检索结果-内蒙古大学图书馆

Improving long-tail classification via decoupling and regularisation

CAAI Transactions on Intelligence technology 2025年第1期10卷 62-71页

作者： Shuzheng Gao Chaozheng Wang Cuiyun Gao Wenjian Luo Peiyi Han Qing Liao Guandong Xu School of Computer Science and Technology Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Harbin Institute of TechnologyShenzhenChina Faculty of Engineering and Information Technology University of Technology SydneySydneyNew South WalesAustralia

Real-world data always exhibit an imbalanced and long-tailed distribution,which leads to poor performance for neural network-based *** methods mainly tackle this problem by reweighting the loss function or rebalancing the ***,one crucial aspect overlooked by previous research studies is the imbalanced feature space problem caused by the imbalanced angle *** this paper,the authors shed light on the significance of the angle distribution in achieving a balanced feature space,which is essential for improving model performance under long-tailed ***,it is challenging to effectively balance both the classifier norms and angle distribution due to problems such as the low feature *** tackle these challenges,the authors first thoroughly analyse the classifier and feature space by decoupling the classification logits into three key components:classifier norm(*** magnitude of the classifier vector),feature norm(*** magnitude of the feature vector),and cosine similarity between the classifier vector and feature *** this way,the authors analyse the change of each component in the training process and reveal three critical problems that should be solved,that is,the imbalanced angle distribution,the lack of feature discrimination,and the low feature *** from this analysis,the authors propose a novel loss function that incorporates hyperspherical uniformity,additive angular margin,and feature norm *** component of the loss function addresses a specific problem and synergistically contributes to achieving a balanced classifier and feature *** authors conduct extensive experiments on three popular benchmark datasets including CIFAR-10/100-LT,ImageNet-LT,and iNaturalist *** experimental results demonstrate that the authors’loss function outperforms several previous state-of-the-art methods in addressing the challenges posed by imbalanced and longtailed datasets,t

关键词： computer vision image classification long-tailed data machine learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous trajectory tracking control method for an agricultural robotic vehicle

引用

International Journal of Agricultural and Biological engineering 2024年第1期17卷 215-224页

作者： Jin Yan Wenguang Zhang Yong Liu Wei Pan Xiaoyu Hou Zhiyu Liu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Information Engineering Xuzhou University of TechnologyXuzhou 221018JiangsuChina National Key Laboratory of Transient Physics Nanjing University of Science and TechnologyNanjing 210094China School of Mechanical Engineering Nanjing University of Science and TechnologyNanjing 210094China

To address the nonlinearities and external disturbances in unstructured and complex agricultural environments,this paper investigates an autonomous trajectory tracking control method for agricultural ground ***,this paper presents the design and implementation of a lightweight,modular two-wheeled differential drive vehicle equipped with two drive wheels and two caster *** vehicle comprises drive wheel modules,passive wheel modules,battery modules,a vehicle frame,a sensor system,and a control ***,a novel robust trajectory tracking method was proposed,utilizing an improved pure pursuit ***,an Online Particle Swarm Optimization Continuously Tuned PID(OPSO-CTPID)controller was introduced to dynamically search for optimal control gains for the PID *** results demonstrate the superiority of the improved pure pursuit algorithm and the OPSO-CTPID control *** validate the performance,the vehicle was integrated with a seeding and fertilizing machine to realize autonomous wheat seeding in an agricultural *** outcomes reveal that the vehicle of this study completed a seeding operation exceeding 1 km in *** proposed method can robustly and smoothly track the desired trajectory with an accuracy of less than 10 cm for the root mean square error(RMSE)of the curve and straight lines,given a suitable set of parameters,meeting the requirements of agricultural *** findings of this study hold significant reference value for subsequent research on trajectory tracking algorithms for ground-based agricultural robots.

