ECG-based driver inattention identification during naturalistic driving using Mel-frequency cepstrum 2-D transform and convolutional neural networks

Enhancing ECG signal classification through pre-trained stacked-CNN embeddings: a transfer learning approach

Rapid and accurate electrocardiogram (ECG) signal classification is crucial in high-stakes healthcare settings. However, existing computational models often struggle to balance high performance with computational efficiency. This study introduces an innovative computational framework that combines transfer learning with traditional machine learning to optimize ECG classification. We use a pre-trained Stacked Convolutional Neural Network (SCNN) to generate high-dimensional feature embeddings, which are then evaluated by an array of machine learning classifiers. Our models demonstrate exceptional performance, particularly when utilizing embeddings from SCNNs trained on diverse datasets. This underscores the importance of data diversity in improving classifier discrimination. Notably, Multilayer Perceptrons (MLPs) stand out for their ability to balance computational efficiency with strong performance, achieving test F1-scores of 0.94 and 1.00 in multi-class and binary tasks on the CinC2017 dataset, and 0.85 and 0.99 on the CPSC2018 dataset. Our approach consistently outperforms existing methods, setting new benchmarks in ECG classification. The synergy between deep learning-based feature extraction and traditional machine learning through transfer learning offers a robust, efficient, and adaptable strategy for ECG classification, addressing a critical research gap and laying the groundwork for future advancements in this crucial healthcare field.

A review of research on driving distraction based on bibliometrics and co-occurrence: Focus on driving distraction recognition methods

INTRODUCTION

The existing selection of driving distraction recognition methods is based on a specific research perspective and does not provide comprehensive information on the entire field of view.

METHOD

We conducted a systematic review of previous studies, aiming to come up with appropriate research methods to identify the driver's distraction state. First, this article selects four sets of search keywords related to driving distraction discrimination from five databases (Web of Science, ScienceDirect, Springer Link, IEEE, and TRID) and identifies 1,620 peer-reviewed documents from 2000 to 2020; these 1,620 documents underwent bibliographic analysis and co-occurrence network analysis. The co-occurrence coupling relationship is analyzed from the aspects of time, country, publication, author and keywords. Second, 37 papers published were screened, and the driving distraction recognition methods proposed by these 37 papers were summarized and analyzed.

RESULTS

The results show that this field has been prevalent since 2013; countries such as the United States, Britain, Germany, Australia, China, and Canada are in the forefront of research in this field, and the cooperation between related countries is relatively close. The cooperation between authors is characterized by aggregation, and the mobile phone as the main keyword is almost connected to other keyword nodes; the recognition model of deep learning algorithm based on video surveillance data sources has become the mainstream hot spot distraction recognition method. The recognition model of machine learning algorithm based on vehicle dynamics data, driver physiology, and eye movement data sources has specific advantages and disadvantages.

PRACTICAL APPLICATIONS

The results can help people to understand the current situation of driving distraction comprehensively and systematically, provide better theoretical support for researchers to choose the subsequent driving distraction recognition model, and provide research direction for driving distraction recognition in the future.

A systematic review and Meta-data analysis on the applications of Deep Learning in Electrocardiogram

The success of deep learning over the traditional machine learning techniques in handling artificial intelligence application tasks such as image processing, computer vision, object detection, speech recognition, medical imaging and so on, has made deep learning the buzz word that dominates Artificial Intelligence applications. From the last decade, the applications of deep learning in physiological signals such as electrocardiogram (ECG) have attracted a good number of research. However, previous surveys have not been able to provide a systematic comprehensive review including biometric ECG based systems of the applications of deep learning in ECG with respect to domain of applications. To address this gap, we conducted a systematic literature review on the applications of deep learning in ECG including biometric ECG based systems. The study analyzed systematically, 150 primary studies with evidence of the application of deep learning in ECG. The study shows that the applications of deep learning in ECG have been applied in different domains. We presented a new taxonomy of the domains of application of the deep learning in ECG. The paper also presented discussions on biometric ECG based systems and meta-data analysis of the studies based on the domain, area, task, deep learning models, dataset sources and preprocessing methods. Challenges and potential research opportunities were highlighted to enable novel research. We believe that this study will be useful to both new researchers and expert researchers who are seeking to add knowledge to the already existing body of knowledge in ECG signal processing using deep learning algorithm.

Supplementary information

The online version contains supplementary material available at 10.1007/s12652-022-03868-z.

Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks

Electromyogram (EMG) signals cannot be forged and have the advantage of being able to change the registered data as they are characterized by the waveform, which varies depending on the gesture. In this paper, a two-step biometrics method was proposed using EMG signals based on a convolutional neural network–long short-term memory (CNN-LSTM) network. After preprocessing of the EMG signals, the time domain features and LSTM network were used to examine whether the gesture matched, and single biometrics was performed if the gesture matched. In single biometrics, EMG signals were converted into a two-dimensional spectrogram, and training and classification were performed through the CNN-LSTM network. Data fusion of the gesture recognition and single biometrics was performed in the form of an AND. The experiment used Ninapro EMG signal data as the proposed two-step biometrics method, and the results showed 83.91% gesture recognition performance and 99.17% single biometrics performance. In addition, the false acceptance rate (FAR) was observed to have been reduced by 64.7% through data fusion.

Distracted and Drowsy Driving Modeling Using Deep Physiological Representations and Multitask Learning

In this paper, we investigated various physiological indicators on their ability to identify distracted and drowsy driving. In particular, four physiological signals are being tested: blood volume pulse (BVP), respiration, skin conductance and skin temperature. Data were collected from 45 participants, under a simulated driving scenario, through different times of the day and during their engagement on a variety of physical and cognitive distractors. We explore several statistical features extracted from those signals and their efficiency to discriminate between the presence or not of each of the two conditions. To that end, we evaluate three traditional classifiers (Random Forests, KNN and SVM), which have been extensively applied by the related literature and we compare their performance against a deep CNN-LSTM network that learns spatio-temporal physiological representations. In addition, we explore the potential of learning multiple conditions in parallel using a single machine learning model, and we discuss how such a problem could be formulated and what are the benefits and disadvantages of the different approaches. Overall, our findings indicate that information related to the BVP data, especially features that describe patterns with respect to the inter-beat-intervals (IBI), are highly associates with both targeted conditions. In addition, features related to the respiratory behavior of the driver can be indicative of drowsiness, while being less associated with distractions. Moreover, spatio-temporal deep methods seem to have a clear advantage against traditional classifiers on detecting both driver conditions. Our experiments show, that even though learning both conditions jointly can not compete directly to individual, task-specific CNN-LSTM models, deep multitask learning approaches have a great potential towards that end as they offer the second best performance on both tasks against all other evaluated alternatives in terms of sensitivity, specificity and the area under the receiver operating characteristic curve (AUC).

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Vision technologies are used in both industrial and smart city applications in order to provide advanced value products due to embedded self-monitoring and assessment services. In addition, for the full utilization of the obtained data, deep learning is now suggested for use. To this end, the current work presents the implementation of image recognition techniques alongside the original the quality assessment of a Parabolic Trough Collector (PTC) reflector surface to locate and identify surface irregularities by classifying images as either acceptable or non-acceptable. The method consists of a three-step solution that promotes an affordable implementation in a relatively small time period. More specifically, a 3D Computer Aided Design (CAD) of the PTC was used for the pre-training of neural networks, while an aluminum reflector surface was used to verify algorithm performance. The results are promising, as this method proved applicable in cases where the actual part was manufactured in small batches or under the concept of customized manufacturing. Consequently, the algorithm is capable of being trained with a limited number of data.