Melodious Micro-frissons: Detecting Music Genres From Skin Response

Rahman, Jessica Sharmin; Gedeon, Tom; Caldwell, Sabrina; Jones, Richard; Hossain, Zakir; Zhu, Xuanying

doi:10.1109/ijcnn.2019.8852318

Cited by 10 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hidden layer consisted of 30 nodes. This was chosen based on the comparison of different hidden layer sizes done in our previous study [16]. Other parameters of the network were: Levenberg-Marquardt method as network training function and mean squared normalized error as performance function.…”

Section: Classification Resultsmentioning

confidence: 99%

“…We chose median smoothing filter process for this step [39]. In keeping with our previous study [16], we chose a 10 point median filter as the optimum number which results in minimum loss of data. For pupil dilation data, we needed to perform an additional preprocessing step because several data points were empty due to blinking by the participant.…”

Section: Preprocessingmentioning

confidence: 99%

“…Some features were also extracted from both normalized and filtered signals. The first 14 features follow some statistical features used in the analysis of our previous study [16]: we expanded the list with more features which are listed below:…”

Section: Feature Extractionmentioning

confidence: 99%

“…Terms such as 'chills', 'thrills' and 'frissons' are often used by psychology researchers to describe the psychophysiological moments of musical experience [9]. A 'frisson' is 'a sudden strong feeling of excitement' and 'micro-frisson' is a sud-den small feeling, which is too small to detect consciously, but is reflected by a person's physiological signals [16]. In particular, chills and micro-frissons are closely related and they reflect the emotional intensity induced by music [10].…”

Section: Introductionmentioning

confidence: 99%

“…All of these signals showed significant changes (reflecting the listener's reaction) to different stimuli [13,14,15]. Our previous study [16] had only explored the effects of EDA signals in differentiating different types of music based on genre and participants' subjective ratings. This study extends that work and investigates the effects of all four different signals using a broader set of features and also the combination of all of those signals.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Towards Effective Music Therapy for Mental Health Care Using Machine Learning Tools: Human Affective Reasoning and Music Genres

Rahman

Gedeon

Caldwell

et al. 2020

Journal of Artificial Intelligence and Soft Computing Research

Self Cite

View full text Add to dashboard Cite

Music has the ability to evoke different emotions in people, which is reflected in their physiological signals. Advances in affective computing have introduced computational methods to analyse these signals and understand the relationship between music and emotion in greater detail. We analyse Electrodermal Activity (EDA), Blood Volume Pulse (BVP), Skin Temperature (ST) and Pupil Dilation (PD) collected from 24 participants while they listen to 12 pieces from 3 different genres of music. A set of 34 features were extracted from each signal and 6 different feature selection methods were applied to identify useful features. Empirical analysis shows that a neural network (NN) with a set of features extracted from the physiological signals can achieve 99.2% accuracy in differentiating among the 3 music genres. The model also reaches 98.5% accuracy in classification based on participants’ subjective rating of emotion. The paper also identifies some useful features to improve accuracy of the classification models. Furthermore, we introduce a new technique called ’Gingerbread Animation’ to visualise the physiological signals we record as a video, and to make these signals more comprehensible to the human eye, and also appropriate for computer vision techniques such as Convolutional Neural Networks (CNNs). Our results overall provide a strong motivation to investigate the relationship between physiological signals and music, which can lead to improvements in music therapy for mental health care and musicogenic epilepsy reduction (our long term goal).

show abstract

Section: Classification Resultsmentioning

confidence: 99%

Section: Preprocessingmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%