检索结果-内蒙古大学图书馆

Toward smart energy user: Real time non-intrusive load monitoring with simultaneous switching operations

APPLIED ENERGY 2021年 287卷 116616-116616页

作者： Liu, Yu Liu, Wei Shen, Yiwen Zhao, Xin Gao, Shan Southeast Univ Sch Elect Engn Nanjing 210018 Peoples R China State Grid Nanjing Power Supply Co Nanjing 210019 Peoples R China

Non-intrusive load monitoring is a promising technology in intelligent energy consumption management, which can provide insights for electricity use patterns and customer living habits, leading to the technical support of multiple smart energy use applications. As the most challenging problem in this specific field, the real time load disaggregation with simultaneous switching operations still remains unsolved due to its complexity and uncertainty. In this paper, a practical and feasible solution for the simultaneous action problems under real time non intrusive load monitoring framework is proposed and investigated, which is capable of filling such research gap. At the first stage, to tackle the different kinds of overlapping combinations, an adaptive-window based detection approach is applied to capture the state changes. Secondly, a deep dictionary learning model is proposed in the real time load monitoring architecture, where the dictionary atom is generated in a semi-supervised modularization way and extended with high order dynamic features of appliances. Then, sparse coding formulized algorithm is presented to solve the problem, which is compatible of handling simultaneous occurrence of multiple switching events. The proposed model and algorithm are tested and verified in both simulation platform and field measurements. Results show that the operation-overlapping issue can be effectively addressed by the presented method, in addition to the high accuracy monitoring performance.

关键词： Dynamic features Machine learning Real time load disaggregation Simultaneous switching events sparse coding

来源：评论

学校读者我要写书评

暂无评论

A sparse Sampling-Based Framework for Semantic Fast-Forward of First-Person Videos

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2021年第4期43卷 1438-1444页

作者： Silva, Michel Ramos, Washington Campos, Mario Nascimento, Erickson R. Univ Fed Minas Gerais Dept Comp Sci Comp Vis & Robot Lab BR-31270901 Belo Horizonte MG Brazil

Technological advances in sensors have paved the way for digital cameras to become increasingly ubiquitous, which, in turn, led to the popularity of the self-recording culture. As a result, the amount of visual data on the Internet is moving in the opposite direction of the available time and patience of the users. Thus, most of the uploaded videos are doomed to be forgotten and unwatched stashed away in some computer folder or website. In this paper, we address the problem of creating smooth fast-forward videos without losing the relevant content. We present a new adaptive frame selection formulated as a weighted minimum reconstruction problem. Using a smoothing frame transition and filling visual gaps between segments, our approach accelerates first-person videos emphasizing the relevant segments and avoids visual discontinuities. Experiments conducted on controlled videos and also on an unconstrained dataset of First-Person Videos (FPVs) show that, when creating fast-forward videos, our method is able to retain as much relevant information and smoothness as the state-of-the-art techniques, but in less processing time.

关键词： Videos Semantics Visualization Acceleration Cameras Encoding Pattern analysis First-person video fast-forward semantic information sparse coding minimum sparse reconstruction problem

来源：评论

学校读者我要写书评

暂无评论

sparse coding from a Bayesian Perspective

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2013年第6期24卷 929-939页

作者： Lu, Xiaoqiang Wang, Yulong Yuan, Yuan Chinese Acad Sci Xian Inst Opt & Precis Mech State Key Lab Transient Opt & Photon Ctr Opt Imagery Anal & Learning OPTIMAL Xian 710119 Peoples R China Hubei Univ Fac Math & Comp Sci Wuhan 430062 Peoples R China

sparse coding is a promising theme in computer vision. Most of the existing sparse coding methods are based on either l(0) or l(1) penalty, which often leads to unstable solution or biased estimation. This is because of the nonconvexity and discontinuity of the l(0) penalty and the over-penalization on the true large coefficients of the l(1) penalty. In this paper, sparse coding is interpreted from a novel Bayesian perspective, which results in a new objective function through maximum a posteriori estimation. The obtained solution of the objective function can generate more stable results than the l(0) penalty and smaller reconstruction errors than the l(1) penalty. In addition, the convergence property of the proposed algorithm for sparse coding is also established. The experiments on applications in single image super-resolution and visual tracking demonstrate that the proposed method is more effective than other state-of-the-art methods.

