Search results for: regularization

Authors: A. Bere, H. G. Sithuba, K. Kyei, C. Sigauke

Abstract:

We employ a discrete logit survival model to investigate the risk factors for early alcohol intake among students at two tertiary institutions in Thohoyandou, South Africa. Data were collected from a sample of 744 students using a self-administered questionnaire. Significant covariates were arrived at through a regularization algorithm implemented using the glmmLasso package. The tuning parameter was determined using a five-fold cross-validation algorithm. The baseline hazard was modelled as a smooth function of time through the use of spline functions. The results show that the hazard of initial alcohol intake peaks at the age of about 16 years and that at any given time, being of a male gender, prior use of other drugs, having drinking peers, having experienced negative life events and physical abuse are associated with a higher risk of alcohol intake debut.

Keywords: cross-validation, discrete hazard model, LASSO, smooth baseline hazard

Procedia PDF Downloads 157

Authors: Ali Pour Yazdanpanah, Farideh Foroozandeh Shahraki, Emma Regentova

Abstract:

The reconstruction from sparse-view projections is one of important problems in computed tomography (CT) limited by the availability or feasibility of obtaining of a large number of projections. Traditionally, convex regularizers have been exploited to improve the reconstruction quality in sparse-view CT, and the convex constraint in those problems leads to an easy optimization process. However, convex regularizers often result in a biased approximation and inaccurate reconstruction in CT problems. Here, we present a nonconvex, Lipschitz continuous and non-smooth regularization model. The CT reconstruction is formulated as a nonconvex constrained L1 − L2 minimization problem and solved through a difference of convex algorithm and alternating direction of multiplier method which generates a better result than L0 or L1 regularizers in the CT reconstruction. We compare our method with previously reported high performance methods which use convex regularizers such as TV, wavelet, curvelet, and curvelet+TV (CTV) on the test phantom images. The results show that there are benefits in using the nonconvex regularizer in the sparse-view CT reconstruction.

Keywords: computed tomography, non-convex, sparse-view reconstruction, L1-L2 minimization, difference of convex functions

Procedia PDF Downloads 283

Authors: Kefaya Qaddoum

Abstract:

Most of greenhouse growers desire a determined amount of yields in order to accurately meet market requirements. The purpose of this paper is to model a simple but often satisfactory supervised classification method. The original naive Bayes have a serious weakness, which is producing redundant predictors. In this paper, utilized regularization technique was used to obtain a computationally efficient classifier based on naive Bayes. The suggested construction, utilized L1-penalty, is capable of clearing redundant predictors, where a modification of the LARS algorithm is devised to solve this problem, making this method applicable to a wide range of data. In the experimental section, a study conducted to examine the effect of redundant and irrelevant predictors, and test the method on WSG data set for tomato yields, where there are many more predictors than data, and the urge need to predict weekly yield is the goal of this approach. Finally, the modified approach is compared with several naive Bayes variants and other classification algorithms (SVM and kNN), and is shown to be fairly good.

Keywords: tomato yield prediction, naive Bayes, redundancy, WSG

Procedia PDF Downloads 204

Authors: Osama A. Omer, Amal Hamed

Abstract:

Successful blind image Super-Resolution algorithms require the exact estimation of the Point Spread Function (PSF). In the absence of any prior information about the imagery system and the true image; this estimation is normally done by trial and error experimentation until an acceptable restored image quality is obtained. Multi-frame blind Super-Resolution algorithms often have disadvantages of slow convergence and sensitiveness to complex noises. This paper presents a Super-Resolution image reconstruction algorithm based on estimation of the PSF that yields the optimum restored image quality. The estimation of PSF is performed by the knife-edge method and it is implemented by measuring spreading of the edges in the reproduced HR image itself during the reconstruction process. The proposed image reconstruction approach is using L1 norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models. A series of experiment results show that the proposed method can outperform other previous work robustly and efficiently.

