Filters








85,308 Hits in 5.8 sec

Learning Signaling Network Structures with Sparsely Distributed Data

Karen Sachs, Solomon Itani, Jennifer Carlisle, Garry P. Nolan, Dana Pe'er, Douglas A. Lauffenburger
2009 Journal of Computational Biology  
To address this problem, we present here an algorithm that enables structure learning for sparsely distributed data, allowing structure learning beyond the measurement technology's upper dimensionality  ...  The single cell nature of the data ensures a very large dataset size, providing a statistically robust dataset for structure learning.  ...  simultaneously, resulting in sparsely distributed data.  ... 
doi:10.1089/cmb.2008.07tt pmid:19193145 pmcid:PMC3198894 fatcat:w3j3xv2o4ffijm7iwxpru3nr7u

Research on the Primary Features of the Internet of Things System and the Corresponding Data Communication Characteristics based on Sparse Coding and Joint Deep Neural Network

Jianping PAN, Wenzhun HUANG, Shanwen ZHANG
2016 International Journal of Future Generation Communication and Networking  
With the advances of the deep neural network, we analyze the topology of the system network structure and extract the pattern features and characteristics to make the signal transmission process more quickly  ...  To enhance the robustness and efficiency of the current IOT systems, we adopt the sparse coded dictionary learning theory to detect the size of the data and optimize the compressive sensing technique to  ...  Deep learning research how to use multilayer structure automatic learning and potential distribution model data and it reduced the number of sample data and labeling requirements, through the training  ... 
doi:10.14257/ijfgcn.2016.9.10.11 fatcat:s65rrtxzqndwrlcvl35u5igix4

A Deep Neural Network Architecture Using Dimensionality Reduction with Sparse Matrices [chapter]

Wataru Matsumoto, Manabu Hagiwara, Petros T. Boufounos, Kunihiko Fukushima, Toshisada Mariyama, Zhao Xiongxin
2016 Lecture Notes in Computer Science  
Abstract We present a new deep neural network architecture, motivated by sparse random matrix theory that uses a low-complexity embedding through a sparse matrix instead of a conventional stacked autoencoder  ...  We present a new deep neural network architecture, motivated by sparse random matrix theory that uses a low-complexity embedding through a sparse matrix instead of a conventional stacked autoencoder.  ...  Section 4 concludes the document. 2 Deep neural network with sparse construction To establish notation, we first define a deep neural network structure. We use the N-dimensional vector = ! , !  ... 
doi:10.1007/978-3-319-46681-1_48 fatcat:e3e7fkwkrvgadliavosmsazmka

Research on mechanical vibration monitoring based on wireless sensor network and sparse Bayes

Xinjun Lei, Yunxin Wu
2020 EURASIP Journal on Wireless Communications and Networking  
The traditional wired monitoring technology faces problems such as high-frequency signal pickup and high-precision data collection.  ...  Therefore, this paper proposes optimization techniques for mechanical vibration monitoring and signal processing based on wireless sensor networks.  ...  Comparison of sparse Bayesian learning and other algorithms In the previous chapter, in addition to introducing the concept of block sparse structure, several reconstruction algorithms using signal block  ... 
doi:10.1186/s13638-020-01836-9 fatcat:tjbcuqeg6za4ro5hprw6idaemq

Learning Structures for Deep Neural Networks [article]

Jinhui Yuan and Fei Pan and Chunting Zhou and Tao Qin and Tie-Yan Liu
2021 arXiv   pre-print
Then as an implementation of the principle, we show that sparse coding can effectively maximize the entropy of the output signals, and accordingly design an algorithm based on global group sparse coding  ...  neuroscience, to guide the procedure of structure learning without label information.  ...  without fine-tuning; (3), initializing the network parameter with pre-trained dictionary and fine-tuned with BP; (4), restricting the network structure with learned mask and randomly initializing the  ... 
arXiv:2105.13905v1 fatcat:vfdwvno575ay7gpfv2u7phj3pm

Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms [article]

Yanna Bai, Wei Chen, Jie Chen, Weisi Guo
2020 arXiv   pre-print
We review how deep learning methods are used in solving different linear inverse problems, and explore the structured neural network architectures that incorporate knowledge used in traditional methods  ...  Nowadays, the rapid development of deep learning provides a fresh perspective for solving the linear inverse problem, which has various well-designed network architectures results in state-of-the-art performance  ...  In [108], Zhang et al. construct their training data set with different noise distributions and train a single NN to deal with multiple noise distributions.  ... 
arXiv:2007.13290v2 fatcat:kqoerts77nftbl32fctx3za2me

End-to-End SAR Deep Learning Imaging Method Based on Sparse Optimization

Siyuan Zhao, Jiacheng Ni, Jia Liang, Shichao Xiong, Ying Luo
2021 Remote Sensing  
soft threshold algorithm (ISTA) sparse algorithm in the two-dimensional data domain, and then reconstructs the observation scene through the superposition and expansion of the multi-layer network.  ...  Based on the existing SAR sparse imaging algorithm, the SAR imaging model is first rewritten to the SAR complex signal form based on the real-value model.  ...  Data Availability Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs13214429 fatcat:6h2aury7j5h3vnl54qz4ym5xii

A Dictionary Learning Approach for Signal Sampling in Task-Based fMRI for Reduction of Big Data

