Douglas C. Creighton

Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances

This paper evaluates the four leading techniques proposed in the literature for construction of prediction intervals (PIs) for neural network point forecasts. The delta, Bayesian, bootstrap, and mean-variance estimation (MVE) methods are reviewed and their performance for generating high-quality PIs is compared. PI-based measures are proposed and applied for the objective and quantitative assessment of each methods performance. A selection of 12 synthetic and real-world case studies is used to examine each methods performance for PI construction. The comparison is performed on the basis of the quality of generated PIs, the repeatability of the results, the computational requirements and the PIs variability with regard to the data uncertainty. The obtained results in this paper indicate that: 1) the delta and Bayesian methods are the best in terms of quality and repeatability, and 2) the MVE and bootstrap methods are the best in terms of low computational load and the width variability of PIs. This paper also introduces the concept of combinations of PIs, and proposes a new method for generating combined PIs using the traditional PIs. Genetic algorithm is applied for adjusting the combiner parameters through minimization of a PI-based cost function subject to two sets of restrictions. It is shown that the quality of PIs produced by the combiners is dramatically better than the quality of PIs obtained from each individual method.

Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals

Prediction intervals (PIs) have been proposed in the literature to provide more information by quantifying the level of uncertainty associated to the point forecasts. Traditional methods for construction of neural network (NN) based PIs suffer from restrictive assumptions about data distribution and massive computational loads. In this paper, we propose a new, fast, yet reliable method for the construction of PIs for NN predictions. The proposed lower upper bound estimation (LUBE) method constructs an NN with two outputs for estimating the prediction interval bounds. NN training is achieved through the minimization of a proposed PI-based objective function, which covers both interval width and coverage probability. The method does not require any information about the upper and lower bounds of PIs for training the NN. The simulated annealing method is applied for minimization of the cost function and adjustment of NN parameters. The demonstrated results for 10 benchmark regression case studies clearly show the LUBE method to be capable of generating high-quality PIs in a short time. Also, the quantitative comparison with three traditional techniques for prediction interval construction reveals that the LUBE method is simpler, faster, and more reliable.

Prediction Intervals to Account for Uncertainties in Travel Time Prediction

The accurate prediction of travel times is desirable but frequently prone to error. This is mainly attributable to both the underlying traffic processes and the data that are used to infer travel time. A more meaningful and pragmatic approach is to view travel time prediction as a probabilistic inference and to construct prediction intervals (PIs), which cover the range of probable travel times travelers may encounter. This paper introduces the delta and Bayesian techniques for the construction of PIs. Quantitative measures are developed and applied for a comprehensive assessment of the constructed PIs. These measures simultaneously address two important aspects of PIs: 1) coverage probability and 2) length. The Bayesian and delta methods are used to construct PIs for the neural network (NN) point forecasts of bus and freeway travel time data sets. The obtained results indicate that the delta technique outperforms the Bayesian technique in terms of narrowness of PIs with satisfactory coverage probability. In contrast, PIs constructed using the Bayesian technique are more robust against the NN structure and exhibit excellent coverage probability.

Efficient Road Detection and Tracking for Unmanned Aerial Vehicle

An unmanned aerial vehicle (UAV) has many applications in a variety of fields. Detection and tracking of a specific road in UAV videos play an important role in automatic UAV navigation, traffic monitoring, and ground-vehicle tracking, and also is very helpful for constructing road networks for modeling and simulation. In this paper, an efficient road detection and tracking framework in UAV videos is proposed. In particular, a graph-cut-based detection approach is given to accurately extract a specified road region during the initialization stage and in the middle of tracking process, and a fast homography-based road-tracking scheme is developed to automatically track road areas. The high efficiency of our framework is attributed to two aspects: the road detection is performed only when it is necessary and most work in locating the road is rapidly done via very fast homography-based tracking. Experiments are conducted on UAV videos of real road scenes we captured and downloaded from the Internet. The promising results indicate the effectiveness of our proposed framework, with the precision of 98.4% and processing 34 frames per second for 1046 × 595 videos on average.

Prediction Interval Construction and Optimization for Adaptive Neurofuzzy Inference Systems

The performance of an adaptive neurofuzzy inference system (ANFIS) significantly drops when uncertainty exists in the data or system operation. Prediction intervals (PIs) can quantify the uncertainty associated with ANFIS point predictions. This paper first presents a methodology to adapt the delta technique for the construction of PIs for outcomes of the ANFIS models. As the ANFIS models are linear in their consequent part, the ANFIS-based PIs are computationally less expensive than neural network (NN)-based PIs. Second, this paper proposes a method to optimize ANFIS-based PIs. A new PI-based cost function is developed for the training of the ANFIS models. A simulated annealing-based algorithm is applied to minimize the new nonlinear cost function and adjust the premise and consequent parameters of the ANFIS model. Using three real-world case studies, it is shown that ANFIS-based PIs are computationally less expensive than NN-based PIs. The application of the proposed optimization algorithm leads to better quality PIs than optimized NN-based PIs.

