Exploring the Time-efficient Evolutionary-based Feature Selection Algorithms for Speech Data under Stressful Work Condition

  • Derry Pramono Adi Universitas Narotama
  • Lukman Junaedi Universitas Narotama
  • Frismanda Universitas Narotama
  • Agustinus Bimo Gumelar Dept. of Electrical Engineering, Faculty of Intelligent Electrical and Informatics Technology (ELECTICS), Institut Teknologi Sepuluh Nopember
  • Andreas Agung Kristanto Fakultas Ilmu Sosial & Ilmu Politik, Universitas Mulawarman
Keywords: Feature Selection Algorithms, Curse of Dimensionality, Speech Data, Work Stress, Evolutionary Algorithm


Initially, the goal of Machine Learning (ML) advancements is faster computation time and lower computation resources, while the curse of dimensionality burdens both computation time and resource. This paper describes the benefits of the Feature Selection Algorithms (FSA) for speech data under workload stress. FSA contributes to reducing both data dimension and computation time and simultaneously retains the speech information. We chose to use the robust Evolutionary Algorithm, Harmony Search, Principal Component Analysis, Genetic Algorithm, Particle Swarm Optimization, Ant Colony Optimization, and Bee Colony Optimization, which are then to be evaluated using the hierarchical machine learning models. These FSAs are explored with the conversational workload stress data of a Customer Service hotline, which has daily complaints that trigger stress in speaking. Furthermore, we employed precisely 223 acoustic-based features. Using Random Forest, our evaluation result showed computation time had improved 3.6 faster than the original 223 features employed. Evaluation using Support Vector Machine beat the record with 0.001 seconds of computation time.


Download data is not yet available.


Altman N, Krzywinski M. The Curse(s) of Dimensionality. Nat Methods. 2018;15(6):399–400. DOI: https://doi.org/10.1038/s41592-018-0019-x

Syarif I. Feature Selection of Network Intrusion Data using Genetic Algorithm and Particle Swarm Optimization. Emit Int J Eng Technol. 2016 Dec 15;4(2). Available from: https://emitter.pens.ac.id/index.php/emitter/article/view/149 DOI: https://doi.org/10.24003/emitter.v4i2.149

Mohammadi FG, Amini MH, Arabnia HR. Evolutionary Computation, Optimization, and Learning Algorithms for Data Science. Optim Learn Control Interdependent Complex Networks Adv Intell Syst Comput. 2020;1123:37–65. DOI: https://doi.org/10.1007/978-3-030-34094-0_3

LeCun Y, Cortes C. MNIST handwritten digit database. 2010; Available from: http://yann.lecun.com/exdb/mnist/

Arora M. Feature Extraction-Principal Component Analysis. Medium. 2019.

Gharavian D, Sheikhan M, Ghasemi SS. Combined Classification Method for Prosodic Stress Recognition in Farsi Language. Int J Speech Technol. 2018;21(2):333–41. DOI: https://doi.org/10.1007/s10772-018-9508-7

Bäck T, Fogel DB, Michalewicz Z. Evolutionary computation 1: Basic algorithms and operators. CRC press; 2018.

Amstrong M. Stress Is Biggest Threat To Workplace Health. Stress and burnout - Statista. 2016.

Ahmad J, Sajjad M, Rho S, Kwon S il, Lee MY, Baik SW. Determining Speaker Attributes from Stress-affected Speech in Emergency Situations with Hybrid SVM-DNN Architecture. Multimed Tools Appl. 2018;77(4):4883–907. DOI: https://doi.org/10.1007/s11042-016-4041-7

Adi DP, Gumelar AB, Arta Meisa RP. Interlanguage of Automatic Speech Recognition. In: 2019 International Seminar on Application for Technology of Information and Communication (iSemantic). IEEE; 2019. p. 88–93. DOI: https://doi.org/10.1109/ISEMANTIC.2019.8884310

Stewart C. Distribution of stress levels at work by those in paid employment and training programs in Scotland in 2017, by gender. State of Health - Statista. 2020.

Holland P, Collins AM. “Whenever I can I push myself to go to work”: a qualitative study of experiences of sickness presenteeism among workers with rheumatoid arthritis. Disabil Rehabil. 2018 Feb;40(4):404–13. DOI: https://doi.org/10.1080/09638288.2016.1258436

Venkataramanan K, Rajamohan HR. Emotion Recognition from Speech. arXiv Prepr arXiv191210458. 2019 Dec;

Ahmad J, Fiaz M, Kwon S, Sodanil M, Vo B, Baik SW. Gender Identification using MFCC for Telephone Applications - A Comparative Study. 2016;3(5).

