IDEAS home Printed from https://ideas.repec.org/a/eee/apmaco/v495y2025ics009630032500044x.html
   My bibliography  Save this article

OP-HHO based feature selection improves the performance of depression classification framework: A gender biased multiband research

Author

Listed:
  • Li, Kun
  • Zhong, PeiYun
  • Dong, Li
  • Wang, LingMin
  • Jiang, Luo-Luo

Abstract

Depression, as a common yet severe mood disorder, can cause irreversible damage to the brain if not detected and treated in a timely manner. Unfortunately, due to the current limitations of medical and technological conditions, only a small number of patients have been able to receive appropriate treatment. Although the traditional Harris Hawk's Optimization (HHO) algorithm has a strong searching ability for global optima which is helpful of early diagnosis of depression, it is highly prone to getting stuck in local optima during the early iterations. In view of this, the Optimized-Parameter Harris Hawk's Optimization (OP-HHO) algorithm proposed in this study is devised by integrating an exponential decay function. This incorporation endows the algorithm with the capacity to dynamically modulate the search step size, progressively diminish the escape energy, thereby bolstering the local search capabilities and efficaciously circumventing the problem of premature convergence that may stem from overzealous global exploration. The performance of the OP-HHO was tested using 23 benchmark functions. Based on the features selected by the OP-HHO algorithm, depression classification was carried out using the K-Nearest Neighbor (KNN) algorithm in combination with the MODMA database. The accuracy rate reached 96.36% - 97.30% across different brain wave frequencies under happy stimuli, and 100% under sad stimuli. Moreover, the classification results in the overall electroencephalogram (EEG) signals also showed excellent performance. This indicates that the OP-HHO algorithm is highly effective in accurately identifying the key features of depression. Our comparative study conducted reveals the existence of gender differences, which are expected to serve as effective features to further improve the accuracy of depression classification, opening up new avenues for the development of depression diagnosis techniques.

Suggested Citation

  • Li, Kun & Zhong, PeiYun & Dong, Li & Wang, LingMin & Jiang, Luo-Luo, 2025. "OP-HHO based feature selection improves the performance of depression classification framework: A gender biased multiband research," Applied Mathematics and Computation, Elsevier, vol. 495(C).
    • Handle: RePEc:eee:apmaco:v:495:y:2025:i:c:s009630032500044x
    DOI: 10.1016/j.amc.2025.129317
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S009630032500044X
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.amc.2025.129317?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:apmaco:v:495:y:2025:i:c:s009630032500044x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: https://www.journals.elsevier.com/applied-mathematics-and-computation .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.