检索结果-南通市图书馆

Journal of Rock Mechanics and Geotechnical engineering 2024年第7期16卷 2732-2748页

作者： Javad Ghorbani Arooran Sounthararajah Troyee Tanu Dutta Jayantha Kodikara ARC Smart Pavements Hub Dept.of Civil EngineeringMonash UniversityVIC3800Australia

This study introduces an advanced finite element model for the light weight deflectometer(LWD),which integrates contact mechanics with fully coupled *** simulating LWD tests on granular soils at various saturation levels,the model accurately reflects the dependence of the LWD modulus on dry density,water content,and effective *** model addresses and overcomes the limitations of previous finite element models for this specific ***,this research presents the first experimentally validated fully coupled contact impact ***,the research provides a comparative assessment of elastoplastic and nonlinear elastic models and contrasts an enriched node-tosegment method(developed in this study)with the more precise mortar technique for contact *** comparisons reveal unique advantages and challenges for each ***,the study underscores the importance of careful application of the LWD modulus,emphasising the need for sophisticated tools to interpret soil behaviour accurately.

关键词： Granular soils Plasticity Finite element analysis Contact mechanics Modulus Degree of saturation

State estimation for delayed switched positive systems: delayed radius approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第8期67卷 190-205页

作者： Weizhong CHEN Zhongyang FEI Xudong ZHAO Zheng-Guang WU School of Electronics and information Xi'an Polytechnic University Research Institute of Intelligent Control and systems Harbin Institute of Technology Key Laboratory of Intelligent Control and Optimization for industrial Equipment of Ministry of Education Dalian University of Technology School of Control Science and engineering Dalian University of Technology State Key Laboratory of industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University

In this paper, an interval estimation scheme is developed for delayed switched positive systems（DSPS） with mode-dependent average dwell time switching. A lossless zonotopic estimation approach is proposed for the delayed intersection zonotope with the positive generator matrix. First, considering the existence of asynchronism between the system mode and the correction matrix mode, the mismatched intersection zonotope is constructed for DSPS to verify the consistency between the system model and ***, by utilizing the introduced radius definitions, the ?∞performance is addressed to optimize the size of delayed intersection zonotopes. Subsequently, we present a joint-design approach of switching signals and the mode-dependent correction matrix by constructing positive generator matrix-based delayed radius functions. Furthermore, guaranteed nonnegative state bounds are derived for the considered DSPS based on the proposed lossless zonotopic estimation criteria. Finally, detailed simulations are conducted to validate the feasibility and superiority of the developed methods.

关键词： delayed switched positive systems interval estimation asynchronous correction matrix zonotopes mode-dependent average dwell time

Leveraging the Empirical Wavelet Transform in Combination with Convolutional LSTM Neural Networks to Enhance the Accuracy of Polar Motion Prediction

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第9期24卷 214-224页

作者： Xu-Qiao Wang Lan Du Zhong-Kai Zhang Ze-Jun Liu Hao Xiang College of Geospatial information Information Engineering UniversityZhengzhou 450001China Henan industrial Technology Academy of Spatio-Temporal Big Data Zhengzhou 450046China

High-precision polar motion prediction is of great significance for deep space exploration and satellite *** motion is affected by a variety of excitation factors,and nonlinear prediction methods are more suitable for polar motion *** order to explore the effect of deep learning in polar motion *** paper proposes a combined model based on empirical wavelet transform(EWT),Convolutional Neural Networks(CNN)and Long Short Term Memory(LSTM).By training and forecasting EOP 20C04 data,the effectiveness of the algorithm is verified,and the performance of two forecasting strategies in deep learning for polar motion prediction is *** results indicate that recursive multi-step prediction performs better than direct multi-step prediction for short-term forecasts within 15 days,while direct multi-step prediction is more suitable for medium and long-term *** the 365 days forecast,the mean absolute error of EWT-CNN-LSTM in the X direction and Y direction is 18.25 mas and 15.78 mas,respectively,which is 23.5% and 16.2% higher than the accuracy of Bulletin *** results show that the algorithm has a good effect in medium and long term polar motion prediction.

