检索结果-南通市图书馆

Automatic Narrow-Deep Feature Recognition for Mould Manufacturing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of computer science & Technology 2011年第3期26卷 528-537页

作者：陈正鸣何坤金刘景 College of computer science and information engineering Hohai University

There usually exist narrow-long-deep areas in mould needed to be machined in special machining. To identify the narrow-deep areas automatically, an automatic narrow-deep feature （NF） recognition method is put forward accordingly. First, the narrow-deep feature is defined innovatively in this field and then feature hint is extracted from the mould by the characteristics of narrow-deep feature. Second, the elementary constituent faces （ECF） of a feature are found on the basis of the feature hint. By means of extending and clipping the ECF, the feature faces are obtained incrementally by geometric reasoning. As a result, basic narrow-deep features （BNF） related are combined heuristically. The proposed NF recognition method provides an intelligent connection between CAD and CAPP for machining narrow-deep areas in mould.

关键词： narrow-deep feature feature recognition face-pair mould

维普期刊数据库

Cross-subcarrier precoder design for massive MIMO-OFDM downlink with symplectic optimization

在线全文

学校读者我要写书评

暂无评论

science China(information sciences) 2025年

作者： Yu-Xuan ZHANG An-An LU Xiang-Gen XIA Xi-Qi GAO National Mobile Communications Research Laboratory Southeast University Purple Mountain Laboratories Department of Electrical and computer engineering University of Delaware

We propose a cross-subcarrier precoder design(CSPD) for massive multiple-input multiple-output(MIMO) orthogonal frequency division multiplexing(OFDM) downlink. This work aims to significantly improve the channel estimation and signal detection performance by enhancing the smoothness of the frequency domain effective channel. This is accomplished by designing a few vectors known as the transform domain precoding vectors(TDPVs), which are then transformed into the frequency domain to generate the precoders for a set of subcarriers. To combat the effect of channel aging, the TDPVs are optimized under imperfect channel state information(CSI). The optimal precoder structure is derived by maximizing an upper bound of the ergodic weighted sum-rate(WSR) and utilizing the a posteriori beam-based statistical channel model(BSCM). To avoid the large-dimensional matrix inversion, we propose an algorithm with symplectic optimization. Simulation results indicate that the proposed cross-subcarrier precoder design significantly outperforms conventional methods.

关键词：

GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(information sciences) 2025年第1期 145-158页

作者： Wei JU Yiyang GU Zhengyang MAO Ziyue QIAO Yifang QIN Xiao LUO Hui XIONG Ming ZHANG School of computer science National Key Laboratory for Multimedia Information ProcessingPeking University Artificial Intelligence Thrust The Hong Kong University of Science and Technology Department of computer science University of California

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views(i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named graph pooling contrast(GPS) to address these *** by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

关键词：

2D SnOx/SnS2的异质结构的忆阻器用于神经形态计算（英文）

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China Materials 2025年

作者：吴扬武李思凡季云翁正进邢厚英 Lester Arauz Travis Hu 洪金华 Kah-Wee Ang 刘松 State Key Laboratory of Chemo/Biosensing and Chemometrics College of Chemistry and Chemical Engineering Hunan University Department of Electrical and computer engineering National University of Singapore Joint International Research Laboratory of information Display and Visualization School of Electronic Science and Engineering Southeast University Department of Mechanical engineering California State University Los Angeles 5151 State University Dr College of Materials science and engineering Hunan University Shenzhen Research Institute Hunan University

层状金属二硫化物（LMDs）神经形态忆阻器为解决传统冯·诺依曼架构在速度和能效上的限制,提供了一个有前景的替代方案.然而由于环境稳定性,晶体LMDs忆阻器的阻变行为和操作电压仍面临挑战,这阻碍了神经网络硬件的开发.在此,我们通过臭...

层状金属二硫化物（LMDs）神经形态忆阻器为解决传统冯·诺依曼架构在速度和能效上的限制,提供了一个有前景的替代方案.然而由于环境稳定性,晶体LMDs忆阻器的阻变行为和操作电压仍面临挑战,这阻碍了神经网络硬件的开发.在此,我们通过臭氧处理控制氧化制备了SnOx/SnS2阻变层,优化了其阻变操作特性.该忆阻器表现出低的开关电压（～1 V）、快的开关速度（～20 ns）、高的开关比（10～2）,并具备模拟突触权重可塑性的能力.通过截面透射电子显微镜和X射线光谱等手段的分析,探测到了阻变开关层中的缺陷和Ti导电丝,这有助于实现均匀开关并减少操作可变性.此外,SnOx/SnS2忆阻器在MNIST手写识别中实现了90%的准确率,并成功地实现了基于忆阻器的图像卷积,展示了SnOx/SnS2忆阻器在神经形态应用中的潜力.

关键词：

A Novel Tree-Based Genetic Algorithm for the Multicast Protocol in Two-Tiered WSNs

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2020年第5期29卷 852-858页

作者： ZHANG Qiongbing XIE Chengwang JIANG Lei School of computer science and engineering Hunan University of Science and Technology School of computer and information engineering Nanning Normal University

Genetic algorithms(GAs) serve as a class of powerful tools to search for an effective multicast routing scheme among multiple cluster header nodes,which strongly affects the lifetime of two-tiered Wireless sensor networks(WSNs). This paper proposes a novel Genetic algorithm(GA) with a new crossover mechanism called Leaf crossover for the multicast routing among upper tier nodes in two-tiered WSNs, which outperforms the existing popular tree-based GAs by not requiring the global network link information, encoding/decoding or repair operations. Our simulation study indicates that the proposed algorithm could prolong the lifetime of multicast service, increase the packet delivery ratio as well as converge fast by comparison with existing GAs.

