr. Yang
To bridge the theoretical gap in the analysis of neutron flux density distributions within annular reactors, this study derives closed-form solutions for the neutron flux density under critical conditions based on the monoenergetic neutron diffusion equation and validates them using MCNP5 simulation…
Xuefen Han, Shen Fei, Zhou Bin, Cai Xiaoxiao, Yi Tiancheng, Hu Zhiliang, Wang Songlin, Liang Tianjiao, Robert Golub, Liang Tianjiao
The ultracold neutron (UCN) transport code, MCUCN, designed initially for simulating UCN transportation from a solid deuterium ($\rm SD_{2}$) source and neutron electric dipole moment experiments, could not simulate UCN storage and transportation in a superfluid $\rm{^{4}{He}}$ (SFHe, He II) source …
Li, Mr. Jiancong, wang, Dr. Shengxiang, Shu, Mr. Xin, Dong, Le, Dr. Yong Lei, Chen, Prof. Jie, wang, Dr. Shengxiang
Neutron CT imaging offers unique advantages in metal defect detection and cultural relic analysis, particularly for exploring internal structures of ancient artifacts like writing knives, due to its high penetrability and hydrogen sensitivity. Accurate segmentation of its images is critical for defe…
Shu, Xin, wang, Dr. Shengxiang, Chen, Prof. Jie, Dr. Xin Ge, Li, Jiancong, Dong, Le, wang, Dr. Shengxiang
X-ray and neutron computed tomography (CT) are widely used for non-destructive characterization of internal structures. Their distinct contrast mechanisms, arised from different interactions with matter, can enhance structural analysis when combined. Dual-modality imaging integrating both techniques…
Peng Wang, Yan Ping, Zhou Yaping, Xiang Yanhui, Xiang Yanhui
Does marriage alter the developmental trajectory of individuals' life satisfaction? This is both a major issue concerning national harmony and stability, and an important question regarding individual quality of life. Based on hedonic adaptation theory and the buffer model, this study utilizes six-w…
Cui,Xuetao, Wu,Qigang, Wang, Jian, Lei,Mingzhun, Song,Yuntao, Cui, Xuetao
Objective: As the primary functional component of a fusion reactor, the fusion blanket pebble bed, composed of numerous particles, is crucial for tritium breeding, neutron multiplication, and radiation shielding. Particles within tritium-breeding pebble beds are subjected to prolonged neutron irradi…
Liu Zhifang, Feng Ximei, \documentclass[twocolumn]{article}
\usepackage[utf8]{inputenc}
\usepackage{amsmath}
\usepackage{graphicx}
\usepackage{CJK}
\usepackage[numbers]{natbib}
\title{Research on Image Classification Methods Based on Deep Learning}
\author{Zhang San \\ School of Computer Science and Technology \\ Peking University}
\date{\today}
\begin{document}
\begin{CJK}{UTF8}{gbsn}
\maketitle
\begin{abstract}
This paper studies image classification methods based on deep learning. It first introduces the fundamental principles and commonly used models of deep learning, and then focuses on analyzing the application of convolutional neural networks in image classification tasks. Experimental results demonstrate that the proposed method achieves 92.5\% accuracy on the CIFAR-10 dataset, outperforming traditional machine learning methods.
\end{abstract}
\keywords{deep learning, image classification, convolutional neural network}
\section{Introduction}
With the rapid development of artificial intelligence technology, machine learning has become an important research direction in the field of computer science. In particular, breakthroughs in deep learning technology in recent years have led to significant progress in tasks such as image classification, speech recognition, and natural language processing. This paper will focus on exploring the application of deep learning in image classification.
\section{Related Work}
Traditional image classification methods mainly rely on hand-crafted feature extractors, such as SIFT\cite{lowe2004distinctive} and HOG\cite{dalal2005histograms}. These methods require domain expert knowledge and have limited generalization capabilities. In contrast, deep learning methods can automatically learn hierarchical feature representations, significantly improving classification performance.
\section{Deep Learning Methods}
\subsection{Convolutional Neural Networks}
Convolutional Neural Networks (CNN) are a type of deep learning model specifically designed for processing data with grid-like structures. They extract image features through a combination of convolutional layers, pooling layers, and fully connected layers. Convolutional layers perform convolution operations on the input using learnable filters, while pooling layers are used to reduce feature dimensions.
\subsection{Residual Networks}
Residual Networks (ResNet) solve the vanishing gradient problem in training deep networks by introducing skip connections. This structure enables the network to learn residual mappings, thereby allowing the training of deeper network architectures. ResNet achieved breakthrough results in the ImageNet Large Scale Visual Recognition Challenge.
\section{Experimental Setup}
We evaluated the proposed method on the CIFAR-10 dataset. This dataset contains 60,000 32×32 color images divided into 10 categories. We used 50,000 images for training and 10,000 images for testing. The experiments were implemented using the PyTorch framework and trained on an NVIDIA Tesla V100 GPU.