Keywords: blind, PSF, super-resolution, knife-edge, blurring, bilateral, L1 norm

Procedia PDF Downloads 334

Authors: Benjamin Bobbia, Matthias Picard

Abstract:

In recent years active learning methodologies based on the representativity of the data seems more promising to limit overfitting. The presented query methodology for regression using the Wasserstein distance measuring the representativity of our labelled dataset compared to the global distribution. In this work a crucial use of GroupSort Neural Networks is made therewith to draw a double advantage. The Wasserstein distance can be exactly expressed in terms of such neural networks. Moreover, one can provide explicit bounds for their size and depth together with rates of convergence. However, heterogeneity of the dataset is also considered by weighting the Wasserstein distance with the error of approximation at the previous step of active learning. Such an approach leads to a reduction of overfitting and high prediction performance after few steps of query. After having detailed the methodology and algorithm, an empirical study is presented in order to investigate the range of our hyperparameters. The performances of this method are compared, in terms of numbers of query needed, with other classical and recent query methods on several UCI datasets.

Keywords: active learning, Lipschitz regularization, neural networks, optimal transport, regression

Procedia PDF Downloads 53

Authors: Fatemeh Valizadeh Gamchi, Edward L. Boone

Abstract:

This research focuses on Lyme disease, a widespread infectious condition in the United States caused by the bacterium Borrelia burgdorferi sensu stricto. It is critical to identify environmental and economic elements that are contributing to the spread of the disease. This study examined data from Virginia to identify a subset of explanatory variables significant for Lyme disease case numbers. To identify relevant variables and avoid overfitting, linear poisson, and regularization regression methods such as a ridge, lasso, and elastic net penalty were employed. Cross-validation was performed to acquire tuning parameters. The methods proposed can automatically identify relevant disease count covariates. The efficacy of the techniques was assessed using four criteria on three simulated datasets. Finally, using the Virginia Department of Health’s Lyme disease data set, the study successfully identified key factors, and the results were consistent with previous studies.

Keywords: lyme disease, Poisson generalized linear model, ridge regression, lasso regression, elastic net regression

Procedia PDF Downloads 87

Authors: Kang-Mo Jung

Abstract:

The use of regularization for statistical methods has become popular. The least absolute shrinkage and selection operator (LASSO) framework has become the standard tool for sparse regression. However, it is well known that the LASSO is sensitive to outliers or leverage points. We consider a new robust estimation which is composed of the weighted loss function of the pairwise difference of residuals and the adaptive penalty function regulating the tuning parameter for each variable. Rank regression is resistant to regression outliers, but not to leverage points. By adopting a weighted loss function, the proposed method is robust to leverage points of the predictor variable. Furthermore, the adaptive penalty function gives us good statistical properties in variable selection such as oracle property and consistency. We develop an efficient algorithm to compute the proposed estimator using basic functions in program R. We used an optimal tuning parameter based on the Bayesian information criterion (BIC). Numerical simulation shows that the proposed estimator is effective for analyzing real data set and contaminated data.

Keywords: adaptive penalty function, robust penalized regression, variable selection, weighted rank regression

Procedia PDF Downloads 429

Authors: Eugene Stepanov, Arkadi Ponossov

Abstract:

Many mathematical models used in biological and other applications are ill-posed. The reason for that is the nature of differential equations, where the nonlinearities are assumed to be step functions, which is done to simplify the analysis. Prominent examples are switched systems arising from gene regulatory networks and neural field equations. This simplification leads, however, to theoretical and numerical complications. In the presentation, it is proposed to apply the theory of hybrid feedback controls to regularize the problem. Roughly speaking, one attaches a finite state control (‘automaton’), which follows the trajectories of the original system and governs its dynamics at the points of ill-posedness. The construction of the automaton is based on the classification of the attractors of the specially designed adjoint dynamical system. This ‘hybridization’ is shown to regularize the original switched system and gives rise to efficient hybrid numerical schemes. Several examples are provided in the presentation, which supports the suggested analysis. The method can be of interest in other applied fields, where differential equations contain step-like nonlinearities.

