Search

The purpose of this study was to evaluate and compare smile treatment outcomes between patients treated with Invisalign clear aligners (Align Technology, Santa Clara, Calif) and those treated with traditional fixed appliances by integrating variables such as lip symmetry, smile index, smile cant, buccal corridors, and gingival display into smile outcome evaluation.Records from 58 patients, 29 of whom received Invisalign treatment (mean age 19.03 years) and 29 of whom received traditional fixed-appliance treatment (mean age 13.83 years), were compared for their smile outcome. Pretreatment scores, posttreatment scores, and differences between within-group smile score before and after treatment were determined for each group. Fifteen variables comprised the smile outcome, and the data were analyzed with the Mann-Whitney U test and the Wilcoxon t test for 2 dependent samples.Six variables within the fixed-appliance group presented with better smile scores than those within the Invisalign group; buccal corridors (%) (mean difference = 8.42%), buccal corridors (mm) (5.35 mm), smile cant (0.42°), maxillary dental midline (0.21 mm), gingival display (0.56 mm), and smile index (1.09%) for P 0.05. Invisalign performed better on 2 variables that determined maxillary incisor position (1.26 mm) and inclination (2.09°). No significant difference (for P = 0.05) was shown between pretreatment and posttreatment scores for either of the 2 groups.Using the 15 variables in this study, the results suggested that for patients with Class I nonextraction, treatment with traditional fixed appliances changes the patient's smile more than Invisalign treatment, and fixed appliances appear to be more effective in improving the variables that quantify posttreatment smile outcome.

This manuscript presents a streamlined protocol to generate and classify synthetic random wind samples. The manuscript is accompanied with a comprehensive and publicly accessible repository...

This article introduces a method that can automatically classify the hemiplegia type (right or left side of the body is paralyzed) between healthy and non-healthy subjects. The proposed method utilizes the data taken from the accelerometer sensor of the RehaGait mobile gait analysis system. These data undergo a pre-processing and feature extraction stage before being sent as input to a scaled conjugate gradient backpropagation (SCG-BP) trained neural network. The proposed system is tested using a custom-created dataset containing 10 healthy and 20 patients suffering from hemiplegia (right or left). The experimental part of the system utilized 7 sensors placed on the left and right foot, the left and right shank, the left and right thigh, and the hip of each subject. Each sensor captured a 3-dimensional (3D) signal from 3 different device types: accelerometer, magnetometer, and gyroscope. The system utilized and split into 2-second windows only the accelerometer data, achieving a classification accuracy of 87.71%.

In this paper, a hybrid learning approach, which combines the extreme learning machine (ELM) with a genetic algorithm (GA), is proposed. The utilization of this hybrid algorithm enables the creation of heterogeneous single layer neural networks (SLNNs) with better generalization ability than traditional ELM in terms of lower mean square error (MSE) for regression problems or higher accuracy for classification problems. The architecture of this method is not limited to traditional linear neurons, where each input participates equally to the neuron’s activation, but is extended to support higher order neurons which affect the network’s generalization ability. Initially, the proposed heterogeneous hybrid extreme learning machine (He-HyELM) algorithm creates a number of custom created neurons with different structure, which are used for the creation of homogeneous SLNNs. These networks are trained with ELM and an application specific GA evolves them into heterogeneous networks according to a fitness criterion utilizing the uniform crossover operator for the recombination process. After the completion of the evolution process, the network with the best fitness is selected as the most optimal. Experimental results demonstrate that the proposed learning algorithm can get better results than traditional ELM, homogeneous hybrid extreme learning machine (Ho-HyELM) and optimally pruned extreme learning machine (OP-ELM) for homogeneous and heterogeneous SLNNs.

Alzheimer’s Disease (AD) is a neurodegenerative disorder and the most common type of dementia with a great prevalence in western countries. The diagnosis of AD and its progression is performed through a variety of clinical procedures including neuropsychological and physical examination, Electroencephalographic (EEG) recording, brain imaging and blood analysis. During the last decades, analysis of the electrophysiological dynamics in AD patients has gained great research interest, as an alternative and cost-effective approach. This paper summarizes recent publications focusing on (a) AD detection and (b) the correlation of quantitative EEG features with AD progression, as it is estimated by Mini Mental State Examination (MMSE) score. A total of 49 experimental studies published from 2009 until 2020, which apply machine learning algorithms on resting state EEG recordings from AD patients, are reviewed. Results of each experimental study are presented and compared. The majority of the studies focus on AD detection incorporating Support Vector Machines, while deep learning techniques have not yet been applied on large EEG datasets. Promising conclusions for future studies are presented.

