检索结果-内蒙古大学图书馆

Cluster-based local modeling (CBLM) paradigm meets deep learning: A novel approach to soil moisture estimation

JOURNAL OF HYDROLOGY 2024年 635卷

作者： Moosavi, Vahid Zuravand, Golnaz Shamsi, Seyed Rashid Fallah Tarbiat Modares Univ Fac Nat Resources & Marine Sci Dept Watershed Management Engn Noor Iran Shiraz Univ Dept Nat Resource & Environm Engn Shiraz Iran Chinese Acad Sci Inst Geog Sci & Nat Resources Res Beijing Peoples R China

Producing precise soil moisture maps through soil moisture modeling is highly valued for a variety of purposes, such as agricultural productivity, water resource management, climate modeling, environmental monitoring, and disaster management. However, the severe spatial variability of soil moisture makes a single model insufficient for accurately estimating soil moisture in an area. In this study, a deep learning-based soil moisture estimation approach using the Cluster-Based Local Modeling (CBLM) paradigm is presented. The approach involves the utilization of Sentinel-2 imagery and ancillary data such as soil maps, geology maps, land use/cover maps as well as topographic and spectral indices to create a database for modeling. The optical trapezoid model (OPTRAM) was also employed to estimate relative soil moisture content as another ancillary data for soil moisture modeling. Some robust clustering algorithms i.e. K-means, genetic algorithm, particle swarm optimization, and densitybased spatial clustering were applied to divide the study area into homogenous sub-areas. Two powerful deep learning methods, i.e., Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), were then trained on the dataset to make accurate soil moisture estimations. Promising results were obtained through the proposed approach in accurately modeling soil moisture. According to the findings, the global modeling approach using both LSTM and CNN models exhibited moderate performance. Isolated pixels with unreasonably high soil moisture values were produced by the LSTM model which may be related to modeling process errors. Significantly enhanced results were observed in both deep learning models with the use of the local modeling approach. The cluster-based local modeling paradigm was able to capture local variations in soil moisture and produce more interpretable results by developing separate models for each cluster. Moreover, the CBLM-based CNN-CLTM hybrid model outperformed bot

关键词： Soil moisture modeling clustering algorithms Global modeling approach Local modeling approach

来源：评论

学校读者我要写书评

暂无评论

Efficient Eigen-Decomposition for Low-Rank Symmetric Matrices in Graph Signal Processing: An Incremental Approach

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 4918-4934页

作者： Deng, Qinwen Zhang, Yangwen Li, Mo Zhang, Songyang Ding, Zhi Univ Calif Davis Dept Elect & Comp Engn Davis CA 95616 USA Univ Louisiana Lafayette Dept Math Lafayette LA 70504 USA Univ Louisiana Lafayette Dept Elect & Comp Engn Lafayette LA 70504 USA

Graph spectral analysis has emerged as an important tool to extract underlying structures among data samples. Central to graph signal processing (GSP) and graph neural networks (GNN), graph spectrum is often derived via eigen-decomposition (ED) of graph representation (adjacency/Laplacian) matrix. Many real-world applications feature dynamic graphs whose representation matrix size varies over time. Such evolving graph usually shares part of the same structures with the previous graphs. We consider efficient ways to estimate the $K$ dominant eigenvectors of the graph representation matrix. We focus on an iterative ED algorithm for low-rank symmetric matrices to update the top $K$ eigen-pairs of the representation matrix for a graph with increasing node size. To accommodate the growing graph size, we propose two Incremental ED algorithms for Low Rank symmetric matrices (ILRED) based on an iterative eigen-updating strategy. We also provide analysis on the resulting error performance, computational complexity and memory usage to showcase the efficiency of ILRED. The experimental results in both synthetic and real-world datasets with the context of spectral clustering and graph filtering validate the power of the proposed ILRED algorithms.

关键词： Signal processing algorithms Symmetric matrices Approximation algorithms Spectral analysis Filters Eigenvalues and eigenfunctions clustering algorithms Eigen-decomposition eigen-updating graph signal processing graph spectral analysis

来源：评论

学校读者我要写书评

暂无评论

Multiple Sound Source Localization in Three Dimensions Using Convolutional Neural Networks and clustering Based Post-Processing

引用

IEEE ACCESS 2022年 10卷 125707-125722页

作者： Sakavicius, Saulius Serackis, Arturas Abromavicius, Vytautas Vilnius Tech Fac Elect Dept Elect Syst Vilnius 10221 Lithuania

