检索结果-南通市图书馆

Adaptive Optimal Discrete-Time Output-Feedback Using an Internal Model Principle and Adaptive Dynamic Programming

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 131-140页

作者： Zhongyang Wang Youqing Wang Zdzisław Kowalczuk the College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China IEEE the department of Robotics and Decision Systems Faculty of ElectronicsTelecommunications and InformaticsGdańsk University of TechnologyGdansk 80-233Poland

In order to address the output feedback issue for linear discrete-time systems, this work suggests a brand-new adaptive dynamic programming(ADP) technique based on the internal model principle(IMP). The proposed method, termed as IMP-ADP, does not require complete state feedback-merely the measurement of input and output data. More specifically, based on the IMP, the output control problem can first be converted into a stabilization problem. We then design an observer to reproduce the full state of the system by measuring the inputs and outputs. Moreover, this technique includes both a policy iteration algorithm and a value iteration algorithm to determine the optimal feedback gain without using a dynamic system model. It is important that with this concept one does not need to solve the regulator equation. Finally, this control method was tested on an inverter system of grid-connected LCLs to demonstrate that the proposed method provides the desired performance in terms of both tracking and disturbance rejection.

关键词： Adaptive dynamic programming(ADP) internal model principle(IMP) output feedback problem policy iteration(PI) value iteration(VI)

FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education department Information Network Engineering Research Center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Few-shot class-incremental learning Embedding augmentation Classifier adaptation Image classification

Bridging element-free Galerkin and pluri-Gaussian simulation for geological uncertainty estimation in an ensemble smoother data assimilation framework

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2024年第3期21卷 1683-1698页

作者： Bogdan Sebacher Remus Hanea department of Applied informatics Military Technical Academy “Ferdinand I” Equinor

The facies distribution of a reservoir is one of the biggest concerns for geologists, geophysicists, reservoir modelers, and reservoir engineers due to its high importance in the setting of any reliable decisionmaking/optimization of field development planning. The approach for parameterizing the facies distribution as a random variable comes naturally through using the probability fields. Since the prior probability fields of facies come either from a seismic inversion or from other sources of geologic information, they are not conditioned to the data observed from the cores extracted from the wells. This paper presents a regularized element-free Galerkin(R-EFG) method for conditioning facies probability fields to facies observation. The conditioned probability fields respect all the conditions of the probability theory(i.e. all the values are between 0 and 1, and the sum of all fields is a uniform field of 1). This property achieves by an optimization procedure under equality and inequality constraints with the gradient projection method. The conditioned probability fields are further used as the input in the adaptive pluri-Gaussian simulation(APS) methodology and coupled with the ensemble smoother with multiple data assimilation(ES-MDA) for estimation and uncertainty quantification of the facies distribution. The history-matching of the facies models shows a good estimation and uncertainty quantification of facies distribution, a good data match and prediction capabilities.

关键词： Element free Galerkin (EFG) Adaptive pluri-Gaussian simulation (APS) Facies distribution estimation Ensemble smoother with multiple data assimilation (ESMDA)

Low-Brightness Object Recognition Based on Deep Learning

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 2024年第5期79卷 1757-1773页

作者： Shu-Yin Chiang Ting-Yu Lin department of Information and telecommunications Engineering Ming Chuan UniversityTaoyuan City333Taiwan

This research focuses on addressing the challenges associated with image detection in low-light environments,particularly by applying artificial intelligence techniques to machine vision and object recognition systems.The primary goal is to tackle issues related to recognizing objects with low brightness levels.In this study,the Intel RealSense Lidar Camera L515 is used to simultaneously capture color information and 16-bit depth information images.The detection scenarios are categorized into normal brightness and low brightness situations.When the system determines a normal brightness environment,normal brightness images are recognized using deep learning methods.In low-brightness situations,three methods are proposed for recognition.The first method is the SegmentationwithDepth image(SD)methodwhich involves segmenting the depth image,creating amask from the segmented depth image,mapping the obtained mask onto the true color(RGB)image to obtain a backgroundreduced RGB image,and recognizing the segmented image.The second method is theHDVmethod(hue,depth,value)which combines RGB images converted to HSV images(hue,saturation,value)with depth images D to form HDV images for recognition.The third method is the HSD(hue,saturation,depth)method which similarly combines RGB images converted to HSV images with depth images D to form HSD images for recognition.In experimental results,in normal brightness environments,the average recognition rate obtained using image recognition methods is 91%.For low-brightness environments,using the SD method with original images for training and segmented images for recognition achieves an average recognition rate of over 82%.TheHDVmethod achieves an average recognition rate of over 70%,while the HSD method achieves an average recognition rate of over 84%.The HSD method allows for a quick and convenient low-light object recognition system.This research outcome can be applied to nighttime surveillance systems or nighttime road safety systems.