A prediction interval-based approach to determine optimal structures of neural network metamodels

Neural networks have been widely used in literature for metamodeling of complex systems and often outperform their traditional counterparts such as regression-based techniques. Despite proliferation of their applications, determination of their optimal structure is still a challenge, especially if they are developed for prediction and forecasting purposes. Researchers often seek a tradeoff between estimation accuracy and structure complexity of neural networks in a trial and error basis. On the other hand, the neural network point prediction performance considerably drops as the level of complexity and amount of uncertainty increase in systems that data originates from. Motivated by these trends and drawbacks, this research aims at adopting a technique for constructing prediction intervals for point predictions of neural network metamodels. Space search for neural network structures will be defined and confined based on particular features of prediction intervals. Instead of using traditional selection criteria such as mean square error or mean absolute percentage error, prediction interval coverage probability and normalized mean prediction interval will be used for selecting the optimal network structure. The proposed method will be then applied for metamodeling of a highly detailed discrete event simulation model which is essentially a validated virtual representation of a large real world baggage handling system. Through a more than 77% reduction in number of potential candidates, optimal structure for neural networks is found in a manageable time. According to the demonstrated results, constructed prediction intervals using optimal neural network metamodel have a satisfactory coverage probability of targets with a low mean of length.

Recent Advances on Singlemodal and Multimodal Face Recognition: A Survey

High performance for face recognition systems occurs in controlled environments and degrades with variations in illumination, facial expression, and pose. Efforts have been made to explore alternate face modalities such as infrared (IR) and 3-D for face recognition. Studies also demonstrate that fusion of multiple face modalities improve performance as compared with singlemodal face recognition. This paper categorizes these algorithms into singlemodal and multimodal face recognition and evaluates methods within each category via detailed descriptions of representative work and summarizations in tables. Advantages and disadvantages of each modality for face recognition are analyzed. In addition, face databases and system evaluations are also covered.

Classification of healthcare data using genetic fuzzy logic system and wavelets

Introduce GSAM model by incorporating genetic algorithm in SAM learning process.GSAM learning has lower computational costs and higher efficiency compared to SAM.Employ wavelet transformation for feature extraction in high-dimensional datasets.This is the first application of fuzzy SAM method in medical diagnosis.This is the first combination of wavelets and fuzzy SAM applied in classification. Healthcare plays an important role in promoting the general health and well-being of people around the world. The difficulty in healthcare data classification arises from the uncertainty and the high-dimensional nature of the medical data collected. This paper proposes an integration of fuzzy standard additive model (SAM) with genetic algorithm (GA), called GSAM, to deal with uncertainty and computational challenges. GSAM learning process comprises three continual steps: rule initialization by unsupervised learning using the adaptive vector quantization clustering, evolutionary rule optimization by GA and parameter tuning by the gradient descent supervised learning. Wavelet transformation is employed to extract discriminative features for high-dimensional datasets. GSAM becomes highly capable when deployed with small number of wavelet features as its computational burden is remarkably reduced. The proposed method is evaluated using two frequently-used medical datasets: the Wisconsin breast cancer and Cleveland heart disease from the UCI Repository for machine learning. Experiments are organized with a five-fold cross validation and performance of classification techniques are measured by a number of important metrics: accuracy, F-measure, mutual information and area under the receiver operating characteristic curve. Results demonstrate the superiority of the GSAM compared to other machine learning methods including probabilistic neural network, support vector machine, fuzzy ARTMAP, and adaptive neuro-fuzzy inference system. The proposed approach is thus helpful as a decision support system for medical practitioners in the healthcare practice.

Real Time Ergonomic Assessment for Assembly Operations Using Kinect

Ergonomic assessments assist in preventing work related musculoskeletal injuries and provide safer workplace environments. The 3D motion capture environments are not suitable for many work places due to space, cost and calibration limitations. The Kinect sensor, which was introduced in the Xbox game console, provides a low-cost portable motion capture system. This sensor is capable of capturing and tracking 3D coordinates of a moving target with an accuracy comparable to state of the art commercial systems. This paper investigates the application of Kinect for real time rapid upper limb assessment (RULA) to aid in ergonomic analysis for assembly operations in industrial environments. A framework to integrate various motion capture technologies as well as different assessment methods is presented.

EEG signal classification for BCI applications by wavelets and interval type-2 fuzzy logic systems

Propose Haar wavelet transformation and ROC curve for EEG signal feature extraction.Combine wavelets and interval type-2 fuzzy logic system for EEG signal classification.Benchmark datasets downloaded from the BCI competition II are used for experiments.Proposed wavelet-IT2FLS outperforms the winner methods of the BCI competition II.IT2FLS dominates competing classifiers: FFNN, SVM, kNN, AdaBoost and ANFIS. The nonlinear, noisy and outlier characteristics of electroencephalography (EEG) signals inspire the employment of fuzzy logic due to its power to handle uncertainty. This paper introduces an approach to classify motor imagery EEG signals using an interval type-2 fuzzy logic system (IT2FLS) in a combination with wavelet transformation. Wavelet coefficients are ranked based on the statistics of the receiver operating characteristic curve criterion. The most informative coefficients serve as inputs to the IT2FLS for the classification task. Two benchmark datasets, named Ia and Ib, downloaded from the brain-computer interface (BCI) competition II, are employed for the experiments. Classification performance is evaluated using accuracy, sensitivity, specificity and F-measure. Widely-used classifiers, including feedforward neural network, support vector machine, k-nearest neighbours, AdaBoost and adaptive neuro-fuzzy inference system, are also implemented for comparisons. The wavelet-IT2FLS method considerably dominates the comparable classifiers on both datasets, and outperforms the best performance on the Ia and Ib datasets reported in the BCI competition II by 1.40% and 2.27% respectively. The proposed approach yields great accuracy and requires low computational cost, which can be applied to a real-time BCI system for motor imagery data analysis.