Improving graph neural network via complex-network-based anchor structure

2021 ◽  
pp. 107528
Author(s):  
Lijun Dong ◽  
Hong Yao ◽  
Dan Li ◽  
Yi Wang ◽  
Shengwen Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Complex Network ◽  
Anchor Structure

scholarly journals Atrial Fibrillation Detection by the Combination of Recurrence Complex Network and Convolution Neural Network

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Xiaoling Wei ◽  
Jimin Li ◽  
Chenghao Zhang ◽  
Ming Liu ◽  
Peng Xiong ◽  
...  
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Complex Network ◽  
Individual Variation ◽  
Deep Neural Network ◽  
Detection Algorithm ◽  
Convolution Neural Network ◽  
Electrocardiogram Signal ◽  
Sensitivity Specificity ◽  
Atrial Fibrillation Detection

In this paper, R wave peak interval independent atrial fibrillation detection algorithm is proposed based on the analysis of the synchronization feature of the electrocardiogram signal by a deep neural network. Firstly, the synchronization feature of each heartbeat of the electrocardiogram signal is constructed by a Recurrence Complex Network. Then, a convolution neural network is used to detect atrial fibrillation by analyzing the eigenvalues of the Recurrence Complex Network. Finally, a voting algorithm is developed to improve the performance of the beat-wise atrial fibrillation detection. The MIT-BIH atrial fibrillation database is used to evaluate the performance of the proposed method. Experimental results show that the sensitivity, specificity, and accuracy of the algorithm can achieve 94.28%, 94.91%, and 94.59%, respectively. Remarkably, the proposed method was more effective than the traditional algorithms to the problem of individual variation in the atrial fibrillation detection.

scholarly journals Neural Network Embedding of Functional Microconnectome.

2022 ◽  
Author(s):  
Arata Shirakami ◽  
Takeshi Hase ◽  
Yuki Yamaguchi ◽  
Masanori Shimono
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Complex Network ◽  
Second Step ◽  
Network System ◽  
Network Embedding ◽  
Neural Network System ◽  
Network Patterns ◽  
Network Metrics ◽  
Electrical Activities

Abstract Our brain works as a vast and complex network system. We need to compress the networks to extract simple principles of network patterns and interpret these paradigms to better comprehend their complexities. This study treats this simplification process using a two-step analysis of topological patterns of functional connectivities that were produced from electrical activities of ~1000 neurons from acute slices of mouse brains [Kajiwara et al. 2021] As the first step, we trained an artificial neural network system called neural network embedding (NNE) and automatically compressed the functional connectivities. As the second step, we widely compared the compressed features with 15 representative network metrics, having clear interpretations, including not only common metrics, such as centralities clusters and modules but also newly developed network metrics. The result demonstrates not only the fact that the newly developed network metrics could complementarily explain the features of what was compressed by the NNE method but was previously relatively hard to explain using common metrics such as hubs, clusters and communities. This NNE method surpasses the limitations of commonly used human-made metrics but also provides the possibility that recognizing our own limitations drives us to extend interpretable targets by developing new network metrics.

Predictive analytics of the copper spot price by utilizing complex network and artificial neural network techniques

2019 ◽  
Vol 63 ◽  
pp. 101414 ◽  
Author(s):  
Chao Wang ◽  
Xinyi Zhang ◽  
Minggang Wang ◽  
Ming K. Lim ◽  
Pezhman Ghadimi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Complex Network ◽  
Predictive Analytics ◽  
Spot Price ◽  
Artificial Neural

Complexities’ day-to-day dynamic evolution analysis and prediction for a Didi taxi trip network based on complex network theory

2018 ◽  
Vol 32 (09) ◽  
pp. 1850062 ◽  
Author(s):  
Lin Zhang ◽  
Jian Lu ◽  
Jialin Zhou ◽  
Jinqing Zhu ◽  
Yunxuan Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Complex Network ◽  
Bp Neural Network ◽  
Network Theory ◽  
Mobile App ◽  
Dynamic Evolution ◽  
Training Set ◽  
Management Level ◽  
Complex Network Theory ◽  
Evolution Analysis

Didi Dache is the most popular taxi order mobile app in China, which provides online taxi-hailing service. The obtained big database from this app could be used to analyze the complexities’ day-to-day dynamic evolution of Didi taxi trip network (DTTN) from the level of complex network dynamics. First, this paper proposes the data cleaning and modeling methods for expressing Nanjing’s DTTN as a complex network. Second, the three consecutive weeks’ data are cleaned to establish 21 DTTNs based on the proposed big data processing technology. Then, multiple topology measures that characterize the complexities’ day-to-day dynamic evolution of these networks are provided. Third, these measures of 21 DTTNs are calculated and subsequently explained with actual implications. They are used as a training set for modeling the BP neural network which is designed for predicting DTTN complexities evolution. Finally, the reliability of the designed BP neural network is verified by comparing with the actual data and the results obtained from ARIMA method simultaneously. Because network complexities are the basis for modeling cascading failures and conducting link prediction in complex system, this proposed research framework not only provides a novel perspective for analyzing DTTN from the level of system aggregated behavior, but can also be used to improve the DTTN management level.

Sign in / Sign up

Export Citation Format

Share Document