WFT-Fati-Dec: Enhanced Fatigue Detection AI System Based on Wavelet Denoising and Fourier Transform
Abstract
:1. Introduction
- Propose a feature extraction method based on trigonometric transformations for EEG signals.
- Medical signal preprocessing using PCA and rescaling techniques.
- Investigate an enhanced method for fatigue detection from EEG signals based on machine and deep learning models.
- Evaluate the methods, discuss the results and highlight their advantages and disadvantages.
- Compare the accomplished performance with the works in the literature.
2. Materials and Methods
3. Results
3.1. Dataset Description
3.2. Evaluation Metrics
- (1)
- The number of sleepy states that were incorrectly labeled “normal” is shown in the false-negative column.
- (2)
- The True Positive metric indicates the percentage of drowsy states that were accurately identified.
- (3)
- The True Negative () value indicates the proportion of false negatives correctly identified as false positives.
- (4)
- The number of times a normal status was mistakenly labeled as a drowsy status is shown in the false positive.
3.3. Hyperparameter Setting
3.4. Simulation Results
4. Discussion
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
Abbreviations
SVM | Support Vector Machine |
KNN | k-Nearest Neighbor |
MLP | Multilayer Perceptron |
RF | Random Forest |
LR | Logistic Regression |
DT | Decision Tree |
QDA | Quadrature Data Analysis |
CNN | Convolutional Neural Network |
C-NN | Concatenated Convolutional Neural Network |
MCC | Matthews Correlation Coefficient |
ANN | Artificial Neural Network |
FFT | Fast Fourier Transform |
DWT | Discrete Wavelet Transform |
DST | Discrete Sine Transform |
DCT | Discrete Cosine Transform |
EEG | Electroencephalogram |
ECG | Electrocardiogram |
EOG | Electrooculogram |
EMG | Electromyogram |
IoT | Internet of Things |
FE | Fuzzy Entropy |
SE | Sample Entropy |
PSD | Power Spectral Density |
References
- Abbas, Q.; Alsheddy, A. Driver Fatigue Detection Systems Using Multi-Sensors, Smartphone, and Cloud-Based Computing Platforms: A Comparative Analysis. Sensors 2020, 21, 56. [Google Scholar] [CrossRef] [PubMed]
- Ramzan, M.; Khan, H.U.; Awan, S.M.; Ismail, A.; Ilyas, M.; Mahmood, A. A Survey on State-of-the-Art Drowsiness Detection Techniques. IEEE Access 2019, 7, 61904–61919. [Google Scholar] [CrossRef]
- Niloy, A.R.; Chowdhury, A.I.; Sharmin, N. A Brief Review on Different Driver’s Drowsiness Detection Techniques. Int. J. Image Graph. Signal Process. 2020, 10, 41. [Google Scholar]
- Choudhary, P.; Sharma, R.; Singh, G.; Das, S. A Survey Paper on Drowsiness Detection & Alarm System for Drivers. Int. Res. J. Eng. Technol. 2016, 3, 1433–1437. [Google Scholar]
