Adaptive Parameterized AdaBoost Algorithm with application in EEG Motor Imagery Classification

Das, Pratyusha; Sadhu, Arup Kumar; Konar, Amit; Bhattacharya, Basabdatta Sen; Nagar, Atulya K.

doi:10.1109/ijcnn.2015.7280835

Cited by 2 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the design principle, the final cascade classifier is called the strong classifier. The classifiers that compose of a strong classifier are called weak classifiers [10] . With this design, when the classifier series being very large, the accuracy of Adaboost algorithm will be perfect.…”

Section: Adaboost Classifier Trainingmentioning

confidence: 99%

Recognition of Aerial Insulator Image Based on Structural Model and the Optimal Entropy Threshold Segmentation

Zhai¹,

Wang²,

Guo³

et al. 2017

dtetr

View full text Add to dashboard Cite

Insulator image recognition is an important research on the after-treatment of power grid patrol by UAV (Unmanned Aerial Vehicle). According to the characteristics of aerial insulator image, this paper centers on a new method of aerial insulator recognition based on the structural model and the optimal entropy threshold (OET) segmentation. Firstly, on the condition of the lack of insulator sample library, SketchUp software is used to build the structural model of the insulator and generate insulator simulation images. Those insulator simulation images are used to build the training sample set. Then the insulator image is grayed and enhanced. Next, OET Algorithm is applied to segment the insulator from backgrounds, and the mathematical morphology is applied to improve the segmentation results. Finally, the moment invariants of the insulator and background are calculated to train classifiers based on Adaboost Algorithm, and then a strong classifier is created. The example and testing results show that this method can effectively achieve insulator image recognition under complex backgrounds.

show abstract

Section: Adaboost Classifier Trainingmentioning

confidence: 99%

Recognition of Aerial Insulator Image Based on Structural Model and the Optimal Entropy Threshold Segmentation

Zhai¹,

Wang²,

Guo³

et al. 2017

dtetr

View full text Add to dashboard Cite

show abstract

“…The latter method yields more stable performance when the validation data and training data are heterogeneous. Moreover, to improve the accuracy of emotion recognition for homogeneous data, MindLink-Eumpy proposes two decision-level fusion methods for multimodal emotion recognition tasks, namely, weight enumerator and adaptive boosting (AdaBoost) technique (Das et al, 2015), to fuse the decision-level information of SVM and CNN. For the heterogeneous data, the subject-independent method we used is the EEG-based LSTM model.…”

Section: Introductionmentioning

confidence: 99%

MindLink-Eumpy: An Open-Source Python Toolbox for Multimodal Emotion Recognition

Liang

Liu

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Emotion recognition plays an important role in intelligent human–computer interaction, but the related research still faces the problems of low accuracy and subject dependence. In this paper, an open-source software toolbox called MindLink-Eumpy is developed to recognize emotions by integrating electroencephalogram (EEG) and facial expression information. MindLink-Eumpy first applies a series of tools to automatically obtain physiological data from subjects and then analyzes the obtained facial expression data and EEG data, respectively, and finally fuses the two different signals at a decision level. In the detection of facial expressions, the algorithm used by MindLink-Eumpy is a multitask convolutional neural network (CNN) based on transfer learning technique. In the detection of EEG, MindLink-Eumpy provides two algorithms, including a subject-dependent model based on support vector machine (SVM) and a subject-independent model based on long short-term memory network (LSTM). In the decision-level fusion, weight enumerator and AdaBoost technique are applied to combine the predictions of SVM and CNN. We conducted two offline experiments on the Database for Emotion Analysis Using Physiological Signals (DEAP) dataset and the Multimodal Database for Affect Recognition and Implicit Tagging (MAHNOB-HCI) dataset, respectively, and conducted an online experiment on 15 healthy subjects. The results show that multimodal methods outperform single-modal methods in both offline and online experiments. In the subject-dependent condition, the multimodal method achieved an accuracy of 71.00% in the valence dimension and an accuracy of 72.14% in the arousal dimension. In the subject-independent condition, the LSTM-based method achieved an accuracy of 78.56% in the valence dimension and an accuracy of 77.22% in the arousal dimension. The feasibility and efficiency of MindLink-Eumpy for emotion recognition is thus demonstrated.

show abstract

Adaptive Parameterized AdaBoost Algorithm with application in EEG Motor Imagery Classification

Cited by 2 publications

References 34 publications

Recognition of Aerial Insulator Image Based on Structural Model and the Optimal Entropy Threshold Segmentation

Recognition of Aerial Insulator Image Based on Structural Model and the Optimal Entropy Threshold Segmentation

MindLink-Eumpy: An Open-Source Python Toolbox for Multimodal Emotion Recognition

Contact Info

Product

Resources

About