Driver Identification System Using Normalized Electrocardiogram Based on Adaptive Threshold Filter for Intelligent Vehicles

Multi modal biometrics based implicit driver identification system using multi-TF images of ECG and EMG

As security is emphasized inside and outside the vehicle, research on driver identification technology using bio-signals is being actively studied. The bio-signals acquired by the behavioral characteristics of the driver include artifacts generated according to the driving environment, which could potentially degrade the accuracy of the identification system. Existing driver identification systems either remove the normalization process of bio-signals in the preprocessing stage or use artifacts included in a single bio-signals, resulting in low identification accuracy. To solve these problems in a real situation, we propose a driver identification system that converts ECG and EMG signals obtained from different driving conditions into 2D spectrograms through multi-TF image and uses multi-stream CNN. The proposed system consists of a preprocessing phase of ECG and EMG signals, a multi-TF image conversion process, and a driver identification stage using a multi-stream-based CNN. Under all driving conditions, the driver identification system reached an average accuracy of 96.8% and an F1 score of 0.973, which overperformed the existing driver identification systems by more than 1%.

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model's performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach significantly reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise.

Design of Moving Target Detection System Using Lightweight Deep Learning Model and Its Impact on the Development of Sports Industry

The intelligent tracking and detection of athletes' actions and the improvement of action standardization are of great practical significance to reducing the injury caused by sports in the sports industry. For the problems of nonstandard movement and single movement mode, this exploration takes the video of sports events as the object and combines it with the video general feature extraction of convolutional neural network (CNN) in the field of deep learning and the filtering detection algorithm of motion trajectory. Then, a target detection and tracking system model is proposed to track and detect targets in sports in real-time. Moreover, through experiments, the performance of the proposed system model is analyzed. After testing the detection quantity, response rate, data loss rate, and target detection accuracy of the model, the results show that the model can track and monitor 50 targets with a loss rate of 3%, a response speed of 4 s and a target detection accuracy of 80%. It can play an excellent role in sports events and postgame video analysis, and provide a good basis and certain design ideas for the goal tracking of the sports industry.

ECG Authentication Based on Non-Linear Normalization under Various Physiological Conditions

The development and use of wearable devices require high levels of security and have sparked interest in biometric authentication research. Among the available approaches, electrocardiogram (ECG) technology is attracting attention because of its strengths in spoofing. However, morphological changes of ECG, which are affected by physical and psychological factors, can make authentication difficult. In this paper, we propose authentication using non-linear normalization of ECG beats that is robust to changes in ECG waveforms according to heart rate fluctuations in various daily activities. We performed a non-linear normalization method through the analysis of ECG alongside heart rate, evaluating similarities and authenticating the performance of our new method compared to existing methods. Compared with beats before normalization, the average similarity of the proposed method increased 23.7% in the resting state and 43% in the non-resting state. After learning in the resting state, authentication performance reached 99.05% accuracy for the resting state and 88.14% for the non-resting state. The proposed method can be applicable to an ECG-based authentication system under various physiological conditions.