A universal deep learning approach for modeling the flow of patients under different severities.

BACKGROUND AND OBJECTIVE: The Accident and Emergency Department (A&ED) is the frontline for providing emergency care in hospitals. Unfortunately, relative A&ED resources have failed to keep up with continuously increasing demand in recent years, which leads to overcrowding in A&ED. Knowing the fluctuation of patient arrival volume in advance is a significant premise to relieve this pressure. Based on this motivation, the objective of this study is to explore an integrated framework with high accuracy for predicting A&ED patient flow under different triage levels, by combining a novel feature selection process with deep neural networks. METHODS: Administrative data is collected from an actual A&ED and categorized into five groups based on different triage levels. A genetic algorithm (GA)-based feature selection algorithm is improved and implemented as a pre-processing step for this time-series prediction problem, in order to explore key features affecting patient flow. In our improved GA, a fitness-based crossover is proposed to maintain the joint information of multiple features during iterative process, instead of traditional point-based crossover. Deep neural networks (DNN) is employed as the prediction model to utilize their universal adaptability and high flexibility. In the model-training process, the learning algorithm is well-configured based on a parallel stochastic gradient descent algorithm. Two effective regularization strategies are integrated in one DNN framework to avoid overfitting. All introduced hyper-parameters are optimized efficiently by grid-search in one pass. RESULTS: As for feature selection, our improved GA-based feature selection algorithm has outperformed a typical GA and four state-of-the-art feature selection algorithms (mRMR, SAFS, VIFR, and CFR). As for the prediction accuracy of proposed integrated framework, compared with other frequently used statistical models (GLM, seasonal-ARIMA, ARIMAX, and ANN) and modern machine models (SVM-RBF, SVM-linear, RF, and R-LASSO), the proposed integrated "DNN-I-GA" framework achieves higher prediction accuracy on both MAPE and RMSE metrics in pairwise comparisons. CONCLUSIONS: The contribution of our study is two-fold. Theoretically, the traditional GA-based feature selection process is improved to have less hyper-parameters and higher efficiency, and the joint information of multiple features is maintained by fitness-based crossover operator. The universal property of DNN is further enhanced by merging different regularization strategies. Practically, features selected by our improved GA can be used to acquire an underlying relationship between patient flows and input features. Predictive values are significant indicators of patients' demand and can be used by A&ED managers to make resource planning and allocation. High accuracy achieved by the present framework in different cases enhances the reliability of downstream decision makings.

A one-versus-all class binarization strategy for bearing diagnostics of concurrent defects.

In bearing diagnostics using a data-driven modeling approach, a concern is the need for data from all possible scenarios to build a practical model for all operating conditions. This paper is a study on bearing diagnostics with the concurrent occurrence of multiple defect types. The authors are not aware of any work in the literature that studies this practical problem. A strategy based on one-versus-all (OVA) class binarization is proposed to improve fault diagnostics accuracy while reducing the number of scenarios for data collection, by predicting concurrent defects from training data of normal and single defects. The proposed OVA diagnostic approach is evaluated with empirical analysis using support vector machine (SVM) and C4.5 decision tree, two popular classification algorithms frequently applied to system health diagnostics and prognostics. Statistical features are extracted from the time domain and the frequency domain. Prediction performance of the proposed strategy is compared with that of a simple multi-class classification, as well as that of random guess and worst-case classification. We have verified the potential of the proposed OVA diagnostic strategy in performance improvements for single-defect diagnosis and predictions of BPFO plus BPFI concurrent defects using two laboratory-collected vibration data sets.

Foot landmarking for footwear customization.

As consumers are becoming increasingly selective of what they wear on their feet, manufacturers are experiencing problems developing and fitting the right footwear. Literature suggests that shoes with a shape similar to feet may be comfortable because they attempt to maintain the feet in a neutral posture. The objective of this paper is to develop a metric to quantify mismatches between feet and lasts and also to be able to generate the two-dimensional outline of the foot using the minimum number of landmarks. Fifty Hong Kong Chinese were participants in the experiment. In addition to subject weight, height, foot length and foot width, the left foot outlines were drawn and 18 landmarks were marked on each of the two-dimensional foot outlines. A step-wise procedure was used to reduce the chosen 18 landmarks to eight, such that the mean absolute negative error (an indicator of 'tightness') between the foot outline and the modelled curve was 1.3 mm. These eight landmarks seem to show an improvement over those proposed by other researchers, thus showing the importance of choosing the right landmarks for modelling the foot. The positive and negative absolute errors were on average 1.8 mm and 1.3 mm respectively. Moreover, the mean errors for the toe region and for the rest of the foot were 1.7 mm and 1.6 mm respectively. The results indicate that the foot outline, an important component for footwear functionality and fitting, may be modelled using eight critical landmarks.