检索结果-内蒙古大学图书馆

Adaptive Graph Embedding With Consistency and Specificity for Domain Adaptation

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2094-2107页

作者： Shaohua Teng Zefeng Zheng Naiqi Wu Luyao Teng Wei Zhang School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems Macao University of Science and TechnologyMacao 999078China School of Information Engineering Guangzhou Panyu PolytechicGuangzhou 511483China Faculty of Information Technology Monash University20 Exhibition Walk ClaytonVIC 3800Australia IEEE

Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples *** approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.

关键词： Adaptive adjustment consistency and specificity domain adaptation graph embedding geometrical and semantic metrics

来源：评论

学校读者我要写书评

暂无评论

Detection and Identification of Tomato Disease Based on Deep Learning and Machine Learning algorithms 1

Detection and Identification of Tomato Disease Based on Deep...

引用

1st IEEE Afro-Mediterranean Conference on Artificial Intelligence, AMCAI 2023

作者： Boukhris, Abdelouafi Antari, Jilali Asri, Hiba Sadiq, Abderrahmane Ibn Zohr University Laboratory of Computer Systems Engineering Mathematics and Applications Polydisciplinary Faculty of Taroudant Taroudant Morocco LISI Laboratory Faculty of Sciences Semlalia Department of Computer Sciences Marrakech Morocco

ISBN: (纸本)9798350394689

Plant diseases negatively affect crop production;the quality and the quantity of crop production are being interrupted. Identifying diseases manually is a hard task and time consuming, also the majority of farmers don't have the necessary knowledge to do this operation. So, we need agriculture engineer which are rare. To address these issues, we need an accurate and automated detection system for crop disease. A new technique based on deep learning to detect crop disease is required. In this paper, we propose a new technique called ALS-NN (Autoencoder Latent Space-Neural network) which combines two models Autoencoder and Neural Network. The Autoencoder compress data into Latent Space representation, and the Neural Network is used for classification based on compressed data. The dataset used in this paper is PlantVillage with 4 types of Tomato diseases. Our system achieved 91% accuracy. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Depth First:Optimal Path Discovery Between Designated Nodes in Random Ring-Based Graphs

引用

China Communications 2024年第9期21卷 225-241页

作者： Li Qi Xu Jiasheng Zhang Haonan Kang Huquan Fu Luoyi Long Fei Wang Xinbing Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Media Convergence Production Technology and Systems Xinhua News AgencyBeijing 100077China

This paper focuses on optimally determining the existence of connected paths between some given nodes in random ring-based *** as a fundamental underlying structure in network modeling,ring topology appears as commonplace in many realistic *** this,we consider graphs composed of rings,with some possible connected paths between *** prior knowledge of the exact node permutations on rings,the existence of each edge can be unraveled through edge testing at a unit cost in one *** problem examined is that of determining whether the given nodes are connected by a path or separated by a cut,with the minimum expected costs *** the problem into different cases based on different topologies of the ring-based networks,we propose the corresponding policies that aim to quickly seek the paths between nodes.A common feature shared by all those policies is that we stick to going in the same direction during edge searching,with edge testing in each step only involving the test between the source and the node that has been tested *** simple searching rule,interestingly,can be interpreted as a delightful property stemming from the neat structure of ring-based networks,which makes the searching process not rely on any sophisticated *** prove the optimality of the proposed policies by calculating the expected cost incurred and making a comparison with the other class of *** effectiveness of the proposed policies is also verified through extensive simulations,from which we even disclose three extra intriguing findings:i)in a onering network,the cost will grow drastically with the number of designated nodes when the number is small and will grow slightly when that number is large;ii)in ring-based network,Depth First is optimal in detecting the connectivity between designated nodes;iii)the problem of multi-ring networks shares large similarity with that of two-ring networks,and a larger number of ties between ri

关键词： connectivity analysis cost minimization path discover ring-based graph

来源：评论

学校读者我要写书评

暂无评论

A morphological word embedding for Arabic language 6

A morphological word embedding for Arabic language

引用

6th International Conference on AI in Computational Linguistics, ACLing 2024

作者： Masbah, Abdelouahab Ababou, Nabil Mazroui, Azzedine Computer Science Research Laboratory Faculty of Sciences Mohammed First University Oujda Morocco Systems Engineering Laboratory Faculty of Science and Technology Sultan Moulay Slimane University Beni Mellal Morocco

Word embedding is a technique for representing words as dense real vectors and is crucial for most natural language processing tasks. Common approaches include non-contextual embeddings such as Word2vec and contextual embeddings like BERT, both of which operate on the principle that words appearing in similar contexts have close vector representations. Despite their effectiveness, these methods often fail to capture some morphological information useful in many natural language processing applications. In this study, we propose an original word embedding of Arabic words based on the morphological characteristics of the words. Tests show that integrating this morphology-based word embedding into a topic detection model outperforms models using Word2vec or AraBERT embeddings. © 2024 Elsevier B.V.. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A survey on hyperspectral image restoration: from the view of low-rank tensor approximation