Bao Ge, Xiang Li, Xi Jiang, Yifei Sun, Tianming Liu
2018 Frontiers in Neuroinformatics  
In this paper, we present a structurally guided fMRI signal sampling method for dictionary learning and sparse representation of task fMRI data.  ...  To address this problem, we propose a signal sampling approach for significant fMRI data reduction before performing structurally-guided dictionary learning and sparse coding of whole brain's fMRI data  ... 
doi:10.3389/fninf.2018.00017 pmid:29706880 pmcid:PMC5906552 fatcat:vivqlf3qcrdjde6ujo7hfq6e7m

Learned-SBL: A Deep Learning Architecture for Sparse Signal Recovery [article]

Rubin Jose Peter, Chandra R. Murthy
2019 arXiv   pre-print
In this paper, we present a computationally efficient sparse signal recovery scheme using Deep Neural Networks (DNN).  ...  The architecture of the introduced neural network is inspired from sparse Bayesian learning (SBL) and named as Learned-SBL (L-SBL).  ...  If the training data contains block sparse vectors, the L-SBL becomes a block sparse recovery algorithm. That is, L-SBL can learn any underlying structure in the training dataset.  ... 
arXiv:1909.08185v1 fatcat:ngeqfk464rct3eyuwo4b5cc47q

A Method of Rolling Bearing Fault Diagnose Based on Double Sparse Dictionary and Deep Belief Network

Junfeng Guo, Pengfei Zheng
2020 IEEE Access  
Firstly, each type of fault signal is trained according to the double sparse dictionary learning algorithm and the corresponding double sparse subdictionaries is obtained.  ...  A novel method based on the double sparse dictionary model joint with Deep Belief Network (DBN) is proposed for the fault diagnosis of rolling bearing.  ...  of the original vibration signal under the double sparse dictionary is used as the data for deep neural network learning in proposed method.  ... 
doi:10.1109/access.2020.3003909 fatcat:syv3oz7q6jdhbi2aww6rsh63li

Power Quality Data Compression and Disturbances Recognition Based on Deep CS-BiLSTM Algorithm With Cloud-Edge Collaboration

Xin Xia, Chuanliang He, Yingjie Lv, Bo Zhang, ShouZhi Wang, Chen Chen, Haipeng Chen
2022 Frontiers in Energy Research  
In terms of data transmission and feature extraction, the dictionary atoms and measurements uploaded at the edge are analyzed in the cloud by building a cloud-edge collaborative framework with distributed  ...  Finally, the simulation analysis of 10 common power quality disturbance signals and 13 complex composite disturbance signals with random noise shows that the proposed method solves the problem of inadequate  ...  AUTHOR CONTRIBUTIONS XX: Drafting the manuscript, CH: experimental analysis, HC: Review and Supervision, YL: Methodology and Formal analysis, BZ: Conceptualization and Revised, SW: Data Curation and Resources  ... 
doi:10.3389/fenrg.2022.874351 fatcat:eub5sunpnjgmdpnmpiant5eu2m

Channel Estimation for Massive MIMO Communication System Using Deep Neural Network [article]

Zohreh Mohades, Vahid TabaTabaVakili
2018 arXiv   pre-print
In this paper we consider the problem of sparse signal recovery in Multiple Measurement Vectors (MMVs) case.  ...  Afterwards, in order to reconstruct sparse vectors corresponding to this new set of equations, a four-layer feed-forward neural network is applied.  ...  The proposed methods, by using deep neural network, learn the structure of sparse vectors and then, applying such learned networks, reconstruct the original sparse signals.  ... 
arXiv:1806.09126v1 fatcat:ufjb236msjealchbvvx5riqwve

Deep Feature Autoextraction Method for Intrapulse Data of Radar Emitter Signal

Shiqiang Wang, Caiyun Gao, Chang Luo, Huiyong Zeng, Guimei Zheng, Qin Zhang, Juan Bai, Binfeng Zong
2021 Mobile Information Systems  
Concerned with the problems that the extracted features are the absence of objectivity for radar emitter signal intrapulse data because of relying on priori knowledge, a novel method is proposed.  ...  Second, by optimizing the sparse autoencoder and confirming the training scheme, intrapulse deep features are autoextracted with encoder layer parameters.  ...  When the intrapulse data are input into the network, the network will automatically learn to obtain the various levels of the input radar emitter signal, that means the feature expression.  ... 
doi:10.1155/2021/6870938 doaj:f0a99bb175644e41aa3257b7af60ab34 fatcat:vd4xfdq26rgl5lksg65nibideq

A Cloud Computing Fault Detection Method Based on Deep Learning

Weipeng Gao, Youchan Zhu
2017 Journal of Computer and Communications  
Therefore, a fault detection method based on depth learning is proposed. An auto-encoder with sparse denoising is used to construct a parallel structure network.  ...  It can automatically learn and extract the fault data characteristics and realize fault detection through deep learning.  ...  In recent years, with the idea of deep learning, depth learning can use a large number of unlabeled data to achieve unsupervised automatic learning [13] , through data feature extraction, and then can  ... 
doi:10.4236/jcc.2017.512003 fatcat:uonygekeojdavn7lz2igrm5jym

Distributed Graph Learning with Smooth Data Priors [article]

Isabela Cunha Maia Nobre, Mireille El Gheche, Pascal Frossard
2021 arXiv   pre-print
It also scales better in communication costs with the increase of the network size, especially for sparse networks.  ...  Graph learning is generally performed centrally with a full knowledge of the graph signals, namely the data that lives on the graph nodes.  ...  We also show that sparse networks wireless sensor network, distributed optimization benefit more from a distributed solution than dense ones.  ... 
arXiv:2112.05887v1 fatcat:w2lkrp6nmzfkjodg3pujtpxviu
« Previous Showing results 1 — 15 out of 85,308 results