Deb S, Dandapat S. Classification of Speech Under Stress Using Harmonic Peak to Energy Ratio. Comput Electr Eng. 2016;55:12–23. DOI: https://doi.org/10.1016/j.compeleceng.2016.09.027

Chadha AN, Zaveri MA, Sarvaiya JN. Optimal feature extraction and selection techniques for speech processing: A review. In: 2016 International Conference on Communication and Signal Processing (ICCSP). IEEE; 2016. p. 1669–73. DOI: https://doi.org/10.1109/ICCSP.2016.7754447

Slavich GM, Taylor S, Picard RW. Stress Measurement Using Speech: Recent Advancements, Validation Issues, and Ethical and Privacy Considerations. Stress. 2019;22(4):408–13. DOI: https://doi.org/10.1080/10253890.2019.1584180

Sharma M, Kaur P. A Comprehensive Analysis of Nature-Inspired Meta-Heuristic Techniques for Feature Selection Problem. Arch Comput Methods Eng. 2020 Feb; DOI: https://doi.org/10.1007/s11831-020-09412-6

Chen X, Bai R, Qu R, Dong H, Chen J. A Data-Driven Genetic Programming Heuristic for Real-World Dynamic Seaport Container Terminal Truck Dispatching. In: 2020 IEEE Congress on Evolutionary Computation (CEC). IEEE; 2020. p. 1–8. DOI: https://doi.org/10.1109/CEC48606.2020.9185659

Talbi E-G, Jourdan L, Garcia-Nieto J, Alba E. Comparison of Population based Metaheuristics for Feature Selection: Application to Microarray Data Classification. In: 2008 IEEE/ACS International Conference on Computer Systems and Applications. IEEE; 2008. p. 45–52. DOI: https://doi.org/10.1109/AICCSA.2008.4493515

Chen Y, Miao D, Wang R. A Rough Set Approach to Feature Selection based on Ant Colony Optimization. Pattern Recognit Lett. 2010 Feb;31(3):226–33. DOI: https://doi.org/10.1016/j.patrec.2009.10.013

Rodriguez-Galiano VF, Luque-Espinar JA, Chica-Olmo M, Mendes MP. Feature selection approaches for predictive modelling of groundwater nitrate pollution: An evaluation of filters, embedded and wrapper methods. Sci Total Environ. 2018 May;624:661–72. DOI: https://doi.org/10.1016/j.scitotenv.2017.12.152

Yuxin Z, Shenghong L, Feng J. Overlapping community detection in complex networks using multi-objective evolutionary algorithm. Comput Appl Math. 2017 Mar;36(1):749–68. DOI: https://doi.org/10.1007/s40314-015-0260-1

Sarkar S, Das S, Chaudhuri SS. Multi-level thresholding with a decomposition-based multi-objective evolutionary algorithm for segmenting natural and medical images. Appl Soft Comput. 2017 Jan;50:142–57. DOI: https://doi.org/10.1016/j.asoc.2016.10.032

Diao R, Shen Q. Feature selection with harmony search. IEEE Trans Syst Man, Cybern Part B. 2012;42(6):1509–23. DOI: https://doi.org/10.1109/TSMCB.2012.2193613

Yusup N, Zain AM, Latib AA. A review of Harmony Search algorithm-based feature selection method for classification. J Phys Conf Ser. 2019 Mar;1192:12038. DOI: https://doi.org/10.1088/1742-6596/1192/1/012038

Jasim YA, Al-Ani AA, Al-Ani LA. Iris recognition using principal component analysis. Proc - 2018 1st Annu Int Conf Inf Sci AiCIS 2018. 2019;5(5):89–95.

Shrestha A, Mahmood A. Review of Deep Learning Algorithms and Architectures. IEEE Access. 2019;7:53040–65. DOI: https://doi.org/10.1109/ACCESS.2019.2912200

Couronné R, Probst P, Boulesteix A-L. Random forest versus logistic regression: a large-scale benchmark experiment. BMC Bioinformatics. 2018 Dec;19(1):270. DOI: https://doi.org/10.1186/s12859-018-2264-5

Cho G, Yim J, Choi Y, Ko J, Lee S-H. Review of Machine Learning Algorithms for Diagnosing Mental Illness. Psychiatry Investig. 2019 Apr;16(4):262–9. DOI: https://doi.org/10.30773/pi.2018.12.21.2

How to Cite
Adi, D. P., Junaedi, L., Frismanda, Gumelar, A. B., & Kristanto, A. A. (2021). Exploring the Time-efficient Evolutionary-based Feature Selection Algorithms for Speech Data under Stressful Work Condition. EMITTER International Journal of Engineering Technology, 9(1), 60-74. https://doi.org/10.24003/emitter.v9i1.571