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor&rsquo, s accuracy, thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 &deg, C for the refrigeration and freezer areas. The purpose of the proposed method is to improve the accuracy of a low-cost digital temperature sensor by correcting its nonlinear response using simple linear regression (SLR). In the experimental part of this study, the proposed method&rsquo, s outcome (in a custom created dataset containing values taken from a refrigerator) is compared against the values taken from a sensor complying with the EN12830 standard. The experimental results confirmed that the proposed method reduced the mean absolute error (MAE) by 82% for the refrigeration area and 69% for the freezer area&mdash, resulting in the accuracy improvement of the low-cost digital temperature sensor. Moreover, it managed to achieve a lower generalization error on the test set when compared to three other machine learning algorithms (SVM, B-ELM, and OS-ELM).

Nonalcoholic fatty liver disease (NAFLD) is one of the most frequent liver conditions representing a wide range of intrahepatic disorders, varying from steatosis to nonalcoholic steatohepatitis (NASH). Steatosis refers to the accumulation of benign fat cells, which at higher rates leads to NASH progression, as the major risk factor for hepatic fibrosis and cirrhosis, as well as for hepatocellular carcinoma (HCC). In recent years the medical field has focused on preventing the progression of these diseases, with microscopic biopsy images being the gold standard imaging modality in modern clinical trials. The proposed work aims at the high classification ability of four histological liver structures, by training a convolutional neural network (CNN) and comparing its diagnostic performance with various pre-trained deep CNN architectures. All diagnostic attempts were made on an augmented image dataset, with the new CNN model achieving a 95.8% classification accuracy, while AlexNet emerging as the most efficient architecture with a corresponding performance of 97.8%.

This paper presents a hybrid algorithm for the creation of heterogeneous single layer neural networks (SLNNs). The proposed self-adaptive heterogeneous hybrid extreme learning machine (SA-He-HyELM) trains a series of SLNNs with different neuron types in the hidden layer utilizing the extreme learning machine (ELM) algorithm. These networks are evolved into heterogeneous networks (networks having different combinations of hidden neurons) with the help of a modified genetic algorithm (GA). The algorithm is able to handle two architecturally different neuron types: traditional low order (linear) units and higher order units with different transfer functions. The GA is fully self-adaptive and uses one novel hybrid crossover operator along with a self-adaptive mutation operator in order to retain ELM’s simplicity and minimize the number of parameters need tuning. The experimental part of the current paper involves testing SA-He-HyELM with traditional ELM and other three ELM-based methods. The experimental part utilized a series of regression and classification experiments on relatively large datasets. In all cases the proposed method managed to get lower MSE or higher classification accuracy when compared to the aforementioned methods.

Structures in a power transmission network, such as towers and conductors, are vulnerable to hurricanes. Failures of these structures trip transmission lines and usually result in large scale power outages in the region. This paper presents a technique for the probabilistic simulation of power transmission systems under hurricane events and provides fundamental insights on the modeling and quantification of power system performance and resilience. The study models the power transmission system as a network of connected individual components, which are subjected to wind-induced mechanical failure and power flow constraints. A realistic power transmission network is developed for the study region. The geographical data are obtained for all components in the network based on a data collection and image processing campaign to reflect the realistic properties of the network serving the Lehigh Valley, PA. A hurricane simulator is utilized to generate a hurricane scenario providing time-varying wind intensities and wind directions for the component failure analysis. The spatio-temporal impact of the hurricane is investigated: a pool of component fragilities is generated to effectively incorporate the uncertainties in structural capacities into the analysis; the spatial correlation among structures is modeled efficiently by a random field based technique. At the system level, Monte Carlo simulation is adopted to determine the failure probability of transmission lines. The unmet demand of the system is computed probabilistically, based on the alternate current optimal power flow analysis, capacity constraints and load shedding process of the system. The simulation results can be used to quantify and visualize the power network performance, and help decision makers to identify critical components in the network to optimize the short-term pre-event preparation for an approaching hurricane and long-term retrofit strategy to enhance system resilience.

