Emo-Tune: Harnessing Emotion-based Music for Patient Wellness

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autores principales: N Jothy, Badhrinath S, Ansulin Jerusha J, Dilshad Mohammed Zulkharnane, Dhikshidha
Formato: Recurso digital
Lenguaje:inglés
Publicado: Zenodo 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866901559722377216
author N Jothy
Badhrinath S
Ansulin Jerusha J
Dilshad Mohammed Zulkharnane
Dhikshidha
author_facet N Jothy
Badhrinath S
Ansulin Jerusha J
Dilshad Mohammed Zulkharnane
Dhikshidha
contents <p><em><span>Music has consistently been a favored means of conveying and comprehending human emotions, serving as a powerful medium of expression. It has profound impact on human emotions, and our work aims to leverage this connection to enhance the human experience. This paper aims to enhance emotional well­being by identifying an individual's emotional state and playing music that aligns with their current feelings. Existing models of emotion-based music recommendation are based on various algorithms like PCA, SVM, ANN, etc., However those models have not yielded optimal results and are still pursued. Among those models, low accuracy and delayed real time emotion recognition are observed. This paper targets to improvise those drawbacks by proposing a simple user-friendly machine learning system that can provide results based on human emotional state. The central focus of this paper endeavor is training machine learning model on extensive datasets of facial emotions as the input training data from the user. The machine is trained enough pto detect the user’s facial expression by their face biometrics using ML algorithm CNN in OpenCV platform. By analyzing physiological data of the user’s face, the proposed system identifies emotional patterns, affinities, and recommends the associated playlists, music tracks and albums based on the recognized emotion. The proposed model is designed to capture the nuances of various emotional states including joy, sadness, neutral, rock and surprise. The proposed system marks a notable advancement in combining machine learning with music, presenting an innovative method to deeply link music with human emotions</span></em></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18275265
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Emo-Tune: Harnessing Emotion-based Music for Patient Wellness
N Jothy
Badhrinath S
Ansulin Jerusha J
Dilshad Mohammed Zulkharnane
Dhikshidha
Machine learning, Convolutional Neural Network, OpenCV, human emotions, facial expression
<p><em><span>Music has consistently been a favored means of conveying and comprehending human emotions, serving as a powerful medium of expression. It has profound impact on human emotions, and our work aims to leverage this connection to enhance the human experience. This paper aims to enhance emotional well­being by identifying an individual's emotional state and playing music that aligns with their current feelings. Existing models of emotion-based music recommendation are based on various algorithms like PCA, SVM, ANN, etc., However those models have not yielded optimal results and are still pursued. Among those models, low accuracy and delayed real time emotion recognition are observed. This paper targets to improvise those drawbacks by proposing a simple user-friendly machine learning system that can provide results based on human emotional state. The central focus of this paper endeavor is training machine learning model on extensive datasets of facial emotions as the input training data from the user. The machine is trained enough pto detect the user’s facial expression by their face biometrics using ML algorithm CNN in OpenCV platform. By analyzing physiological data of the user’s face, the proposed system identifies emotional patterns, affinities, and recommends the associated playlists, music tracks and albums based on the recognized emotion. The proposed model is designed to capture the nuances of various emotional states including joy, sadness, neutral, rock and surprise. The proposed system marks a notable advancement in combining machine learning with music, presenting an innovative method to deeply link music with human emotions</span></em></p>
title Emo-Tune: Harnessing Emotion-based Music for Patient Wellness
topic Machine learning, Convolutional Neural Network, OpenCV, human emotions, facial expression
url https://doi.org/10.5281/zenodo.18275265