Fiber Nonlinearity Equalization with Multi-Label Deep Learning Scalable to High-Order DP-QAM

2018 ◽  
Author(s):  
Toshiaki Koike-Akino ◽  
David S. Millar ◽  
Kieran Parsons ◽  
Keisuke Kojima
Keyword(s):  
Deep Learning ◽  
High Order ◽  
Fiber Nonlinearity

A new method to predict anomaly in brain network based on graph deep learning

2020 ◽  
Vol 31 (6) ◽  
pp. 681-689
Author(s):  
Jalal Mirakhorli ◽  
Hamidreza Amindavar ◽  
Mojgan Mirakhorli
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Brain Plasticity ◽  
Brain Network ◽  
High Order ◽  
Brain Diseases ◽  
Simultaneous Occurrence ◽  
Generative Adversarial Network ◽  
The Brain ◽  
Brain Connections

AbstractFunctional magnetic resonance imaging a neuroimaging technique which is used in brain disorders and dysfunction studies, has been improved in recent years by mapping the topology of the brain connections, named connectopic mapping. Based on the fact that healthy and unhealthy brain regions and functions differ slightly, studying the complex topology of the functional and structural networks in the human brain is too complicated considering the growth of evaluation measures. One of the applications of irregular graph deep learning is to analyze the human cognitive functions related to the gene expression and related distributed spatial patterns. Since a variety of brain solutions can be dynamically held in the neuronal networks of the brain with different activity patterns and functional connectivity, both node-centric and graph-centric tasks are involved in this application. In this study, we used an individual generative model and high order graph analysis for the region of interest recognition areas of the brain with abnormal connection during performing certain tasks and resting-state or decompose irregular observations. Accordingly, a high order framework of Variational Graph Autoencoder with a Gaussian distributer was proposed in the paper to analyze the functional data in brain imaging studies in which Generative Adversarial Network is employed for optimizing the latent space in the process of learning strong non-rigid graphs among large scale data. Furthermore, the possible modes of correlations were distinguished in abnormal brain connections. Our goal was to find the degree of correlation between the affected regions and their simultaneous occurrence over time. We can take advantage of this to diagnose brain diseases or show the ability of the nervous system to modify brain topology at all angles and brain plasticity according to input stimuli. In this study, we particularly focused on Alzheimer’s disease.

scholarly journals A High-Order CFS Algorithm for Clustering Big Data

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Fanyu Bu ◽  
Zhikui Chen ◽  
Peng Li ◽  
Tong Tang ◽  
Ying Zhang
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Clustering Algorithm ◽  
Big Data Analytics ◽  
Learning Model ◽  
Heterogeneous Data ◽  
High Order ◽  
Tensor Model ◽  
Industrial Internet ◽  
Deep Learning Model

With the development of Internet of Everything such as Internet of Things, Internet of People, and Industrial Internet, big data is being generated. Clustering is a widely used technique for big data analytics and mining. However, most of current algorithms are not effective to cluster heterogeneous data which is prevalent in big data. In this paper, we propose a high-order CFS algorithm (HOCFS) to cluster heterogeneous data by combining the CFS clustering algorithm and the dropout deep learning model, whose functionality rests on three pillars: (i) an adaptive dropout deep learning model to learn features from each type of data, (ii) a feature tensor model to capture the correlations of heterogeneous data, and (iii) a tensor distance-based high-order CFS algorithm to cluster heterogeneous data. Furthermore, we verify our proposed algorithm on different datasets, by comparison with other two clustering schemes, that is, HOPCM and CFS. Results confirm the effectiveness of the proposed algorithm in clustering heterogeneous data.

scholarly journals Deep Learning in Digital Modulation Recognition Using High Order Cumulants

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 63760-63766 ◽  
Author(s):  
Wenwu Xie ◽  
Sheng Hu ◽  
Chao Yu ◽  
Peng Zhu ◽  
Xin Peng ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Order ◽  
Modulation Recognition ◽  
Digital Modulation ◽  
High Order Cumulants

scholarly journals Deep Learning-Based Adaptive Neural-Fuzzy Structure Scheme for Bearing Fault Pattern Recognition and Crack Size Identification

