Search

Background Low-acuity outpatients constitute the majority of emergency department (ED) patients, and these patients often experience an unpredictable length of stay (LOS). Effective LOS prediction might improve the quality of ED care and reduce ED crowding. Objective The objective of this study was to explore the potential of natural language processing (NLP) of the first ED physicians' clinical notes and to evaluate NLP-based short-term prediction models based on mixed-type clinical data. Methods A retrospective study was conducted at an ED of a tertiary teaching hospital in Taiwan from January 2017 to June 2017. In total, 12,962 low-acuity outpatients were enrolled. Using structured data (e.g., demographic variables and vital signs) and different sections of the first SOAP notes as predictors, we developed six NLP-based prediction models (i.e., term frequency-inverse document frequency (TF-IDF) and truncated singular value decomposition (SVD)) to predict LOS. The metric for model evaluation is the mean squared error (MSE). Results Of the six NLP-based models, the model using structured data and all the sections of the first SOAP notes processed by the TF-IDF and truncated SVD method performed the best, with an MSE of 3.00 [95% CI: 2.94–3.06]. In addition, ten important topics extracted by the TF-IDF and truncated SVD method had significant effects on the LOS (p Conclusion NLP-based models can be used as an early short-term prediction of LOS and have the potential for mixed-type clinical data analysis. The proposed models would likely aid ED physicians' decision-making processes and improve ED quality of care.

During the evaluation of body surface area (BSA), precise measurement of psoriasis is crucial for assessing disease severity and modulating treatment strategies. Physicians usually evaluate patients subjectively through direct visual evaluation. However, judgment based on the naked eye is not reliable. This study is aimed at evaluating the use of machine learning methods, specifically U-net models, and developing an artificial neural network prediction model for automated psoriasis lesion segmentation and BSA measurement. The segmentation of psoriasis lesions using deep learning is adopted to measure the BSA of psoriasis so that the severity can be evaluated automatically in patients. An automated psoriasis lesion segmentation method based on the U-net architecture was used with a focus on high-resolution images and estimation of the BSA. The proposed method trained the model with the same patch size of 512 × 512 and predicted testing images with different patch sizes. We collected 255 high-resolution psoriasis images representing large anatomical sites, such as the trunk and extremities. The average residual of the ground truth image and the predicted image was approximately 0.033. The interclass correlation coefficient between the U-net and dermatologist’s segmentations measured in the ratio of affected psoriasis over the body area in the test dataset was 0.966 (95% CI: 0.981–0.937), indicating strong agreement. Herein, the proposed U-net model achieved dermatologist-level performance in estimating the involved BSA for psoriasis.

The novel single index fuzzy neural network models are proposed in this paper for general machine learning problems. The proposed models are different from the usual fuzzy neural network models in that the output nodes of the networks are replaced by (nonparametric) single index models. Specifically, instead of pre-specifying the output activation functions as in the usual models, they are re-estimated adaptively during the training process via “Loess” (“LOcal regrESSion”), a powerful (nonparametric) scatterplot smoother. These estimated activation functions are not necessarily the usual sigmoidal or identity functions. It is interesting to find that in many cases the estimated output activation functions are well approximated by simple polynomial or generalized hyperbolic tangent functions. These problem-tailored simple functions can, if necessary, then be used as the actual output activation functions for neural network training and prediction. Particle swarm optimization, a commonly used evolutionary computation technique, is adopted in this study to search the optimal connection weights of the neural networks. The main advantages of the single index fuzzy neural network models are that they are well suited in situations when one lacks the information about the probability distribution of the response and it is not necessary to specify the output activation functions of the neural networks. Simulation results show that the proposed models usually provide better fits than the usual models for the data at hand.

