检索结果-内蒙古大学图书馆

Complex Drivers of Riparian Soil Oxygen Variability Revealed Using Self-Organizing Maps

WATER RESOURCES RESEARCH 2023年第6期59卷

作者： Lancellotti, Brittany V. Underwood, Kristen L. Perdrial, Julia N. Schroth, Andrew W. Roy, Eric D. Adair, Carol E. Univ Vermont Rubenstein Sch Environm & Nat Resources Burlington VT 05405 USA Univ Virgin Isl Virgin Isl EPSCoR Kingshill VI USA Univ Vermont Civil & Environm Engn Burlington VT USA Univ Vermont Dept Geol Burlington VT USA

Oxygen (O-2) regulates soil reduction-oxidation processes and therefore modulates biogeochemical cycles. The difficulties associated with accurately characterizing soil O-2 variability have prompted the use of soil moisture as a proxy for O-2, as O-2 diffusion into soil water is much slower than in soil air. The use of soil moisture alone as a proxy measurement for O-2 could result in inaccurate O-2 estimations. For example, O-2 may remain high during cool months when soil respiration rates are low. We analyzed high-frequency sensor data (e.g., soil moisture, CO2, gas-phase soil pore O-2) with a machine learning technique, the Self-Organizing Map, to pinpoint suites of soil conditions associated with contrasting O-2 regimes. At two riparian sites in northern Vermont, we found that O-2 levels varied seasonally, and with soil moisture. For example, 47% of low O-2 levels were associated with wet and cool soil conditions, whereas 32% were associated with dry and warm conditions. Contrastingly, the majority (62%) of high O-2 conditions occurred under dry and warm conditions. High soil moisture levels did not always lead to low O-2, as 38% of high O-2 values occurred under wet and cool conditions. Our results highlight challenges with predicting soil O-2 solely based on water content, as variable combinations of soil and hydrologic conditions can complicate the relationship between water content and O-2. This indicates that process-based ecosystem and denitrification models that rely solely on soil moisture to estimate O-2 may need to incorporate other site and climate-specific drivers to accurately predict soil O-2.

关键词： self-organizing map clustering algorithm riparian zone soil oxygen soil moisture high frequency data

来源：评论

学校读者我要写书评

暂无评论

An Improved Neighborhood-Based Recommendation algorithm Optimization with clustering Analysis and Latent Factor Model 38

An Improved Neighborhood-Based Recommendation Algorithm Opti...

引用

38th Chinese Control Conference (CCC)

作者： Yao, Zhenyu Wang, Jinkuan Han, Yinghua Northeastern Univ Coll Informat Sci & Engn Shenyang 110004 Peoples R China Northeastern Univ Qinhuangdao Sch Comp & Commun Engn Qinhuangdao 066004 Hebei Peoples R China

ISBN: (纸本)9789881563972

With the development of Internet, information overload about products is pervasive. It is important for commercial platforms to predict users' preferences and recommend information. Neighborhood-based recommendation algorithm is one of the most popular methods, which are used to predict the rating of items that have not yet been rated. However, neighborhood-based algorithm suffers from data sparsity in practice, causing low accuracy. A recommendation algorithm is proposed in this paper, in which auxiliary information of users and items are utilized. Specifically, clustering method is introduced to divide users into categories, which reduces the time complexity of the algorithm. and latent factor model approach is applied to predict user-item matrix, which improves the accuracy of neighborhood-based algorithm. Experiments on real-world dataset demonstrate that the proposed KC-LFMCF approach is superior to the conventional neighborhood-based algorithm in terms of recommendation accuracy and time complexity.

关键词： KC-LFMCF Rating Predict clustering algorithm Latent Factor Model

来源：评论

学校读者我要写书评

暂无评论

A Defects Localization algorithm Based on the Lamb Wave of Plate Structure

引用

JOURNAL OF NONDESTRUCTIVE EVALUATION, DIAGNOSTICS AND PROGNOSTICS OF ENGINEERING SYSTEMS 2021年第2期4卷 021001页

作者： Deng, Fei Chen, Honglei Shanghai Inst Technol Sch Elect & Elect Engn Shanghai 201418 Peoples R China Beijing Univ Technol Coll Mech Engn & Appl Elect Technol Beijing 100124 Peoples R China