关键词： trajectory tracking autonomy control agricultural robotic vehicle online PSO continuously tuned PID dynamic pure pursuit algorithm

来源：评论

学校读者我要写书评

暂无评论

Driving deep-learning-based metasurface design with Kramers-Kronig relations

引用

Physical Review Applied 2024年第4期22卷 L041002页

作者： Guangfeng You Chao Qian Shurun Tan Erping Li Hongsheng Chen ZJU-UIUC Institute Interdisciplinary Center for Quantum Information State Key Laboratory of Extreme Photonics and Instrumentation ZJU-Hangzhou Global Science and Technology Innovation Center Key Laboratory of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang Jinhua Institute of Zhejiang University

Two-decade strides in metasurfaces have enabled a multitude of theoretical breakthroughs and experimental discoveries that outride established comprehension. Deep learning has recently found favor for expediting metasurface design and unearthing complex light-matter interactions, in contrast to resource-intensive numerical simulations. However, most “black box” algorithms lack enough discernment on parsing internal physical connections. Here, we propose a physical adversary channel to be complementary to gradient descent channel by embedding the Kramers-Kronig (KK) relations into a neural network, quantifying the inherent spectral contradictions at the output side. We evaluate the superiority of the KK-driven neural network in forward prediction and inverse metasurface design by modifying loss function and shaping probability distribution in latent space, respectively. The exceptional outcome suggests that the similarity between output and given spectra reaches up to 99.8% and maintains an extremely high fidelity even in a mutant band. Our work provides a physically explicable perspective to explain “black box” models, possibly reviving intelligent metasurface applications.

关键词： Inverse problems Artificial neural networks Metamaterials Metasurfaces Deep learning Electromagnetic wave theory

来源：评论

学校读者我要写书评

暂无评论

Stabilizing alkaline hydrogen evolution activity of heterogeneous metal-oxide-nitride cathode by dynamic reconstruction and doping engineering

引用

稀有金属（英文版） 2025年第2期44卷 1084-1095页

作者： Jin-Di He Han-Du Wang Xu-Ming Zhang Li Huang Yun Li Lu Xia Chao-Ran Pi Jian-Ping Li Yang Zheng Biao Gao Kai-Fu Huo The State Key Laboratory of Refractories and Metallurgy and Institute of Advanced Materials and Nanotechnology Wuhan University of Science and TechnologyWuhan 430081China Guizhou Wujiang Hydropower Development Co. LTD.Guiyang 550002China The College of Resources and Environment Engineering and Hubei Key Laboratory for Efficient Utilization and Agglomeration of Metallurgic Mineral Resources Wuhan University of Science and TechnologyWuhan 430081China Wuhan National Laboratory for Optoelectronics(WNLO) School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074China

The development of cost-effective,highly effi-cient and stable catalysts is critical to promote the indus-trial alkaline hydrogen evolution reaction(HER).However,single-component catalysts often cannot handle the multiple kinetic steps during hydrogen *** address this challenge,a heterogeneous catalyst comprising metal Co,CoO and carbon-doped Mo2N(Co-CoO-C/Mo2N/CC)was synthesized by heat treatment of carbon cloth-supported CoMoO4 microrods in a mixed reduction *** resulting catalyst has rich interfaces,exhibiting excellent initial HER activity with an overpotential of 27 mV at 10 mA·cm-2 and a Tafel slope of 37 mV·*** studies show that the activity and stability of the catalyst can be tailored by the dynamic surface reconfiguration and doping *** carbon doping and high crystallinity in Mo2N help to reduce the dissolution of Mo and the surface metal Co is preferentially converted into stable Co(OH)2,thus stabilizing the struc-ture of the catalyst and coordinating various reaction *** an electrolyzer comprising a heterogeneous Co-CoO-C/Mo2N cathode and NiFe layered double hydroxides(LDH)anode,only 1.58 V is required to achieve a current density of 50 mA·cm-2,outperforming Pt/RuO *** continuous electrolysis for 100 h,the potential increases by merely 19 mV from the initial 1.58 V,indicating excellent *** study presents a novel strategy for developing highly active and stable heterogeneous catalysts,offering insights into the dynamic evolution of catalyst structures and laying the groundwork for designing efficient and stable composite catalysts for energy conversion applications.