- Khan, M.Q.; Lee, S. A Comprehensive Survey of Driving Monitoring and Assistance Systems. Sensors 2019, 19, 2574. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Chen, L.; Zhi, X.; Wang, H.; Wang, G.; Zhou, Z.; Yazdani, A.; Zheng, X. Driver Fatigue Detection via Differential Evolution Extreme Learning Machine Technique. Electronics 2020, 9, 1850. [Google Scholar] [CrossRef]
- Fuletra, J.D.; Bosamiya, D. A Survey on Drivers Drowsiness Detection Techniques. Int. J. Recent Innov. Trends Comput. Commun. 2013, 1, 816–819. [Google Scholar]
- Bergasa, L.M.; Nuevo, J.; Sotelo, M.A.; Barea, R.; Lopez, M.E. Real-Time System for Monitoring Driver Vigilance. IEEE Trans. Intell. Transp. Syst. 2006, 7, 63–77. [Google Scholar] [CrossRef] [Green Version]
- Flores, M.J.; Armingol, J.M.; de la Escalera, A. Real-Time Warning System for Driver Drowsiness Detection Using Visual Information. J. Intell. Robot. Syst. 2010, 59, 103–125. [Google Scholar] [CrossRef]
- Abtahi, S.; Hariri, B.; Shirmohammadi, S. Driver Drowsiness Monitoring Based on Yawning Detection. In Proceedings of the 2011 IEEE International Instrumentation and Measurement Technology Conference, Hangzhou, China, 10–12 May 2011; pp. 1–4. [Google Scholar]
- Lenskiy, A.A.; Lee, J.-S. Driver’s Eye Blinking Detection Using Novel Color and Texture Segmentation Algorithms. Int. J. Control. Autom. Syst. 2012, 10, 317–327. [Google Scholar] [CrossRef]
- Jo, J.; Lee, S.J.; Kim, J.; Jung, H.G.; Park, K.R. Vision-Based Method for Detecting Driver Drowsiness and Distraction in Driver Monitoring System. Opt. Eng. 2011, 50, 127202. [Google Scholar] [CrossRef]
- Malla, A.M.; Davidson, P.R.; Bones, P.J.; Green, R.; Jones, R.D. Automated Video-Based Measurement of Eye Closure for Detecting Behavioral Microsleep. In Proceedings of the 2010 annual international conference of the IEEE engineering in medicine and biology, Buenos Aires, Argentina, 31 August–4 September 2010; pp. 6741–6744. [Google Scholar]
- Xiong, Y.; Gao, J.; Yang, Y.; Yu, X.; Huang, W. Classifying Driving Fatigue Based on Combined Entropy Measure Using EEG Signals. Int. J. Control Autom. 2016, 9, 329–338. [Google Scholar] [CrossRef]
- Chai, R.; Naik, G.R.; Nguyen, T.N.; Ling, S.H.; Tran, Y.; Craig, A.; Nguyen, H.T. Driver Fatigue Classification with Independent Component by Entropy Rate Bound Minimization Analysis in an EEG-Based System. IEEE J. Biomed. Health Inform. 2016, 21, 715–724. [Google Scholar] [CrossRef]
- Yin, J.; Hu, J.; Mu, Z. Developing and Evaluating a Mobile Driver Fatigue Detection Network Based on Electroencephalograph Signals. Healthc. Technol. Lett. 2017, 4, 34–38. [Google Scholar] [CrossRef] [PubMed]
- Hu, J. Automated Detection of Driver Fatigue Based on AdaBoost Classifier with EEG Signals. Front. Comput. Neurosci. 2017, 11, 72. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Min, J.; Wang, P.; Hu, J. Driver Fatigue Detection through Multiple Entropy Fusion Analysis in an EEG-Based System. PLoS ONE 2017, 12, e0188756. [Google Scholar] [CrossRef] [Green Version]