引用

Science China(Information Sciences) 2023年第4期66卷 33-63页

作者： Na LIU Wei LI Yinjian WANG Ran TAO Qian DU Jocelyn CHANUSSOT School of Information and Electronics and Beijing Key Laboratory of Fractional Signals and Systems Beijing Institute of Technology Department of Electrical and Computer Engineering Mississippi State University GIPSA-Lab University of Grenoble Alpes Aerospace Information Research Institute Chinese Academy of Sciences

The ability to capture fine spectral discriminative information enables hyperspectral images(HSIs) to observe, detect and identify objects with subtle spectral discrepancy. However, the captured HSIs may not represent the true distribution of ground objects and the received reflectance at imaging instruments may be degraded, owing to environmental disturbances, atmospheric effects, and sensors' hardware limitations. These degradations include but are not limited to complex noise, heavy stripes, deadlines,cloud/shadow occlusion, blurring and spatial-resolution degradation, etc. These degradations dramatically reduce the quality and usefulness of HSIs. Low-rank tensor approximation(LRTA) is such an emerging technique, having gained much attention in the HSI restoration community, with an ever-growing theoretical foundation and pivotal technological innovation. Compared to low-rank matrix approximation(LRMA),LRTA characterizes more complex intrinsic structures of high-order data and owns more efficient learning abilities, being established to address convex and non-convex inverse optimization problems induced by HSI restoration. This survey mainly attempts to present a sophisticated, cutting-edge, and comprehensive technical survey of LRTA toward HSI restoration, specifically focusing on the following six topics: denoising, fusion,destriping, inpainting, deblurring, and super-resolution. For each topic, state-of-the-art restoration methods are introduced, with quantitative and visual performance assessments. Open issues and challenges are also presented, including model formulation, algorithm design, prior exploration, and application concerning the interpretation requirements.

关键词： hyperspectral image image restoration low-rank tensor approximation multisource fusion remote sensing

来源：评论

学校读者我要写书评

暂无评论

Modeling the Efficiency of an Edge Coupler with a Si3N4-based Taper 25

Modeling the Efficiency of an Edge Coupler with a Si3N4-base...

引用

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Barbin, Evgenij S. Nesterenko, Tamara G. Koleda, Aleksej N. Myrzakhmetov, Ayan Kulinich, Ivan V. Mokhovikov, Denis M. Laboratory of microsystems engineering Tomsk State University of Control Systems and Radioelectronics Laboratory of Radiophotonics V.E. Zuev Institute of Atmospheric Optics of SB RAS Tomsk Russia Laboratory of microsystems engineering Tomsk State University of Control Systems and Radioelectronics Tomsk Russia Laboratory of Radiophotonics Tomsk State University of Control Systems and Radioelectronics Tomsk Russia Laboratory of Photonic Integrated Circuits Tomsk State University of Control Systems and Radioelectronics Tomsk Russia Laboratory of Radiophotonics Tomsk State University of Control Systems and Radioelectronics Laboratory of Intelligent Computer Systems V.E. Zuev Institute of Atmospheric Optics of SB RAS Tomsk Russia

ISBN: (纸本)9798350389234

The article studies the efficiency of optical radiation input/output between a photonic integrated circuit (PIC) and an edge-coupled tapered silicon nitride waveguide with dimensions 350 nm x 850 nm at a wavelength of 1550 nm. The work determines the losses by radiation for transverse electric and transverse magnetic modes at different taper width and input mode diameter for direct (edge width more than 850 nm) and inverted tapers (edge width less than 850 nm). The results show that the admissible width of the inverted taper edge lies within 150–300 nm with losses by input/output of up to 2 dB and low sensitivity to optical polarization. For the direct taper, the highest input efficiency (losses amounted to 3-6 dB) belongs to the optical fibers with a beam waist diameter of 2–3 μm and taper edge width of 2–3 μm. For both types of edge couplers, the effect of the waist diameter of lensed fiber is more important: the spread should be within 150 nm. © 2024 IEEE.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

A model to measure the spread power of rumors

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13787-13811页

作者： Jahanbakhsh-Nagadeh, Zoleikha Feizi-Derakhshi, Mohammad-Reza Ramezani, Majid Akan, Taymaz Asgari-Chenaghlu, Meysam Nikzad-Khasmakhi, Narjes Feizi-Derakhshi, Ali-Reza Ranjbar-Khadivi, Mehrdad Zafarani-Moattar, Elnaz Balafar, Mohammad-Ali Computerized Intelligence Systems Laboratory Department of Computer Engineering University of Tabriz Tabriz Iran Department of Computer Engineering Naghadeh Branch Islamic Azad University Naghadeh Iran Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Department of Software Engineering Istanbul Topkapi University Istanbul Turkey Clinical Informatics Louisiana State University Health Sciences Center Shreveport Shreveport United States Department of Computer Engineering Shabestar Branch Islamic Azad University Shabestar Iran Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Computer Engineering University of Tabriz Tabriz Iran