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2102
Author(s):  
Farzin Piltan ◽  
Bach Phi Duong ◽  
Jong-Myon Kim
Keyword(s):  
Pattern Recognition ◽  
Deep Learning ◽  
Variable Structure ◽  
Crack Size ◽  
High Order ◽  
Support Vector ◽  
Signal Estimation ◽  
Vector Autoregressive ◽  
Order Variable ◽  
Neural Fuzzy

Bearings are complex components with onlinear behavior that are used to mitigate the effects of inertia. These components are used in various systems, including motors. Data analysis and condition monitoring of the systems are important methods for bearing fault diagnosis. Therefore, a deep learning-based adaptive neural-fuzzy structure technique via a support vector autoregressive-Laguerre model is presented in this study. The proposed scheme has three main steps. First, the support vector autoregressive-Laguerre is introduced to approximate the vibration signal under normal conditions and extract the state-space equation. After signal modeling, an adaptive neural-fuzzy structure observer is designed using a combination of high-order variable structure techniques, the support vector autoregressive-Laguerre model, and adaptive neural-fuzzy inference mechanism for normal and abnormal signal estimation. The adaptive neural-fuzzy structure observer is the main part of this work because, based on the difference between signal estimation accuracy, it can be used to identify faults in the bearings. Next, the residual signals are generated, and the signal conditions are detected and identified using a convolution neural network (CNN) algorithm. The effectiveness of the proposed deep learning-based adaptive neural-fuzzy structure technique by support vector autoregressive-Laguerre model was analyzed using the Case Western Reverse University (CWRU) bearing vibration dataset. The proposed scheme is compared to five state-of-the-art techniques. The proposed algorithm improved the average pattern recognition and crack size identification accuracy by 1.99%, 3.84%, 15.75%, 5.87%, 30.14%, and 35.29% compared to the combination of the high-order variable structure technique with the support vector autoregressive-Laguerre model and CNN, the combination of the variable structure technique with the support vector autoregressive-Laguerre model and CNN, the combination of RAW signal and CNN, the combination of the adaptive neural-fuzzy structure technique with the support vector autoregressive-Laguerre model and support vector machine (SVM), the combination of the high-order variable structure technique with the support vector autoregressive-Laguerre model and SVM, and the combination of the variable structure technique with the support vector autoregressive-Laguerre model and SVM, respectively.

scholarly journals Proposing Algorithm Using YOLOV4 and VGG-16 for Smart-Education

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Phat Nguyen Huu ◽  
Khang Doan Xuan
Keyword(s):  
Deep Learning ◽  
High Order ◽  
Second Step ◽  
Systems Of Equations ◽  
Web Based ◽  
Solution Methods ◽  
Smart Education

In this paper, we propose an algorithm to identify and solve systems of high-order equations. We rely on traditional solution methods to build algorithms to solve automated equations based on deep learning. The proposal method includes two main steps. In the first step, we use YOLOV4 (Kumar et al. 2020; Canu, 2020) to recognize equations and letters associated with the VGG-16 network (Simonyan and Zisserman, 2015) to classify them. We then used the SymPy model to solve the equations in the second step. Data are images of systems of equations that are typed and designed by ourselves or handwritten from other sources. Besides, we also built a web-based application that helps users select an image from their devices. The results show that the proposed algorithm is set out with 95% accuracy for smart-education applications.

Corse-to-Fine Road Extraction Based on Local Dirichlet Mixture Models and Multiscale-High-Order Deep Learning

2020 ◽  
Vol 21 (10) ◽  
pp. 4283-4293 ◽  
Author(s):  
Ziyi Chen ◽  
Wentao Fan ◽  
Bineng Zhong ◽  
Jonathan Li ◽  
Jixiang Du ◽  
...  
Keyword(s):  
Deep Learning ◽  
Mixture Models ◽  
High Order ◽  
Road Extraction ◽  
Dirichlet Mixture
Sign in / Sign up

Export Citation Format

Share Document