scholarly journals Deep ECG-Respiration Network (DeepER Net) for Recognizing Mental Stress

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 3021 ◽  
Author(s):  
Wonju Seo ◽  
Namho Kim ◽  
Sehyeon Kim ◽  
Chanhee Lee ◽  
Sung-Min Park
Keyword(s):  
Deep Learning ◽  
Mental Stress ◽  
Detection Algorithm ◽  
Workplace Stress ◽  
Physiological Signals ◽  
Work Related ◽  
Average Accuracy ◽  
Conventional Machine ◽  
End To End

Unmanaged long-term mental stress in the workplace can lead to serious health problems and reduced productivity. To prevent this, it is important to recognize and relieve mental stress in a timely manner. Here, we propose a novel stress detection algorithm based on end-to-end deep learning using multiple physiological signals, such as electrocardiogram (ECG) and respiration (RESP) signal. To mimic workplace stress in our experiments, we used Stroop and math tasks as stressors, with each stressor being followed by a relaxation task. Herein, we recruited 18 subjects and measured both ECG and RESP signals using Zephyr BioHarness 3.0. After five-fold cross validation, the proposed network performed well, with an average accuracy of 83.9%, an average F1 score of 0.81, and an average area under the receiver operating characteristic (ROC) curve (AUC) of 0.92, demonstrating its superiority over conventional machine learning models. Furthermore, by visualizing the activation of the trained network’s neurons, we found that they were activated by specific ECG and RESP patterns. In conclusion, we successfully validated the feasibility of end-to-end deep learning using multiple physiological signals for recognition of mental stress in the workplace. We believe that this is a promising approach that will help to improve the quality of life of people suffering from long-term work-related mental stress.

scholarly journals Sleep disturbance and work-related mental strain: A national prospective cohort study of the prediction of subsequent long-term sickness absence, disability pension and mortality

2020 ◽  
Vol 48 (8) ◽  
pp. 888-895
Author(s):  
Torbjörn Åkerstedt ◽  
Ellenor Mittendorfer-Rutz ◽  
Syed Rahman
Keyword(s):  
Sleep Disturbance ◽  
Sickness Absence ◽  
Work Disability ◽  
Disability Pension ◽  
Sleep Disturbances ◽  
Workplace Stress ◽  
Mental Strain ◽  
Work Related ◽  
Synergy Effects

Aims: Sleep disturbances and work-related mental strain are linked to increased sickness absence and disability pension (DP), but we have no information on synergy effects. The aim of this study was to examine the combined (and separate) association of the two predictors with subsequent long-term work disability and mortality. Methods: A total of 45,498 participants aged 16–64 years were interviewed in the Swedish Surveys of Living Conditions between 1997 and 2013, and were followed up on long-term sickness absence (LTSA; >90 days/year), DP and mortality via national registers until 2016. Crude and multivariable Cox analyses were used to estimate hazard ratios (HR) and 95% confidence intervals (CI). Results: For LTSA, the HRs for sleep disturbances and work-related mental strain were 1.6 (95% CI 1.5–1.7) and 1.3 (95% CI 1.2–1.4), respectively. For DP, the HRs were 2.0 (95% CI 1.8–2.2) and 1.4 (95% CI 1.2–1.5). Mortality was only predicted by sleep disturbances (HR=1.2, 95% CI 1.1–1.4). No synergy effect was seen. Conclusions: Work-related mental strain and, in particular, sleep disturbances were associated with a higher risk of subsequent LTSA and DP, but without synergy effects. Sleep disturbances were also associated with mortality. Exposure to interventions tackling sleep disturbance and prevention of workplace stress may reduce work disability.

scholarly journals Can We Ditch Feature Engineering? End-to-End Deep Learning for Affect Recognition from Physiological Sensor Data

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6535
Author(s):  
Maciej Dzieżyc ◽  
Martin Gjoreski ◽  
Przemysław Kazienko ◽  
Stanisław Saganowski ◽  
Matjaž Gams
Keyword(s):  
Deep Learning ◽  
Stress Test ◽  
Wearable Sensors ◽  
Physiological Signals ◽  
Trier Social Stress Test ◽  
Bayesian Optimization ◽  
Sensor Data ◽  
Affect Recognition ◽  
Affective Stimuli ◽  
End To End

To further extend the applicability of wearable sensors in various domains such as mobile health systems and the automotive industry, new methods for accurately extracting subtle physiological information from these wearable sensors are required. However, the extraction of valuable information from physiological signals is still challenging—smartphones can count steps and compute heart rate, but they cannot recognize emotions and related affective states. This study analyzes the possibility of using end-to-end multimodal deep learning (DL) methods for affect recognition. Ten end-to-end DL architectures are compared on four different datasets with diverse raw physiological signals used for affect recognition, including emotional and stress states. The DL architectures specialized for time-series classification were enhanced to simultaneously facilitate learning from multiple sensors, each having their own sampling frequency. To enable fair comparison among the different DL architectures, Bayesian optimization was used for hyperparameter tuning. The experimental results showed that the performance of the models depends on the intensity of the physiological response induced by the affective stimuli, i.e., the DL models recognize stress induced by the Trier Social Stress Test more successfully than they recognize emotional changes induced by watching affective content, e.g., funny videos. Additionally, the results showed that the CNN-based architectures might be more suitable than LSTM-based architectures for affect recognition from physiological sensors.

scholarly journals A Demand-Side Load Event Detection Algorithm Based on Wide-Deep Neural Networks and Randomized Sparse Backpropagation

