2,912 Hits in 2.4 sec

How to Identify Patterns of Citywide Dynamic Traffic at a Low Cost? An In-Depth Neural Network Approach with Digital Maps

Li Zhang, Ke Gong, Maozeng Xu, Aixing Li, Yuanxiang Dong, Yong Wang, Guang Li
2021 Complexity  
We propose a stacked convolutional autoencoder-based method to extract a low-dimension feature vector for each input. We compute and analyze the distances between vectors.  ...  The distance captured by our method can represent the evolution of different traffic conditions during the morning and evening peak hours.  ...  Parameters of the Stacked Convolutional Autoencoder. To achieve better training performance, we set the stacked convolutional autoencoder shown in Figure 3 .  ... 
doi:10.1155/2021/6648116 fatcat:eti5u5ljrfdqrajejouaqtaqfa

Evolutionary Hierarchical Sparse Extreme Learning Autoencoder Network for Object Recognition

Yujun Zeng, Lilin Qian, Junkai Ren
2018 Symmetry  
In this paper, a novel sparse autoencoder derived from ELM and differential evolution is proposed and integrated into a hierarchical hybrid autoencoder network to accomplish the end-to-end learning with  ...  When extended to the stacked autoencoder network, which is a typical symmetrical representation learning model architecture, ELM manages to realize hierarchical feature extraction and classification, which  ...  However, differential evolution was only applied to the evolutionary sparse ELM autoencoder, which was stacked at higher layers of the whole network for high-level feature extraction.  ... 
doi:10.3390/sym10100474 fatcat:bgmt5gtjonerrkynpynn5akq7q

No-reference image quality assessment using shearlet transform and stacked autoencoders

Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan, Chun-Ho Cheung, Kwok-Wai Cheung
2015 2015 IEEE International Symposium on Circuits and Systems (ISCAS)  
Then, stacked autoencoders are applied to exaggerate the discriminative parts of the primary features.  ...  The resulting algorithm, which we name SESANIA (ShEarlet and Stacked Autoencoders based Noreference Image quality Assessment), is tested on several databases (LIVE, Multiply Distorted LIVE and TID2008)  ...  A stacked autoencoder is a neural network consisting of multiple layers of sparse autoencoders in which the outputs of each layer are wired to the inputs of the successive layer.  ... 
doi:10.1109/iscas.2015.7168953 dblp:conf/iscas/LiPXFYCC15 fatcat:5l5swe4gmbcrfjgks7u4d7djuy

Detection of COVID-19 from Chest X-ray and CT Scan Images using Improved Stacked Sparse Autoencoder

Syahril Ramadhan Saufi, Muhd Danial Abu Hasan, Zair Asrar Ahmad, Mohd Salman Leong, Lim Meng Hee
2021 Pertanika journal of science & technology  
This radiology image is usually examined by the expert to detect the presence of COVID-19 symptom. In this study, the improved stacked sparse autoencoder is used to examine the radiology images.  ...  COVID-19 can be potentially detected by using Chest X-ray and computed tomography (CT) images, as these images contain essential information of lung infection.  ...  MATERIALS AND METHODS Stacked Sparse Autoencoder Architecture The stacked sparse autoencoder is built by stacking the sparse autoencoder with many numbers.  ... 
doi:10.47836/pjst.29.3.14 fatcat:73zbmp2jqnevbn7r4trqkz2cze

No-reference image quality assessment with shearlet transform and deep neural networks

Yuming Li, Lai-Man Po, Xuyuan Xu, Litong Feng, Fang Yuan, Chun-Ho Cheung, Kwok-Wai Cheung
2015 Neurocomputing  
Then, stacked autoencoders are applied as 'evolution process' to 'amplify' the primary features and make them more discriminative.  ...  The resulting algorithm, which we name SESANIA (ShEarlet and Stacked Autoencoders based Noreference Image quality Assessment) is tested on several database (LIVE, Multiply Distorted LIVE and TID2008) individually  ...  Acknowledgement The work described in this paper was substantially supported by a grant from the City University of Hong Kong, Kowloon, Hong Kong with Project number of 7004058.  ... 
doi:10.1016/j.neucom.2014.12.015 fatcat:gqjtnaadw5fojgyd6zfxax3ram