Defect imaging algorithms play an important role in Lamb waves based researches of nondestructive testing (NDT) and structural health monitoring (SHM). In classical algorithms, the location or distribution of defects is visualized through mapping the amplitude or phase information of signals gotten by multiple inspection pairs from the time domain to every discrete spatial grid of plates. It is time-consuming in the detection of plates with large size and many transducers. Transforming the defect imaging problem into a scattering source search problem, an intelligent defect localization algorithm was proposed for NDT and SHM with the Lamb waves and sparse array. In the algorithm, the elliptic trajectory-dependent individuals of every inspection pair were extracted first, then the defect position was identified by analyzing the distribution of individuals these located at the intersection of multiply elliptic trajectories. Considering the fuzzy and diversity characteristics in the detection of defects, a fuzzy control parameter and an adaptive individual updating strategy based on the k-means algorithm were introduced to ensure the robustness of the algorithm. The effectiveness of the proposed algorithm was verified by numerical models and experiments. The influences of the fuzzy control parameter and the individual updating strategy on the performance of the algorithm were analyzed furthermore.

关键词： Lamb waves defect localization intelligent analysis clustering algorithm damage classification elastic wave ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Application of Optimized Partitioning Around Medoid algorithm in Image Retrieval

引用

INTERNATIONAL JOURNAL OF DISTRIBUTED SYSTEMS AND TECHNOLOGIES 2021年第1期12卷 77-94页

作者： Jin, Yanxia Zhang, Xin Jia, Yao North Univ China Taiyuan Peoples R China Beihang Univ Beijing Peoples R China

In image retrieval, the major challenge is that the number of images in the gallery is large and irregular, which results in low retrieval accuracy. This paper analyzes the disadvantages of the PAM (partitioning around medoid) clustering algorithm in image data classification and the excessive consumption of time in the computation process of searching clustering representative objects using the PAM clustering algorithm. Fireworks particle swarm algorithm is utilized in the optimization process. PF-PAM algorithm, which is an improved PAM algorithm, is proposed and applied in image retrieval. First, extract the feature vector of the image in the gallery for the first clustering. Next, according to the clustering results, the most optimal cluster center is searched through the firework particle swarm algorithm to obtain the final clustering result. Finally, according to the incoming query image, determine the related image category and get similar images. The experimental comparison with other approaches shows that this method can effectively improve retrieval accuracy.

关键词： clustering algorithm Image Retrieval Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamical clustering in Electronic Commerce Systems via Optimization and Leadership Expansion

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2020年第8期16卷 5327-5334页

作者： Li, Hui-Jia Bu, Zhan Wang, Zhen Cao, Jie Beijing Univ Posts & Telecommun Sch Sci Beijing 100876 Peoples R China Nanjing Univ Finance & Econ Jiangsu Prov Key Lab E Business Nanjing 210003 Peoples R China Northwestern Polytech Univ Ctr Opt IMagery Anal & Learning Xian 710072 Peoples R China

In many electronic commerce systems, detecting significant clusters is of great value to the analysis, design, and optimization of the commerce behaviors. In this article, we propose a new dynamical approach to detect the cluster configuration fast and accurately which can be applied to electronic commerce systems. First, we analyze the two-stage game in which the leader group members make contributions prior to the follower group, and propose an exact index, i.e., the leadership, to characterize the key leaders. Then an efficient dynamical system is used to guarantee the cluster configuration converges to an optimal state, which assigns each node to the corresponding cluster based on quality optimization, repeatedly. Our method is of high efficiency-the exponential term in the proposed dynamical system makes the convergence to be very fast with a nearly linear time. Extensive experiments on multiple types of datesets demonstrate the state-of-the-art performance of proposed method.

关键词： Computational complexity clustering algorithm dynamical systems electronic commerce systems game theory

来源：评论

学校读者我要写书评

暂无评论

Optimal cluster head selection using modified rider assisted clustering for IoT

引用

IET COMMUNICATIONS 2020年第13期14卷 2189-2201页

作者： Poluru, Ravi Kumar Ramasamy, Lokesh Kumar Vellore Inst Technol Sch Comp Sci & Engn Vellore Tamil Nadu India

The vital concern of this research work is to propose a new clustering algorithm based on IoT devices. This process is made up with four stages namely, Cluster Formation, Splitting and merging, CH selection and Data transformation. The first and foremost step is the cluster formation;in thisk-mean clustering is exploited to cluster the network, where the count of needed clusters is optimally selected using a new algorithm. Further, this selection is to either split or merge the cluster structure. Subsequently, the proposed clustering model defines the optimal cluster head selection of each cluster by the proposed algorithm. Finally, in the data transmission phase, the delay optimized data fusion tree is subjected for reducing the manipulation of data fusion on transmission delay. More importantly, to solve all the optimization problems (optimal count of clusters and cluster heads), this paper introduces a new Cyclic Rider Optimization algorithm (C-ROA), which is the modification of Rider Optimization algorithm (ROA). To the end, the performance of the adopted method is compared over the other classical models like FF, GWO, WOA and conventional ROA in terms of delay, normalized energy, alive nodes and cost function measures.