Acyclic multistate information network (AMIN), a variant of multistate information network (MIN) that is not dependent on the conservation laws of flow, plays an important role in the current-day network communications because many modern network structures are based on AMIN, e.g., social networks, local area networks (LANs), and 4G/5G networks. An effective evaluation of the network reliability of an AMIN serves as a major and primary metric for determining the performance and quality of the overall network. The network reliability, which was shown to be NP-hard, has been successfully resolved by the universal generation function method (UGFM). However, the UGFM can only address small-scale problems owing to the limitations of the current-day computer memories. To overcome this problem, an improved and enhanced binary-addition tree algorithm (BAT) is proposed in this study to effectively evaluate and analyze the reliability of the AMIN. The performance of the proposed BAT is validated via a few examples.

Robust template design for cellular neural networks (CNNs) implementing an arbitrary Boolean function is currently an active research area. If the given Boolean function is linearly separable, a single robust uncoupled CNN can be designed preferably as a maximal margin classifier to implement the Boolean function. On the other hand, if the linearly separable Boolean function has a small geometric margin or the Boolean function is not linearly separable, a popular approach is to find a sequence of robust uncoupled CNNs implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are usually restricted to assume only a given finite set of integers. In this study, we try to remove this unnecessary restriction. NXOR- or XOR-based decomposition algorithm utilizing the soft margin and maximal margin support vector classifiers is proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.

In this paper, least trimmed squares (LTS) estimators, frequently used in robust (or resistant) linear parametric regression problems, will be generalized to nonparametric LTS neural networks for nonlinear regression problems. Emphasis is put particularly on the robustness against outliers. This provides alternative learning machines when faced with general nonlinear learning problems. Simple weight updating rules based on gradient descent and iteratively reweighted least squares (IRLS) algorithms will be provided. The important parameter of trimming percentage for the data at hand can be determined by cross validation. Some simulated and real-world data will be used to illustrate the use of LTS neural networks. We will compare the robustness against outliers for usual neural networks with least squares criterion and the proposed LTS neural networks. Simulation results show that the LTS neural networks proposed in this paper have good robustness against outliers. Nonparametric least trimmed squares neural networks are proposed.We emphasize the issue of robustness against outliers.The trimming percentage for the data at hand is determined by cross validation.

The object tracking problem is an important research topic in computer vision. For real applications such as vehicle tracking and face tracking, there are many efficient and real-time algorithms. In this study, we will focus on the Lucas-Kanade (LK) algorithm for object tracking. Although this method is time consuming, it is effective in tracking accuracy and environment adaptation. In the standard LK method, the sum of squared errors is used as the cost function, while least trimmed squares is adopted as the cost function in this study. The resulting estimator is robust against outliers caused by noises and occlusions in the tracking process. Simulations are provided to show that the proposed algorithm outperforms the standard LK method in the sense that it is robust against the outliers in the object tracking problems.

The well-known sequential minimal optimization (SMO) algorithm is the most commonly used algorithm for numerical solutions of the support vector learning problems. At each iteration in the traditional SMO algorithm, also called 2PSMO algorithm in this paper, it jointly optimizes only two chosen parameters. The two parameters are selected either heuristically or randomly, whilst the optimization with respect to the two chosen parameters is performed analytically. The 2PSMO algorithm is naturally generalized to the three-parameter sequential minimal optimization (3PSMO) algorithm in this paper. At each iteration of this new algorithm, it jointly optimizes three chosen parameters. As in 2PSMO algorithm, the three parameters are selected either heuristically or randomly, whilst the optimization with respect to the three chosen parameters is performed analytically. Consequently, the main difference between these two algorithms is that the optimization is performed at each iteration of the 2PSMO algorithm on a line segment, whilst that of the 3PSMO algorithm on a two-dimensional region consisting of infinitely many line segments. This implies that the maximum can be attained more efficiently by 3PSMO algorithm. Main updating formulae of both algorithms for each support vector learning problem are presented. To assess the efficiency of the 3PSMO algorithm compared with the 2PSMO algorithm, 14 benchmark datasets, 7 for classification and 7 for regression, will be tested and numerical performances are compared. Simulation results demonstrate that the 3PSMO outperforms the 2PSMO algorithm significantly in both executing time and computation complexity.

