检索结果-内蒙古大学图书馆

A Hybrid Set of complexity Metrics for Large-Scale Object-Oriented software systems

Journal of Computer Science & Technology 2010年第6期25卷 1184-1201页

作者：马于涛何克清李兵刘婧周晓燕 State Key Lab of Software Engineering Wuhan University Complex Networks Research Center Wuhan University Institute of Electronic System Engineering

Large-scale object-oriented（OO） software systems have recently been found to share global network characteristics such as small world and scale free,which go beyond the scope of traditional software measurement and assessment *** measure the complexity at various levels of granularity,namely graph,class（and object） and source code,we propose a hierarchical set of metrics in terms of coupling and cohesion-the most important characteristics of software,and analyze a sample of 12 open-source OO software systems to empirically validate the *** results of the correlations between cross-level metrics indicate that the graph measures of our set complement traditional software metrics well from the viewpoint of network thinking,and provide more effective information about fault-prone classes in practice.

关键词： complexity metrics quality analysis and evaluation object-oriented programming reverse engineering complex networks

来源：评论

学校读者我要写书评

暂无评论

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

引用

IEEE/CAA Journal of Automatica Sinica 2025年第5期12卷 841-858页

作者： Xiong, Luolin Wang, Haofen Chen, Xi Sheng, Lu Xiong, Yun Liu, Jingping Xiao, Yanghua Chen, Huajun Han, Qing-Long Tang, Yang Ministry of Education Engineering Research Center of Process System Engineering East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai 200237 China College of Design and Innovation Tongji University Shanghai 200092 China School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Shanghai 200433 China School of Software Beihang University Beijing 100191 China School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 China College of Computer Science and Technology Zhejiang University AZFT Joint Laboratory for Knowledge Engine Hangzhou Innovation Center Hangzhou 310058 China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne 3122 VIC Australia

DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek's engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek's innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning. © 2014 Chinese Association of Automation.

关键词： DeepSeek large AI models reasoning capability reinforcement learning test-time scaling

来源：评论

学校读者我要写书评

暂无评论

A Random Forest-Based Precipitation Detection Algorithm for FY-3C/3D MWTS2 over Oceanic Regions

引用

Remote Sensing 2025年第9期17卷 1566-1566页

作者： Luo, Tengling Yu, Yi Ma, Gang Zhang, Weimin Qin, Luyao Shi, Weilai Dai, Qiudan Zhang, Peng College of Meteorology and Oceanography National University of Defense Technology Changsha410073 China Chinese Academy of Meteorological Sciences China Meteorological Administration Beijing100081 China Key Laboratory of Software Engineering for Complex Systems Changsha410073 China Institute of Atmospheric Physics Chinese Academy of Sciences Beijing100029 China Beijing100081 China

Satellite microwave-sounding radiometer data assimilation under clear-sky conditions typically requires the exclusion of precipitation-affected field-of-view (FOV) regions. However, the traditional scatter index (SI) and cloud liquid water path (CLWP)-based precipitation sounding algorithms from earlier NOAA microwave sounders are built on window channels which are not available from FY-3C/D MWTS-II. To address this limitation, this study establishes a nonlinear relationship between multispectral visible/infrared data from the FY-2F geostationary satellite and microwave sounding channels using an artificial intelligence (AI)-driven approach. The methodology involves three key steps: (1) The spatiotemporal integration of FY-2F VISSR-derived products with NOAA-19 AMSU-A microwave brightness temperatures was achieved through the GEO-LEO pixel fusion algorithm. (2) The fused observations were used as a training set and input into a random forest model. (3) The performance of the RF_SI method was evaluated by using individual cases and time series observations. Results demonstrate that the RF_SI method effectively captures the horizontal distribution of microwave scattering signals in deep convective systems. Compared with those of the NOAA-19 AMSU-A traditional SI and CLWP-based precipitation sounding algorithms, the accuracy and sounding rate of the RF_SI method exceed 94% and 92%, respectively, and the error rate is less than 3%. Also, the RF_SI method exhibits consistent performance across diverse temporal and spatial domains, highlighting its robustness for cross-platform precipitation screening in microwave data assimilation. © 2025 by the authors.

关键词： Microwave acoustics

来源：评论

学校读者我要写书评

暂无评论

Anomaly-aware self-supervised feature learning for weakly supervised video anomaly detection

引用

Computer Vision and Image Understanding 2025年 257卷

作者： Yang, Zhen Wang, Guodong Guo, Yuanfang Bao, Xiuguo Huang, Di State Key Laboratory of Complex and Critical Software Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029 China