关键词： Heterogeneous catalyst Dynamic reconstruction Doping engineering Hydrogen evolution reaction Nitride

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional quantum Griffiths singularity in bulk iron-pnictide superconductors

引用

National science Review 2024年第12期11卷 104-111页

作者： Shao-Bo Liu Congkuan Tian Yongqing Cai Hang Cui Xinjian Wei Mantang Chen Yang Zhao Yuan Sui Shuyue Guan Shuang Jia Yu Zhang Ya Feng Jiankun Li Jian Cui Yuanjun Song Tingting Hao Chaoyu Chen Jian-Hao Chen International Centerfor Quantum Materials School of Physics Peking University Beijing Academy of Quantum Information Sciences School of Physics Dalian University of Technology Shenzhen Institute for Quantum Science and Engineering and Department of Physics Southern University of Science and Technology Key Laboratory for the Physics and Chemistry of Nanodevices Peking University Hefei National Laboratory

The quantum Griffiths singularity（QGS） is a phenomenon driven by quenched disorders that break conventional scaling invariance and result in a divergent dynamic critical exponent during quantum phase transitions（QPT）. While this phenomenon has been well-documented in low-dimensional conventional superconductors and in three-dimensional（3D） magnetic metal systems, its presence in 3D superconducting systems and in unconventional high-temperature superconductors（high-TcSCs） remains unclear. In this study, we report the observation of robust QGS in the superconductor-metal transition（SMT） of both quasi-2D and 3D anisotropic unconventional high-Tcsuperconductor CaFe1-xNixAsF（x <5%） bulk single crystals, where the QGS states persist to up to 5.3 K. A comprehensive quantum phase diagram is established that delineates the 3D anisotropic QGS of SMT induced by perpendicular and parallel magnetic fields. Our findings reveal the universality of QGS in 3D superconducting systems and unconventional high-TcSCs, thereby substantially expanding the range of applicability of QGS.

关键词： quantum phase transition superconductor-metal transition iron-based superconductor quantum Griffiths singularity

来源：评论

学校读者我要写书评

暂无评论

Seasonal prediction of extreme high-temperature days over the Yangtze River basin

引用

science China Earth sciences 2024年第7期67卷 2137-2147页

作者： Shifeng PAN Zhicong YIN Mingkeng DUAN Tingting HAN Yi FAN Yangyang HUANG Huijun WANG Key Laboratory of Meteorological Disaster Ministry of Education/Joint International Research Laboratory of Climate and Environment Change/Collaborative Innovation Center on Forecast and Evaluation of Meteorological DisastersNanjing University of Information Science and TechnologyNanjing 210044China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) Zhuhai 519080China

Extreme high temperatures occur frequently over the densely populated Yangtze River basin(YRB)in China during summer,significantly impacting the local economic development and ecological ***,accurate prediction of extreme high-temperature days in this region remains a ***,the Climate Forecast System Version 2(CFSv2)exhibits poor performance in this ***,based on the interannual increment approach,we develop a hybrid seasonal prediction model over the YRB(HM_(YRB))to improve the prediction of extreme high-temperature days in *** HM_(YRB)relies on the following four predictors:the observed preceding April-May snowmelt in north western Europe;the snow depth in March over the central Siberian Plateau;the CFSv2-forecasted concurrent summer sea surface temperatures around the Maritime Continent;and the 200-hPa geopotential height over the Tibetan *** HM_(YRB)indicates good capabilities in predicting the interannual variability and trend of extreme high-temperature days,with a markable correlation coefficient of 0.58 and a percentage of the same sign(PSS)of 76% during 1983-2015 in the one-year-out ***,the HM_(YRB) maintains high PSS skill(86%)and robustness in the independent prediction period(2016-2022).Furthermore,the HM_(YRB) shows a good performance for years with high occurrence of extreme high-temperature days,with a hit ratio of 40%.These predictors used in HM_(YRB)are beneficial in terms of the prediction skill for the average daily maximum temperature in summer over the YRB,albeit with biases existing in the *** study provides promising insights into the prediction of 2022-like hot extremes over the YRB in China.