Sound source localization methods are successfully applied for various estimation tasks, such as tracking and detecting objects, aiming cameras, and navigating robots. However, large and usually complex distributed microphone arrays are used for three-dimensional acoustic source localization. This study proposes a convolutional neural network architecture for three-dimensional sound source localization using a single tetrahedral microphone array. A spectrum phase component of a microphone array signal was designed as the input of the model, while the output represents a three-dimensional space. The paper provides extensive experimental results of the given method on a semi-synthetic audio data set and a real-world microphone array. Furthermore, cluster-based post-processing has been shown to increase the accuracy of three-dimensional localization by more than 30%. The experimental results on a synthesized data set using the image source method showed 1.08 m localization uncertainties. The estimate of the investigated sound sources had a mean absolute error of 18.97 & DEG;and elevation error of 48.49 & DEG;. An additional advantage of the proposed method is the ability to predict the location of the sound source from a single signal analysis frame. This gives instant localization and is in line with many alternative applications. The proposed solution does not require intensive preprocessing of the audio signals and can be used as a video camera pointing system based on a microphone array. In the future, it would be relevant to investigate the localization performance of more than two sound sources, and the variable acoustic conditions could also be assessed.

关键词： Location awareness Microphone arrays Acoustics clustering algorithms Direction-of-arrival estimation Cameras Estimation clustering convolutional neural networks microphone array multiple sound sources sound source localization three-dimensional

来源：评论

学校读者我要写书评

暂无评论

Hierarchical clustering Nodes Collaborative Scheduling in Wireless Sensor Network

引用

IEEE SENSORS JOURNAL 2022年第2期22卷 1786-1798页

作者： Wang, Minghua Zeng, Jingxian Univ South China Sch Elect Engn Hunan Prov Key Lab Ultrafast Micro Nano Technol & Hengyang 421001 Peoples R China

Network lifetime and coverage are the key evaluation metrics of Wireless Sensor Networks (WSNs). Aiming at network lifetime, Hierarchical clustering-task Scheduling Policy (HCSP) breaks the traditional clustering framework, but it doesnt fully consider the network coverage problem. We propose a Hierarchical clustering Node Collaborative Scheduling (HCNCS) protocol that optimizes HCSP to extend the network lifetime and improves the coverage performance of WSNs by nodes collaborative sensing. According to the deployment location, HCNCS classifies nodes into Node Collaborative Sensing Disks(NCSDs), which as units for data sensing and transmission. Nodes are rotated in WSNs to balance the energy consumption and through collaborative sensing to improve the coverage of NCSDs. In addition, HCNCS constrains the number of clusters by NCSDs classification based on K-means to reduce the communication energy consumption of clustering. Based on the HCNCS, this paper further proposes an Enhanced Hierarchical clustering Node Collaborative Scheduling (EHCNCS) protocol. Compared with HCNCS, EHCNCS selects NCSDs according to Node Collaborative Scheduling (NCS) algorithm after clustering, which improves the coverage capability of NCSDs at the cost of increasing a small amount of the communication energy consumption. EHCNCS also rotates Cluster Heads (CHs) by the CH rotation candidate table to balance network energy consumption. The extensive simulations show that HCNCS has an obvious advantage over HCSP in terms of network lifetime and network coverage. Compared with HCNCS, EHCNCS significantly prolongs the network lifetime of WSNs at the expense of a bit of coverage performance.

关键词： Wireless sensor networks Sensors Collaboration Protocols Energy consumption clustering algorithms Routing Wireless sensor networks hierarchical clustering-task scheduling policy K-means nodes collaborative sensing

来源：评论

学校读者我要写书评

暂无评论

FedOrbit: Energy Efficient Federated Learning for Orbital Edge Computing Using Block Minifloat Arithmetic

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2024年第6期17卷 3657-3671页

作者： Jabbarpour, Mohammad Reza Javadi, Bahman Leong, Philip H. W. Calheiros, Rodrigo N. Boland, David Western Sydney Univ Sch Comp Data & Math Sci Sydney NSW 2000 Australia Univ Sydney Sch Elect & Informat Engn Camperdown NSW 2050 Australia

Low Earth Orbit (LEO) satellite constellations have diverse applications, including earth observation, communication services, navigation, and positioning. These constellations have evolved into a valuable data source;however, their use in a ground station (GS) for analysis via machine learning algorithms presents challenges due to constraints on power consumption, communication bandwidth, and onboard computing capabilities. While the combination of Federated Learning (FL) and Orbital Edge Computing has been employed to address these challenges, its heavy reliance on the GS for model aggregation and edge resource limitations remains a research challenge. This article presents FedOrbit, a novel energy-efficient and decentralised FL method to optimise communication with the GS and reduce power consumption. FedOrbit utilises reinforcement learning for cluster formation, satellite visiting patterns for master satellite selection, and block minifloat arithmetic for power reduction. Extensive performance evaluation under Walker Delta-based LEO constellation configurations and different datasets reveals that FedOrbit can maintain high accuracy while significantly reduce communication demand, power consumption and training time in comparison to state-of-the-art FL approaches. The proposed technique can also reduce the training time by 5x compared with the centralised FL approaches. In addition, the utilisation of block minifloat representation as low-precision arithmetic enhanced the energy consumption by 3.5x compared with the single-precision (FP32) format.