The deterioration of reinforced concrete (RC) structures due to chloride-induced corrosion is not spatially uniform because of the spatial variability related to material properties and environmental stressors. This variation has a substantial effect on the reliability of RC structures. However, few experimental studies have focused on the effect of the interaction of corrosion pits among tensile rebars on the reliability of RC structures. Therefore, in this paper, an experimental procedure that incorporates X-ray and digital image processing techniques was conducted on RC slab specimens subjected to accelerated corrosion. Using the experimental results, the parameter of the transverse correlation function of steel weight loss distributions was estimated to investigate how the corrosion pits in corroded rebars are correlated. Based on the experimentally obtained model parameters, the spatial steel weight loss distributions were simulated by spectral representation method. A three-dimensional (3D) nonlinear finite element (FE) analysis of RC structures with simulated steel weight loss distributions was conducted to obtain the ultimate bending capacity of RC structures. In an illustrative example, the effect of the transverse correlation among steel weight loss distributions of multiple tensile rebars on the failure probability of RC girders was quantified.

Non-alcoholic fatty liver disease (NAFLD) covers a range of chronic medical conditions varying from hepatocellular inflammation which characterizes nonalcoholic steatohepatitis (NASH) to steatosis, as the key element of a nonalcoholic fatty liver (NAFL). It is globally linked to the increasing prevalence of obesity and other components of metabolic syndrome and is expected to be the main indication for the existence of the liver disease in the coming years. Its eradication has become a major challenge due to the difficulties in clinical diagnosis, complex pathogenesis and the lack of approved therapies. In this study, an automated image analysis method is presented providing quantitative assessments of fat deposition in steatotic liver biopsy specimens. The methodology applies image processing, machine learning and evolutionary algorithm optimization techniques, producing a 1.93% mean classification error compared to the semiquantitative interpretations of specialized hepatologists.

Discrimination of eye movements and visual states is a flourishing field of research and there is an urgent need for non-manual EEG-based wheelchair control and navigation systems. This paper presents a novel system that utilizes a brain–computer interface (BCI) to capture electroencephalographic (EEG) signals from human subjects while eye movement and subsequently classify them into six categories by applying a random forests (RF) classification algorithm. RF is an ensemble learning method that constructs a series of decision trees where each tree gives a class prediction, and the class with the highest number of class predictions becomes the model’s prediction. The categories of the proposed random forests brain–computer interface (RF-BCI) are defined according to the position of the subject’s eyes: open, closed, left, right, up, and down. The purpose of RF-BCI is to be utilized as an EEG-based control system for driving an electromechanical wheelchair (rehabilitation device). The proposed approach has been tested using a dataset containing 219 records taken from 10 different patients. The BCI implemented the EPOC Flex head cap system, which includes 32 saline felt sensors for capturing the subjects’ EEG signals. Each sensor caught four different brain waves (delta, theta, alpha, and beta) per second. Then, these signals were split in 4-second windows resulting in 512 samples per record and the band energy was extracted for each EEG rhythm. The proposed system was compared with naïve Bayes, Bayes Network, k-nearest neighbors (K-NN), multilayer perceptron (MLP), support vector machine (SVM), J48-C4.5 decision tree, and Bagging classification algorithms. The experimental results showed that the RF algorithm outperformed compared to the other approaches and high levels of accuracy (85.39%) for a 6-class classification are obtained. This method exploits high spatial information acquired from the Emotiv EPOC Flex wearable EEG recording device and examines successfully the potential of this device to be used for BCI wheelchair technology.

A significant amount of problems and applications in stochastic mechanics and engineering involve multi-dimensional random functions. The probabilistic analysis of these problems is usually computationally very expensive if a brute-force Monte Carlo method is used. Thus, a technique for the optimal selection of a moderate number of samples effectively representing the entire space of sample realizations is of paramount importance. Functional Quantization is a novel technique that has been proven to provide optimal approximations of random functions using a predetermined number of representative samples. The methodology is very easy to implement and it has been shown to work effectively for stationary and non-stationary one-dimensional random functions. This paper discusses the application of the Functional Quantization approach to the domain of multi-dimensional random functions and the applicability is demonstrated for the case of a 2D non-Gaussian field and a two-dimensional panel with uncertain Young modulus under plane stress.

A novel method for the implementation of parallel genetic algorithms is introduced to locate the global minimum of a multidimensional function inside a rectangular hyperbox. The algorithm relies on...