Keywords: hybrid feedback control, ill-posed problems, singular perturbation analysis, step-like nonlinearities

Procedia PDF Downloads 208

Authors: Hsien-Wei Kuo

Abstract:

The thoughts of the military citizens, pragmatism, naturalism and nationalism related to physical education were developed during the warring period of the Republic of China. Moreover, the development of martial art formed by nationalism and political party was to utilize to save the nation, the people and the world. The martial art was also promoted in the system of school physical education gradually at the same time. The aim of this study is to explore the role, duty and position of the martial art education with the political color and advocacy in the system of school physical education. This study focuses on the practice, course hours, selective materials and competitive rules of physical education in the school system in modern China. Therefore, the methods of the historical research and content analysis were used to collect the historical materials and documents for going into them. The results will give a detailed account of the developed model of institutionalization, unification and regularization of martial art, and its growing, golden and stagnant periods in the school physical education system under the impact of western sport and physical education. It may sum up the meaning relationships among the politics, education practice and sport for all.

Keywords: martial art education, national martial arts institution, sick man of East Asia, the may 4th movement

Procedia PDF Downloads 346

Authors: Anita Kushwaha

Abstract:

We propose a new evolutionary computational model called Artificial Reproduction System which is based on the complex process of meiotic reproduction occurring between male and female cells of the living organisms. Artificial Reproduction System is an attempt towards a new computational intelligence approach inspired by the theoretical reproduction mechanism, observed reproduction functions, principles and mechanisms. A reproductive organism is programmed by genes and can be viewed as an automaton, mapping and reducing so as to create copies of those genes in its off springs. In Artificial Reproduction System, the binding mechanism between male and female cells is studied, parameters are chosen and a network is constructed also a feedback system for self regularization is established. The model then applies Mendel’s law of inheritance, allele-allele associations and can be used to perform data analysis of imbalanced data, multivariate, multiclass and big data. In the experimental study Artificial Reproduction System is compared with other state of the art classifiers like SVM, Radial Basis Function, neural networks, K-Nearest Neighbor for some benchmark datasets and comparison results indicates a good performance.

Keywords: bio-inspired computation, nature- inspired computation, natural computing, data mining

Procedia PDF Downloads 234

Authors: Yoonsuh Jung

Abstract:

As DNA microarray data contain relatively small sample size compared to the number of genes, high dimensional models are often employed. In high dimensional models, the selection of tuning parameter (or, penalty parameter) is often one of the crucial parts of the modeling. Cross-validation is one of the most common methods for the tuning parameter selection, which selects a parameter value with the smallest cross-validated score. However, selecting a single value as an "optimal" value for the parameter can be very unstable due to the sampling variation since the sample sizes of microarray data are often small. Our approach is to choose multiple candidates of tuning parameter first, then average the candidates with different weights depending on their performance. The additional step of estimating the weights and averaging the candidates rarely increase the computational cost, while it can considerably improve the traditional cross-validation. We show that the selected value from the suggested methods often lead to stable parameter selection as well as improved detection of significant genetic variables compared to the tradition cross-validation via real data and simulated data sets.

Keywords: cross validation, parameter averaging, parameter selection, regularization parameter search

Procedia PDF Downloads 382

Authors: Siddharth Vashisth, Varun Mathur

Abstract:

This review provides an overview of the impact that implementation of various Knowledge Management (KM) strategies has had on the growth of a department in a Public Sector Company in India. In a regulated utility controlled by the government, the growth of an organization such as Hindustan Petroleum Corporation Limited (HPCL) had depended largely on the efficiencies of the systems and its people. However, subsequent to the de-regularization & to the entry of the private competition, the need for a ‘systematic templating’ of knowledge was recognized. This necessitated the introduction of Knowledge Management Centre (KMC). Projects & Pipelines Department (P&P) of HPCL introduced KMC that contributed significantly towards KM by adopting various strategies such as standardization, leveraging information system, competency enhancement, and improvements & innovations. These strategies gave both tangible as well as intangible benefits towards KM. Knowledge, technology & people are the three pillars that need to be catered for effective knowledge management in any organization. In HPCL, the initiative of KMC has served as an intermediary between these three major pillars as each activity of the strategy was centered on them and contributed significantly to their growth and up-gradation, ensuring overall growth of KM in the department.