关键词： Training Satellites Quantization (signal) Orbits Servers Computational modeling clustering algorithms Power demand Low earth orbit satellites Arithmetic Block minifloat energy consumption federated learning low-earth orbit orbital edge computing

来源：评论

学校读者我要写书评

暂无评论

clustering Point Process Based Network Topology Structure Constrained Urban Road Extraction From Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 2087-2098页

作者： Wu, You Zhao, Quanhua Shen, Zhaoyu Li, Yu Liaoning Tech Univ Sch Geomat Fuxin 123000 Peoples R China

To extract complicated road network from remote sensing images on urban scenes, this article presents a clustering point process (CPP) based network topology structure constrained road extraction algorithm. Firstly, the CPP is constructed to model the feature points, such as endpoints, bends, and crossroads in a road system. Based on that, an initial network topology structure is constructed by connecting the points with lines. Then, according to the network structure characteristic and the spectral characteristic of road, a network topology structure constraining model and a spectral measurement constraining model are constructed, respectively. By combining the models above, a road extraction model is built under the framework of Bayes' theorem. Finally, to simulate from the road extraction model and extract an optimal road network, a solution strategy, reversible jump Markov Chain Monte Carlo (RJMCMC) simulation algorithm with related transfer operations, is designed according to the CPP and network topology structure. Several high-resolution remote sensing images on urban scenes are tested. According to a buffer evaluation method, and compared with the comparing algorithms, accuracy and extraction rate of results from the proposed algorithm are increased by 10.86% and 8.75% on average, respectively. It is proved that the proposed algorithm can extract the complicated road network effectively.

关键词： Roads Feature extraction Network topology Remote sensing Junctions clustering algorithms Bending clustering point process (CPP) feature points network topology structure reversible jump Markov chain Monte Carlo (RJMCMC) urban road extraction

来源：评论

学校读者我要写书评

暂无评论

Projective Multiple Kernel Subspace clustering

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2022年 24卷 2567-2579页

作者： Sun, Mengjing Wang, Siwei Zhang, Pei Liu, Xinwang Guo, Xifeng Zhou, Sihang Zhu, En Natl Univ Def Technol Sch Comp Changsha 410073 Peoples R China Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha 410073 Peoples R China

Multiple kernel subspace clustering (MKSC), as an important extension for handling multi-view non-linear subspace data, has shown notable success in a wide variety of machine learning tasks. The key objective of MKSC is to build a flexible and appropriate graph for clustering from the kernel space. However, existing MKSC methods apply a mechanism utilizing the kernel trick to the traditional self-expressive principle, where the similarity graphs are built on the respective high-dimensional (or even infinite) reproducing kernel Hilbert space (RKHS). Regarding this strategy, we argue that the original high-dimensional spaces usually include noise and unreliable similarity measures and, therefore, output a low-quality graph matrix, which degrades clustering performance. In this paper, inspired by projective clustering, we propose the utilization of a complementary similarity graph by fusing the multiple kernel graphs constructed in the low-dimensional partition space, termed projective multiple kernel subspace clustering (PMKSC). By incorporating intrinsic structures with multi-view data, PMKSC alleviates the noise and redundancy in the original kernel space and obtains high-quality similarity to uncover the underlying clustering structures. Furthermore, we design a three-step alternate algorithm with proven convergence to solve the proposed optimization problem. The experimental results on ten multiple kernel benchmark datasets validate the effectiveness of our proposed PMKSC, compared to the state-of-the-art multiple kernel and kernel subspace clustering methods, by a large margin. Our code is available at https://***/MengjingSun/PMKSC-code.

关键词： Kernel Optimization clustering algorithms Integrated circuits Hilbert space Redundancy clustering methods Kernel clustering multiple kernel subspace clustering multi-view information fusion

来源：评论

学校读者我要写书评

暂无评论

Subspace clustering via Structured Sparse Relation Representation

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4610-4623页

作者： Wei, Lai Ji, Fenfen Liu, Hao Zhou, Rigui Zhu, Changming Zhang, Xiafen Shanghai Maritime Univ Coll Informat Engn Shanghai 201306 Peoples R China Wuhan Digit Engn Inst Wuhan 430205 Peoples R China

