Hyperparameter optimization in CNN for learning-centered emotion recognition for intelligent tutoring systems

Zataraín-Cabada, Ramón; Rangel, Héctor Rodríguez; Barrón-Estrada, María Lucia; Lopez, Hector Manuel Cardenas

doi:10.1007/s00500-019-04387-4

Cited by 57 publications

(25 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies investigated the combination of data retrieved from brain-imaging techniques with data retrieved from other devices to produce more robust data sets in order to better classify students' cognitive phenomena in the technology-enhanced learning context. For example, studies that aimed to detect students' emotions combined data related to students' brain activities with data related to facial recognition (retrieved with camera (Zatarain Cabada et al, 2019)) and related to behavior in the system (retrieved with mouse (Azcarraga & Suarez, 2013)).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

On the joint use of Artificial Intelligence and Brain-Imaging Techniques in Technology-enhanced Learning Environments: A Systematic Literature Review

Tenório

Santos

Accete

et al. 2021

RBIE

View full text Add to dashboard Cite

Recent meta-analysis and literature reviews support that adaptive learning systems are components of effective instruction. These exciting results are motivating researchers to explore new technologies that provide relevant students' information to promote a better-personalized experience for students to achieve better learning outcomes in technology-enhanced learning environments. A new trend is related to the studies that use brain-imaging techniques to provide relevant students' information for educational systems, aiming to enable an enhanced personalized experience. Some of these studies are making use of artificial intelligence to provide real-time monitoring of students' cognitive phenomena supplied by brain-imaging techniques such as electroencephalography and functional magnetic resonance imaging. Therefore, considering the relevance of the application of artificial intelligence in studies that use brain-imaging techniques combined with technology-enhanced learning environments and the lack of a current understanding of how these techniques have been used in this context, we present a systematic literature review (SLR) that aims to explore which artificial intelligence algorithms have been adopted, what are their purposes in studies that apply brain-imaging techniques in educational technologies and which were the results reported in these studies related to the use of artificial intelligence algorithms. The systematic literature review was conducted according to the recommendation of a well-accepted guideline to perform a rigorous review of the current literature. The search was conducted in seven academic databases in January 2020 and resulted in a total of 6089 studies that was reduced to 20 studies for the final analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Li et al, 2011;Kang et al, 2015). For example, a recent study improves the recognition rate of emotions in intelligent tutoring systems by means of a genetic algorithm for optimization of hyper-parameters in a CNN using data from an EEG-based brain-computer interface (Zatarain Cabada et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

On the joint use of Artificial Intelligence and Brain-Imaging Techniques in Technology-enhanced Learning Environments: A Systematic Literature Review

Tenório

Santos

Accete

et al. 2021

RBIE

View full text Add to dashboard Cite

show abstract

“…Other modification of CNN networks is found in Alenazy & Alqahtani (2020) , Ozcan & Basturk (2020) , Wu, Wang & Wang (2019) and Zatarain Cabada et al (2020) . Ozcan & Basturk (2020) improved FER system performance with transfer learning and hyperparameter tuning.…”

Section: Related Workmentioning

confidence: 99%

Multilabel convolution neural network for facial expression recognition and ordinal intensity estimation

Ekundayo¹,

Viriri²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Facial Expression Recognition (FER) has gained considerable attention in affective computing due to its vast area of applications. Diverse approaches and methods have been considered for a robust FER in the field, but only a few works considered the intensity of emotion embedded in the expression. Even the available studies on expression intensity estimation successfully assigned a nominal/regression value or classified emotion in a range of intervals. Most of the available works on facial expression intensity estimation successfully present only the emotion intensity estimation. At the same time, others proposed methods that predict emotion and its intensity in different channels. These multiclass approaches and extensions do not conform to man heuristic manner of recognising emotion and its intensity estimation. This work presents a Multilabel Convolution Neural Network (ML-CNN)-based model, which could simultaneously recognise emotion and provide ordinal metrics as the intensity estimation of the emotion. The proposed ML-CNN is enhanced with the aggregation of Binary Cross-Entropy (BCE) loss and Island Loss (IL) functions to minimise intraclass and interclass variations. Also, ML-CNN model is pre-trained with Visual Geometric Group (VGG-16) to control overfitting. In the experiments conducted on Binghampton University 3D Facial Expression (BU-3DFE) and Cohn Kanade extension (CK+) datasets, we evaluate ML-CNN’s performance based on accuracy and loss. We also carried out a comparative study of our model with some popularly used multilabel algorithms using standard multilabel metrics. ML-CNN model simultaneously predicts emotion and intensity estimation using ordinal metrics. The model also shows appreciable and superior performance over four standard multilabel algorithms: Chain Classifier (CC), distinct Random K label set (RAKEL), Multilabel K Nearest Neighbour (MLKNN) and Multilabel ARAM (MLARAM).

show abstract

“…Some hyperparameters, such as regularization coefficient, have limited influence on the model performance, while other hyperparameters, such as learning rate, have great influence on the model performance. Optimizing the hyperparameters by appropriate optimization methods to choose the best performance configuration is very critical [41].…”

Section: Optimize Classifiermentioning

confidence: 99%

Two-Stream Convolutional Neural Network Based on Gradient Image for Aluminum Profile Surface Defects Classification and Recognition

Duan

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, a novel two-stream convolutional neural network based on gradient image is performed to effectively classify and identify aluminum profiles defects for the first time. Recent feature fusion methods based on two-stream network prove promising performance for defects classification and recognition. In this paper, we use data enhancement methods to obtain a large number of samples to prevent the over fitting phenomenon in deep learning. The image gradient is calculated with the Sobel operator, and normalized to transform the data between zero and one under the same dimension. We design a two-stream convolutional neural network model adopting Wavelet transform fusion strategy to realize feature fusion on the ReLU6 layer, which uses the original RGB image of aluminum profile and the gradient image corresponding to the original RGB image as inputs to extract features through two sub-networks and fuses features on a concatenate layer to be input into SVM classifier for classification and recognition. Using Bayesian Optimization function and computing the cross-validation classification error to optimize the hyperparameters to choose the best performance configuration is performed. A series of experimental data, which include accuracy and estimated generalized classification errors of single-stream and two-stream networks with different feature fusion strategies on different fusion layers, are conducted and show that the current model has good convergence, accuracy, stability and generalization. On this basis, this paper also proposes a series of innovative methods for the future research of other defects. INDEX TERMS Aluminum profile surface defects, two-stream network, gradient image, convolutional neural network, SVM.

show abstract

Hyperparameter optimization in CNN for learning-centered emotion recognition for intelligent tutoring systems

Cited by 57 publications

References 33 publications

On the joint use of Artificial Intelligence and Brain-Imaging Techniques in Technology-enhanced Learning Environments: A Systematic Literature Review

On the joint use of Artificial Intelligence and Brain-Imaging Techniques in Technology-enhanced Learning Environments: A Systematic Literature Review

Multilabel convolution neural network for facial expression recognition and ordinal intensity estimation

Two-Stream Convolutional Neural Network Based on Gradient Image for Aluminum Profile Surface Defects Classification and Recognition

Contact Info

Product

Resources

About