Discriminative Feature Learning with Constraints of Category and Temporal for Action Recognition [chapter]

Zhize Wu, Shouhong Wan, Peiquan Jin, Lihua Yue
2015 Lecture Notes in Computer Science  
Representations of depth maps are learned and reconstructed using a stacked denoising autoencoder.  ...  Recently, with the availability of the depth cameras, a lot of studies of human action recognition have been conducted on the depth sequences.  ...  We use the output of the last autoencoder as the output for the stacked architecture. Fig. 3 . Fine tuning of the stacking architecture.  ... 
doi:10.1007/978-3-319-21963-9_16 fatcat:odgieaepofe6lczfsrxygvg24y

Graphical classification of DNA sequences of HLA alleles by deep learning

Jun Miyake, Yuhei Kaneshita, Satoshi Asatani, Seiichi Tagawa, Hirohiko Niioka, Takashi Hirano
2018 Human Cell  
Alleles of human leukocyte antigen (HLA)-A DNAs are classified and expressed graphically by using artificial intelligence "Deep Learning (Stacked autoencoder)".  ...  The two-dimensional plot of HLA-A DNAs gives a clear outlook for characterizing the various alleles.  ...  of Japan and by a research support of Osaka University.  ... 
doi:10.1007/s13577-017-0194-6 pmid:29327117 pmcid:PMC5852191 fatcat:r6logiap7bgpxgqihmy7dzh7kq

Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans

Jie-Zhi Cheng, Dong Ni, Yi-Hong Chou, Jing Qin, Chui-Mei Tiu, Yeun-Chung Chang, Chiun-Sheng Huang, Dinggang Shen, Chung-Ming Chen
2016 Scientific Reports  
Technical explanation of SDAE method The stacked autoencoder (SDAE) architecture can be constructed by the basic building block of autoencoder.  ...  An autoencoder is a two layered neural network that attempts to seek the representative patterns (mostly sparse), denoted as , of the original data , at the hidden (second) layer with the deterministic  ...  Technical explanation of SDAE method The stacked autoencoder (SDAE) architecture can be constructed by the basic building block of autoencoder.  ... 
doi:10.1038/srep24454 pmid:27079888 pmcid:PMC4832199 fatcat:l7gevkmohrdkhlqabmwi6n4yyy

An evolutionary autoencoder for dynamic community detection

Zhen Wang, Chunyu Wang, Chao Gao, Xuelong Li, Xianghua Li
2020 Science China Information Sciences  
In this paper, we propose a semi-supervised algorithm (sE-Autoencoder) to overcome the effects of nonlinear property on the low-dimensional representation.  ...  However, such reconstruction does not address the nonlinear characteristics of networks.  ...  More specifically, three stacked autoencoders are applied because existing studies have proved that three stacked autoencoders can reach well effectiveness in the static community detection [25] .  ... 
doi:10.1007/s11432-020-2827-9 fatcat:io44rpasn5fypgqebitcmplmda

Exploring order parameters and dynamic processes in disordered systems via variational autoencoders [article]

Sergei V. Kalinin, Ondrej Dyck, Stephen Jesse, Maxim Ziatdinov
2021 arXiv   pre-print
extension of the variational autoencoder applied to semantically segmented atom-resolved data seeking the most effective reduced representation for the system that still contains the maximum amount of  ...  This approach allowed us to explore the dynamic evolution of electron beam-induced processes in a silicon-doped graphene system, but it can be also applied for a much broader range of atomic-scale and  ...  An image stack was then acquired capturing the continued evolution of the four holes under the 100 kV e-beam.  ... 
arXiv:2006.10267v2 fatcat:skmrjsmhtvblvjxcclblrqbkma