关键词： data analysis methods:miscellaneous astrometry reference systems Earth

维普期刊数据库

Symmetric silicon microring resonator optical crossbar array for accelerated inference and training in deep learning

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2024年第8期12卷 1681-1688页

作者： RUI TANG SHUHEI OHNO KEN TANIZAWA KAZUHIRO IKEDA MAKOTO OKANO KASIDIT TOPRASERTPONG SHINICHI TAKAGI MITSURU TAKENAKA Department of Electrical engineering and information systems The University of TokyoTokyo 113-8656Japan Quantum ICT Research Institute Tamagawa UniversityTokyo 194-8610Japan National Institute of Advanced industrial Science and Technology Ibaraki 305-8568Japan

Photonic integrated circuits are emerging as a promising platform for accelerating matrix multiplications in deep learning,leveraging the inherent parallel nature of *** various schemes have been proposed and demonstrated to realize such photonic matrix accelerators,the in situ training of artificial neural networks using photonic accelerators remains challenging due to the difficulty of direct on-chip backpropagation on a photonic *** this work,we propose a silicon microring resonator(MRR)optical crossbar array with a symmetric structure that allows for simple on-chip backpropagation,potentially enabling the acceleration of both the inference and training phases of deep *** demonstrate a 4×4 circuit on a Si-on-insulator platform and use it to perform inference tasks of a simple neural network for classifying iris flowers,achieving a classification accuracy of 93.3%.Subsequently,we train the neural network using simulated on-chip backpropagation and achieve an accuracy of 91.1%in the same inference task after ***,we simulate a convolutional neural network for handwritten digit recognition,using a 9×9 MRR crossbar array to perform the convolution *** work contributes to the realization of compact and energy-efficient photonic accelerators for deep learning.

关键词： resonator neural matrix

维普期刊数据库

Gradient sparsification for efficient wireless federated learning with differential privacy

在线全文

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第4期67卷 272-288页

作者： Kang WEI Jun LI Chuan MA Ming DING Feng SHU Haitao ZHAO Wen CHEN Hongbo ZHU School of Electronic and Optical engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and information Integration(Southeast University) Ministry of Education Data61 Commonwealth Scientific and Industrial Research Organisation School of information and Communication engineering Hainan University School of Communications and information engineering Nanjing University of Posts and Telecommunications School of Electronic information and Electrical engineering Shanghai Jiao Tong University

Federated learning(FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy(DP)protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client’s local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client’s DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.

关键词： federated learning differential privacy gradient sparsification Lyapunov drift convergence analysis

Detection of Oscillations in Process Control Loops From Visual Image Space Using Deep Convolutional Networks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 982-995页

作者： Tao Wang Qiming Chen Xun Lang Lei Xie Peng Li Hongye Su the Department of Electronic engineering the School of InformationYunnan UniversityKunming 650091China DAMO Academy Alibaba GroupHangzhou 311100China the State Key Laboratory of industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou 310027China

Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant *** numerous automatic detection techniques have been proposed,most of them can only address part of the practical *** oscillation is heuristically defined as a visually apparent periodic ***,manual visual inspection is labor-intensive and prone to missed *** neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction *** this work,an exploration of the typical CNN models for visual oscillation detection is ***,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation *** feasibility and validity of this framework are verified utilizing extensive numerical and industrial *** with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and *** addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.

关键词： Convolutional neural networks(CNNs) deep learning image processing oscillation detection process industries

维普期刊数据库

DEM investigation of strength and critical state behaviours of granular materials under true triaxial loadings

在线全文

学校读者我要写书评

暂无评论

Particuology 2024年第2期85卷 198-212页

作者： Minyi Zhu Guobin Gong Jun Xia Stephen Wilkinson Department of Civil engineering Xi'an Jiaotong-Liverpool UniversityChina Department of Civil engineering and industrial Design University of LiverpoolLiverpoolUK Faculty of engineering and information Sciences University of Wollongong in DubaiUnited Arab Emirates

This paper investigates the strength and critical state(CS)behaviours of granular materials via DEM simulations of true triaxial drained tests under three different loading modes including constant b(in-termediate stress ratio)tests with constantσ'1(major principal stress),constant p(mean pressure)and constantσ'3(minor principal stress)*** this end,a series of samples are generated with the same particle size distribution,and with the confining stresses ranging from 100 kPa to 900 *** CS is achieved for all *** the macroscopic behaviours and the microscopic behaviours are examined and compared considering different loading modes,confining stresses and intermediate stress ratios(b).The critical state lines(CSLs)are found to be unique and independent of the loading modes,but dependent on the b *** CSLs with b=0 and b=1 form the two boundaries of CSLs respectively beyond which CSLs under all other b tests cannot go *** different strength criteria are examined and compared in terms of both peak and CS *** Mohr-Coulomb strength criterion is found to be only suitable for axisymmetric loading *** Lade-Duncan criterion is only suitable for describing peak strengths,which is dependent on the loading modes and confining *** Satake criterion and Matsuoka-Nakai criterion are the more appropriate strength criteria for describing CS failures,indicating that the CS values of both the Satake parameter and the Matsuoka-Nakai parameter describe an inherent property that characterizes the CS failure for a given type of *** CS mechanical coordination number is fitted by a curved line for a given b value,which is unique regardless of the loading *** peak and CS values of both major and minor principal fabric tensors decrease with increasing b values,while they increase with increasing b values for the intermediate principal fabric tensor.