- Ko, W.; Oh, K.; Jeon, E.; Suk, H.-I. Vignet: A Deep Convolutional Neural Network for Eeg-Based Driver Vigilance Estimation. In Proceedings of the 2020 8th International Winter Conference on Brain-Computer Interface (BCI), Gangwon, Republic of Korea, 26–28 February 2020; pp. 1–3. [Google Scholar]
- Wang, Y.; Liu, X.; Zhang, Y.; Zhu, Z.; Liu, D.; Sun, J. Driving Fatigue Detection Based on EEG Signal. In Proceedings of the 2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC), Qinhuangdao, China, 18–20 September 2015; pp. 715–718. [Google Scholar]
- Zhendong, M.; Jinghai, Y. Mobile Healthcare System for Driver Based on Drowsy Detection Using EEG Signal Analysis. Metall. Min. Ind. 2015, 7, 266–273. [Google Scholar]
- Nugraha, B.T.; Sarno, R.; Asfani, D.A.; Igasaki, T.; Munawar, M.N. Classification of driver fatigue state based on eeg using emotiv epoc+. J. Theor. Appl. Inf. Technol. 2016, 86. [Google Scholar]
- Luo, H.; Qiu, T.; Liu, C.; Huang, P. Research on Fatigue Driving Detection Using Forehead EEG Based on Adaptive Multi-Scale Entropy. Biomed. Signal Process. Control 2019, 51, 50–58. [Google Scholar] [CrossRef]
- Gao, Z.-K.; Li, Y.-L.; Yang, Y.-X.; Ma, C. A Recurrence Network-Based Convolutional Neural Network for Fatigue Driving Detection from EEG. Chaos Interdiscip. J. Nonlinear Sci. 2019, 29, 113126. [Google Scholar] [CrossRef]
- Karuppusamy, N.S.; Kang, B.-Y. Multimodal System to Detect Driver Fatigue Using EEG, Gyroscope, and Image Processing. IEEE Access 2020, 8, 129645–129667. [Google Scholar] [CrossRef]
- Aamir, M.; Rahman, Z.; Dayo, Z.A.; Abro, W.A.; Uddin, M.I.; Khan, I.; Imran, A.S.; Ali, Z.; Ishfaq, M.; Guan, Y. A Deep Learning Approach for Brain Tumor Classification Using MRI Images. Comput. Electr. Eng. 2022, 101, 108105. [Google Scholar] [CrossRef]
- Aamir, M.; Pu, Y.-F.; Rahman, Z.; Tahir, M.; Naeem, H.; Dai, Q. A Framework for Automatic Building Detection from Low-Contrast Satellite Images. Symmetry 2018, 11, 3. [Google Scholar] [CrossRef] [Green Version]
- Siam, A.I.; Soliman, N.F.; Algarni, A.D.; Abd El-Samie, F.E.; Sedik, A. Deploying Machine Learning Techniques for Human Emotion Detection. Comput. Intell. Neurosci. 2022, 2022, 8032673. [Google Scholar] [CrossRef]
- El-Moneim, S.A.; Sedik, A.; Nassar, M.A.; El-Fishawy, A.S.; Sharshar, A.M.; Hassan, S.E.A.; Mahmoud, A.Z.; Dessouky, M.I.; El-Banby, G.M.; El-Samie, F.E.A.; et al. Text-Dependent and Text-Independent Speaker Recognition of Reverberant Speech Based on CNN. Int. J. Speech Technol. 2021, 24, 993–1006. [Google Scholar] [CrossRef]