Weakly supervised video anomaly detection (WSVAD) aims to achieve frame-level anomaly detection utilizing video-level labeled training data. Most of the WSVAD methods typically focus on developing various anomaly detectors and employ the models pretrained on general large-scale databases (e.g. Kinetics-400) for video feature extraction. However, such features are pretrained in a supervised manner to recognize significantly distinct human actions, making them sub-optimal for the WSVAD task, which involves detecting more complex events including subtle human and non-human motions. Unlike previous efforts, in this work, we address WSVAD from another fundamental perspective of feature learning, and considering the anomaly attributes, we propose an anomaly-aware self-supervised learning (SSL) based method. Specifically, we design a series of pretext tasks, including temporal order verification, speed prediction, arrow of time prediction, and abrupt change detection, to directly pretrain the model on the anomaly datasets, thus rendering features tailored for the WSVAD task. Moreover, to deal with the limitation of the existing methods which adapt the pretrained features to anomaly detection by utilizing top-k anomaly-scored samples, we present a hard instance mining strategy (HIMS) to additionally explore valuable cues from unused non-top-k ones, enhancing the discriminability between normal and abnormal instances. Experimental results clearly demonstrate that our method outperforms state-of-the-art counterparts on the UCF-Crime, ShanghaiTech and XD-Violence benchmark datasets, highlighting its effectiveness. © 2025 Elsevier Inc.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Water hammer prediction and control:the Green's function method

引用

Acta Mechanica Sinica 2012年第2期28卷 266-273页

作者： Li-Jun Xuan Feng Mao Jie-Zhi Wu State Key Laboratory of Turbulence and Complex System College of EngineeringPeking University100871 BeijingChina

By Green＇s function method we show that the water hammer （WH） can be analytically predicted for both laminar and turbulent flows （for the latter, with an eddy vis- cosity depending solely on the space coordinates）, and thus its hazardous effect can be rationally controlled and mini- mized. To this end, we generalize a laminar water hammer equation of Wang et al. （J. Hydrodynamics, B2, 51, 1995） to include arbitrary initial condition and variable viscosity, and obtain its solution by Green＇s function method. The pre- dicted characteristic WH behaviors by the solutions are in excellent agreement with both direct numerical simulation of the original governing equations and, by adjusting the eddy viscosity coefficient, experimentally measured turbulent flow data. Optimal WH control principle is thereby constructed and demonstrated.

关键词： Water hammer Two-dimensional analytical theory - Pressure transients Pipe-valve flow control

来源：评论

学校读者我要写书评

暂无评论

Continuous Detonation Engine and Effects of Different Types of Nozzle on Its Propulsion Performance

引用

Chinese Journal of Aeronautics 2010年第6期23卷 647-652页

作者： Shao Yetao Liu Meng Wang Jianping State Key Laboratory of Turbulence and Complex System College of EngineeringPeking UniversityBeijing 100871China

The rotating propagation of a continuous detonation engine (CDE) with different types of nozzles is investigated in three-dimensional numerical simulation using a one-step chemical reaction model. Flux terms are solved by the so-called monotonicity-preserving weighted essentially non-oscillatory (MPWENO) scheme. The simulated flow field agrees well with the previous experimental results. Once the initial transient effects die down, the detonation wave maintains continuous oscillatory propagation in the annular chamber as long as fuel is continuously injected. Using a numerical flow field, the propulsion per- formance of a CDE is computed for four types of nozzles, namely the constant-area nozzle, Laval nozzle, diverging nozzle and converging nozzle. The gross specific impulse of the CDE ranges 1 540-1 750 s and the mass flux per square meter ranges 313-330 kg/(m2·s) for different nozzles. Among these four types of nozzles, Laval nozzle performs the best, and these parameters are 1 800 N, 1 750 s and 313 kg/(m2.s). A nozzle can greatly improve the propulsion performance.

关键词： continuous detonation engine propulsion performance nozzle effects Laval nozzle hypersonic

来源：评论

学校读者我要写书评

暂无评论

Scale-up of bubbling fluidized beds with continuous particle flow based on particle-residence-time distribution

引用

Particuology 2015年第2期13卷 155-163页

作者： Juwei Zhang Guangwen Xu State Key Laboratory of Multi-phase Complex System Institute of Process EngineeringChinese Academy of Sciences

Few studies have investigated scale-up of the residence-time distribution （RTD） of particles in bubbling fluidized beds （BFBs） with continuous particle flow. Two approaches were investigated in this study： first, using well-known scaling laws that require changes in particle properties and gas velocity; second, using a simple approach keeping the same particles and gas velocity for different beds. Our theoretical analysis indicates it is possible to obtain similar RTDs in different BFBs with scaling laws if the plug-flow residence time （tpiug） is changed as m^0.5, where m is the scaling ratio of the bed; however, neither approach can ensure similar RTDs if tplug is kept invariant. To investigate RTD variations using two approaches without changing tplug, we performed experiments in three BFBs. The derivatives dE（θ）/dθ （where E（θ） is the dimensionless RTD density function and θ is the dimensionless time） in the early stage of the RTDs always varied with m 1, which was attributed to the fact that the particle movement in the early stage were mainly subject to dispersion. Using the simple approach, we obtained similar RTDs by separately treating the RTDs in the early and post-stages. This approach guarantees RTD similarity and provides basic rules for designing BFBs.