关键词： Discrete element method Intermediate stress ratio Dilation Critical state Failure criterion

Enhancing Data Forwarding Efficiency in SIoT with Multidimensional Social Relations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 1095-1113页

作者： Fang Xu Songhao Jiang Yi Ma Manzoor Ahmed Zenggang Xiong Yuanlin Lyu School of Computer and information Science Hubei Engineering UniversityXiaogan432000China School of Computer Science and information engineering Hubei UniversityWuhan430062China Artificial Intelligence industrial Technology Research Institute Hubei Engineering UniversityXiaogan432000China

Effective data communication is a crucial aspect of the Social Internet of Things(SIoT)and continues to be a significant research *** paper proposes a data forwarding algorithm based on Multidimensional Social Relations(MSRR)in SIoT to solve this *** proposed algorithm separates message forwarding into intra-and cross-community forwarding by analyzing interest traits and social connections among *** new metrics are defined:the intensity of node social relationships,node activity,and community *** the community,messages are sent by determining which node is most similar to the sender by weighing the strength of social connections and node *** a node performs cross-community forwarding,the message is forwarded to the most reasonable relay community by measuring the node activity and the connection between *** proposed algorithm was compared to three existing routing algorithms in simulation *** indicate that the proposed algorithmsubstantially improves message delivery efficiency while lessening network overhead and enhancing connectivity and coordination in the SIoT context.

关键词： SIoT data forwarding social attributes social relations community

Research on Driver’s Fatigue Detection Based on information Fusion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1039-1061页

作者： Meiyan Zhang Boqi Zhao Jipu Li Qisong Wang Dan Liu Jinwei Sun Jingxiao Liao Harbin Institute of Technology School of Instrument Science and EngineeringHarbin150036China Department of industrial and systems engineering The Hong Kong Polytechnic UniversityHong Kong100872China

Driving fatigue is a physiological phenomenon that often occurs during *** the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly reduced,which can easily cause traffic ***,studying driver fatigue detectionmethods is significant in ensuring safe ***,the fatigue state of actual drivers is easily interfered with by the external environment(glasses and light),which leads to many problems,such as weak reliability of fatigue driving ***,fatigue is a slow process,first manifested in physiological signals and then reflected in human face *** improve the accuracy and stability of fatigue detection,this paper proposed a driver fatigue detection method based on image information and physiological information,designed a fatigue driving detection device,built a simulation driving experiment platform,and collected facial as well as physiological information of drivers during ***,the effectiveness of the fatigue detection method was *** movement feature parameters and physiological signal features of drivers’fatigue levels were *** driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted *** rates of the image,electroencephalogram(EEG),and blood oxygen signals were 86%,82%,and 71%,*** fusion theory was presented to facilitate the fatigue detection effect;the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%.It can be seen that the fatigue driving detectionmethod based onmulti-source feature fusion effectively detected driver fatigue state,and the accuracy rate was higher than that of a single information *** summary,fatigue drivingmonitoring has broad development prospects and can be used in traffic accident prevention and wearable dr

关键词： Driving fatigue information fusion EEG blood oxygen

Saliency-guided meta-hallucinator for few-shot learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第10期67卷 189-210页

作者： Hongguang ZHANG Chun LIU Jiandong WANG Linru MA Piotr KONIUSZ Philip H.S.TORR Lin YANG systems engineering Institute Academy of Military Sciences Data61 Commonwealth Scientific and Industrial Research Organisation Australian National University Oxford University

Learning novel object concepts from limited samples remains a considerable challenge in deep learning. The main directions for improving the few-shot learning models include(i) designing a stronger backbone,(ii) designing a powerful(dynamic) meta-classifier, and(iii) using a larger pre-training set obtained by generating or hallucinating additional samples from the small scale dataset. In this paper, we focus on item(iii) and present a novel meta-hallucination strategy. Presently, most image generators are based on a generative network(i.e., GAN) that generates new samples from the captured distribution of images. However, such networks require numerous annotated samples for training. In contrast, we propose a novel saliency-based end-to-end meta-hallucinator, where a saliency detector produces foregrounds and backgrounds of support images. Such images are fed into a two-stream network to hallucinate feature samples directly in the feature space by mixing foreground and background feature samples. Then, we propose several novel mixing strategies that improve the quality and diversity of hallucinated feature ***, as not all saliency maps are meaningful or high quality, we further introduce a meta-hallucination controller that decides which foreground feature samples should participate in mixing with backgrounds. To our knowledge, we are the first to leverage saliency detection for few-shot learning. Our proposed network achieves state-of-the-art results on publicly available few-shot image classification and anomaly detection benchmarks, and outperforms competing sample mixing strategies such as the so-called Manifold Mixup.

关键词： few-shot learning saliency detection object recognition anomaly detection computer vision