Prototype-based Classifier for Automatic Diagnosis of Depressive Mood

Cholet, Stéphane; Paugam-Moisy, Hélène

doi:10.1109/icbea.2018.8471736

Cited by 2 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was initially proposed by Azcarraga and Giacometti [19] and later adapted to supervised classification tasks by Puzenat [20]. More recently, the INN was successfully used in affective computing in order to classify depressive states with respect to the Beck Depression Inventory measurement scale [21]. In this paper, we extend and publish the framework that was used.…”

Section: Overviewmentioning

confidence: 99%

“…In its development phase, the framework was used and tested on several toy datasets, including (but not limited to) iris, wine, breast cancer, and MNIST. However, it was designed with the goal of being applied in the field of affective computing, mainly on multimodal data for the emotion and depression classification tasks [10,11,21]. Thus, some utilities were left in the published source code to address these tasks, although they do not alter the genericity of the algorithm.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…The INN implementation was initially designed to address multimodal classification problems in affective computing, and more specifically concerning emotion and depression classification. Several results have been published [11,21], including a live prototype demonstration [30].…”

Section: Application To Affective Computingmentioning

confidence: 99%

See 2 more Smart Citations

A Framework for Frugal Supervised Learning with Incremental Neural Networks

Cholet

Biabiany

2023

Applied Sciences

Self Cite

View full text Add to dashboard Cite

This study proposes an implementation of an incremental neural network (INN) that was initially designed for affective computing tasks. INNs are a family of machine learning algorithms that combine prototype-based classifiers with neural networks. They achieve state-of-the-art performance with less data than traditional approaches. In this research, we conduct an in-depth review of INN mechanisms and present a research-grade framework that enables the use of INNs on arbitrary data. We evaluated our implementation on two different datasets, including the AVEC2014 Challenge, which involved predicting depressive state from auditive and visual modalities. Our results are encouraging, demonstrating the potential of INNs in situations where approaches have to be explainable or when data are scarce.

show abstract

Section: Overviewmentioning

confidence: 99%

Section: Implementation Detailsmentioning

confidence: 99%