With technologies that have democratized the production and reproduction of information, a significant portion of daily interacted posts in social media has been infected by rumors. Despite the extensive research on rumor detection and verification, so far, the problem of calculating the spread power of rumors has not been considered. To address this research gap, the present study seeks a model to calculate the Spread Power of Rumor (SPR) as the function of content-based features in two categories: False Rumor (FR) and True Rumor (TR). For this purpose, the theory of Allport and Postman will be adopted, which it claims that importance and ambiguity are the key variables in rumor-mongering and the power of rumor. Totally 42 content features in two categories "importance" (28 features) and "ambiguity" (14 features) are introduced to compute SPR. The proposed model is evaluated on two datasets, Twitter and Telegram. The results showed that (i) the spread power of False Rumor documents is rarely more than True Rumors. (ii) there is a significant difference between the SPR means of two groups False Rumor and True Rumor. (iii) SPR as a criterion can have a positive impact on distinguishing False Rumors and True Rumors. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Cell proliferation

来源：评论

学校读者我要写书评

暂无评论

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

引用

Control Theory and Technology 2024年第2期22卷 149-162页

作者： Yue Ju Biqiang Mu Tianshi Chen School of Data Science and Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhenShenzhen518172GuangdongChina Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technology10044StockholmSweden Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and System ScienceChinese Academy of SciencesBeijing100190China

Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

关键词： Regularized system identification Hyper-parameter estimator Empirical Bayes Convergence of covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Assessment of Operational and Harsh Environmental Stress Factors for Solar Inverters Using Field Measurements

Data-Driven Assessment of Operational and Harsh Environmenta...

引用

2024 IEEE Power and Energy Society General Meeting, PESGM 2024

作者： Luo, Yi Liu, Liming Yuan, Yuxuan Wang, Zhaoyu Qiu, Feng Zhao, Shijia Yildirim, Murat Iowa State University Electrical and Computer Engineering AmesIA United States Energy Systems Division Argonne National Laboratory LemontIL United States Wayne State University Industrial and Systems Engineering DetroitMI United States

The operation of inverters in distributed photovoltaic (PV) systems within distribution systems is critical for ensuring the reliability and durability of the PV system, particularly when challenged by diverse operational and environmental stress conditions. This study delves into analyzing the inverter stress factors to assess the impact of under-sizing and varying environmental stresses on the reliability and service life of PV inverters. A new operational stress metric, equivalent under-sizing rate (EUR), is proposed to quantify the actual inverter stress from the under-sizing problem. Along with the designed weather and extreme event metrics, the proposed EUR is evaluated in a real-world PV inverter dataset. To handle the censored working time variable, the Cox proportional hazards model is adopted to conduct the data-driven stress factor analysis. The regression results reveal aside from the high temperature and large temperature variance, the inverter under-sizing problem is also a significant factor that could influence the lifetime of inverters. Meanwhile, further applications and potential future directions for the proposed work are explored. © 2024 IEEE.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

ETAG: An Energy-Neutral Ear Tag for Real-Time Body Temperature Monitoring of Dairy Cattle 23

ETAG: An Energy-Neutral Ear Tag for Real-Time Body Temperatu...

引用

29th Annual International Conference on Mobile Computing and Networking, MobiCom 2023

作者： Vu, Hien Chung, Hanwook Choi, Christopher Kim, Younghyun Department of Electrical and Computer Engineering College of Engineering Wisconsin Embedded Systems and Computing Laboratory University of Wisconsin-Madison MadisonWI60032179 United States

ISBN: (纸本)9781450399906

Heat stress, caused by a warming climate and the increasingly high milk-producing dairy cattle, is one of the major threats to the well-being of dairy cattle as well as the economic, environmental, and social sustainability of dairy farming around the world. Timely identification of cows under heat stress is crucial to improving animal welfare, preventing milk production losses, and preserving water and energy for *** paper presents a smart ear tag, named eTag, and an associated system that can read a passive microchip temperature sensor subcutaneously injected into the animal with minimal discomfort. It features a lightweight design using a single coil shared for microchip scanning and wireless charging. eTag is autonomously recharged by a wireless charger over the head during daily milking sessions, enabling perpetual operation without battery replacement after deployment. The real-world performance of the proposed system was examined intensively in a three-week deployment on seven lactating Holstein cows. We demonstrate that eTag can reliably collect accurate body temperature in real time while maintaining a positive energy flow. The deployment of eTag will enable the timely detection of heat stress and facilitate precision control of barn cooling systems. © 2023 ACM.

关键词： Energy harvesting

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：