Power transmission conductors work as links in power transmission system. They allow the bulk transportation of energy between power plants and substations. A large number of these conductors may fail when subjected to hurricanes. Failure of these conductors may result in significant disruption in the power network and millions of dollars of replacement cost. This paper presents a framework for the development of fragility models of the transmission conductors. The framework considers the uncertainties in the wind turbulence and conductor capacity. The modal superposition method has been used to model the mechanical response of the conductors efficiently, and is validated by nonlinear finite element analysis. The first order reliability method has been implemented to capture the low failure probability of a single conductor with sufficient accuracy as confirmed by Monte Carlo simulation. The results of this study show that the failure probability of the conductors increases significantly once the wind speed reaches a certain critical value. The wind direction and span length have large influence on the failure probability. Therefore, the variability of span lengths over the transmission network has a substantial effect on the overall system failure. The fragility model provided in this research constitutes a major component for risk assessment of power transmission networks against hurricane hazards. It can be used to help engineers gain fundamental insights on the mechanical and probabilistic performance of power transmission conductors.

Nonalcoholic fatty liver disease (NAFLD) is responsible for a wide range of pathological disorders. It is characterized by the prevalence of steatosis, which results in excessive accumulation of triglyceride in the liver tissue. At high rates, it can lead to a partial or total occlusion of the organ. In contrast, nonalcoholic steatohepatitis (NASH) is a progressive form of NAFLD, with the inclusion of hepatocellular injury and inflammation histological diseases. Since there is no approved pharmacotherapeutic solution for both conditions, physicians and engineers are constantly in search for fast and accurate diagnostic methods. The proposed work introduces a fully automated classification approach, taking into consideration the high discrimination capability of four histological tissue alterations. The proposed work utilizes a deep supervised learning method, with a convolutional neural network (CNN) architecture achieving a classification accuracy of 95%. The classification capability of the new CNN model is compared with a pre-trained AlexNet model, a visual geometry group (VGG)-16 deep architecture and a conventional multilayer perceptron (MLP) artificial neural network. The results show that the constructed model can achieve better classification accuracy than VGG-16 (94%) and MLP (90.3%), while AlexNet emerges as the most efficient classifier (97%).

The paper presents a methodology for the selection of an optimal set of stochastic intensity measure (IM) maps representing the regional hazard over a geographic area, which can subsequentl...

The modeling of multiple hazards for regional risk assessment has attracted increasing interest during the last years, and several methods have been developed. Traditional hazard maps concisely present the probabilistic frequency and magnitude of natural hazards. However, these maps have been developed for the analysis of individual sites. Instead, the probabilistic risk assessment for spatially distributed systems is a much more complex problem, and it requires more information than what is provided by traditional hazard maps. Engineering problems dealing with interdependent systems, such as lifeline risk assessment or regional loss estimation, are highly coupled, and thus it is necessary to know the probability of having simultaneously certain values of the intensity measure (e.g., peak ground acceleration) at all locations of interest. Therefore, the problem of quantifying and modeling the spatial correlation between pairs of geographically distributed points has been addressed in several different ways. In this chapter, a brief review of some of these approaches is provided. Then, a new methodology is presented for the generation of an optimal set of maps, representing the intensity measure of a natural disaster over a region. This methodology treats the intensity measures as two-dimensional, non-homogeneous, non-Gaussian random fields. Thus, it can take advantage of probabilistic tools for the optimal sampling of multidimensional stochastic functions. Even with few sample maps generated in this way, it is possible to capture accurately the hazard at all individual sites, as well as the spatial correlation among the disaster intensities at the various locations. The framework of random field theory enables a very elegant formulation of the problem, which can be applied to all types of hazards with minimal adjustments. This makes the proposed methodology particularly appropriate for multi-hazard analysis.

This paper presents a methodology to simulate multi-dimensional non-Gaussian random fields and uses this to model, in a probabilistic sense, the spatial distribution of corrosion in a steel beam. In particular, the proposed approach is an extension of a recently developed iterative technique that generates one-dimensional, uni-variate sample functions of non-Gaussian random fields and processes. The contribution of this work is the extension to the case of multi-dimensional random functions and its application to a steel cantilever beam with simulation of corrosion penetration. The amount of corrosion is modeled as a random field and applied to a finite element mesh on the top flange. The field matches both the arbitrarily prescribed spectral density function and the non-Gaussian marginal distribution. The effect of the spatial variability of the corrosion on the flange is evaluated using the tip displacement as representative structural response metric, while a series of finite element analyses are performed for a Monte Carlo simulation. The results show that the spatial variability has a substantial effect on the structural response and an equivalent deterministic model with the same average corrosion uniformly distributed would not capture properly the structural behavior.