关键词： Low-brightness depth image image segmentation image recognition HDV HSD

A detailed rock density model of the Hong Kong territories

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

Geodesy and Geodynamics 2024年第1期15卷 75-81页

作者： Albertini Nsiah Ababio Robert Tenzer department of Land Surveying and Geo-informatics Hong Kong Polytechnic UniversityHong KongChina

We used the geological map and published rock density measurements to compile the digital rock density model for the Hong Kong territories.We then estimated the average density for the whole territory.According to our result,the rock density values in Hong Kong vary from 2101 to 2681 kg·m^(-3).These density values are typically smaller than the average density of 2670 kg·m^(-3),often adopted to represent the average density of the upper continental crust in physical geodesy and gravimetric geophysics applications.This finding reflects that the geological configuration in Hong Kong is mainly formed by light volcanic formations and lava flows with overlying sedimentary deposits at many locations,while the percentage of heavier metamorphic rocks is very low(less than 1%).This product will improve the accuracy of a detailed geoid model and orthometric heights.

关键词： Density model Rock types Gravimetric modeling Hong Kong

Factors Impacting Participatory Post‑Disaster Relocation and Housing Reconstruction:The Case of Tsholotsho District,Zimbabwe

在线全文

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Science 2024年第1期15卷 58-72页

作者： Nombulelo Kitsepile Ngulube Hirokazu Tatano Subhajyoti Samaddar department of Social informatics Graduate School of InformaticsKyoto UniversityKyoto 606-8507Japan Disaster Prevention Research Institute(DPRI) Kyoto UniversityKyoto 611-0011Japan

Relocation is not typically considered the best planning option for post-disaster reconstruction and rehabilitation,but it may be necessary if the site has suffered severe damage or is at imminent risk.There is a growing recognition that strong community participation is necessary in the post-disaster relocation decision-making process since relocation can have detrimental effects on a community’s livelihood,cultural system,and way of life,among others.However,the realization of this still needs to be improved.As of yet,few studies have examined a comprehensive account of meaningful community engagement in post-disaster relocation and reconstruction,particularly in developing countries.This study investigated what factors influenced local communities’ participation in post-disaster relocation and reconstruction works after the 2017Cyclone Dineo flood disaster in the Tsholotsho District of Zimbabwe.Qualitative research methods such as face-to-face interviews,observations,and focus groups were used to collect qualitative data from a purposive sample of 25 community members and 6 stakeholders.This empirical investigation showed that despite the fact that the relocation project was conceived as a community-centered project,there was no meaningful community engagement,due to the absence of a participatory framework or planning guidelines for stakeholder engagement,as well as the lack of political willingness among government officials.The study concluded that the lack of community involvement led to local communities abandoning the reconstruction sites because relocation projects failed to accommodate the cultural beliefs,place attachments,and livelihood concerns of local communities.This study suggested that it is imperative to enhance the awareness of government officials and other stakeholders about the importance of community participation for the effective implementation of post-disaster relocation works.Meaningful community participation can also provide avenues for incorporating local needs and concerns,cultura

关键词： Community rehabilitation Housing reconstruction-Participatory relocation Zimbabwe

Digital twin for Industrial Internet

在线全文

学校读者我要写书评

暂无评论

Fundamental Research 2024年第1期4卷 21-24页

作者： Yushuai Li Yan Zhang department of informatics University of Oslo Oslo 0316Norway