Fuzzy neural network (FNN) has long been recognized as an efficient and powerful learning machine for general machine learning problems. Recently, Wilcoxon fuzzy neural network (WFNN), which generalizes the rank-based Wilcoxon approach for linear parametric regression problems to nonparametric neural network, was proposed aiming at improving robustness against outliers. FNN and WFNN are nonparametric models in the sense that they put no restrictions, except possibly smoothness, on the functional form of the regression function. However, they may be difficult to interpret and, even worse, yield poor estimates with high computational cost when the number of predictor variables is large. To overcome this drawback, semiparametric models have been proposed in statistical regression theory. A semiparametric model keeps the easy interpretability of its parametric part and retains the flexibility of its nonparametric part. Based on this, semiparametric FNN and semiparametric WFNN will be proposed in this paper. The learning rules are based on the backfitting procedure frequently used in semiparametric regression. Simulation results show that the semiparametric models perform better than their nonparametric counterparts.

In this paper, M-estimators, where M stands for maximum likelihood, used in robust regression theory for linear parametric regression problems will be generalized to nonparametric maximum likelihood fuzzy neural networks (MFNNs) for nonlinear regression problems. Emphasis is put particularly on the robustness against outliers. This provides alternative learning machines when faced with general nonlinear learning problems. Simple weight updating rules based on gradient descent and iteratively reweighted least squares (IRLS) will be derived. Some numerical examples will be provided to compare the robustness against outliers for usual fuzzy neural networks (FNNs) and the proposed MFNNs. Simulation results show that the MFNNs proposed in this paper have good robustness against outliers.

In this paper, a genetic algorithm with a hybrid select mechanism is proposed to speed up the fractal encoder. First, all of the image blocks including domain blocks and range blocks are classified into three classes: smooth; horizontal/vertical edge; and diagonal/sub-diagonal edge, according to their discrete cosine transformation (DCT) coefficients. Then, during the GA evolution, the population of every generation is separated into two clans: a superior clan and an inferior clan, according to whether the chromosome type is the same as that of the range block to be encoded or not. The hybrid select mechanism proposed by us is used to select appropriate parents from the two clans in order to reduce the number of MSE computations and maintain the retrieved image quality. Experimental results show that, since the number of MSE computations in the proposed GA method is about half of the traditional GA method, the encoding time for the proposed GA method is less than that of the traditional GA method. For retrieved image quality, the proposed GA method is almost the same as the traditional GA method or only has a little decay. Moreover, in comparison with the full search method, the encoding speed of the proposed GA method is some 130 times faster than that of the full search method, whereas the retrieved image quality is still relatively acceptable.

As is well known in statistics, the resulting linear regressors by using the rank-based Wilcoxon approach to linear regression problems are usually robust against (or insensitive to) outliers. This motivates us to introduce in this paper the Wilcoxon approach to the area of machine learning. Specifically, we investigate four new learning machines, namely Wilcoxon neural network (WNN), Wilcoxon generalized radial basis function network (WGRBFN), Wilcoxon fuzzy neural network (WFNN), and kernel-based Wilcoxon regressor (KWR). These provide alternative learning machines when faced with general nonlinear learning problems. Simple weights updating rules based on gradient descent will be derived. Some numerical examples will be provided to compare the robustness against outliers for various learning machines. Simulation results show that the Wilcoxon learning machines proposed in this paper have good robustness against outliers. We firmly believe that the Wilcoxon approach will provide a promising methodology for many machine learning problems.

This paper presents a particle swarm optimization (PSO) algorithm to solve the parameter estimation problem for nonlinear dynamic rational filters. For the modeling of the nonlinear rational filter, the unknown filter parameters are arranged in the form of a parameter vector which is called a particle in the terminology of PSO. The proposed PSO algorithm applies the velocity updating and position updating formulas to the population composed of many particles such that better particles are generated. Because the PSO algorithm manipulates the parameter vectors directly as real numbers rather than binary strings, implementing the PSO algorithm into the computer programs becomes fairly easy and straightforward. Finally, an illustrative example for the modeling of the nonlinear rational filter is provided to show the validity, as compared with the traditional genetic algorithm, of the proposed method.

In this paper, a general problem of the robust template decomposition with restricted weights for cellular neural networks (CNNs) implementing an arbitrary Boolean function is investigated. First, the geometric margin of a linear classifier with respect to a training data set is used to define the robustness of an uncoupled CNN implementing a linearly separable Boolean function. Second, maximal margin classifiers, i.e. robust CNNs, for such Boolean functions can be designed via support vector machines (SVMs). Third, some general properties of robust CNNs with or without restricted weights are discussed. Moreover, all robust CNNs with restricted weights are characterized. Finally, for an arbitrarily given Boolean function, we propose an algorithm, which is the generalized version of the well-known CFC algorithm, to find a sequence of robust uncoupled CNNs implementing the given Boolean function. Several illustrative examples demonstrate the efficiency of the proposed method. It will be seen that, in general, the tradeoff between the complexity regarding the number of terms in the decomposition and the guaranteed robustness regarding the geometric margins of the resulting CNNs must be made in the robust template decomposition with restricted weights.

In this paper, an approach of QR code detection using histograms of oriented gradients (HOG) and AdaBoost is proposed. There are two steps in our approach. In the first step, feature vectors are extracted using HOG with various cell sizes and overlapping or non-overlapping blocks. In the second step, the AdaBoost algorithms are trained by the input feature vectors from HOG and output targets. The QR code position is then detected via the predicted outputs from the AdaBoost algorithm. Experimental results show that the proposed method is an effective way to detect QR code position. Frankly speaking, the results reported here only provide preliminary study on QR code detection using HOG and AdaBoost.

Nowadays, touch panel is used as the interface of many portable consumer electronic products, such as smart phone, digital camera, GPS, and notebook. To ensure the quality of touch panel, it is necessary to inspect the serious defects during the production process. The manufacturing processes of the capacitive touch panel are complicated. The touch sensor is one of the most important components because it directly defines the function of touch panels. The quality of the touch sensor will greatly influence the overall quality and cost of the touch panel. Regular textures can be found on the touch sensor, and it would increase the workload of manual inspection. The automated machine vision can be applied to improve these problems if a good defect detection algorithm can be provided. This research develops an automated surface defect inspection system for capacitive touch sensor by using several image processing methods. First, Fourier transformation and a multi band-pass filter is applied to filter out regular texture. Second, based on Canny edge detection, binarization, and morphology method, the defects can be detected. 60 touch sensor images of size 640×320 are tested. The average accuracy is 96.67% and the processing time is 0.15 seconds for each image.

In this paper, a new approach is proposed for image super-resolution by combining morphological component analysis and least squares support vector machines. The proposed approach for image super-resolution consists of three steps. First, under morphological component analysis, the high resolution and low resolution images are individually decomposed into high and low frequency components, respectively. Second, the weights of two least squares support vector machines are trained by the low frequency components of the low/high resolution images and the high frequency component of low/high resolution images, respectively. Finally, the high resolution image is then reconstructed via sum of the predicted outputs from two least squares support vector machines. Experimental results show that the proposed super-resolution method performs better than the traditional bi-cubic interpolation method.

New algorithms are proposed in this paper for single image super-resolution using multiple dictionaries based on sparse representation. In the proposed algorithms, a classifier is constructed which is based on the edge properties of image patches via the two lowest discrete cosine transformation (DCT) coefficients. The classifier partitions all training patches into three classes. Training patches from each of the three classes can then be used for the training of the corresponding dictionary via the K-SVD (singular value decomposition) algorithm. Experimental results show that the high resolution image quality using the proposed algorithms is better than that using the traditional bi-cubic interpolation and Yang’s method.

This study explored the predictive value of disease insight for violent behavior for a group of Taiwanese schizophrenic outpatients over a one-year period. The Schedule of Assessment of Insight in Psychosis and its expanded version were used to provide a baseline insight score for sixty-three schizophrenic outpatients considered to be in remission or to have minimal psychopathology. A psychiatrist reassessed subjects at the end of the period to determine the predictive value of initial insight rating on the presence of violent behaviors. The binary logistic regression model was built first, which could explain 65.2 percent of the variance of patients' violent behavior tendency. Then, a support vector machine (SVM) was developed. After the training with cross validation, no misclassifications were found in the training data, and the average percentage of misclassification for the testing data was 23.8 percent, resulting in a 76.2 percent predictive power. These findings showed that SVM is more robust than ...

This project developed a Support Vector Machine for predicting nurses' intention to quit, using working motivation, job satisfaction, and stress levels as predictors. This study was conducted in three hospitals located in southern Taiwan. The target population was all nurses (389 valid cases). For cross-validation, we randomly split cases into four groups of approximately equal sizes, and performed four training runs. After the training, the average percentage of misclassification on the training data was 0.86, while that on the testing data was 10.8, resulting in predictions with 89.2% accuracy. This Support Vector Machine can predict nurses' intention to quit, without asking these nurses whether they have an intention to quit.

The object tracking problem is an important research topic in computer vision. For real applications such as vehicle tracking and face tracking, there are many efficient and real-time algorithms. In this study, we will focus on the Lucas-Kanade (LK) algorithm for object tracking. In the standard LK method, sum of squared errors is used as the cost function, while least trimmed squares is adopted as the cost function in this study. The resulting estimator is robust against outliers caused by noises in the tracking process. Simulation is provided to show that the proposed algorithm outperforms the standard LK method in the sense that it is robust against the outliers in the object tracking problem.

If the given Boolean function is linearly separable, a robust uncoupled cellular neural network can be designed as a maximal margin classifier. On the other hand, if the given Boolean function is linearly separable but has a small geometric margin or it is not linearly separable, a popular approach is to find a sequence of robust uncoupled cellular neural networks implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are restricted to assume only a given finite set of integers, and this is certainly unnecessary for the template design. In this study, we try to remove this restriction. Minterm- and maxterm-based decomposition algorithms utilizing the soft margin and maximal margin support vector classifiers are proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.

In traditional fractal image compression, the encoding procedure is time-consuming due to the full search mechanism. In order to speed-up the encoder, we adopt particle swarm optimization method performed under classification and Dihedral transformation to further decrease the amount of MSE computations. The classifier partitions all of the blocks in domain pool and range pool into three classes according to the third level wavelet coefficients. Each range block searches the most similar block only from the blocks of the same class. Furthermore, according to the property of Dihedral transformation, only four transformations for each domain block are considered so as to reduce the encoding time. Experimental results show that, the encoding time of the proposed method is faster than that of the full search method.

The well-known (two-parameter) sequential minimal optimization (2PSMO) algorithm for support vector classification is generalized to three-parameter sequential minimal optimization (3PSMO) algorithm in this paper. This new algorithm retains all the good properties of the former one. The main difference between these two algorithms is that the optimization is performed in each iteration of the 2PSMO algorithm on a line segment, whilst that of the 3PSMO algorithm on a region consisting of infinitely many line segments. Four public data sets are used to show the performance of both algorithms.

In this paper, an improved version of CFC algorithm is proposed. The main contribution is the reduction of a dimension in the search space. Moreover, the elements in the reduced search space are entries of control templates of uncoupled CNNs and the corresponding linearly separable Boolean functions are robust in the sense of maximal geometric margin. Illustrative examples demonstrate the efficiency of the proposed method.

A modified Rosenblatt's perceptron algorithm (1959) and Novikoff's theorem (1962) for binary classification problem is presented in this paper. For a linearly separable training set, the modified Rosenblatt's perceptron algorithm could get better convergence result. An example is provided to illustrate our main result.