- Hammad, M.; Abd El-Latif, A.A.; Hussain, A.; Abd El-Samie, F.E.; Gupta, B.B.; Ugail, H.; Sedik, A. Deep Learning Models for Arrhythmia Detection in IoT Healthcare Applications. Comput. Electr. Eng. 2022, 100, 108011. [Google Scholar] [CrossRef]
- Ibrahim, F.E.; Emara, H.M.; El-Shafai, W.; Elwekeil, M.; Rihan, M.; Eldokany, I.M.; Taha, T.E.; El-Fishawy, A.S.; El-Rabaie, E.M.; Abdellatef, E. Deep Learning-based Seizure Detection and Prediction from EEG Signals. Int. J. Numer. Method. Biomed. Eng. 2022, 38, e3573. [Google Scholar] [CrossRef]
- Shoaib, M.R.; Emara, H.M.; Elwekeil, M.; El-Shafai, W.; Taha, T.E.; El-Fishawy, A.S.; El-Rabaie, E.-S.M.; El-Samie, F.E.A. Hybrid Classification Structures for Automatic COVID-19 Detection. J. Ambient Intell. Humaniz. Comput. 2022, 13, 4477–4492. [Google Scholar] [CrossRef]
- Daoui, A.; Yamni, M.; Karmouni, H.; Sayyouri, M.; Qjidaa, H.; Motahhir, S.; Jamil, O.; El-Shafai, W.; Algarni, A.D.; Soliman, N.F. Efficient Biomedical Signal Security Algorithm for Smart Internet of Medical Things (IoMTs) Applications. Electronics 2022, 11, 3867. [Google Scholar] [CrossRef]
- Li, L.; Jamieson, K.; DeSalvo, G.; Rostamizadeh, A.; Talwalkar, A. Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization. J. Mach. Learn. Res. 2017, 18, 6765–6816. [Google Scholar]
- Crammer, K.; Singer, Y. On the Algorithmic Implementation of Multiclass Kernel-Based Vector Machines. J. Mach. Learn. Res. 2001, 2, 265–292. [Google Scholar]
- Massoz, Q.; Langohr, T.; François, C.; Verly, J.G. The ULg Multimodality Drowsiness Database (Called DROZY) and Examples of Use. In Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, 7–10 March 2016; pp. 1–7. [Google Scholar]
- Chicco, D.; Jurman, G. The Advantages of the Matthews Correlation Coefficient (MCC) over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genom. 2020, 21, 6. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Karpiński, R. Knee Joint Osteoarthritis Diagnosis Based on Selected Acoustic Signal Discriminants Using Machine Learning. Appl. Comput. Sci. 2022, 18, 71–85. [Google Scholar] [CrossRef]
- Karpiński, R.; Krakowski, P.; Jonak, J.; Machrowska, A.; Maciejewski, M.; Nogalski, A. Diagnostics of Articular Cartilage Damage Based on Generated Acoustic Signals Using ANN—Part II: Patellofemoral Joint. Sensors 2022, 22, 3765. [Google Scholar] [CrossRef] [PubMed]
- Correa, A.G.; Orosco, L.; Laciar, E. Automatic Detection of Drowsiness in EEG Records Based on Multimodal Analysis. Med. Eng. Phys. 2014, 36, 244–249. [Google Scholar] [CrossRef]
- Ko, L.-W.; Lai, W.-K.; Liang, W.-G.; Chuang, C.-H.; Lu, S.-W.; Lu, Y.-C.; Hsiung, T.-Y.; Wu, H.-H.; Lin, C.-T. Single Channel Wireless EEG Device for Real-Time Fatigue Level Detection. In Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, 12–17 July 2015; pp. 1–5. [Google Scholar]