Keywords: knowledge, knowledge management, public sector organization, standardization, technology, people, skill, information system, innovation, competency, impact

Procedia PDF Downloads 414

Authors: Rachida Ouysse

Abstract:

This paper proposes a constrained principal components (CnPC) estimator for efficient estimation of large-dimensional factor models when errors are cross sectionally correlated and the number of cross-sections (N) may be larger than the number of observations (T). Although principal components (PC) method is consistent for any path of the panel dimensions, it is inefficient as the errors are treated to be homoskedastic and uncorrelated. The new CnPC exploits the assumption of bounded cross-sectional dependence, which defines Chamberlain and Rothschild’s (1983) approximate factor structure, as an explicit constraint and solves a constrained PC problem. The CnPC method is computationally equivalent to the PC method applied to a regularized form of the data covariance matrix. Unlike maximum likelihood type methods, the CnPC method does not require inverting a large covariance matrix and thus is valid for panels with N ≥ T. The paper derives a convergence rate and an asymptotic normality result for the CnPC estimators of the common factors. We provide feasible estimators and show in a simulation study that they are more accurate than the PC estimator, especially for panels with N larger than T, and the generalized PC type estimators, especially for panels with N almost as large as T.

Keywords: high dimensionality, unknown factors, principal components, cross-sectional correlation, shrinkage regression, regularization, pseudo-out-of-sample forecasting

Procedia PDF Downloads 116

Authors: Arka Roy, Chandra Prakash Dubey

Abstract:

Inverse problem generally used for recovering hidden information from outside available data. Vertical component of gravity field we will be going to use for underneath density structure calculation. Ill-posing nature is main obstacle for any inverse problem. Linear regularization using Tikhonov formulation are used for appropriate choice of SVD and GSVD components. For real time data handle, signal to noise ratios should have to be less for reliable solution. In our study, 2D and 3D synthetic model with rectangular grid are used for gravity field calculation and its corresponding inversion for density reconstruction. Fine grid also we have considered to hold any irregular structure. Keeping in mind of algebraic ambiguity factor number of observation point should be more than that of number of data point. Picard plot is represented here for choosing appropriate or main controlling Eigenvalues for a regularized solution. Another important study is depth resolution plot (DRP). DRP are generally used for studying how the inversion is influenced by regularizing or discretizing. Our further study involves real time gravity data inversion of Vredeforte Dome South Africa. We apply our method to this data. The results include density structure is in good agreement with known formation in that region, which puts an additional support of our method.

Keywords: depth resolution plot, gravity inversion, Picard plot, SVD, Tikhonov formulation

Procedia PDF Downloads 174

Authors: Bowei Yuan, Shi Li, Liuyang Song, Huaqing Wang, Lingli Cui

Abstract:

Convolutional neural networks (CNN) have received extensive attention in the field of fault diagnosis. Many fault diagnosis methods use CNN for fault type identification. However, when the amount of raw data collected by sensors is massive, the neural network needs to perform a time-consuming classification task. In this paper, a mechanical fault diagnosis method based on vibration signal down-sampling and the improved one-dimensional convolutional neural network is proposed. Through the robust principal component analysis, the low-rank feature matrix of a large amount of raw data can be separated, and then down-sampling is realized to reduce the subsequent calculation amount. In the improved one-dimensional CNN, a smaller convolution kernel is used to reduce the number of parameters and computational complexity, and regularization is introduced before the fully connected layer to prevent overfitting. In addition, the multi-connected layers can better generalize classification results without cumbersome parameter adjustments. The effectiveness of the method is verified by monitoring the signal of the centrifugal pump test bench, and the average test accuracy is above 98%. When compared with the traditional deep belief network (DBN) and support vector machine (SVM) methods, this method has better performance.