关键词： wireless sensor networks sensor fusion pattern clustering Internet of Things optimisation optimal cluster head selection delay optimised data fusion tree cluster heads cyclic rider optimisation algorithm clustering algorithm IoT devices cluster formation k-mean clustering cluster structure nonuniform clustering structure clustering model

来源：评论

学校读者我要写书评

暂无评论

Automated real-space lattice extraction for atomic force microscopy images

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2023年第1期4卷 015015-015015页

作者： Corrias, Marco Papa, Lorenzo Sokolovic, Igor Birschitzky, Viktor Gorfer, Alexander Setvin, Martin Schmid, Michael Diebold, Ulrike Reticcioli, Michele Franchini, Cesare Univ Vienna Fac Phys Ctr Computat Mat Sci Kolingasse 14-16 A-1090 Vienna Austria Univ Vienna Vienna Doctoral Sch Phys Boltzmanngasse 5 A-1090 Vienna Austria TU Wien Inst Appl Phys Wiedner Hauptstr 8-10-134 A-1040 Vienna Austria Charles Univ Prague Fac Math & Phys Dept Surface & Plasma Sci 5 Holesovickach 2 Prague 8 18000 Czech Republic Univ Bologna Dipartimento Fis & Astron I-40127 Bologna Italy

Analyzing atomically resolved images is a time-consuming process requiring solid experience and substantial human intervention. In addition, the acquired images contain a large amount of information such as crystal structure, presence and distribution of defects, and formation of domains, which need to be resolved to understand a material's surface structure. Therefore, machine learning techniques have been applied in scanning probe and electron microscopies during the last years, aiming for automatized and efficient image analysis. This work introduces a free and open source tool (AiSurf: Automated Identification of Surface Images) developed to inspect atomically resolved images via scale-invariant feature transform and clustering algorithms. AiSurf extracts primitive lattice vectors, unit cells, and structural distortions from the original image, with no pre-assumption on the lattice and minimal user intervention. The method is applied to various atomically resolved non-contact atomic force microscopy images of selected surfaces with different levels of complexity: anatase TiO2(101), oxygen deficient rutile TiO2(110) with and without CO adsorbates, SrTiO3(001) with Sr vacancies and graphene with C vacancies. The code delivers excellent results and is tested against atom misclassification and artifacts, thereby facilitating the interpretation of scanning probe microscopy images.

关键词： machine learning clustering algorithm unsupervised learning computer vision atomic force microscopy scanning probe microscopy surface science

来源：评论

学校读者我要写书评

暂无评论

Robust and interpretable mineral identification using laser-induced breakdown spectroscopy mapping

引用

SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY 2023年 206卷

作者： Capela, Diana Ferreira, Miguel F. S. Lima, Alexandre Dias, Filipa Guimara, Diana Jorge, Pedro A. S. Silva, Nuno A. INESC TEC Ctr Appl Photon Rua Campo Alegre 687 P-4169007 Porto Portugal Univ Porto Fac Ciencias Dept Fis & Astron Rua Campo Alegre 687 P-4169007 Porto Portugal Univ Porto Fac Ciencias Dept Geociencias Ambiente & Ordenamento Terr Rua Campo Alegre 687 P-4169007 Porto Portugal Pole Univ Porto ICT Inst Earth Sci P-4169007 Porto Portugal

Fast and precise identification of minerals in geological samples is of paramount importance for the study of rock constituents and for technological applications in the context of mining. However, analyzing samples based only on the extrinsic properties of the minerals such as color can often be insufficient, making additional analysis crucial to improve the accuracy of the methods. In this context, Laser-induced breakdown spectroscopy mapping is an interesting technique to perform the study of the distribution of the chemical elements in sample surfaces, thus allowing deeper insights to help the process of mineral identification. In this work, we present the development and deployment of a processing pipeline and algorithm to identify spatial regions of the same mineralogical composition through chemical information in a fast and automatic way. Furthermore, by providing the necessary labels to the results on a training sample, we can turn this unsupervised methodology into a classifier that can be used to generalize and classify minerals in similar but unseen samples. The results obtained show good accuracy in reproducing the expected mineral regions and extend the interpretability of previous unsupervised methods with a visualization tool for cluster assignment, thus paving for future applications in contexts requiring high-throughput mineral identification systems, such as mining.

