Augmented Lagrangian method for TV-l 1 -l 2 based colour image restoration

บทความในวารสาร

ผู้เขียน/บรรณาธิการ

กลุ่มสาขาการวิจัยเชิงกลยุทธ์

ไม่พบข้อมูลที่เกี่ยวข้อง

รายละเอียดสำหรับงานพิมพ์

รายชื่อผู้แต่ง: Padcharoen A., Kumam P., Martํnez-Moreno J.

ผู้เผยแพร่: Institute of Electrical and Electronics Engineers Inc.

ปีที่เผยแพร่ (ค.ศ.): 2019

Volume number: 354

Issue number: 3

หน้าแรก: 507

หน้าสุดท้าย: 519

จำนวนหน้า: 13

นอก: 2379-8920

eISSN: 2379-8920

URL: https://www2.scopus.com/inward/record.uri?eid=2-s2.0-85068172252&doi=10.1109%2fTCDS.2019.2924648&partnerID=40&md5=9567a8adbc5ea96d87ccfd2f27b61cf9

ภาษา: English-Great Britain (EN-GB)

ดูในเว็บของวิทยาศาสตร์ | ดูบนเว็บไซต์ของสำนักพิมพ์ | บทความในเว็บของวิทยาศาสตร์

บทคัดย่อ

Electroencephalography (EEG) is another method for performing Person Identification (PI). Due to the nature of the EEG signals, EEG-based PI is typically done while a person is performing a mental task such as motor control. However, few studies used EEG-based PI while the person is in different mental states (affective EEG). The aim of this study is to improve the performance of affective EEG-based PI using a deep learning approach. We proposed a cascade of deep learning using a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). CNNs are used to handle the spatial information from the EEG while RNNs extract the temporal information. We evaluated two types of RNNs, namely, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The proposed method is evaluated on the state-of-the-art affective dataset DEAP. The results indicate that CNN-GRU and CNN-LSTM can perform PI from different affective states and reach up to 99.90–100% mean Correct Recognition Rate. This significantly outperformed a support vector machine baseline system that used power spectral density features. Notably, the 100% mean CRR came from 32 subjects in DEAP dataset. Even after the reduction of the number of EEG electrodes from thirty-two to five for more practical applications, the model could still maintain an optimal result obtained from the frontal region, reaching up to 99.17%. Amongst the two deep learning models, we found that CNN-GRU and CNN-LSTM performed similarly while CNN-GRU expended faster training time. In conclusion, the studied DL approaches overcame the influence of affective states in EEG-Based PI reported in the previous works. IEEE

คำสำคัญ

Biometrics, Convolutional neural networks, Electroencephalography, Long Short-term memory, Personal identification, Recurrent neural networks.