关键词： Hot extremes Yangtze River basin CFSv2 Seasonal prediction One-year-out cross-validation

来源：评论

学校读者我要写书评

暂无评论

MIMO performance enhancement of MIMO arrays using PCS-based near-field optimization technique

引用

science China(information sciences) 2023年第6期66卷 170-185页

作者： Yipeng WANG Xiaoming CHEN Huiling PEI Wei E.I.SHA Yi HUANG Ahmed A.KISHK School of Information and Communications Engineering Xi'an Jiaotong University Key Laboratory of Micro-Nano Electronic Devices and Smart Systems of Zhejiang Province College of Information Science and Electronic EngineeringZhejiang University Department of Electrical Engineering and Electronics University of Liverpool Department of Electrical and Computer Engineering Concordia University

Extensive efforts have been made in designing large multiple-input multiple-output(MIMO)arrays. Nevertheless, improvements in conventional antenna characteristics cannot ensure significant MIMO performance improvement in realistic multipath environments. Array decorrelation techniques have been proposed, achieving correlation reductions by either tilting the antenna beams or shifting the phase centers away from each other. Hence, these methods are mainly limited to MIMO terminals with small arrays. To avoid such problems, this work proposes a decorrelation optimization technique based on phase correcting surface(PCS)that can be applied to large MIMO arrays, enhancing their MIMO performances in a realistic(non-isotropic)multipath environment. First, by using a near-field channel model and an optimization algorithm, a near-field phase distribution improving the MIMO capacity is obtained. Then the PCS(consisting of square elements)is used to cover the array's aperture, achieving the desired near-field phase *** examples demonstrate the effectiveness of this PCS-based near-field optimization technique. One is a1 × 4 dual-polarized patch array(working at 2.4 GHz)covered by a 2 × 4 PCS with 0.6λ center-to-center distance. The other is a 2 × 8 dual-polarized dipole array, for which a 4 × 8 PCS with 0.4λ center-to-center distance is designed. Their MIMO capacities can be effectively enhanced by 8% and 10% in single-cell and multi-cell scenarios, respectively. The PCS has insignificant effects on mutual coupling, matching, and the average radiation efficiency of the patch array, and increases the antenna gain by about 2.5 dB while keeping broadside radiations to ensure good cellular coverage, which benefits the MIMO performance of the *** proposed technique offers a new perspective for improving large MIMO arrays in realistic multipath in a statistical sense.

关键词： antenna correlation array antenna multiple-input multiple-output (MIMO) capacity

来源：评论

学校读者我要写书评

暂无评论

Synergistically enhanced dielectric, insulating and thermally conductive performances of sandwich PMMA based dielectric films

引用

Progress in Natural science:Materials International 2024年第3期34卷 591-597页

作者： Dongmei Zhang Yufan Li Yuchao Li Zhonggui Sun Hanxue Zhu Lujia Yang Yanhu Zhan Yankai Li Shi Wang Jun-Wei Zha School of Mathematical Sciences Liaocheng University School of Materials Science and Engineering Liaocheng University State Key Laboratory of Organic Electronics and Information Displays & Institute of Advanced Materials (IAM) Nanjing University of Posts & Telecommunications School of Chemistry and Biological Engineering University of Science and Technology Beijing

A tri-layered(B-G-B) dielectric films were simply prepared by alternatively spin-coating boron nitride/polymethylmethacrylate(BN/PMMA, B) and graphene nanosheets(GNS/PMMA, G) compound solutions. The structure, morphology, thermal conductivity, and particularly the dielectric and relaxation behaviors were systematically studied. Results showed that a good exfoliation and dispersion of BN and GNS can be simply achieved through intensive mechanical compounding with PMMA in the internal mixer. The dielectric constant and breakdown strength of the obtained 1-3-1(B-G-B) sandwich composite film reached 4.3(@1 kHz) and 458.6kV/mm, being 119 % and 113 % higher than that of pure PMMA, respectively. Furthermore, the overall thermal conductivity of sandwich 1-3-1 composite increased by 112 % due to the addition of thermally conductive BN and GNS. The sandwich design strategy provided an effective way of achieving good permittivity, high insulation, and improved thermal conductivity simultaneously, showing potential applications in the miniaturization and integration of electronic devices.

