Back to Search
Start Over
A Multi-Modal Stacked Ensemble Model for Bipolar Disorder Classification
- Source :
- IEEE Transactions on Affective Computing. 14:236-244
- Publication Year :
- 2023
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2023.
-
Abstract
- We propose an automatic ternary classification model for Bipolar Disorder (BD) states. As input information, the model uses speech signals from patients' audio-visual recordings of structured interviews. The model classifies the patient's clinical state as Mania, Hypo-Mania, or Remission. We capture Mel-Frequency Cepstral Coefficients (MFCCs) and Geneva Minimalistic Acoustic Parameter Set (GeMAPS) as audio features. We compute linguistic and sentiment features for each subject's transcript. We present a stacked ensemble classifier to classify all fused features after feature selection. A set of three homogeneous Convolutional Neural Networks (CNNs) and a Multi Layer Perceptron (MLP) construct the first-level and second-level of the stacked ensemble classifier respectively. Moreover, we use reinforcement learning to optimize the networks and their hyperparameters. We show that our stacked ensemble framework outperforms existing models on the BD Turkish corpus with a %59.3 Unweighted Average Unit (UAR) on the test set. To the best of our knowledge, this is the highest UAR achieved on this dataset.
- Subjects :
- Ensemble forecasting
Computer science
business.industry
Feature selection
Pattern recognition
Convolutional neural network
Human-Computer Interaction
Set (abstract data type)
Multilayer perceptron
Test set
Classifier (linguistics)
Artificial intelligence
Mel-frequency cepstrum
business
Software
Subjects
Details
- ISSN :
- 23719850
- Volume :
- 14
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Affective Computing
- Accession number :
- edsair.doi...........ac81356e43f2adbe5eb3a1625af654ab