Due to the corruptions or noises that existed in real-world data sets, the affinity graphs constructed by the classical spectral clustering-based subspace clustering algorithms may not be able to reveal the intrinsic subspace structures of data sets faithfully. In this article, we reconsidered the data reconstruction problem in spectral clustering-based algorithms and proposed the idea of ``relation reconstruction.'' We pointed out that a data sample could be represented by the neighborhood relation computed between its neighbors and itself. The neighborhood relation could indicate the true membership of its corresponding original data sample to the subspaces of a data set. We also claimed that a data sample's neighborhood relation could be reconstructed by the neighborhood relations of other data samples;then, we suggested a much different way to define affinity graphs consequently. Based on these propositions, a sparse relation representation (SRR) method was proposed for solving subspace clustering problems. Moreover, by introducing the local structure information of original data sets into SRR, an extension of SRR, namely structured sparse relation representation (SSRR) was presented. We gave an optimization algorithm for solving SRR and SSRR problems and analyzed its computation burden and convergence. Finally, plentiful experiments conducted on different types of databases showed the superiorities of SRR and SSRR.

关键词： clustering algorithms Sparse matrices Image reconstruction Optimization Faces Convergence Task analysis Low-rank representation (LRR) neighborhood relation sparse subspace clustering (SSC) subspace clustering

来源：评论

学校读者我要写书评

暂无评论

scRAE: Deterministic Regularized Autoencoders With Flexible Priors for clustering Single-Cell Gene Expression Data

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022年第5期19卷 2996-3007页

作者： Mondal, Arnab Kumar Asnani, Himanshu Singla, Parag Ap, Prathosh IIT Delhi New Delhi 110016 India TIFR Mumbai 400005 Maharashtra India

clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as 'dropout' events. Recently, Regularized Auto-Encoder (RAE) based deep neural network models have achieved remarkable success in learning robust low-dimensional representations. The basic idea in RAEs is to learn a non-linear mapping from the high-dimensional data space to a low-dimensional latent space and vice-versa, simultaneously imposing a distributional prior on the latent space, which brings in a regularization effect. This paper argues that RAEs suffer from the infamous problem of bias-variance trade-off in their naive formulation. While a simple AE wita latent regularization results in data over-fitting, a very strong prior leads to under-representation and thus bad clustering. To address the above issues, we propose a modified RAE framework (called the scRAE) for effective clustering of the single-cell RNA sequencing data. scRAE consists of deterministic AE with a flexibly learnable prior generator network, which is jointly trained with the AE. This facilitates scRAE to trade-off better between the bias and variance in the latent space. We demonstrate the efficacy of the proposed method through extensive experimentation on several real-world single-cell Gene expression datasets. The code for our work is available at https://***/arnabkmondal/scRAE.

关键词： Computer architecture Microprocessors clustering algorithms Partitioning algorithms Data models Dimensionality reduction Deep learning Dimensionality reduction of scRNA-seq data clustering of scRNA-seq data regularized auto-encoder scRAE

来源：评论

学校读者我要写书评

暂无评论

Identifying Gene Signatures for Cancer Drug Repositioning Based on Sample clustering

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022年第2期19卷 953-965页

作者： Wang, Fei Ding, Yulian Lei, Xiujuan Liao, Bo Wu, Fangxiang Univ Saskatchewan Div Biomed Engn 57 Campus Dr Saskatoon SK S7N 5A9 Canada Shaanxi Normal Univ Sch Comp Sci Xian 710119 Peoples R China Hainan Normal Univ Sch Math & Stat Haikou 571158 Hainan Peoples R China Univ Saskatchewan Dept Mech Engn 57 Campus Dr Saskatoon SK S7N 5A9 Canada Univ Saskatchewan Dept Comp Sci 57 Campus Dr Saskatoon SK S7N 5A9 Canada

Drug repositioning is an important approach for drug discovery. Computational drug repositioning approaches typically use a gene signature to represent a particular disease and connect the gene signature with drug perturbation profiles. Although disease samples, especially from cancer, may be heterogeneous, most existing methods consider them as a homogeneous set to identify differentially expressed genes (DEGs)for further determining a gene signature. As a result, some genes that should be in a gene signature may be averaged off. In this study, we propose a new framework to identify gene signatures for cancer drug repositioning based on sample clustering (GS4CDRSC). GS4CDRSC first groups samples into several clusters based on their gene expression profiles. Second, an existing method is applied to the samples in each cluster for generating a list of DEGs. Then a weighting approach is used to identify an intergrated gene signature from all the lists of DEGs. The integrated gene signature is used to connect with drug perturbation profiles in the Connectivity Map (CMap)database to generate a list of drug candidates. GS4CDRSC has been tested with several cancer datasets and existing methods. The computational results show that GS4CDRSC outperforms those methods without the sample clustering and weighting approaches in terms of both number and rate of predicted known drugs for specific cancers.

关键词： Drugs Cancer Databases clustering algorithms Gene expression Perturbation methods Drug repositioning sample clustering gene signature gene expression drug perturbation

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：