Keywords: fault diagnosis, vibration signal down-sampling, 1D-CNN

Procedia PDF Downloads 100

Authors: André Felipe Gimenez, Flávia Alessandra Ribeiro da Silva, Roberto Saverio Souza Costa

Abstract:

Currently, the rural producer has been facing problems regarding environmental regularization, which is precisely why the CAR (Rural Environmental Registry) was created. CAR is an electronic registry for rural properties with the purpose of assimilating notions about legal reserve areas, permanent preservation areas, areas of limited use, stable areas, forests and remnants of native vegetation, and all rural properties in Brazil. . The objective of this work was to evaluate and compare altimetry and slope data from google Earth with a digital terrain model (MDT) generated by aerophotogrammetry, in three plots of a steep slope, for the purpose of declaration in the CAR (Rural Environmental Registry). The realization of this work is justified in these areas, in which rural landowners have doubts about the reliability of the use of the free software Google Earth to diagnose inclinations greater than 25 degrees, as recommended by federal law 12651/2012. Added to the fact that in the literature, there is a deficiency of this type of study for the purpose of declaration of the CAR. The results showed that when comparing the drone altimetry data with the Google Earth image data, in areas of high slope (above 40% slope), Google underestimated the real values of terrain slope. Thus, it is concluded that Google Earth is not reliable for diagnosing areas with an inclination greater than 25 degrees (46% declivity) for the purpose of declaration in the CAR, being essential to carry out the local topographic survey.

Keywords: MDT, drone, RPA, SiCar, photogrammetry

Procedia PDF Downloads 94

Authors: Jianwei Ma, Diriba Gemechu

Abstract:

In seismic data processing, attenuation of random noise is the basic step to improve quality of data for further application of seismic data in exploration and development in different gas and oil industries. The signal-to-noise ratio of the data also highly determines quality of seismic data. This factor affects the reliability as well as the accuracy of seismic signal during interpretation for different purposes in different companies. To use seismic data for further application and interpretation, we need to improve the signal-to-noise ration while attenuating random noise effectively. To improve the signal-to-noise ration and attenuating seismic random noise by preserving important features and information about seismic signals, we introduce the concept of anisotropic total fractional order denoising algorithm. The anisotropic total fractional order variation model defined in fractional order bounded variation is proposed as a regularization in seismic denoising. The split Bregman algorithm is employed to solve the minimization problem of the anisotropic total fractional order variation model and the corresponding denoising algorithm for the proposed method is derived. We test the effectiveness of theproposed method for synthetic and real seismic data sets and the denoised result is compared with F-X deconvolution and non-local means denoising algorithm.

Keywords: anisotropic total fractional order variation, fractional order bounded variation, seismic random noise attenuation, split Bregman algorithm

Procedia PDF Downloads 180

Authors: RAM PAL SINGH, VIKASH CHAUDHARY, MONIKA VERMA

Abstract:

In this paper, we proposed the implementation of optimization based Extreme Learning Machine (ELM) for watermarking of B-channel of color image in discrete wavelet transform (DWT) domain. ELM, a regularization algorithm, works based on generalized single-hidden-layer feed-forward neural networks (SLFNs). However, hidden layer parameters, generally called feature mapping in context of ELM need not to be tuned every time. This paper shows the embedding and extraction processes of watermark with the help of ELM and results are compared with already used machine learning models for watermarking.Here, a cover image is divide into suitable numbers of non-overlapping blocks of required size and DWT is applied to each block to be transformed in low frequency sub-band domain. Basically, ELM gives a unified leaning platform with a feature mapping, that is, mapping between hidden layer and output layer of SLFNs, is tried for watermark embedding and extraction purpose in a cover image. Although ELM has widespread application right from binary classification, multiclass classification to regression and function estimation etc. Unlike SVM based algorithm which achieve suboptimal solution with high computational complexity, ELM can provide better generalization performance results with very small complexity. Efficacy of optimization method based ELM algorithm is measured by using quantitative and qualitative parameters on a watermarked image even though image is subjected to different types of geometrical and conventional attacks.

Keywords: BER, DWT, extreme leaning machine (ELM), PSNR

Procedia PDF Downloads 277

Authors: Leonard D. Agana, Wendell Ace Dela Cruz, Arjan C. Lingaya, Bonifacio T. Doma Jr.