关键词： Bayesian compressive sensing (CS) computer vision maximum a posteriori (MAP) sparse coding

来源：评论

学校读者我要写书评

暂无评论

Influence of bio-inspired activity regulation through neural thresholds learning in the performance of neural networks

引用

NEUROCOMPUTING 2021年 462卷 294-308页

作者： Lopez-Hazas, Jessica Montero, Aaron Rodriguez, Francisco B. Univ Autonoma Madrid Escuela Politecn Super Dept Ingn Informat Grp Neurocomp Biol Madrid 28049 Spain

Studies on Kenyon Cells (KCs) in the olfactory system of locust have found evidence that some of them are more responsive towards stimuli than others. This variability suggests that there could be a heterogeneous neural threshold distribution among KCs. This work explores the hypothesis that the heterogeneity in neural thresholds could control the activity level of populations of neurons and facilitate the generation of sparse code to achieve a better representation of stimuli. In order to study this hypothesis, an artificial neural network that adapts many of the strategies observed in the locust olfactory system is proposed, including a new learning algorithm capable of finding the best neural threshold distribution to resolve a certain classification problem and a gain control term that keeps the activity level of the neurons in the hidden layer under a certain limit. The bio-inspired neural network gets the best results when the activity level in the hidden layer is low, for which neural thresholds are more important for a better performance than the connections between the neurons in different layers. Also, it was found that the separability of the internal representations of the different patterns in the classification problem improves when the thresholds are adjusted by the learning algorithm in order to control the activity level. Finally, the performance of this network was compared to SVMs and MLP when applied to resolve a complex classification task with data collected by electronic noses and affected by sensor drift, for which the bio-inspired network obtains very satisfactory results, reaching a performance similar or even better than SVMs and MLP. (c) 2021 Elsevier B.V. All rights reserved.

关键词： sparse coding Neural sensitivity Olfactory system Gain control Bio-inspired Pattern discrimination

来源：评论

学校读者我要写书评

暂无评论

Application of a Simple, Spiking, Locally Competitive Algorithm to Radionuclide Identification

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 2021年第3期68卷 292-304页

作者： Carson, Merlin Woods, Walt Reynolds, Sebastian Wetzel, Mark Morton, Adam J. Hecht, Adam A. Osinski, Marek Teuscher, Christof Portland State Univ Dept Elect & Comp Engn Portland OR 97201 USA Legacy Hlth Dow Neurosci Labs Portland OR 97232 USA Univ New Mexico Dept Nucl Engn Albuquerque NM 87131 USA Univ New Mexico Ctr High Technol Mat Albuquerque NM 87106 USA

Many radionuclide identification algorithms use statistical inference to collect a variety of features from gamma-ray spectra to deduce the presence of particular radionuclides. More modern algorithms require large amounts of data to learn and use latent features from spectra for classification. Both approaches are computationally expensive, which is reflected in their power consumption, and require large amounts of user intervention to prepare. In this article, we introduce a low-power, neuromorphic algorithm for the real-time identification of radionuclides which simultaneously considers the entire shape of a gamma-ray spectrum. Utilizing the output of a traditional gamma-ray detector, our spiking, locally competitive algorithm uses sparse coding optimization to compare global patterns in a gamma-ray spectrum with a dictionary of radionuclide templates. This approach allows us to model informative global features resulting from both photoelectric absorption and Compton scattering. For the purpose of radiation threat reduction, the dictionary consists of data from the Nuclear Wallet Cards, a list of radionuclides and their properties compiled by the National Nuclear Data Center. To test our algorithm, we use a variety of gamma-ray spectra created using radionuclides measured under laboratory conditions with varying durations, distances, activity levels, and backgrounds, resulting in a wide range of signal-to-noise ratios. We have created test sets for three different gamma-ray detector types, with Co-57, Cs-137, Eu-152, Co-60, Pu-239, and U-235 sources, to quantify the effect of resolution, efficiency, and background on the accuracy of the algorithm. We demonstrate a true positive accuracy of 91% with a high-resolution detector and 89% with a low-resolution detector on the corresponding test sets. Experimenting with the same radionuclides included in the test sets in a variety of special nuclear material (SNM) masking configurations, we show that our algorithm is c

关键词： Gamma-rays Detectors Software algorithms Prediction algorithms Dictionaries Feature extraction Shape Compton scatter gamma-ray identification locally competitive algorithm (LCA) memristor neuromorphic power efficient radionuclide simple spiking LCA (SSLCA) sparse coding spectrum spiking architecture

