Time Series Analysis Based on Modular Architectures of Neural Networks

Yarushev, Sergey; Averkin, Alexey

doi:10.1016/j.procs.2018.01.085

Cited by 9 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a second compositional axis, the design and organization of a space influence the perception of clarity and mental dissipation by using, for example, unobstructed lines of sight that allow the creation of sensations such as order and control, while a more chaotic space packed with items can create feelings of confusion and disorientation [9].…”

Section: 2mentioning

confidence: 99%

Neuroarchitecture applied to the study of psychological conditions within physical rehabilitation spaces

Pazmiño,

Pérez Mato,

Flores Beltrán

2023

Eximia

View full text Add to dashboard Cite

Neuroarchitecture as a multidisciplinary study science has been influenced in Ecuador at the case study level to buildings without spaces for external interaction with nature or internal spatial development, which has caused poor treatment. The objective of this scientific article is the design of neuroarchitecture parameters applied to architectural and spatial design to improve treatment in rehabilitation spaces. The considerations will be evaluated under a quantitative approach methodology of the architectural spaces and the user's perception through the decision-making scheme of the Kepner and Tregoe Method that analyzed the situation, evaluated results and established potential risks within the study. In conclusion, the characterization of the architectural spaces by shape and color contributed to the perception of tranquility within the space, the contact with the green areas improved the cognitive and sensory conditions of the users, integrating better with their environment, while the design of the Semi-open spaces and open spaces generate greater confidence and tranquility for comprehensive socialization, so it can be determined that the neuroarchitecture focused on the conditional evaluation and decision-making of the user improves the satisfactory treatment of patients by 90%.

show abstract

Section: 2mentioning

confidence: 99%

Neuroarchitecture applied to the study of psychological conditions within physical rehabilitation spaces

Pazmiño,

Pérez Mato,

Flores Beltrán

2023

Eximia

View full text Add to dashboard Cite

show abstract

“…Increased risk of failure: Because monolithic architectures are difficult to understand and modify, there is an increased risk of failure when making changes to the architecture. Hence, fixing it can be computationally costly and time-consuming [35].…”

mentioning

confidence: 99%

Predicting Forex Currency Fluctuations Using a Novel Bio-Inspired Modular Neural Network

Bormpotsis,

Sedky,

Patel

2023

BDCC

View full text Add to dashboard Cite

In the realm of foreign exchange (Forex) market predictions, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been commonly employed. However, these models often exhibit instability due to vulnerability to data perturbations attributed to their monolithic architecture. Hence, this study proposes a novel neuroscience-informed modular network that harnesses closing prices and sentiments from Yahoo Finance and Twitter APIs. Compared to monolithic methods, the objective is to advance the effectiveness of predicting price fluctuations in Euro to British Pound Sterling (EUR/GBP). The proposed model offers a unique methodology based on a reinvigorated modular CNN, replacing pooling layers with orthogonal kernel initialisation RNNs coupled with Monte Carlo Dropout (MCoRNNMCD). It integrates two pivotal modules: a convolutional simple RNN and a convolutional Gated Recurrent Unit (GRU). These modules incorporate orthogonal kernel initialisation and Monte Carlo Dropout techniques to mitigate overfitting, assessing each module’s uncertainty. The synthesis of these parallel feature extraction modules culminates in a three-layer Artificial Neural Network (ANN) decision-making module. Established on objective metrics like the Mean Square Error (MSE), rigorous evaluation underscores the proposed MCoRNNMCD–ANN’s exceptional performance. MCoRNNMCD–ANN surpasses single CNNs, LSTMs, GRUs, and the state-of-the-art hybrid BiCuDNNLSTM, CLSTM, CNN–LSTM, and LSTM–GRU in predicting hourly EUR/GBP closing price fluctuations.

show abstract

“…Nevertheless, on the global level of analysis, Bitcoin, Ethereum and the whole cryptocurrency market has a potential of the deeper penetration into most spheres of our life. Using the calculations and statistical data from the research paper of Ryerson University specialists (Yarushev & Averkin, 2018;Eldyaeva, Yarnykh, Lebedinskaya, Kuzin, & Kovanova, 2018;Romanov, Moskovoy, & Onokhova, 2014), making simplified own calculations, the conclusion can be made: the world distribution as a payment system is the major factor of Bitcoin development as already the most popular cryptocurrency in the world (according to Table 01). However, Ethereum is the leader in terms of developing cryptotechnologies and creating financial (and also not financial) technologies, because initially Ethereum and Bitcoin have different goals and potential ways of development in the global financial market (according to Table 02).…”

mentioning

confidence: 99%

Prospects For The Development Of Cryptocurrency In Russia. From Bitcoin To Ethereum

Grigorev

Timofeev²,

Lebedinskaya³

et al. 2019

The European Proceedings of Social and Behavioural Sciences

View full text Add to dashboard Cite

show abstract

Time Series Analysis Based on Modular Architectures of Neural Networks

Cited by 9 publications

References 6 publications

Neuroarchitecture applied to the study of psychological conditions within physical rehabilitation spaces

Neuroarchitecture applied to the study of psychological conditions within physical rehabilitation spaces

Predicting Forex Currency Fluctuations Using a Novel Bio-Inspired Modular Neural Network

Prospects For The Development Of Cryptocurrency In Russia. From Bitcoin To Ethereum

Contact Info

Product

Resources

About