2021 ◽  
Vol 9 ◽  
Author(s):  
Chen Li ◽  
Gaoqi Liang ◽  
Huan Zhao ◽  
Guo Chen
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Event Detection ◽  
Detection Algorithm ◽  
Demand Side ◽  
Rule Based ◽  
Detection Algorithms ◽  
Deep Model ◽  
Conventional Machine

Event detection is an important application in demand-side management. Precise event detection algorithms can improve the accuracy of non-intrusive load monitoring (NILM) and energy disaggregation models. Existing event detection algorithms can be divided into four categories: rule-based, statistics-based, conventional machine learning, and deep learning. The rule-based approach entails hand-crafted feature engineering and carefully calibrated thresholds; the accuracies of statistics-based and conventional machine learning methods are inferior to the deep learning algorithms due to their limited ability to extract complex features. Deep learning models require a long training time and are hard to interpret. This paper proposes a novel algorithm for load event detection in smart homes based on wide and deep learning that combines the convolutional neural network (CNN) and the soft-max regression (SMR). The deep model extracts the power time series patterns and the wide model utilizes the percentile information of the power time series. A randomized sparse backpropagation (RSB) algorithm for weight filters is proposed to improve the robustness of the standard wide-deep model. Compared to the standard wide-deep, pure CNN, and SMR models, the hybrid wide-deep model powered by RSB demonstrates its superiority in terms of accuracy, convergence speed, and robustness.

scholarly journals A deep learning-based algorithm for detection of cortical arousal during sleep

SLEEP ◽  
2020 ◽  
Vol 43 (12) ◽  
Author(s):  
Ao Li ◽  
Siteng Chen ◽  
Stuart F Quan ◽  
Linda S Powers ◽  
Janet M Roveda
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Characteristic Curve ◽  
Detection Algorithm ◽  
Physiological Data ◽  
Ecg Signal ◽  
Cortical Arousal ◽  
Eeg Data ◽  
Varying Length ◽  
End To End

Abstract Study Objectives The frequency of cortical arousals is an indicator of sleep quality. Additionally, cortical arousals are used to identify hypopneic events. However, it is inconvenient to record electroencephalogram (EEG) data during home sleep testing. Fortunately, most cortical arousal events are associated with autonomic nervous system activity that could be observed on an electrocardiography (ECG) signal. ECG data have lower noise and are easier to record at home than EEG. In this study, we developed a deep learning-based cortical arousal detection algorithm that uses a single-lead ECG to detect arousal during sleep. Methods This study included 1,547 polysomnography records that met study inclusion criteria and were selected from the Multi-Ethnic Study of Atherosclerosis database. We developed an end-to-end deep learning model consisting of convolutional neural networks and recurrent neural networks which: (1) accepted varying length physiological data; (2) directly extracted features from the raw ECG signal; (3) captured long-range dependencies in the physiological data; and (4) produced arousal probability in 1-s resolution. Results We evaluated the model on a test set (n = 311). The model achieved a gross area under precision-recall curve score of 0.62 and a gross area under receiver operating characteristic curve score of 0.93. Conclusion This study demonstrated the end-to-end deep learning approach with a single-lead ECG has the potential to be used to accurately detect arousals in home sleep tests.

Surgical management of extracranial carotid artery aneurysms

VASA ◽  
2016 ◽  
Vol 45 (3) ◽  
pp. 223-228 ◽  
Author(s):  
Jan Paweł Skóra ◽  
Jacek Kurcz ◽  
Krzysztof Korta ◽  
Przemysław Szyber ◽  
Tadeusz Andrzej Dorobisz ◽  
...  
Keyword(s):  
Carotid Artery ◽  
Surgical Management ◽  
Minor Stroke ◽  
Stroke Rate ◽  
Extracranial Carotid Artery ◽  
Long Term Follow Up ◽  
End To End ◽  
Dacron Patch ◽  
Major Stroke

Abstract. Background: We present the methods and results of the surgical management of extracranial carotid artery aneurysms (ECCA). Postoperative complications including early and late neurological events were analysed. Correlation between reconstruction techniques and morphology of ECCA was assessed in this retrospective study. Patients and methods: In total, 32 reconstructions of ECCA were performed in 31 symptomatic patients with a mean age of 59.2 (range 33 - 84) years. The causes of ECCA were divided among atherosclerosis (n = 25; 78.1 %), previous carotid endarterectomy with Dacron patch (n = 4; 12.5 %), iatrogenic injury (n = 2; 6.3 %) and infection (n = 1; 3.1 %). In 23 cases, intervention consisted of carotid bypass. Aneurysmectomy with end-to-end suture was performed in 4 cases. Aneurysmal resection with patching was done in 2 cases and aneurysmorrhaphy without patching in another 2 cases. In 1 case, ligature of the internal carotid artery (ICA) was required. Results: Technical success defined as the preservation of ICA patency was achieved in 31 cases (96.9 %). There was one perioperative death due to major stroke (3.1 %). Two cases of minor stroke occurred in the 30-day observation period (6.3 %). Three patients had a transient hypoglossal nerve palsy that subsided spontaneously (9.4 %). At a mean long-term follow-up of 68 months, there were no major or minor ipsilateral strokes or surgery-related deaths reported. In all 30 surviving patients (96.9 %), long-term clinical outcomes were free from ipsilateral neurological symptoms. Conclusions: Open surgery is a relatively safe method in the therapy of ECCA. Surgical repair of ECCAs can be associated with an acceptable major stroke rate and moderate minor stroke rate. Complication-free long-term outcomes can be achieved in as many as 96.9 % of patients. Aneurysmectomy with end-to-end anastomosis or bypass surgery can be implemented during open repair of ECCA.

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

Sign in / Sign up

Export Citation Format

Share Document