来源：评论

学校读者我要写书评

暂无评论

A Label-Constraint Building Roof Detection Method From Airborne LiDAR Point Clouds

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2021年第8期18卷 1466-1470页

作者： Yang, Juntao Kang, Zhizhong Akwensi, Perpetual Hope China Univ Geosci Sch Land Sci & Technol Beijing 100083 Peoples R China Minist Educ Peoples Republ China Ctr Space Explorat Subctr Int Cooperat & Res Lunar & Planetary Explo Beijing 100083 Peoples R China Shanxi Key Lab Resources Environm & Disaster Moni Jinzhong 030600 Peoples R China

Airborne light detection and ranging (LiDAR) point clouds have become growingly popular as a reliable data source for 3-D digital building model reconstruction. Therefore, we develop a label-constraint approach for automatically detecting building roofs using airborne LiDAR point clouds and multispectral images, where the label information is introduced in both the discriminative feature space generation and the detection procedure. To obtain a robust and highly discriminative descriptor, a supervised sparse coding-enhanced bag of visual word (SC-BOVW) model based on a learned discriminative dictionary is used to encode local geometric and spectral information within each super-voxel into high-level semantic representation, which is then fed into a support vector machine (SVM) classifier for distinguishing buildings from others. Additionally, a graph cut-based procedure is used as a postprocessing step to guarantee the spatial consistency in detection results. Experiments were conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) benchmark data sets. Results indicate that the proposed method is accurate and efficient in terms of building roof region detection. Moreover, the proposed method is superior to other existing methods with average differences in recall of 2.23%, precision of 0.28% and quality of 1.99%.

关键词： Buildings Laser radar Feature extraction Dictionaries Semantics Three-dimensional displays Task analysis Airborne light detection and ranging (LiDAR) building roof extraction high-level semantic representation multispectral images sparse coding spatial consistency

来源：评论

学校读者我要写书评

暂无评论

Learning sparse and meaningful representations through embodiment

引用

NEURAL NETWORKS 2021年 134卷 23-41页

作者： Clay, Viviane Koenig, Peter Kuehnberger, Kai-Uwe Pipa, Gordon Univ Osnabruck Inst Cognit Sci Wachsbleiche 27 D-49090 Osnabruck Germany Univ Med Ctr Hamburg Eppendorf Inst Neurophysiol & Pathophysiol Hamburg Germany

How do humans acquire a meaningful understanding of the world with little to no supervision or semantic labels provided by the environment? Here we investigate embodiment with a closed loop between action and perception as one key component in this process. We take a close look at the representations learned by a deep reinforcement learning agent that is trained with high-dimensional visual observations collected in a 3D environment with very sparse rewards. We show that this agent learns stable representations of meaningful concepts such as doors without receiving any semantic labels. Our results show that the agent learns to represent the action relevant information, extracted from a simulated camera stream, in a wide variety of sparse activation patterns. The quality of the representations learned shows the strength of embodied learning and its advantages over fully supervised approaches. (C) 2020 The Authors. Published by Elsevier Ltd.

关键词： Reinforcement learning Deep learning Embodiment Embodied cognition Representation learning sparse coding

来源：评论

学校读者我要写书评

暂无评论

sparse coding and classifier ensemble based multi-instance learning for image categorization

引用

SIGNAL PROCESSING 2013年第1期93卷 1-11页

作者： Song, Xiangfa Jiao, L. C. Yang, Shuyuan Zhang, Xiangrong Shang, Fanhua Xidian Univ Minist Educ China Key Lab Intelligent Percept & Image Understanding Xian 710071 Peoples R China

In this paper, we propose a novel method based on sparse coding and classifier ensemble for tackling image categorization problem under the framework of multi-instance learning (MIL). Specifically, a dictionary is learned from the instances of all the training bags. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is also represented one feature vector which is achieved via sparse representations of all instances within the bag. Thus, the MIL problem is converted to a single-instance learning problem that can be solved by well-know single-instance learning methods, such as support vector machines (SVMs). Two strategies are used to improve classification performance: first, the component classifiers are obtained by repeatedly using the above method with dictionaries of different sizes;second, the result of classifier ensemble is used for prediction. Experimental results on the COREL data sets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods. (c) 2012 Elsevier B.V. All rights reserved.

