Personalizing EEG-Based Affective Models with Transfer Learning

Authors: Wei-Long Zheng, Bao-Liang Lu

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results demonstrate that our proposed subject transfer framework achieves the mean accuracy of 76.31% in comparison with a conventional generic classifier with 56.73% in average.
Researcher Affiliation Academia 1Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering 2Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering 3Brain Science and Technology Research Center Shanghai Jiao Tong University, Shanghai, China
Pseudocode Yes Algorithm 1 TCA-based Subject Transfer [...] Algorithm 2 KPCA-based Subject Transfer [...] Algorithm 3 TPT-based Subject Transfer
Open Source Code No The paper refers to a dataset link (http://bcmi.sjtu.edu.cn/ seed/index.html) but does not provide a link or explicit statement about releasing the source code for the described methodology.
Open Datasets Yes We evaluate the performance of these approaches on an EEG dataset, SEED1, to personalize EEG-based affective models. 1http://bcmi.sjtu.edu.cn/ seed/index.html
Dataset Splits Yes We adopt a leave-one-subject-out cross validation method for the evaluation.
Hardware Specification No The paper does not specify any particular hardware used for running the experiments.
Software Dependencies No The paper mentions 'All the algorithms are implemented in MATLAB' and 'We use the implement of T-SVM in SV M light [Joachims, 1999]' but does not provide specific version numbers for these software components or any other libraries.
Experiment Setup Yes The regularization parameter µ is set to 1, the same as [Pan et al., 2011]. ... The value of the regularization parameter for TPT is 0.1. To deal with multi-class classification task, we adopt the one vs one strategy to avoid label unbalance problem.