Industrial Internet upgrades the traditional industrial manufacturing to digitization,networking and intellectualization era,which calls for brand-new technology supports.As a promising solution,the emergence Digital Twin(DT)offers enhanced digital mapping capability with strong feasibility,security,economic and intelligence,which fits well with the concept of Industrial Internet.In this paper,we focus on establishing a new reference architecture of DT to support the development of Industrial Internet.It is composed of three interdependent layers(i.e.,physical layer,DT layer and DT networks layer)and four critical attributes(i.e.,privacy,security,awareness and real-time).We illustrate our perspectives for the functionality and relationship of the three layers,and features and feasible solutions of the four attributes.With those efforts,the proposed DT architecture can provide both smart manufacturing and networked services for Industrial Internet era.Moreover,we also illustrate the relevant and open challenges.Finally,the conclusion and future perspective are pointed out.

关键词： Digital twin Industrial Internet Industry 4.0 Made in China 2025 Networked services

Combining graph neural network with deep reinforcement learning for resource allocation in computing force networks

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

Frontiers of Information Technology & Electronic Engineering 2024年第5期25卷 701-712页

作者： Xueying HAN Mingxi XIE Ke YU Xiaohong HUANG Zongpeng DU Huijuan YAO School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China School of Artificial Intelligence Beijing University of Posts and TelecommunicationsBeijing 100876China department of Infrastructure Network Technology Research China Mobile Research InstituteBeijing 100032China

Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements,the computing force network(CFN)has become a hot research subject.The primary CFN challenge is to leverage network resources and computing resources.Although recent advances in deep reinforcement learning(DRL)have brought significant improvement in network optimization,these methods still suffer from topology changes and fail to generalize for those topologies not seen in training.This paper proposes a graph neural network(GNN)based DRL framework to accommodate network trafic and computing resources jointly and efficiently.By taking advantage of the generalization capability in GNN,the proposed method can operate over variable topologies and obtain higher performance than the other DRL methods.

关键词： Computing force network Routing optimization Deep learning Graph neural network Resource allocation

Automated evaluation of parapapillary choroidal microvasculature in crowded optic discs:a controlled,optical coherence tomography angiography study

在线全文

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2024年第1期17卷 113-118页

作者： Hatice Arda Hidayet Sener Ozge Temizyurek Hatice Kubra Sonmez Duygu Gulmez Sevim Cem Evereklioglu Fatih Horozoglu Ayse Busra Gunay Sener department of Ophthalmology Erciyes University Medical FacultyKayseri 38090Turkey department of Medical informatics and Biostatistics Erciyes University Medical FacultyKayseri 38090Turkey

AIM:To compare superficial and deep vascular properties of optic discs between crowded discs and controls using optical coherence tomography angiography(OCT-A).METHODS:Thirty patients with crowded discs,and 47 control subjects were enrolled in the study.One eye of each individual was included and OCT-A scans of optic discs were obtained in a 4.5×4.5 mm^(2) rectangular area.Radial peripapillary capillary(RPC)density,peripapillary retinal nerve fiber layer(pRNFL)thickness,cup volume,rim area,disc area,cup-to-disc(c/d)area ratio,and vertical c/d ratio were obtained automatically using device software.Automated parapapillary choroidal microvasculature(PPCMv)density was calculated using MATLAB software.When the vertical c/d ratio of the optic disc was absent or small cup,it was considered as a crowded disc.RESULTS:The mean signal strength index of OCT-A images was similar between the crowded discs and control eyes(P=0.740).There was no difference in pRNFL between the two groups(P=0.102).There were no differences in RPC density in whole image(P=0.826)and peripapillary region(P=0.923),but inside disc RPC density was higher in crowded optic discs(P=0.003).The PPCMv density in the inner-hemisuperior region was also lower in crowded discs(P=0.026).The pRNFL thickness was positively correlated with peripapillary RPC density(r=0.498,P<0.001).The inside disc RPC density was negatively correlated with c/d area ratio(r=-0.341,P=0.002).CONCLUSION:The higher inside disc RPC density and lower inner-hemisuperior PPCMv density are found in eyes with crowded optic discs.

关键词： crowded optic disc ischemic optic neuropathy optical coherence tomography angiography parapapillary choroidal microvasculature