- Liu, Y.; Lan, Z.; Cui, J.; Sourina, O.; Müller-Wittig, W. Inter-Subject Transfer Learning for EEG-Based Mental Fatigue Recognition. Adv. Eng. Inform. 2020, 46, 101157. [Google Scholar] [CrossRef]
Hyper Parameter | Accuracy | |||||
---|---|---|---|---|---|---|
No. of Filters | Activation Function | Dropout | Epochs | Learning Rate | Optimizer | |
128 | relu | 0.4 | 150 | 0.01 | adam | 1 |
256 | relu | 0.2 | 200 | 0.001 | rmsprop | 1 |
256 | relu | 0.3 | 150 | 0.01 | adam | 1 |
256 | relu | 0.2 | 150 | 0.001 | rmsprop | 0.99900794 |
64 | relu | 0.3 | 150 | 0.01 | rmsprop | 0.99900794 |
256 | relu | 0.2 | 200 | 0.01 | rmsprop | 0.99900794 |
128 | relu | 0.3 | 200 | 0.01 | adam | 0.99900794 |
256 | relu | 0.2 | 150 | 0.001 | adam | 0.99900794 |
64 | relu | 0.4 | 100 | 0.001 | rmsprop | 0.991071403 |
64 | relu | 0.4 | 150 | 0.001 | adam | 0.990079343 |
64 | relu | 0.3 | 100 | 0.01 | adam | 0.990079343 |
64 | relu | 0.4 | 100 | 0.01 | adam | 0.989087284 |
256 | relu | 0.4 | 100 | 0.001 | adam | 0.988095224 |
256 | relu | 0.2 | 100 | 0.001 | adam | 0.987103164 |
256 | relu | 0.3 | 200 | 0.01 | adam | 0.986111104 |
56 | 56 | 75 | 96 | 52 | 56 | 72 |
59 | 68 | 88 | 91 | 57 | 62 | 65 |
50 | 54 | 18 | 77 | 71 | 59 | 34 |
Model | Hyperparameters |
---|---|
SVM | C: 275 gamma: ‘scale’ kernel: ‘rbf’ |
RF | n_estimators:79 Criterion: ‘entropy’ |
DT | criterion: ‘gini’ min_samples_leaf: 1 min_samples_split: 2 ccp_alpha: 0 |
KNN | n_neighbors:1 leaf_size: 30 metric: ‘minkowski’ p: 2 weights’: ‘uniform’ |
QDA | tol = 0.0001 |
MLP | Num_hidden_layers:2 hidden_layer_sizes: [34,35] activation: ‘relu’ max_iter: 200 solver: ‘adam’ |
LR | solver: ‘lbfgs’ C: 1.0 fit_intercept: True |
CNN | Optimizer: adam Epochs: 150 Batch size: 20 Activation function: relu Number of filters: 128 Dropout: 0.4 Learning rate: 0.01 |
C-CNN | Optimizer: adam Epochs: 150 Batch size: 20 Activation function: relu Number of filters: 128 Dropout: 0.4 Learning rate: 0.01 |
Scenario | Model | Feature Extraction Method | |||||||
---|---|---|---|---|---|---|---|---|---|
Time Domain | Time Domain + DWT | FFT | FFT + DWT | DCT | DCT + DWT | DST | DST + DWT | ||
Multiclass | SVM | 41 | 50 | 89 | 87 | 50 | 50 | 48 | 48 |
RF | 47 | 56 | 84 | 89 | 49 | 46 | 42 | 48 | |
DT | 38 | 42 | 67 | 73 | 32 | 41 | 47 | 29 | |
KNN | 43 | 51 | 82 | 90 | 38 | 38 | 34 | 34 | |
QDA | 37 | 44 | 84 | 88 | 36 | 33 | 35 | 41 | |
MLP | 39 | 40 | 82 | 87 | 42 | 44 | 48 | 44 | |
L.R. | 43 | 43 | 86 | 90 | 40 | 44 | 49 | 41 | |
CNN | 43 | 52 | 71 | 79 | 42 | 47 | 53 | 43 | |
C-CNN | 34 | 56 | 28 | 47 | 30 | 18 | 20 | 44 | |
Binary-Classes | SVM | 41 | 57 | 77 | 97 | 63 | 63 | 68 | 68 |
RF | 58 | 67 | 83 | 96 | 68 | 65 | 61 | 67 | |
DT | 53 | 57 | 82 | 82 | 41 | 50 | 66 | 48 | |
KNN | 47 | 55 | 70 | 92 | 53 | 53 | 51 | 51 | |
QDA | 47 | 54 | 69 | 92 | 57 | 54 | 42 | 48 | |
MLP | 51 | 52 | 64 | 93 | 57 | 59 | 63 | 59 | |