\section{Experimental Results}
As shown in Table\ref{tab:results}, our method achieved 92.5\% accuracy on the test set. Figure\ref{fig:confusion_matrix} shows the confusion matrix, which demonstrates that the model performs relatively balanced across all categories. Compared with the baseline method, the accuracy improved by 5.2 percentage points.
\begin{table}[h]
\centering
\caption{Performance Comparison of Different Methods}
\label{tab:results}
\begin{tabular}{lc}
\hline
Method & Accuracy(\%) \\
\hline
Traditional machine learning method & 87.3 \\
Deep learning method & 92.5 \\
\hline
\end{tabular}
\end{table}
\section{Conclusion}
This paper proposes an image classification method based on deep learning and validates its effectiveness on the CIFAR-10 dataset. Experimental results demonstrate that deep learning methods have significant advantages in image classification tasks. Future work will explore more efficient model architectures and training strategies.
\bibliographystyle{plain}
\bibliography{references}
\end{CJK}
\end{document}, Liu Zhifang
This study utilized the fixation-related potential technique to examine predictive processing in Chinese reading and the cognitive mechanisms underlying its influence on lexical recognition effects. Analyses of eye movement and electroencephalographic (EEG) data in the pre-target and target word reg…
Liqing Zhang, Liqing Zhang
Single crystal GaN epilayers were irradiated with heavy inert-gas ions (2.3-MeV Ne8+, 5.3-MeV Kr19+) to fluences ranging from 1.0×1011 to 1.0×1015 ions/cm2. The strain-related damage accumulation versus ion fluences was studied by using a high-resolution X-ray diffractometer (HRXRD) and an ultraviol…
Nian Jingqing, Tan Jiang, Zhang Di, Zhang Yu, Luo Yu, Luo Yu
Threat stimuli possess strong priority in attentional processing, yet whether they facilitate or interfere with the formation of learned distractor inhibition remains unclear. This study examined the influence of threat stimuli on the formation of location-probability-based learned distractor inhibi…
Xin-Yu Yang, Yang, Dr. Jian, Zeng, Dr. GQ, Deng, Mr. Haowen, Tian, Chengshuai, HU, Dr. Chuan-hao, Yang, Dr. Jian
Abstract: For radioactive source localization, traditional Compton cameras are limited by the imaging field of view and low detection efficiency, resulting in slow response in complex environments. To address the limitations in the azimuthal sensitivity of conventional dual-layer scintillator detect…
Zhang Chenglong, Yuan Yuan, Liu Guoming, Zhang Peng, Xiao Huiwen, Dong Jianhua, Guan Jingyu, He Kai, Yi Xuan
Gas-cooled micro-reactors are constrained by their compact arrangement and high-temperature operating environment, which limits core monitoring to only a small number of ex-core detectors. A nuclear measurement system layout scheme coupling neutron sources with ex-core detectors for micro-reactors i…
Dr. Zhenhua Chen, Prof. Ying Zou, Junqin Li, Zhu, Dr. Fangyuan, Cheng, Dr. Yiwei, Huang, Prof. Yaobo, Wang, Prof. Yong, Tai, Prof. Renzhong, Tai, Prof. Renzhong
The ultrahigh-energy-resolution soft X-ray beamline, "Dreamline," at the Shanghai Synchrotron Radiation Facility (SSRF), has been successfully constructed and is now fully operational for conducting angle-resolved photoemission spectroscopy (ARPES) and photoelectron emission microscopy (PEEM) experi…
Li, Jian, Xu, Wei, She, Ding, Xie, Heng, Liu, Zhihong, Shi, Lei, She, Ding
High flux reactors (HFRs) are a special type of research reactor aimed at providing a high neutron flux. Compared with power reactors and other research reactors, HFRs have unique technical features in terms of reactor core design, irradiation capability, and operating characteristics. They can be a…
Sqin Fan, Qi Yuan, Furong Xu, Philip Malzard Walker, Furong XU
High multipole electromagnetic transitions are rare in nature. The highest multipole transition observed in atomic nuclei is the electric hexacontatetrapole E6 transition from the T1/2 = 2.54(2)-min Jπ = 19/2− isomer to the 7/2− ground state in 53Fe with an angular momentum change of six units. In t…
Dexin Wang, Meirong Huang, Su-Ya-La-Tu Zhang, DanDan Niu, Guo Li, Hao Chun Yu, Geriletu Bao, Dexin Wang, Su-Ya-La-Tu Zhang
The fusion dynamics of \ce{^6Li} and \ce{^7Li} projectiles incident on \ce{^{13}C} and \ce{^{12}C} targets, respectively, near the Coulomb barrier, were investigated theoretically using the antisymmetrized molecular dynamics (AMD) model. Within the AMD framework, the ground state configurations of \…