关键词： Wireless sensor networks (WSNs) Multicast Genetic algorithm (GA) Leaf crossover

Free vibration and transient response of double curved beams connected by intermediate straight beams

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2025年第1期46卷 37-62页

作者： R.A.JAFARI-TALOOKOLAEI H.GHANDVAR E.JUMAEV S.KHATIR T.CUONG-LE School of Mechanical engineering Babol Noshirvani University of Technology Department of Mechanical engineering Faculty of Engineering New Uzbekistan University University of Business and science Center for engineering Application and Technology Solutions Ho Chi Minh City Open University

This paper investigates the free vibration and transient response of interconnected structures including double curved beams and intermediate straight beams,which are all constructed from functionally graded porous(FGP) materials. The strain potential and kinetic energies of each beam along with the work done by the external force are calculated. Additionally, a higher-order beam element is introduced to derive stiffness and mass matrices, along with the force vector. The curved and straight beams are discretized, and their assembled stiffness, mass matrices, and force vectors, are *** conditions at the joints are used to derive the total matrices of the entire structure. Subsequently, the natural frequencies and transient response of the system are determined. The accuracy of the mathematical model and the self-developed computer program is validated through the comparison of the obtained results with those of the existing literature and commercial software ANSYS, demonstrating excellent ***, a comprehensive study is conducted to investigate the effects of various parameters on the free vibration and transient response of the considered structure.

关键词：

5DGWO-GAN:A Novel Five-Dimensional Gray Wolf Optimizer for Generative Adversarial Network-Enabled Intrusion Detection in IoT Systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2025年第1期82卷 881-911页

作者： Sarvenaz Sadat Khatami Mehrdad Shoeibi Anita Ershadi Oskouei Diego Martín Maral Keramat Dashliboroun Department of Data science engineering University of HoustonHoustonTX 77204USA The WPI Business School Worcester Polytechnic InstituteWorcesterMA 01609USA School of Systems and Enterprises Stevens Institute of TechnologyHobokenNJ 07030USA Department of computer science Escuela de Ingeniería Informática de SegoviaUniversidad de ValladolidSegovia40005Spain Ernest G.Welch School of Art&Design Georgia State UniversityAtlantaGA 30303USA

The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control *** the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are *** detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate *** paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT ***,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss *** address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN *** 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local *** proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model *** generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded *** evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and *** conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false *** 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence *** proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and

关键词： Internet of things intrusion detection generative adversarial networks five-dimensional binary gray wolf optimizer deep learning

A Deep Deterministic Policy Gradient-Based Method for Enforcing Service Fault-Tolerance in MEC

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第4期33卷 899-909页

作者： Tingyan LONG Peng CHEN Yunni XIA Yong MA Xiaoning SUN Jiale ZHAO Yifei LYU College of computer science Chongqing University School of computer and Software engineering Xihua University School of computer and information engineering Jiangxi Normal University School of computer and information science Chongqing Normal University

Mobile edge computing(MEC) provides edge services to users in a distributed and on-demand *** to the heterogeneity of edge applications, deploying latency and resource-intensive applications on resourceconstrained devices is a key challenge for service providers. This is especially true when underlying edge infrastructures are fault and error-prone. In this paper, we propose a fault tolerance approach named DFGP, for enforcing mobile service fault-tolerance in MEC. It synthesizes a generative optimization network(GON) model for predicting resource failure and a deep deterministic policy gradient(DDPG) model for yielding preemptive migration *** show through extensive simulation experiments that DFGP is more effective in fault detection and guaranteeing quality of service, in terms of fault detection accuracy, migration efficiency, task migration time, task scheduling time,and energy consumption than other existing methods.

关键词： Fault tolerance Multi-access edge computing Processor scheduling Fault detection Image edge detection Fault tolerant systems Quality of service

An Adaptive Task Creation Pruning Strategy for Optimizing Irregular Applications

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第3期24卷 535-541页

作者： CAO Qian LI Huiyong ZUO Min DENG Yun YU Yuan School of computer and information engineering Beijing Technology and Business University School of Electronics engineering and computer science Peking University College of information science and engineering Guilin University of Technology

The Open MP task directive makes it possible to efficiently parallelize irregular applications, with task granularity as one of the most critical issues. To implement Open MP specification on multi-core architecture,a model is presented specializing in the execution of irregular applications. The model captures computation and communication within a node with host cores and accelerator cores. Based on this model, we propose an adaptive task creation pruning strategy including two stages to adjust dynamically task granularity. The first stage is task creation in breadth-first manner until getting to a threshold, which utilizes potential parallelism of multi-core processor. The second stage is starvation-triggered task regeneration once some worker thread becomes starved, which ensures work-stealing and thus achieves load balance. The evaluation is conducted with a series of typical irregular benchmarks, and the results indicate that our approach offers more effective performance in parallel execution of irregular benchmarks.

关键词： Task granularity Adaptive Irregular applications Multi-core