L.R. | 56 | 56 | 75 | 96 | 52 | 56 | 72 | 64 | |
CNN | 59 | 68 | 88 | 91 | 57 | 62 | 65 | 55 | |
C-CNN | 50 | 54 | 18 | 77 | 71 | 59 | 34 | 48 |
Scenario | Classifier | Feature Extraction Method | |||||||
---|---|---|---|---|---|---|---|---|---|
Time Domain | Time Domain + DWT | FFT | FFT + DWT | DCT | DCT + DWT | DST | DST + DWT | ||
Multiclass | SVM | 41 | 50 | 84 | 87 | 47 | 49 | 48 | 48 |
RF | 45 | 55 | 83 | 89 | 48 | 46 | 45 | 42 | |
DT | 37 | 41 | 66 | 73 | 32 | 40 | 38 | 47 | |
KNN | 36 | 44 | 81 | 85 | 32 | 35 | 34 | 34 | |
QDA | 36 | 43 | 75 | 87 | 36 | 40 | 38 | 35 | |
MLP | 39 | 40 | 82 | 87 | 41 | 44 | 46 | 48 | |
L.R. | 42 | 42 | 86 | 90 | 39 | 44 | 45 | 49 | |
CNN | 43 | 52 | 69 | 79 | 42 | 47 | 47 | 52 | |
C-CNN | 33 | 37 | 27 | 48 | 30 | 18 | 30 | 18 | |
Binary-Classes | SVM | 48 | 57 | 68 | 96 | 61 | 63 | 65 | 65 |
RF | 57 | 67 | 83 | 96 | 67 | 65 | 63 | 60 | |
DT | 53 | 57 | 82 | 82 | 42 | 50 | 57 | 66 | |
KNN | 47 | 55 | 70 | 91 | 49 | 52 | 51 | 51 | |
QDA | 47 | 54 | 59 | 89 | 46 | 50 | 45 | 42 | |
MLP | 51 | 52 | 64 | 93 | 55 | 58 | 61 | 63 | |
L.R. | 56 | 56 | 71 | 96 | 51 | 56 | 67 | 71 | |
CNN | 59 | 68 | 88 | 89 | 57 | 62 | 60 | 65 | |
C-CNN | 50 | 54 | 18 | 51 | 71 | 59 | 34 | 48 |
Scenario | Classifier | Feature Extraction Method | |||||||
---|---|---|---|---|---|---|---|---|---|
Time Domain | Time Domain + DWT | FFT | FFT + DWT | DCT | DCT + DWT | DST | DST + DWT | ||
Multiclass | SVM | 39 | 58 | 84 | 86 | 45 | 48 | 47 | 47 |
RF | 44 | 55 | 84 | 89 | 48 | 46 | 45 | 42 | |
DT | 37 | 41 | 66 | 73 | 32 | 40 | 38 | 47 | |
KNN | 34 | 43 | 81 | 85 | 26 | 32 | 34 | 34 | |
QDA | 37 | 44 | 73 | 87 | 36 | 31 | 30 | 27 | |
MLP | 38 | 39 | 82 | 87 | 41 | 44 | 45 | 47 | |
L.R. | 42 | 42 | 86 | 90 | 39 | 44 | 45 | 49 | |
CNN | 43 | 51 | 70 | 78 | 42 | 46 | 46 | 51 | |
C-CNN | 32 | 36 | 29 | 47 | 30 | 22 | 29 | 17 | |
Binary-Classes | SVM | 38 | 57 | 65 | 96 | 60 | 63 | 63 | 63 |
RF | 56 | 67 | 83 | 96 | 67 | 65 | 62 | 59 | |
DT | 53 | 57 | 82 | 82 | 42 | 50 | 57 | 66 | |
KNN | 44 | 53 | 70 | 91 | 46 | 52 | 48 | 48 | |
QDA | 47 | 54 | 53 | 90 | 59 | 54 | 45 | 42 | |
MLP | 51 | 52 | 64 | 93 | 55 | 58 | 61 | 63 | |
L.R. | 56 | 56 | 69 | 96 | 51 | 56 | 67 | 71 | |
CNN | 59 | 67 | 88 | 90 | 58 | 62 | 60 | 65 | |
C-CNN | 50 | 54 | 17 | 64 | 66 | 58 | 34 | 48 |
Scenario | Classifier | Feature Extraction Method | |||||||
---|---|---|---|---|---|---|---|---|---|
Time Domain | Time Domain + DWT | FFT | FFT + DWT | DCT | DCT + DWT | DST | DST + DWT | ||
Multiclass | SVM | 41 | 50 | 84 | 86 | 47 | 49 | 48 | 48 |
RF | 45 | 55 | 83 | 89 | 48 | 46 | 45 | 42 | |
DT | 37 | 41 | 66 | 73 | 32 | 40 | 38 | 47 | |
KNN | 36 | 43 | 81 | 84 | 32 | 35 | 34 | 34 | |
QDA | 36 | 43 | 75 | 87 | 36 | 33 | 38 | 35 | |
MLP | 39 | 40 | 82 | 87 | 41 | 44 | 46 | 48 | |
