Journal Browser

► Journal Browser

Entropy-Based Methods in Time Series Identification and Classification with Applications to Engineering and Science

Special Issue Editors
Special Issue Information
Published Papers

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Complexity".

Deadline for manuscript submissions: 18 September 2024 | Viewed by 2180

Share This Special Issue

Special Issue Editor

Special Issue Information

Dear Colleagues,

Identification and classification of continuous and discrete time-series is an important area of research in engineering and science. Nowadays, the analyses of electrical, mechanical, biological, chemical, astrophysical and other nonlinear dynamical systems rely on quite complicated and sophisticated new methods and algorithms, including those originating in machine learning, parallel computing, bifurcation phenomena and statistics.

In this Special Issue, we aim to publish new results in computational aspects of time-series analysis in applied research areas. New entropy-based methods and algorithms of time-series identification and classification are particularly welcome using machine learning tools, bifurcation phenomena and parallel computing in engineering and science, for example, the nonlinear vibrating systems, EEG, EKG (and similar) time-series, fluid dynamics, memristive circuits and devices, etc. Analysis of chaotic time-series should focus on new phenomena, two and three parameter bifurcation diagrams (two and three parameters varying simultaneously) and the submitted work should be based on the concepts of entropy. The papers should clearly describe the novelty of the proposed analysis. Studies taking into account the randomness or measuring the disorder of the information being processed are particularly welcome. Reports on new or improved numerical algorithms and tests for chaos applied to oscillatory dynamical models in engineering and science will also be considered.

Dr. Wieslaw Marszalek
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (2 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

20 pages, 1228 KiB

Open AccessArticle

Machine Learning Classification of Event-Related Brain Potentials during a Visual Go/NoGo Task

by Anna Bryniarska, José A. Ramos and Mercedes Fernández

Entropy 2024, 26(3), 220; https://doi.org/10.3390/e26030220 - 29 Feb 2024

Viewed by 792

Abstract

Machine learning (ML) methods are increasingly being applied to analyze biological signals. For example, ML methods have been successfully applied to the human electroencephalogram (EEG) to classify neural signals as pathological or non-pathological and to predict working memory performance in healthy and psychiatric patients. ML approaches can quickly process large volumes of data to reveal patterns that may be missed by humans. This study investigated the accuracy of ML methods at classifying the brain’s electrical activity to cognitive events, i.e., event-related brain potentials (ERPs). ERPs are extracted from the ongoing EEG and represent electrical potentials in response to specific events. ERPs were evoked during a visual Go/NoGo task. The Go/NoGo task requires a button press on Go trials and response withholding on NoGo trials. NoGo trials elicit neural activity associated with inhibitory control processes. We compared the accuracy of six ML algorithms at classifying the ERPs associated with each trial type. The raw electrical signals were fed to all ML algorithms to build predictive models. The same raw data were then truncated in length and fitted to multiple dynamic state space models of order

n_{x}

using a continuous-time subspace-based system identification algorithm. The

4 n_{x}

numerator and denominator parameters of the transfer function of the state space model were then used as substitutes for the data. Dimensionality reduction simplifies classification, reduces noise, and may ultimately improve the predictive power of ML models. Our findings revealed that all ML methods correctly classified the electrical signal associated with each trial type with a high degree of accuracy, and accuracy remained high after parameterization was applied. We discuss the models and the usefulness of the parameterization. Full article

(This article belongs to the Special Issue Entropy-Based Methods in Time Series Identification and Classification with Applications to Engineering and Science)

► Show Figures

Figure 1

16 pages, 6178 KiB

Open AccessArticle

Cryptographically Secure PseudoRandom Bit Generator for Wearable Technology

by Michał Melosik, Mariusz Galan, Mariusz Naumowicz, Piotr Tylczyński and Scott Koziol

Entropy 2023, 25(7), 976; https://doi.org/10.3390/e25070976 - 25 Jun 2023

Viewed by 918

Abstract

This paper presents a prototype wearable Cryptographically Secure PseudoRandom Bit Generator CSPRBG (wearable CSPRBG). A vest prototype has been fabricated to which an evaluation board with a ZYBO (ZYnq BOard) Zynq Z-7010 has been mounted using tailoring technology. In this system, a seed generator and block cryptographic algorithms responsible for the generation of pseudo-random values were implemented. A microphone and an accelerometer recorded sound and acceleration during the use of the prototype vest, and these recordings were passed to the seed generator and used as entropy sources. Hardware implementations were made for several selected Block Cryptographic algorithms such as Advanced Encryption Standard (AES), Twofish and 3DES. The random binary values generated by the wearable CSPRBG were analyzed by National Institute of Standards and Technology (NIST) statistical tests as well as ENT tests to evaluate their randomness, depending on the configuration of the entropy sources used. The idea of possible development of the wearable CSPRBG as a System on Chip (SoC) solution is also presented. Full article

(This article belongs to the Special Issue Entropy-Based Methods in Time Series Identification and Classification with Applications to Engineering and Science)

► Show Figures

Journal Menu

Journal Browser

Entropy-Based Methods in Time Series Identification and Classification with Applications to Engineering and Science

Share This Special Issue

Special Issue Editor

Special Issue Information

Published Papers (2 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI