Skip to main content

Advertisement

SpringerLink
Log in

Optimized deep learning for genre classification via improved moth flame algorithm

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Musical genres are categorical labels created by humans for characterizing pieces of music. This categorization of musical genre is done by the common characteristics shared by its members. Typically these are associated to the rhythmic structure, instrumentation, and harmonic content of the music. In fact, automated musical genre classification could replace or assist the human user in this categorization process and might be the valuable one along with music information retrieval systems. This paper intends to propose a new automated music genre classification model with the aid of an enhanced deep learning model. The proposed model includes two major phases: (a) Feature Extraction and (b) Classification. In the feature extraction phase, the most relevant features like Non-Negative Matrix Factorization (NMF) features, Short-Time Fourier Transform (STFT) features and pitch features are extracted from the given music signal. Subsequently, a weight function is multiplied with the extracted features, particularly to enhance the association between them. Further, these weighted features are subjected to classification via an Optimized Deep belief Network (DBN), where the weights and activation function are fine-tuned. A new Improved Moth Flame Optimization Algorithm (IMFO) is introduced in this work for fine-tuning. The performance of adopted work is evaluated over other existing approaches with respect to Type I and Type II measures, and error analysis, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

STFT:

Short-Time Fourier Transform

NMF:

Non-Negative Matrix Factorization

MCC:

Matthews Correlation Coefficient

NPV:

Net Present Value

FDR:

False Discovery Rate

DBN:

Deep Belief Network

MFO:

Moth Flame Optimization

MSE:

Mean Square Error

FF:

FireFly

PSO:

Particle Swarm optimization

GWO:

Grey Wolf Optimization

FNR:

False Negative Rate

FVs:

Feature Vectors

MFCC:

Mel Frequency Cepstral Coefficient

FPR:

False Positive Rate

FrFT:

Timbral Features And Fractional Fourier Transform

DNN:

Deep Neural Network

CRNN:

Convolutional Recurrent Neural Networks

LSTM:

Long Short-Term Memory

CNN:

Convolutional Neural Network

GRU:

Gated Recurrent Unit

MRMR:

Minimum Redundancy Maximum Relevance

PCA:

Principal Components Analysis

ASC:

Auditory Spike Code

SVM:

Support Vector Machine

MGC:

Music Genre Classification

NMF:

Non-Negative Matrix Factorization

k-NN:

K-Nearest Neighbors

DT:

Decision Tree

SVM:

Support Vector Machines

References

  1. Abdalla HB, Lin J, Li G, Gilani SMM (2016) NoSQL: confidential on data security and data management by using a mobile application. Int J Inf Electron Eng 6(2):84

    Google Scholar 

  2. Abdalla HB, Ahmed AM, Al Sibahee MA (2020) Optimization driven mapreduce framework for indexing and retrieval of big data. KSII Trans Int Inform Syst 14(5):1886–1908

    Google Scholar 

  3. Adiyansjah AASG, Suhartono D (2019) Music recommender system based on genre using convolutional recurrent neural networks. Procedia Comput Sci 157:99–109

    Article  Google Scholar 

  4. Aljanaki A, Wiering F, Veltkamp RC (January 2016) Studying emotion induced by music through a crowdsourcing game. Inf Process Manag 52(1):115–128

    Article  Google Scholar 

  5. Baniya BK, Lee J (2016) Importance of audio feature reduction in automatic music genre classification. Multimed Tools Appl 75:3013–3026

  6. Belfi AM, Evans E, Heskje J, Bruss J, Tranel D (2017) Musical anhedonia after focal brain damage. Neuropsychologia 97:29–37

    Article  Google Scholar 

  7. Bisandu DB, Prasad R, Liman MM (2019) Data clustering using efficient similarity measures. J Stati Manag Syst 22(5):901–922

    Google Scholar 

  8. Coca AE, Zhao L (2016) Musical rhythmic pattern extraction using relevance of communities in networks. Inf Sci 329:819–848

    Article  Google Scholar 

  9. Corrêa DC, Rodrigues FA (2016) A survey on symbolic data-based music genre classification. Expert Syst Appl 60:190–210

  10. Costa YMG, Oliveira LS, Silla CN (2017) An evaluation of Convolutional Neural Networks for music classification using spectrograms. Appl Soft Comput 52:28–38

    Article  Google Scholar 

  11. da Silva ACM, Coelho MAN, Neto RF (2020) A Music Classification model based on metric learning applied to MP3 audio files. Expert Syst Appl 144

  12. Di Mauro M, Di Sarno C (2014) A framework for internet data real-time processing: a machine-learning approach. In: 2014 international Carnahan conference on security technology (ICCST). IEEE, pp 1-6

  13. Di Mauro M, Longo M (2015) Revealing encrypted WebRTC traffic via machine learning tools. In: 2015 12th international joint conference on e-business and telecommunications (ICETE), vol 4. IEEE, pp 259–266

  14. Dong Y, Yang X, Zhao X, Li J (2019) Bidirectional convolutional recurrent sparse network (BCRSN): an efficient model for music emotion recognition. IEEE Tran Multimed 21(12):3150–3163

    Article  Google Scholar 

  15. Durak L, Arıkan O (2003) Short-time fourier transform: two fundamental properties and an optimal implementation. IEEE Trans Signal Process 51(5):1231–1241

    Article  MathSciNet  MATH  Google Scholar 

  16. Fan J, Zeng J (2013) A Levenberg–Marquardt algorithm with correction for singular system of nonlinear equations. Appl Math Comput 219(17):9438–9446

    MathSciNet  MATH  Google Scholar 

  17. Fister I, Fister I, Yang X-S, Brest J (2013) A comprehensive review of firefly algorithms. Swarm Evol Comput 13:34–46

    Article  Google Scholar 

  18. Gangappa M, Kiran Mai C, Sammulal P (2019) Enhanced crow search optimization algorithm and hybrid NN-CNN classifiers for classification of land cover images. Multimed Res 2(3):12–22

    Google Scholar 

  19. George A, Rajakumar BR (2013) APOGA: an adaptive population pool size based genetic algorithm. AASRI Procedia - 2013 AASRI Conference on Intelligent Systems and Control (ISC 2013), vol 4, pp 288–296. https://doi.org/10.1016/j.aasri.2013.10.043

  20. Gonzalez S, Brookes M (2011) A pitch estimation filter robust to high levels of noise (PEFAC). 19th European Signal Processing Conference (EUSIPCO 2011)

  21. Han Y, Kim J, Lee K (2017) Deep convolutional neural networks for predominant instrument recognition in polyphonic music. IEEE/ACM Trans Audio Speech Lang Process 25(1):208–221

    Article  Google Scholar 

  22. Innocenti ED, Geronazzo M, Vescovi D, Nordahl R, Avanzini F (2019) Mobile virtual reality for musical genre learning in primary education. Comput Educ 139:102–117

    Article  Google Scholar 

  23. Jakubec M, Chmulik M (2019) Automatic music genre recognition for in-car infotainment. Transp Res Procedia 40:1364–1371

    Article  Google Scholar 

  24. Kleć M, Koržinek D (2014) Unsupervised feature pre-training of the scattering wavelet transform for musical genre recognition. Procedia Technol 18:133–139

    Article  Google Scholar 

  25. Kumaraswamy B, Poonacha PG (2021) Deep convolutional neural network for musical genre classification via new self adaptive sea lion optimization. Appl Soft Comput 108:107446

    Article  Google Scholar 

  26. Leartpantulak K, Kitjaidure Y (2019) Music genre classification of audio signals using particle swarm optimization and stacking ensemble. In: 2019 7th international electrical engineering congress (iEECON). IEEE, pp 1-4

  27. Li Y, Hu H, Zhou G (2018) Using data augmentation in continuous authentication on smartphones. IEEE Internet Things J 6(1):628–640

    Article  Google Scholar 

  28. Li Y, Hu H, Zhu Z, Zhou G (2020) SCANet: sensor-based continuous authentication with two-stream convolutional neural networks. ACM Trans Sens Netw 16(3):1–27

    Article  Google Scholar 

  29. Li Y, Zou B, Deng S, Zhou G (2020) Using feature fusion strategies in continuous authentication on smartphones. IEEE Internet Comput 24(2):49–56

    Article  Google Scholar 

  30. Lijun Z, Zhengguang C, Miao Z, Xiaofei H (2011) Robust non-negative matrix factorization. Front Electr Electron Eng 6(2):192–200

    Article  Google Scholar 

  31. Lizardo O (2018) The mutual specification of genres and audiences: Reflective two-mode centralities in person-to-culture data. Poetics 68:52–71

    Article  Google Scholar 

  32. Michael Mahesh K (2020) Workflow scheduling using improved moth swarm optimization algorithm in cloud computing. Multimedia Res 3(3)

  33. Mirjalili S (2015) Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm. Knowl Based Syst 89:228–249

    Article  Google Scholar 

  34. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61

    Article  Google Scholar 

  35. Muñoz-Romero S, Arenas-García J, Gómez-Verdejo V (2018) Nonnegative OPLS for supervised design of filter banks: application to image and audio feature extraction. IEEE Trans Multimed 20(7):1751–1766

    Article  Google Scholar 

  36. Nanni L, Costa YMG, Lumini A, Kim MY, Baek SR (2016) Combining visual and acoustic features for music genre classification. Expert Syst Appl 45:108–117

    Article  Google Scholar 

  37. Poluru RK, Lokesh Kumar R (2019) Enhancement of ATC by optimizing TCSC configuration using adaptive moth flame optimization algorithm. Journal of Computational Mechanics, Power System and Control 2(3):1–9

    Article  Google Scholar 

  38. Rajakumar BR (2013) Impact of static and adaptive mutation techniques on genetic algorithm. Int J Hybrid Intell Syst 10(1):11–22. https://doi.org/10.3233/HIS-120161

    Article  Google Scholar 

  39. Rajakumar BR (2013) Static and adaptive mutation techniques for genetic algorithm: a systematic comparative analysis. Int J Comput Sci Eng 8(2):180–193. https://doi.org/10.1504/IJCSE.2013.053087

    Article  MathSciNet  Google Scholar 

  40. Rajakumar BR, George A (2012) A new adaptive mutation technique for genetic algorithm. In: Proceedings of IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), December 18–20, Coimbatore, India, pp 1–7. https://doi.org/10.1109/ICCIC.2012.6510293

  41. Rajesh B, Bhalke DG (2016) Automatic genre classification of Indian Tamil and western music using fractional MFCC. Int J Speech Technol 19:551–563

    Article  Google Scholar 

  42. Raposo F, Ribeiro R, Martins de Matos D (2016) Using generic summarization to improve music information retrieval tasks. IEEE/ACM Trans Audio Speech Lang Process 24(6):1119–1128

    Article  Google Scholar 

  43. Rosner A, Kostek B (2018) Automatic music genre classification based on musical instrument track separation. J Intell Inform Syst 50:363–384

    Article  Google Scholar 

  44. Shin S, Yun H, Jang W, Park H (2019) Extraction of acoustic features based on auditory spike code and its application to music genre classification. IET Signal Processing 13(2):230–234

    Article  Google Scholar 

  45. Sonnett J (2016) Ambivalence, indifference, distinction: a comparative netfield analysis of implicit musical boundaries. Poetics 54:38–53

    Article  Google Scholar 

  46. Swamy SM, Rajakumar BR, Valarmathi IR (2013) Design of Hybrid Wind and Photovoltaic Power System using Opposition-based Genetic Algorithm with Cauchy Mutation. IET Chennai Fourth International Conference on Sustainable Energy and Intelligent Systems (SEISCON 2013), Chennai, India. https://doi.org/10.1049/ic.2013.0361

  47. Vlegels J, Lievens J (2017) Music classification, genres, and taste patterns: a ground-up network analysis on the clustering of artist preferences. Poetics 60:76–89

    Article  Google Scholar 

  48. Wassi G, Iloga S, Romain O, Granado B, Tchuenté M (2018) FPGA-based simultaneous multichannel audio processor for musical genre indexing applications in broadcast band. J Parallel Distrib Comput 119:146–161

    Article  Google Scholar 

  49. Wehrmann J, Barros RC (2017) Movie genre classification: a multi-label approach based on convolutions through time. Appl Soft Comput 61:973–982

    Article  Google Scholar 

  50. Yu Y, Luo S, Liu S, Qiao H, Feng L (2020) Deep attention based music genre classification. Neurocomputing 372:84–91

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. B.M.S. College of Engineering, Bangalore, India

    Balachandra Kumaraswamy

Authors
  1. Balachandra Kumaraswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Balachandra Kumaraswamy.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumaraswamy, B. Optimized deep learning for genre classification via improved moth flame algorithm. Multimed Tools Appl 81, 17071–17093 (2022). https://doi.org/10.1007/s11042-022-12254-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12254-y

Keywords

Search

Navigation