Qu, Xiaoying, Chen, Kangmin, Pang, Cong, Yu, Yangyang, Zhang, Kaiyuan, Zhang, Kaiyuan
Nuclear masses play a crucial role in both nuclear physics and astrophysics, driving sustained efforts toward their precise experimental determination and reliable theoretical prediction. In this work, we compile the newly measured masses for 296 nuclides from 40 references published between 2021 an…
Heo, Dr. Su Jeong, Cho, Dr. Yung-Zun, Kang, Dr. Kweonho, Lee, Dr. Ju Ho, Heo, Dr. Su Jeong
Understanding the long-term behavior of spent nuclear fuel (SNF) is crucial for safe radioactive waste management. This study evaluates how burn-up, sintering temperature, and leaching temperature impact the leaching and microstructural stability of SIMulated FUEL (SIMFUEL) pellets designed to simul…
Wang Xin, Yuan Yuan, Zhao Xuan, Luo Guanghao, Wei Qiqiao, Wu Hexi, Xiong Chao, Xiong Chao
Unmanned aerial vehicle (UAV)-borne gamma-ray spectrum surveys play a crucial role in geological mapping, radioactive mineral exploration, and environmental monitoring. However, raw data are often compromised by flight and instrument background noise, as well as detector resolution limitations, whic…
Cheng Ruoyu, Xu Zhicheng, Xu Zhicheng
To study the uncertainty quantification of resonant states in open quantum systems, we developed a Bayesianframework by integrating a reduced basis method (RBM) emulator with the Gamow coupled-channel (GCC)approach. The RBM, constructed via eigenvector continuation and trained on both bound and reso…
Dr. Haifei Zhang, Chen, Dr. Wei, Xiao-Long Huang, Yang, Prof. Dong, Dr. Haifei Zhang
A methodology based on low energy photon spectrometry with a silicon drift detector (SDD) is developed for the determination of 235U/238U atom ratio in uranium samples. The SDD is well suited for measuring low energy photons emitted from thin uranium sample source with low self-absorption. The main …
Xinling Dai, De-chang Cai, Yan-min Zhang, Jin Cai, Cai De-chang
To ensure the safe transportation of radioactive materials, numerous countries have established specific stan dards. For the transfer of fissile materials, it is imperative that the material within the packaging remains in a subcritical state during routine, normal, and accidental transport conditio…
Miao, Dexing, Xu, Prof. Zijun, Dr. Zhiyu Xiang, Liu, Dr. Pingcheng, Ambrosi, Prof. Giovanni, Barbanera, Dr. Mattia, Dr. Mengke Cai, Prof. Xudong Cai, Dr. Hsin-Yi Chou, Duranti, Prof. Matteo, Formato, Dr. Valerio, Ionica, Dr. Maria, Jiang, Dr. Yaozu, Jin, Liangchenglong, Dr. Vladimir Koutsenko, Li, Mr. Qinze, Liu, Mr. Cong, Lv, Xingjian, Oliva, Dr. Alberto, Peng, Wenxi, Qiao, Dr. Rui, Silvestre, Dr. Gianluigi, Wu, Mr. Zibing, Prof. Xuhao Yuan, Hongyu Zhang, Dr. Xiyuan Zhang, Wang, Jianchun, Wang, Jianchun
A silicon microstrip detector (SSD) has been developed to have state of the art spatial resolution and a large sensitive area under stringent power constraints. The design incorporates three floating strips with their bias resistors inserted between two aluminum readout strips. Beam test measurement…
Heng Zhang, Yun-Ling He, Dong Liu, Qin Hang, He-Min Yao, Di Xiang, Dong Liu
The neutron diffusion equation plays a pivotal role in the analysis of nuclear reactors. Nevertheless, employ#2;ing the Physics-Informed Neural Network (PINN) method for its solution entails certain limitations. TraditionalPINN approaches often utilize fully connected network (FCN) architecture, whi…
Shaohua Hu, Qi Qiu, De-Tao Xiao, Xiang-Yuan Deng, Xiang-Yu Xu, Peng-hao Fan, Lei Dai, Zhi-Wen Hu, Tao Zhu, Qing-Zhi Zhou, Tao Zhu, Qing-Zhi Zhou
Physics-informed neural networks (PINNs) play a vital role in machine learning and demonstrate significant advantages in addressing complex physical problems. The PINN method enables rapid prediction of 220Rn progeny concentration and holds significant importance for the regulation and measurement o…
Fei, Xionghui, Wang, Ke, Wang, Xiaodong
In this study, the dosimetric characteristics (thickness applicability, preheating time, temperature and hu midity dependence, in-batch uniformity, readout reproducibility, dose linearity, self-decay, and electron energy response) of engineered polycarbonate films irradiated with an electron beam (0…
Guiqiang He, Dan Lin, Jian Zhou, Guiqiang He