关键词： LIBS Mineral identification Mapping clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Combination of HF set and MCDM for stable clustering in VANETs

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2020年第3期14卷 190-195页

作者： Chettibi, Saloua Abdelhamid Mehri Constantine 2 Univ MISC Lab Constantine Algeria

Fast-moving nodes in vehicular ad hoc network (VANET) make network topology very dynamic, which deteriorates communication reliability and scalability. To overcome this problem, a hierarchical topology can be created using a clustering algorithm. This study presents a novel hesitant fuzzy (HF) multi-criteria ranking framework to deal with cluster-heads (CHs) election problem in VANET. An analogy is suggested between 'ranking of HF elements' and 'CH selection in VANET'. Within the proposed framework, a multiple criteria decision-making (MCDM) method should be used to calculate vehicle eligibility to become CH. In this study, technique for order of preference by similarity to ideal solution (TOPSIS), Vlse Kriterijumska Optimizacija Kompromisno Resenje (VIKOR) and EVAluation of MIXed data (EVAMIX) MCDM methods are applied. A simulation study, under a highway scenario, is conducted to investigate the performance of HF-TOPSIS, HF-VIKOR and HF-EVAMIX-based clustering algorithms. Obtained results show that CH election based on HF-EVAMIX leads to more stable clustering in comparison with HF-TOPSIS, HF-VIKOR and the conventional threshold-based method.

关键词： telecommunication network topology fuzzy set theory vehicular ad hoc networks pattern clustering decision making TOPSIS operations research telecommunication network reliability HF-EVAMIX-based clustering algorithm EVAMIX MCDM method technique for order of preference by similarity to ideal solution CH election HF-VIKOR HF-TOPSIS multicriteria decision-making method CH selection cluster-heads election problem hesitant fuzzy multicriteria ranking clustering algorithm hierarchical topology communication reliability network topology VANET vehicular ad hoc network fast-moving nodes stable clustering

来源：评论

学校读者我要写书评

暂无评论

Semi-Empirical Error Ellipsoid clustering for Identifying the Second-Order Structural Features From a Laboratory AE Source Location Cloud: Method, Validation, and Application to a Hydraulic Fracturing Test

引用

EARTH AND SPACE SCIENCE 2022年第10期9卷

作者： Xiong, Qiquan Hampton, Jesse C. Univ Wisconsin Dept Civil & Environm Engn Geomech & Damage Grp GeoD Madison WI 53706 USA

Point cloud of sources in the form of acoustic emission (AE) or seismicity at both field- and laboratory-scales are indicative of causative structures. The error ellipsoid clustering (EC) method, whose underlying premise is reducing the amount of discarded data, is helpful for seeking the causative structure(s) from field-scale seismic sources. However, a proper EC method does not exist for laboratory sources. Interpretation of laboratory AE sources usually involves systematic discarding of the assumed "low-quality" data. We seek the successful transfer of the field-scale EC method into the investigation of laboratory-scale sources. For that, a new semi-empirical EC method (serendipity method) is devised, and we have systematically modified the previous EC method (standard method) in (1) error ellipsoid formation, (2) iterative clustering algorithm, and (3) clustering stopping criterion. In the literature, the standard method and its limitations were validated using synthetic data. We validate the modifications by comparing its post-clustering results with the original source locations and with the in-situ and post-mortem inspections of the laboratory rock fractures;and similarly for the serendipity method. We apply the serendipity method to a laboratory hydraulic fracturing test. The serendipity method implies the existence of a 3D damage zone as the second-order feature caused by the hydraulic fracturing in addition to the primary hydraulic fracture. This complex damage zone provides a logical explanation to the previously observed reverse permeability-distance relationship for hydraulic fracture. Plain Language Summary Point cloud source locations of acoustic emission (AE) or seismicity at both field- and laboratory-scales are indicative of their underlying causative structures. In efforts to reduce the amount of data discarded throughout the analysis of point cloud source data, the source location errors have been used to modify/re-locate events based on their p

关键词： error ellipsoid source location hydraulic fracturing geological structure clustering algorithm

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：