L.R. | 42 | 42 | 86 | 90 | 39 | 44 | 45 | 49 | |
CNN | 43 | 51 | 69 | 78 | 42 | 47 | 47 | 52 | |
C-CNN | 33 | 37 | 27 | 48 | 30 | 18 | 30 | 18 | |
Binary-Classes | SVM | 48 | 57 | 68 | 96 | 61 | 63 | 65 | 65 |
RF | 57 | 67 | 83 | 96 | 67 | 65 | 63 | 60 | |
DT | 53 | 57 | 82 | 83 | 42 | 50 | 57 | 66 | |
KNN | 47 | 54 | 70 | 91 | 49 | 52 | 51 | 51 | |
QDA | 47 | 54 | 59 | 90 | 57 | 54 | 45 | 42 | |
MLP | 51 | 52 | 64 | 93 | 55 | 58 | 61 | 63 | |
L.R. | 56 | 56 | 71 | 96 | 51 | 56 | 67 | 71 | |
CNN | 59 | 67 | 88 | 90 | 57 | 62 | 60 | 65 | |
C-CNN | 50 | 54 | 18 | 64 | 45 | 59 | 34 | 48 |
Scenario | Model | Precision | Recall | F1-Score | Accuracy | MCC |
---|---|---|---|---|---|---|
Multiclass | SVM | 87 | 87 | 86 | 86 | 80 |
RF | 89 | 89 | 89 | 89 | 83 | |
DT | 73 | 73 | 73 | 73 | 59 | |
KNN | 90 | 85 | 85 | 84 | 79 | |
QDA | 88 | 87 | 87 | 87 | 75 | |
MLP | 87 | 87 | 87 | 87 | 81 | |
L.R. | 90 | 90 | 90 | 90 | 86 | |
CNN | 79 | 79 | 78 | 78 | 73 | |
C-CNN | 47 | 48 | 47 | 48 | 42 | |
Binary-Classes | SVM | 97 | 96 | 96 | 96 | 93 |
RF | 96 | 96 | 96 | 96 | 92 | |
DT | 82 | 82 | 82 | 83 | 65 | |
KNN | 92 | 91 | 91 | 91 | 83 | |
QDA | 92 | 89 | 90 | 90 | 81 | |
MLP | 93 | 93 | 93 | 93 | 87 | |
L.R. | 96 | 96 | 96 | 96 | 94 | |
CNN | 91 | 89 | 90 | 90 | 82 | |
C-CNN | 77 | 51 | 64 | 64 | 59 |
Work | Year | Feature Extractor | Classifier | Accuracy |
---|---|---|---|---|
Corea et al. [40] | 2014 | Multimodal Analysis | ANN | 83 |
Ko et al. [41] | 2015 | FFT | ANN | 90 |
Xiong et al. [14] | 2016 | AE and SE | SVM | 90 |
Chai et al. [15] | 2016 | Entropy Rate Round Minimization Analysis | BNN | 88.2 |
Yin et al. [16] | 2017 | FE | SVM | 95 |
Karuppusamy et al. [25] | 2020 | DNN | DNN | 73 |
Lui et al. [42] | 2020 | Deep Transfer Learning | Deep Learning | 93 |
Proposed | 2023 | FFT + DWT | SVM | 96 |
FFT + DWT | RF | 96 | ||
FFT + DWT | LR | 96 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sedik, A.; Marey, M.; Mostafa, H. WFT-Fati-Dec: Enhanced Fatigue Detection AI System Based on Wavelet Denoising and Fourier Transform. Appl. Sci. 2023, 13, 2785. https://doi.org/10.3390/app13052785
Sedik A, Marey M, Mostafa H. WFT-Fati-Dec: Enhanced Fatigue Detection AI System Based on Wavelet Denoising and Fourier Transform. Applied Sciences. 2023; 13(5):2785. https://doi.org/10.3390/app13052785
Chicago/Turabian StyleSedik, Ahmed, Mohamed Marey, and Hala Mostafa. 2023. "WFT-Fati-Dec: Enhanced Fatigue Detection AI System Based on Wavelet Denoising and Fourier Transform" Applied Sciences 13, no. 5: 2785. https://doi.org/10.3390/app13052785
APA StyleSedik, A., Marey, M., & Mostafa, H. (2023). WFT-Fati-Dec: Enhanced Fatigue Detection AI System Based on Wavelet Denoising and Fourier Transform. Applied Sciences, 13(5), 2785. https://doi.org/10.3390/app13052785