Many adsorbents have been developed for uranium recovery to ensure global energy and environmental security. However, most reported adsorbents involve complex preparation process and rely heavily on petrochemical feedstocks, which undoubtedly increases carbon emissions from production in the nuclear…
Yan, Shuchang, Qiu, Rui, Luo, Xiyu, Hu, Ankang, Wu, Zhen, Li, Junli, Qiu, Rui
Computational phantoms play an essential role in radiation dosimetry and health physics. Although mesh-type phantoms offer a high resolution and adjustability, their use in dose calculations is limited by their slow computational speed. Progress in heterogeneous computing has allowed for substantial…
Yao Shuoyuan, Jia-Yin Du, Morteza Aslaninejad, Jing-Tong Du, Ming-Yang Huang, S. Wang, Yao Shuo-Yuan
With the significant development of high-intensity hadron (proton and heavy ion) accelerator facilities, the space charge effect has become a major limiting factor for increasing beam intensity because it can drive particle resonance, forming beam halos and causing beam quality degradation or even b…
Wang, Jian, Mingzhun Lei, Deng, Haishun, Wang, Jian, Deng, Haishun
In this paper, a novel method for investigating the particle-crushing behavior of breeding particles in a fusion blanket is proposed. The fractal theory and Weibull distribution are combined to establish a theoretical model, and its validity was verified using a simple impact test. A crushable discr…
Yin, Dr. dayu, Dr. Jinquan Zhang, Chai, Dr. Weiping, Yin, Dr. dayu
Maximizing beam energy deposition requires capturing the entire ion population within a single short-duration bunch to achieve peak power. Using the typical beam 238 U 35+ in the Booster Ring (BRing) at the High Intensity Heavy-Ion Accelerator Facility (HIAF) as an example, we systematically analyze…
Li, Dr. Ouyi, Dr. Weijia Meng, Fang, Dr. Wenxiang, Dr. Bin Zhong, Prof. Tianyu Ma, Prof. Ganglin Yu, yu, Prof. ganglin
For controlled nuclear fusion, it is of significance to develop a comprehensive simulation environment for Inertial Confinement Fusion(ICF) . This environment must accurately calculate the energy loss of charged particles in high-temperature, high-density plasma, and simulate the physical parameters…
Ms. Yuting Wang, Hu, Dr. Jifeng, Guo, Dr. Yuhang, Lv, Dr. You, Chen, Dr. Cong, Wu, Dr. Chen, bao, Dr. yu, Bao, Dr. Yu
The muonium to antimuonium conversion research would be enhanced by an intense pulsed muon source. However, the high intensity muon source induces high pile-up rate in the detector system and reduces the total efficiency. Here we propose a Low Gain Avalanche Detector (LGAD)-based system to search fo…
Liang Zhongcheng, Dong Kaijun, Liang Zhongcheng
Originating in the early 20th century, the revolutions of relativity and quantum theory failed to deliver the anticipated ultimate physical theory; instead, physics in the 21st century confronts even greater perplexities and profound crises. The persistent visibility yet elusiveness of grand unified…
Sun Yuqing, Zhang Binhang, Yuan Xianbao, Tang Haibo
Reactor burnup calculations are crucial to the safe operation and fuel management of nuclear power plants. In recent years, the Chebyshev Rational Approximation Method (CRAM) has emerged as one of the primary methods for solving burnup equation systems. When employing CRAM, complex matrix computatio…
Zhou, Dr. En-Fu, Dr. Xian-Ye Wu, Xiang, Prof. Jian, Yao, Dr. J. M., Ring, Prof. Peter, Yao, Dr. J. M.
We present a new development in the multireference covariant density functional theory (MR-CDFT) for the low-lying states of odd-mass nuclei by mixing the configurations not only with different intrinsic quadrupole shapes, but also with different $K$ quantum numbers. All the configurations are proje…
Cao, Dr. Pei, Cao, Xuetao, Dr. Hui Ding, Prof. Sixuan Zhuang, Yang, Dr. Zihui, Sun, Dr. Guomin, cao, Dr. pei
In the future, advanced reactors will face harsh core environments. Utilizing off-situ detection signals to invert the neutron distribution within the core represents a crucial means for ensuring safe core operation. The latest data-driven off-situ inversion algorithms have not fully considered the …
Yu Guobing, Gu Xianbao, Xiang Yunxiang, Liu Yi, HE Xu, Zhang Wenliang, Wang Jinlong
To calculate the detection efficiency curve and coincidence correction factors for a well-type HPGe detector, the detection efficiency of the HPGe was calibrated using commonly employed single-energy γ radionuclide standard sources, while cascade coincidence correction factors for common radionuclid…