关键词： Sandwich structure Breakdown strength Thermal conductivity Dielectric constant Composites

来源：评论

学校读者我要写书评

暂无评论

Ion migration in metal halide perovskite QLEDs and its inhibition

引用

Chinese Physics B 2023年第1期32卷 11-21页

作者：董宇辉严丹妮杨帅魏乃炜邹友生曾海波 Institute of Optoelectronics&Nanomaterials College of Materials Science and EngineeringNanjing University of Science and TechnologyNanjing 210094China Key Laboratory of Advanced Display Materials and Devices Ministry of Industry and Information TechnologyNanjing 210094China

Benefiting from the excellent properties such as high photoluminescence quantum yield(PLQY), wide gamut range,and narrow emission linewidth, as well as low-temperature processability, metal halide perovskite quantum dots(QDs)have attracted wide attention from researchers. Despite tremendous progress has been made during the past several years,the commercialization of perovskite QDs-based LEDs(PeQLEDs) is still plagued by the instability. The ion migration in halide perovskites is recognized as the key factor causing the performance degradation of PeQLEDs. In this review, the elements species of ion migration, the effects of ion migration on device performance and stability, and effective strategies to hinder/mitigate ion migration in PeQLEDs are successively discussed. Finally, the forward insights on the future research are highlighted.

关键词： perovskite quantum dots light-emitting diodes ion migration stability

来源：评论

学校读者我要写书评

暂无评论

Integrated Clustering and Routing Design and Triangle Path Optimization for UAV-Assisted Wireless Sensor Networks

引用

China Communications 2024年第4期21卷 178-192页

作者： Shao Liwei Qian Liping Wu Mengru Wu Yuan College of Information Engineering Zhejiang University of TechnologyHangzhou 310014China State Key Laboratory of Internet of Things for Smart City University of MacaoMacaoChina Department of Computer and Information Science University of MacaoMacaoChina

With the development of the Internet of Things(IoT),it requires better performance from wireless sensor networks(WSNs),such as larger coverage,longer lifetime,and lower ***,a large amount of data generated from monitoring and long-distance transmission places a heavy burden on sensor nodes with the limited battery *** this,we investigate an unmanned aerial vehicles assisted mobile wireless sensor network(UAV-assisted WSN)to prolong the network lifetime in this ***,we use UAVs to assist the WSN in collecting *** the current UAV-assisted WSN,the clustering and routing schemes are determined ***,such a separate consideration might not maximize the lifetime of the whole WSN due to the mutual coupling of clustering and *** efficiently prolong the lifetime of the WSN,we propose an integrated clustering and routing scheme that jointly optimizes the clustering and routing *** the whole network space,it is intractable to efficiently obtain the optimal integrated clustering and routing ***,we propose the Monte-Las search strategy based on Monte Carlo and Las Vegas ideas,which can generate the chain matrix to guide the algorithm to find the solution *** point-to-point collection leads to long collection paths,so a triangle optimization strategy is then proposed that finds a compromise path to shorten the collection path based on the geometric distribution and energy of sensor *** avoid the coverage hole caused by the death of sensor nodes,the deployment of mobile sensor nodes and the preventive mechanism design are *** emergency data transmission mechanism is further proposed to reduce the latency of collecting the latency-sensitive data due to the absence of *** with the existing schemes,the proposed scheme can prolong the lifetime of the UAVassisted WSN at least by 360%,and shorten the collection path of UAVs by 56.24%.

关键词： Monte-Las search strategy triangle path optimization unmanned aerial vehicles wireless sensor networks

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：