Advanced texture analysis and classification methods for the automatic diagnosis of the Hepatocellular Carcinoma

2019 Applied Medical Informatics  
Deep learning techniques such as Stacked Denoising Autoencoders (SAE) and Convolutional Neural Networks (CNN) were also experimented [3].  ...  Thus, we perform the characterization and supervised recognition of HCC, as well as the unsupervised discovery of the HCC evolution phases.  ...  Deep learning techniques such as Stacked Denoising Autoencoders (SAE) and Convolutional Neural Networks (CNN) were also experimented [3] .  ... 
doaj:e7cc07c1da5a47dfae317b52f80d14d2 fatcat:353qkfnuabcevor63mgdwufnli

Temporal Autoencoding Restricted Boltzmann Machine [article]

Chris Häusler, Alex Susemihl
2012 arXiv   pre-print
A lot of this work has focused on the development of Gabor-like filters learned when enforcing sparsity constraints on a natural image dataset.  ...  Here we investigate exactly this problem in established temporal deep learning algorithms as well as a new learning paradigm suggested here, the Temporal Autoencoding Restricted Boltzmann Machine (TARBM  ...  Martin Nawrot of the Freie Universität Berlin for his enthusiastic support and invaluable feedback.  ... 
arXiv:1210.8353v1 fatcat:is5upswkrfcudaxy3ehv2ooqlq

Stacked Autoencoder based Feature Compression for Optimal Classification of Parkinson Disease from Vocal Feature Vectors using Immune Algorithms

K. Kamalakannan, G.Anandharaj
2021 International Journal of Advanced Computer Science and Applications  
The selected features will further be extracted using the Stacked Autoencoder technique to improve and increase the accuracy rate and quality of classification with reduced run time.  ...  Machine Learning is an integral part of artificial intelligence it takes huge data as input and train by making use of existing algorithms to understand the pattern of the data.  ...  The results of AIRS -Stacked Autoencoder, AIRS 2 -Stacked Autoencoder, and the proposed AIRS Parallel -Stacked Autoencoder were presented as the Table V for comparison.  ... 
doi:10.14569/ijacsa.2021.0120558 fatcat:uny3wkrhtzgttmvouind73mn6m

Building Extraction Based on an Optimized Stacked Sparse Autoencoder of Structure and Training Samples Using LIDAR DSM and Optical Images

Yiming Yan, Zhichao Tan, Nan Su, Chunhui Zhao
2017 Sensors  
In this paper, a building extraction method is proposed based on a stacked sparse autoencoder with an optimized structure and training samples.  ...  Since stacked sparse autoencoder (SSAE) neural network can learn the essential characteristics of the data in depth, SSAE was employed to extract buildings from the combined DSM data and optical image.  ...  Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/s17091957 pmid:28837118 pmcid:PMC5621110 fatcat:icft4yrtobfatfdp3f2sj5w6ru

Proactive Critical Energy Infrastructure Protection via Deep Feature Learning

Konstantina Fotiadou, Terpsichori Helen Velivassaki, Artemis Voulkidis, Dimitrios Skias, Corrado De Santis, Theodore Zahariadis
2020 Energies  
Specifically, we propose the two challenging architectures based on learning deep features, namely—Long Short Term Memory-Stacked Autoencoders (LSTM-SAE), and Convolutional Neural Network (CNN-SAE), for  ...  This paper focuses on the challenging application of wind turbine (WT) monitoring.  ...  An extension of the aforementioned analysis is the so-called Stacked Sparse autoencoders (SSAE) scheme in which multiple shallow SAE architectures are stacked.  ... 
doi:10.3390/en13102622 fatcat:6m5znvk3hbgmdotlzqwkyqw2sy
« Previous Showing results 1 — 15 out of 2,912 results