Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning
In this study, the optimal features of electrocardiogram (ECG) signals were investigated for the implementation of a personal authentication system using a reinforcement learning (RL) algorithm. ECG signals were recorded from 11 subjects for 6 days. Consecutive 5-day datasets (from the 1st to the 5t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1230 |
| _version_ | 1797623266779594752 |
|---|---|
| author | Suwhan Baek Juhyeong Kim Hyunsoo Yu Geunbo Yang Illsoo Sohn Youngho Cho Cheolsoo Park |
| author_facet | Suwhan Baek Juhyeong Kim Hyunsoo Yu Geunbo Yang Illsoo Sohn Youngho Cho Cheolsoo Park |
| author_sort | Suwhan Baek |
| collection | DOAJ |
| description | In this study, the optimal features of electrocardiogram (ECG) signals were investigated for the implementation of a personal authentication system using a reinforcement learning (RL) algorithm. ECG signals were recorded from 11 subjects for 6 days. Consecutive 5-day datasets (from the 1st to the 5th day) were trained, and the 6th dataset was tested. To search for the optimal features of ECG for the authentication problem, RL was utilized as an optimizer, and its internal model was designed based on deep learning structures. In addition, the deep learning architecture in RL was automatically constructed based on an optimization approach called Bayesian optimization hyperband. The experimental results demonstrate that the feature selection process is essential to improve the authentication performance with fewer features to implement an efficient system in terms of computation power and energy consumption for a wearable device intended to be used as an authentication system. Support vector machines in conjunction with the optimized RL algorithm yielded accuracy outcomes using fewer features that were approximately 5%, 3.6%, and 2.6% higher than those associated with information gain (IG), ReliefF, and pure reinforcement learning structures, respectively. Additionally, the optimized RL yielded mostly lower equal error rate (EER) values than the other feature selection algorithms, with fewer selected features. |
| first_indexed | 2024-03-11T09:26:15Z |
| format | Article |
| id | doaj.art-8dd64a829388406b8bb7cf421baf3fc1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:26:15Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8dd64a829388406b8bb7cf421baf3fc12023-11-16T17:58:02ZengMDPI AGSensors1424-82202023-01-01233123010.3390/s23031230Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement LearningSuwhan Baek0Juhyeong Kim1Hyunsoo Yu2Geunbo Yang3Illsoo Sohn4Youngho Cho5Cheolsoo Park6Department of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of KoreaDepartment of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaDepartment of Electrical and Communication Engineering, Daelim University, Kyoung 13916, Republic of KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of KoreaIn this study, the optimal features of electrocardiogram (ECG) signals were investigated for the implementation of a personal authentication system using a reinforcement learning (RL) algorithm. ECG signals were recorded from 11 subjects for 6 days. Consecutive 5-day datasets (from the 1st to the 5th day) were trained, and the 6th dataset was tested. To search for the optimal features of ECG for the authentication problem, RL was utilized as an optimizer, and its internal model was designed based on deep learning structures. In addition, the deep learning architecture in RL was automatically constructed based on an optimization approach called Bayesian optimization hyperband. The experimental results demonstrate that the feature selection process is essential to improve the authentication performance with fewer features to implement an efficient system in terms of computation power and energy consumption for a wearable device intended to be used as an authentication system. Support vector machines in conjunction with the optimized RL algorithm yielded accuracy outcomes using fewer features that were approximately 5%, 3.6%, and 2.6% higher than those associated with information gain (IG), ReliefF, and pure reinforcement learning structures, respectively. Additionally, the optimized RL yielded mostly lower equal error rate (EER) values than the other feature selection algorithms, with fewer selected features.https://www.mdpi.com/1424-8220/23/3/1230ECGauthenticationbiometricsreinforcement learningfeature selectionhyperparameter optimization |
| spellingShingle | Suwhan Baek Juhyeong Kim Hyunsoo Yu Geunbo Yang Illsoo Sohn Youngho Cho Cheolsoo Park Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning Sensors ECG authentication biometrics reinforcement learning feature selection hyperparameter optimization |
| title | Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning |
| title_full | Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning |
| title_fullStr | Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning |
| title_full_unstemmed | Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning |
| title_short | Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning |
| title_sort | intelligent feature selection for ecg based personal authentication using deep reinforcement learning |
| topic | ECG authentication biometrics reinforcement learning feature selection hyperparameter optimization |
| url | https://www.mdpi.com/1424-8220/23/3/1230 |
| work_keys_str_mv | AT suwhanbaek intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning AT juhyeongkim intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning AT hyunsooyu intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning AT geunboyang intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning AT illsoosohn intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning AT younghocho intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning AT cheolsoopark intelligentfeatureselectionforecgbasedpersonalauthenticationusingdeepreinforcementlearning |