Combining contextual neural networks for time series classification

Flow starvation during square-flow assisted ventilation detected by supervised deep learning techniques

BACKGROUND

Flow starvation is a type of patient-ventilator asynchrony that occurs when gas delivery does not fully meet the patients' ventilatory demand due to an insufficient airflow and/or a high inspiratory effort, and it is usually identified by visual inspection of airway pressure waveform. Clinical diagnosis is cumbersome and prone to underdiagnosis, being an opportunity for artificial intelligence. Our objective is to develop a supervised artificial intelligence algorithm for identifying airway pressure deformation during square-flow assisted ventilation and patient-triggered breaths.

METHODS

Multicenter, observational study. Adult critically ill patients under mechanical ventilation > 24 h on square-flow assisted ventilation were included. As the reference, 5 intensive care experts classified airway pressure deformation severity. Convolutional neural network and recurrent neural network models were trained and evaluated using accuracy, precision, recall and F1 score. In a subgroup of patients with esophageal pressure measurement (ΔPes), we analyzed the association between the intensity of the inspiratory effort and the airway pressure deformation.

RESULTS

6428 breaths from 28 patients were analyzed, 42% were classified as having normal-mild, 23% moderate, and 34% severe airway pressure deformation. The accuracy of recurrent neural network algorithm and convolutional neural network were 87.9% [87.6-88.3], and 86.8% [86.6-87.4], respectively. Double triggering appeared in 8.8% of breaths, always in the presence of severe airway pressure deformation. The subgroup analysis demonstrated that 74.4% of breaths classified as severe airway pressure deformation had a ΔPes > 10 cmH2O and 37.2% a ΔPes > 15 cmH2O.

CONCLUSIONS

Recurrent neural network model appears excellent to identify airway pressure deformation due to flow starvation. It could be used as a real-time, 24-h bedside monitoring tool to minimize unrecognized periods of inappropriate patient-ventilator interaction.

Cross Modal Few-Shot Contextual Transfer for Heterogenous Image Classification

Deep transfer learning aims at dealing with challenges in new tasks with insufficient samples. However, when it comes to few-shot learning scenarios, due to the low diversity of several known training samples, they are prone to be dominated by specificity, thus leading to one-sidedness local features instead of the reliable global feature of the actual categories they belong to. To alleviate the difficulty, we propose a cross-modal few-shot contextual transfer method that leverages the contextual information as a supplement and learns context awareness transfer in few-shot image classification scenes, which fully utilizes the information in heterogeneous data. The similarity measure in the image classification task is reformulated via fusing textual semantic modal information and visual semantic modal information extracted from images. This performs as a supplement and helps to inhibit the sample specificity. Besides, to better extract local visual features and reorganize the recognition pattern, the deep transfer scheme is also used for reusing a powerful extractor from the pre-trained model. Simulation experiments show that the introduction of cross-modal and intra-modal contextual information can effectively suppress the deviation of defining category features with few samples and improve the accuracy of few-shot image classification tasks.

Research on Bearing Fault Diagnosis Method Based on an Adaptive Anti-Noise Network under Long Time Series

In the era of big data, longer time series fault signals will not only be easy to copy and store, but also reduce the labor cost of manual labeling, which can better meet the needs of industrial big data. Aiming to effectively extract the key classification information from a longer time series of bearing vibration signals and achieve high diagnostic accuracy under noise and different load conditions. The one-dimensional adaptive long sequence convolutional network (ALSCN) is proposed. ALSCN can better extract features directly from high-dimensional original signals without manually extracting features and relying on expert knowledge. By adding two improved multi-scale modules, ALSCN can not only extract important features efficiently from noise signals, but also alleviate the problem of losing key information due to continuous down-sampling. Moreover, a Bayesian optimization algorithm is constructed to automatically find the best combination of hyperparameters in ALSCN. Based on two bearing data sets, the model is compared with traditional model such as SVM and deep learning models such as convolutional neural networks (CNN) et al. The results prove that ALSCN has a higher diagnostic accuracy rate on 5120-dimensional sequences under −5 signal to noise ratio (SNR) with better generalization.