Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution

This study presents a differential evolution (DE)-based optimization approach for fractional-order convolutional neural networks (FOCNNs) aimed at enhancing the accuracy of groove classification in music. Groove, an essential element in music perception, is typically influenced by rhythmic patterns...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiangang Chen, Pei Su, Daxin Li, Junbo Han, Gaoquan Zhou, Donghui Tang
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Fractal and Fractional
Subjects:
Online Access:https://www.mdpi.com/2504-3110/8/11/616
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153537516470272
author Jiangang Chen
Pei Su
Daxin Li
Junbo Han
Gaoquan Zhou
Donghui Tang
author_facet Jiangang Chen
Pei Su
Daxin Li
Junbo Han
Gaoquan Zhou
Donghui Tang
author_sort Jiangang Chen
collection DOAJ
description This study presents a differential evolution (DE)-based optimization approach for fractional-order convolutional neural networks (FOCNNs) aimed at enhancing the accuracy of groove classification in music. Groove, an essential element in music perception, is typically influenced by rhythmic patterns and acoustic features. While FOCNNs offer a promising method for capturing these subtleties through fractional-order derivatives, they face challenges in efficiently converging to optimal parameters. To address this, DE is applied to optimize the initial weights and biases of FOCNNs, leveraging its robustness and ability to explore a broad solution space. The proposed DE-FOCNN was evaluated on the Janata dataset, which includes pre-rated music tracks. Comparative experiments across various fractional-order values demonstrated that DE-FOCNN achieved superior performance in terms of higher test accuracy and reduced overfitting compared to a standard FOCNN. Specifically, DE-FOCNN showed optimal performance at fractional-order values such as <i>v</i> = 1.4. Further experiments demonstrated that DE-FOCNN achieved higher accuracy and lower variance compared to other popular evolutionary algorithms. This research primarily contributes to the optimization of FOCNNs by introducing a novel DE-based approach for the automated analysis and classification of musical grooves. The DE-FOCNN framework holds promise for addressing other related engineering challenges.
format Article
id doaj-art-bc7c7cb77cb94e8b9035233365cb22f1
institution Kabale University
issn 2504-3110
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Fractal and Fractional
spelling doaj-art-bc7c7cb77cb94e8b9035233365cb22f12024-11-26T18:04:55ZengMDPI AGFractal and Fractional2504-31102024-10-0181161610.3390/fractalfract8110616Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential EvolutionJiangang Chen0Pei Su1Daxin Li2Junbo Han3Gaoquan Zhou4Donghui Tang5School of P.E. and Sports, Beijing Normal University, Beijing 100875, ChinaSchool of P.E. and Sports, Beijing Normal University, Beijing 100875, ChinaSchool of P.E. and Sports, Beijing Normal University, Beijing 100875, ChinaSchool of P.E. and Sports, Beijing Normal University, Beijing 100875, ChinaSchool of P.E. and Sports, Beijing Normal University, Beijing 100875, ChinaSchool of P.E. and Sports, Beijing Normal University, Beijing 100875, ChinaThis study presents a differential evolution (DE)-based optimization approach for fractional-order convolutional neural networks (FOCNNs) aimed at enhancing the accuracy of groove classification in music. Groove, an essential element in music perception, is typically influenced by rhythmic patterns and acoustic features. While FOCNNs offer a promising method for capturing these subtleties through fractional-order derivatives, they face challenges in efficiently converging to optimal parameters. To address this, DE is applied to optimize the initial weights and biases of FOCNNs, leveraging its robustness and ability to explore a broad solution space. The proposed DE-FOCNN was evaluated on the Janata dataset, which includes pre-rated music tracks. Comparative experiments across various fractional-order values demonstrated that DE-FOCNN achieved superior performance in terms of higher test accuracy and reduced overfitting compared to a standard FOCNN. Specifically, DE-FOCNN showed optimal performance at fractional-order values such as <i>v</i> = 1.4. Further experiments demonstrated that DE-FOCNN achieved higher accuracy and lower variance compared to other popular evolutionary algorithms. This research primarily contributes to the optimization of FOCNNs by introducing a novel DE-based approach for the automated analysis and classification of musical grooves. The DE-FOCNN framework holds promise for addressing other related engineering challenges.https://www.mdpi.com/2504-3110/8/11/616fractional-order convolutional neural networksdifferential evolutiongroove classificationmusic information retrievaloptimization algorithms
spellingShingle Jiangang Chen
Pei Su
Daxin Li
Junbo Han
Gaoquan Zhou
Donghui Tang
Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution
Fractal and Fractional
fractional-order convolutional neural networks
differential evolution
groove classification
music information retrieval
optimization algorithms
title Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution
title_full Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution
title_fullStr Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution
title_full_unstemmed Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution
title_short Optimizing Fractional-Order Convolutional Neural Networks for Groove Classification in Music Using Differential Evolution
title_sort optimizing fractional order convolutional neural networks for groove classification in music using differential evolution
topic fractional-order convolutional neural networks
differential evolution
groove classification
music information retrieval
optimization algorithms
url https://www.mdpi.com/2504-3110/8/11/616
work_keys_str_mv AT jiangangchen optimizingfractionalorderconvolutionalneuralnetworksforgrooveclassificationinmusicusingdifferentialevolution
AT peisu optimizingfractionalorderconvolutionalneuralnetworksforgrooveclassificationinmusicusingdifferentialevolution
AT daxinli optimizingfractionalorderconvolutionalneuralnetworksforgrooveclassificationinmusicusingdifferentialevolution
AT junbohan optimizingfractionalorderconvolutionalneuralnetworksforgrooveclassificationinmusicusingdifferentialevolution
AT gaoquanzhou optimizingfractionalorderconvolutionalneuralnetworksforgrooveclassificationinmusicusingdifferentialevolution
AT donghuitang optimizingfractionalorderconvolutionalneuralnetworksforgrooveclassificationinmusicusingdifferentialevolution