关键词： Multi-instance learning Image categorization sparse coding Classifier ensemble

来源：评论

学校读者我要写书评

暂无评论

SpaRec: sparse Systematic RLNC Recoding in Multi-Hop Networks

引用

IEEE ACCESS 2021年 9卷 168567-168586页

作者： Tasdemir, Elif Toemoeskoezi, Mate Cabrera, Juan A. Gabriel, Frank You, Dongho Fitzek, Frank H. P. Reisslein, Martin Tech Univ Dresden Deutsch Telekom Chair Lab Germany 5G Dresden Germany Tech Univ Dresden Ctr Tactile Internet Human Loop CeTI D-01062 Dresden Germany Hannam Univ Dept Informat & Commun Engn Daejeon 34430 South Korea Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85287 USA

sparse Random Linear Network coding (RLNC) reduces the computational complexity of the RLNC decoding through a low density of the non-zero coding coefficients, which can be achieved through sending uncoded (systematic) packets. However, conventional recoding of sparse RLNC coded packets at an intermediate node in a multi-hop network increases the density of non-zero coding coefficients. We develop and evaluate sparsity-preserving recoding (SpaRec) strategies that preserve the low density of non-zero coding coefficients of sparse RLNC with systematic packets. We develop SpaRec strategies with and without decoding at the intermediate nodes, with and without a specified coding rate, as well as with finite and infinite recoding window lengths. We evaluate the SpaRec strategies in multi-hop networks in terms of packet loss, packet delivery delay, as well as recoding and decoding (computation) throughput. We find that the SpaRec strategies substantially improve the RLNC performance compared to conventional recoding.

关键词： Systematics Encoding Decoding Delays Spread spectrum communication Codes Throughput Intermediate network node low coding coefficient density multi-hop network random linear network coding (RLNC) recoding sliding window coding sparse coding systematic packet

来源：评论

学校读者我要写书评

暂无评论

Functional and Structural Properties of Highly Responsive Somatosensory Neurons in Mouse Barrel Cortex

引用

CEREBRAL CORTEX 2021年第10期31卷 4533-4553页

作者： Barz, C. S. Garderes, P. M. Ganea, D. A. Reischauer, S. Feldmeyer, D. Haiss, F. Res Ctr Julich Inst Neurosci & Med INM 10 D-52425 Julich Germany Rhein Westfal TH Aachen Dept Psychiat Psychotherapy & Psychosomat Med Sch D-52074 Aachen Germany Julich Aachen Res Alliance Translat Brain Med D-52074 Aachen Germany Rhein Westfal TH Aachen Med Sch IZKF Aachen D-52074 Aachen Germany Rhein Westfal TH Aachen Med Sch Dept Neuropathol D-52074 Aachen Germany Rhein Westfal TH Aachen Med Sch Dept Ophthalmol D-52074 Aachen Germany Univ Basel Biomed Dept CH-4056 Basel Switzerland Justus Liebig Univ Giessen Med Clin 1 Cardiol Angiol D-35390 Giessen Germany Justus Liebig Univ Giessen Campus Kerckhoff D-35390 Giessen Germany Max Planck Inst Heart & Lung Res Dept Dev Genet D-61231 Bad Nauheim Germany Cardiopulm Inst CPI D-35392 Giessen Germany Inst Pasteur Unit Neural Circuits Dynam & Decis Making F-75015 Paris France

sparse population activity is a well-known feature of supragranular sensory neurons in neocortex. The mechanisms underlying sparseness are not well understood because a direct link between the neurons activated in vivo, and their cellular properties investigated in vitro has been missing. We used two-photon calcium imaging to identify a subset of neurons in layer L2/3 (L2/3) of mouse primary somatosensory cortex that are highly active following principal whisker vibrotactile stimulation. These high responders (HRs) were then tagged using photoconvertible green fluorescent protein for subsequent targeting in the brain slice using intracellular patch-clamp recordings and biocytin staining. This approach allowed us to investigate the structural and functional properties of HRs that distinguish them from less active control cells. Compared to less responsive L2/3 neurons, HRs displayed increased levels of stimulus-evoked and spontaneous activity, elevated noise and spontaneous pairwise correlations, and stronger coupling to the population response. Intrinsic excitability was reduced in HRs, while we found no evidence for differences in other electrophysiological and morphological parameters. Thus, the choice of which neurons participate in stimulus encoding may be determined largely by network connectivity rather than by cellular structure and function.

关键词： barrel cortex patch clamp somatosensory sparse coding two-photon imaging

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：