Electroencephalogram (EEG) serves as an effective indicator of detecting fatigue driving. Utilizing the open accessible Shanghai Jiao Tong University Emotion Electroencephalography Dataset (SEED-VIG), driving states are divided into three categories including awake, tired and drowsy for investigation. Given the characteristics of mutual influence and interdependence among EEG channels, as well as the consistency of the graph convolutional neural network (GCNN) structure, we designed an adjacency matrix based on the Pearson correlation coefficients of EEG signals among channels and their positional relationships. Subsequently, we developed a GCNN for recognition. The experimental results show that the average classification accuracy of driving state categories for 20 subjects, from the SEED-VIG dataset under the smooth feature of differential entropy (DE) linear dynamic system is 91.66%. Moreover, the highest classification accuracy can reach 98.87%, and the average Kappa coefficient is 0.83. This work demonstrates the reliability of this method and provides a guideline for the research field of safe driving brain computer interface.
Humans ; Electroencephalography/methods* ; Neural Networks, Computer ; Fatigue/physiopathology* ; Automobile Driving ; Brain-Computer Interfaces ; Signal Processing, Computer-Assisted ; Convolutional Neural Networks

The aim of this study is to investigate the growth and proliferation of bone marrow mesenchymal stem cells (BMSCs) three-dimensionally cultured in Pluronic F-127 gel, in order to explore the cellular compatibility of gel and to investigate the feasibility of BMSCs differentiating into adipocytes in gel. Rat BMSCs were isolated from adult bone marrow, and then cultured and amplified in vitro. The BMSCs derived from the 4th passage were seeded on the scaffolds and incubated in adipogenic stimuli culture to differentiate into adipocytes. BMSCs were dispersed into gel and cultured in vitro for two weeks then the status of adhesion, growth and proliferation of the cells were observed. The edipogenic differentiation of the BMSCs was assessed by cellular morphology and further confirmed by Oil Red O staining. BMSCs were able to attach, grow and proliferate well in Pluronic F-127 gel. The BMSCs differentiated into adipocytes in gel in the presence of adipogenic stimuli over a period of 2 weeks. After only 4 days of adipogenic induction, small lipid droplets were observed within BMSCs in gel wells treated with differentiation media. At the end of 14 days, in the presence of differentiation media in gel, the size of the lipid droplets increased to occupy most of the cytoplasm, consistent with differentiation of BMSCs into adipocytes. Lipid droplets in differentiating BMSCs were positively stained with Oil Red O in the presence of differentiation media in the Pluronic F-127 treatment. We demostrated BMSCs incubated in the 3D Pluronic F-127 gel scaffolds could be induced and differentiated into adipocytes. The system for inducing differentiation of BMSCs into adipocytes is promising to apply in the construction of tissue engineering adipose tissue and the repair of fat injury, and Pluronic F-127 gel may be a suitable scaffold for cellular therapy of BMSCs.
Adipocytes ; cytology ; Adipose Tissue ; cytology ; Animals ; Bone Marrow Cells ; cytology ; Cell Differentiation ; drug effects ; Cells, Cultured ; Hydrogels ; chemistry ; Mesenchymal Stromal Cells ; cytology ; Poloxamer ; chemistry ; Rats ; Rats, Sprague-Dawley ; Tissue Engineering