We propose ENCASE to combine expert features and DNNs (Deep Neural Networks) together for ECG classification. We first explore and implement expert features from statistical area, signal processing area and medical area. Then, we build DNNs to automatically extract deep features. Besides, we propose a new algorithm to find the most representative wave (called centerwave) among long ECG record, and extract features from centerwave. Finally, we combine these features together and put them into ensemble classifiers. Experiment on 4-class ECG data classification reports 0.84 F 1 score, which is much better than any of the single model.
Objective: We aim to combine deep neural networks and engineered features (hand-crafted features based on medical domain knowledge) for cardiac arrhythmia detection from short single-lead ECG recordings. Approach: We propose a two-stage method named for cardiac arrhythmia detection. The first stage is feature extraction and the second stage is classifier building. In the feature extraction stage, we extract both deep features and engineered features. Deep features are obtained by modifying deep neural networks into a deep feature extractor. Engineered features are extracted by summarizing existing approaches into four feature groups. Then, we propose a feature aggregation approach to combine these features. In the classifier building stage, we build multiple gradient boosting decision trees and combine them to get the final detector. Main results: Experiments are performed on the PhysioNet/Computing in Cardiology Challenge 2017 dataset (Clifford et al 2017 Computing in Cardiology vol 44). Using F1 scores reported on the hidden test set as measurements, got 0.9117 on Normal (F1N), 0.8128 on Atrial Fibrillation (AF) (F1A), 0.7505 on Others (F1O), and 0.5671 on Noise (F1P). It placed 5th in the Challenge and 8th in the follow-up challenge (ranked by considering the average of Normal, AF, and Others (F1NAO = 0.825)). When rounding to two decimal places, we were part a three-way tie for 1st place and were part a seven-way tie for 2nd place in the follow-up challenge. Further experiments show that combined features perform better than individual features, and deep features show more importance scores than other features. Significance: can benefit from both feature engineering-based methods and recent deep neural networks. It is flexible and can easily assimilate the ability of new cardiac arrhythmia detection methods.
In this study we explored the use of coherence and Granger causality (GC) to separate patients in minimally conscious state (MCS) from patients with severe neurocognitive disorders (SND) that show signs of awareness. We studied 16 patients, 7 MCS and 9 SND with age between 18 and 49 years. Three minutes of ongoing electroencephalographic (EEG) activity was obtained at rest from 19 standard scalp locations, while subjects were alert but kept their eyes closed. GC was formulated in terms of linear autoregressive models that predict the evolution of several EEG time series, each representing the activity of one channel. The entire network of causally connected brain areas can be summarized as a graph of incompletely connected nodes. The 19 channels were grouped into five gross anatomical regions, frontal, left and right temporal, central, and parieto-occipital, while data analysis was performed separately in each of the five classical EEG frequency bands, namely delta, theta, alpha, beta, and gamma. Our results showed that the SND group consistently formed a larger number of connections compared to the MCS group in all frequency bands. Additionally, the number of connections in the delta band (0.1-4 Hz) between the left temporal and parieto-occipital areas was significantly different (P < 0.1%) in the two groups. Furthermore, in the beta band (12-18 Hz), the input to the frontal areas from all other cortical areas was also significantly different (P < 0.1%) in the two groups. Finally, classification of the subjects into distinct groups using as features the number of connections within and between regions in all frequency bands resulted in 100% classification accuracy of all subjects. The results of this study suggest that analysis of brain connectivity networks based on GC can be a highly accurate approach for classifying subjects affected by severe traumatic brain injury.
Multi-resonant wideband energy harvester based on a folded asymmetric M-shaped cantileverThis article reports a compact wideband piezoelectric vibration energy harvester consisting of three proof masses and an asymmetric M-shaped cantilever. The M-shaped beam comprises a main beam and two folded and dimension varied auxiliary beams interconnected through the proof mass at the end of the main cantilever. Such an arrangement constitutes a three degree-of-freedom vibrating body, which can tune the resonant frequencies of its first three orders close enough to obtain a utility wide bandwidth. The finite element simulation results and the experimental results are well matched. The operation bandwidth comprises three adjacent voltage peaks on account of the frequency interval shortening mechanism. The result shows that the proposed piezoelectric energy harvester could be efficient and adaptive in practical vibration circumstance based on multiple resonant modes. C
Background: It is becoming more and more important to judge whether patients with coronary heart disease (CHD) have phlegm and blood stasis syndromes in the process of traditional Chinese medicine (TCM) diagnosis and treatment of CHD. The syndrome differentiation strategy of phlegm and blood stasis syndromes of CHD is still not standardized, and it is particularly necessary to make syndrome differentiation simpler and more accurate.Methods: Twenty-eight medical cases that met the criteria, comprising 10 ancient medical cases and 18 modern ones, were selected from the TCM literature, which were then analyzed by 57 experts via questionnaire. Statistical analysis of the data was mainly based on frequency analysis.Results: (I) The average age of the 57 experts from 20 provinces was 48.9±8.5 years; 89.5% were associate professor or above, and 75.4% of them worked at a tertiary hospital. (II) Consistency of expert consultation over medical cases: for the ancient medical cases, the diagnostic consistency rate of phlegm syndrome was 27/34 (79.4%) and additional diagnosis rate of the blood stasis syndrome was 27/57 (47.4%); for the modern medical cases, the consistency rate compared with the original diagnosis of phlegm syndrome was 54/80 (67.5%) and that of blood stasis syndrome was 73/90 (81.1%). (III) The top five experts' diagnostic basics of phlegm syndrome were oppression in the chest, slippery pulse, greasy fur, coughing of phlegm, and chest pain; the top five diagnostic basics of blood stasis syndrome were chest pain, dark tongue, oppression in chest, red tongue, and ecchymosis on tongue. (IV) In the questionnaire consultation on CHD phlegm-blood stasis syndrome cases, the diagnostic basis of "symptom or (and) tongue manifestation" accounted for 12/27 (44.4%) of the diagnostic basics of phlegm syndrome and 28/38 (73.7%) of that of blood stasis syndrome basis.Conclusions: Modern Chinese medicine experts pay much attention to the diagnosis and treatment of CHD based on TCM pathology theories of phlegm and blood stasis. To collect and detect the patients' symptoms and tongue manifestation is an important strategy of the experts for CHD phlegm and blood stasis syndrome differentiation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.