关键词： Bubbling fluidized bed （BFB） Scale-up Residence time distribution （RTD） Similarity

来源：评论

学校读者我要写书评

暂无评论

DRSC: Dual-Reweighted Siamese Contrastive Learning Network for Cross-Domain Rotating Machinery Fault Diagnosis With Multi-Source Domain Imbalanced Data

引用

IEEE Internet of Things Journal 2025年

作者： Bi, Yuanguo Fu, Rao Jiang, Cunyu Zhang, Xiaoling Li, Fengyun Zhao, Liang Han, Guangjie Northeastern University School of Computer Science and Engineering Shenyang110169 China Ministry of Education Engineering Research Center of Security Technology of Complex Network System Shenyang110169 China Shenyang University of Technology Institute of Artificial Intelligence Shenyang110870 China Shenyang Aerospace University School of Computer Science Shenyang110135 China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China

To enhance the reliability of rotating machinery, cross-domain fault diagnosis becomes vital for detecting faults under unknown operating conditions. However, multi-source domain imbalanced data present significant challenges, as divergent label distributions across domains cause complex domain-class shifts and degrade the performance of cross-domain fault diagnosis. Moreover, diagnostic models often struggle to learn features from minority classes due to label imbalance within each domain, which may degrade the performance in diagnosing these minority classes. To address these challenges, we propose a Dual-Reweighted Siamese Contrastive learning network (DRSC) for cross-domain fault diagnosis with multi-source domain imbalanced data. In DRSC, we design a Siamese feature extractor based on a wide-kernel convolutional neural network to capture short-term characteristics and leverage the convenience in extracting domain-invariant features. Subsequently, to alleviate domain-class shifts, we design a reweighted contrastive domain-class alignment mechanism that strategically pulls domain-class pairs together while pushing other health conditions away. Finally, to enable the diagnostic model to learn from minority health conditions, a reweighted health condition classifier is developed by assigning higher weights to the minority classes. Evaluation results on two public datasets illustrate DRSC outperforms comparison models in cross-domain fault diagnosis. © 2014 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Selective Regulation of ray tissue for achieving ultrastable Zero-Poisson's-ratio material out of wood

引用

Journal of Advanced Research 2025年

作者： Yu, Xia Liu, Bo Zhou, Xinyi Wu, Tong Ren, Bohua Fang, Tao Cong, Chaonan Wu, Guofang Yao, Lihong Wei, Xiaoding Lu, Yun Research Institute of Wood Industry Chinese Academy of Forestry Beijing 100091 China College of Material Science and Art Design Inner Mongolia Agricultural University Hohhot 010018 China State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering Science College of Engineering Peking University Beijing 100871 China

Introduction: Materials exhibiting a Poisson's ratio of zero have attracted considerable interest due to their unique properties and potential applications in various fields, including aerospace, athletic footwear, and sporting equipment. However, the high costs associated with their structural fabrication and the dependence on synthetic chemical materials for most zero Poisson's ratio materials complicate the preparation processes of current elastic materials, resulting in negative environmental impacts. Objectives: This study presents a sustainable treatment strategy that utilizes the inherent cellular structure of wood to achieve a zero Poisson's ratio, thereby enhancing its elasticity. Methods: By strategically selecting tree species with varying tissue compositions and employing simple chemical and heat treatments, we developed a commercially viable elastic wood material with a zero Poisson's ratio that meets diverse stress rebound requirements. Results: The unique internal structure of the wood not only provides high fatigue resistance—capable of withstanding 5000 cycles of compression at a strain of 40 %—but also ensures excellent resilience and processability. At a deformation level of 60 %, the elastic modulus reaches 90.9 MPa. Additionally, the material retains its elasticity even at extremely low temperatures of −196 °C and demonstrates the ability to endure elevated temperatures following carbonization at 1200 °C. Conclusion: This study demonstrates that wood-based materials with a zero Poisson's ratio exhibit remarkable stability after cyclic compression, presenting a viable pathway for developing superelastic materials suitable for both high- and low-temperature applications. © 2024

关键词： Ray tissue Superelastic Ultrastability Zero Poisson's ratio

来源：评论

学校读者我要写书评

暂无评论

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

引用

IEEE Transactions on Multimedia 2025年

作者： Fu, Congrui Yuan, Hui Jiang, Shiqi Zhang, Guanghui Shen, Liquan Hamzaoui, Raouf Center of Experimental Teaching China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China Shandong University School of software Shandong Jinan China Shandong University School of Computer Science and Technology China Shanghai University School of Communication and Information Engineering Shanghai China De Montfort University School of Engineering and Sustainable Development LeicesterLE1 9BH United Kingdom

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. Our method combines long-term global information and short-term local information from the video to better extract complete and accurate spatial-temporal information. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This provides a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms open source state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.2 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectiv

关键词： Long short-term memory

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：