Abstract:

The purpose of this paper is to study the predict the fuel performance parameters, which include drivability index (DI), vapor lock index (VLI), and vapor lock potential using distillation curve and Reid vapor pressure (RVP) of dual alcohol-gasoline fuel blends. Distillation curve and Reid vapor pressure were predicted using artificial neural networks (ANN) with macroscopic properties such as boiling points, RVP, and molecular weights as the input layers. The ANN consists of 5 hidden layers and was trained using Bayesian regularization. The training mean square error (MSE) and R-value for the ANN of RVP are 91.4113 and 0.9151, respectively, while the training MSE and R-value for the distillation curve are 33.4867 and 0.9927. Fuel performance analysis of the dual alcohol–gasoline blends indicated that highly volatile gasoline blended with dual alcohols results in non-compliant fuel blends with D4814 standard. Mixtures of low-volatile gasoline and 10% methanol or 10% ethanol can still be blended with up to 10% C3 and C4 alcohols. Intermediate volatile gasoline containing 10% methanol or 10% ethanol can still be blended with C3 and C4 alcohols that have low RVPs, such as 1-propanol, 1-butanol, 2-butanol, and i-butanol. Biography: Graduate School of Chemical, Biological, and Materials Engineering and Sciences, Mapua University, Muralla St., Intramuros, Manila, 1002, Philippines

Keywords: dual alcohol-gasoline blends, distillation curve, machine learning, reid vapor pressure

Procedia PDF Downloads 63

Authors: David Alejandro Lazo-Vasquez, Jorge Luis Balino

Abstract:

In the petroleum industry, multiphase flow occurs when oil, gas, and water are transported in the same pipe through large pipeline systems. The flow can take different patterns depending on parameters like fluid velocities, pipe diameter, pipe inclination, and fluid properties. Mainly, intermittent flow is produced by the natural propagation of short and long waves, according to the Kelvin-Helmholtz Stability Theory. To model stratified flow and the onset of intermittent flow, it is crucial to have knowledge of short and long waves behavior. The two-fluid model, frequently employed for characterizing multiphase systems, becomes ill-posed for high liquid and gas velocities and large inclination angles, for short waves can develop infinite growth rates. We are interested in focusing attention on long-wave instability, which leads to the production of roll waves that may grow and result in the transition from stratified flow to intermittent flow. In this study, global and local linear stability analyses for dynamic and kinematic stability criteria predict the regions of stability of the flow for different pipe inclinations and fluid velocities in regularized and non-regularized systems, concurrently. It was possible to distinguish when: wave growth rates are absolutely bounded (stable stratified smooth flow), waves have finite growth rates (unstable stratified wavy flow), and when the equation system becomes elliptic and hyperbolization is needed. In order to bound short wave growth rates and regularize the equation system, we incorporated some lower and higher-order terms like interfacial drag and surface tension, respectively.

Keywords: linear stability analysis, multiphase flow, onset of slugging, two-fluid model regularization

Procedia PDF Downloads 103

Authors: Solaine Hachem, Frédéric Bourquin, Dominique Siegert

Abstract:

The brutal collapse of bridges is mainly due to scour. Indeed, the soil erosion in the riverbed around a pier modifies the embedding conditions of the structure, reduces its overall stiffness and threatens its stability. Hence, finding an efficient technique that allows early scour detection becomes mandatory. Vibration analysis is an indirect method for scour detection that relies on real-time monitoring of the bridge. It tends to indicate the presence of a scour based on its consequences on the stability of the structure and its dynamic response. Most of the research in this field has focused on the dynamic behavior of a single pile and has examined the depth of the scour. In this paper, a bridge is fully modeled with all piles and spans and the scour is represented by a reduction in the foundation's stiffnesses. This work aims to identify the vibration modes sensitive to the rigidity’s loss in the foundations so that their variations can be considered as a scour indicator: the decrease in soil-structure interaction rigidity leads to a decrease in the natural frequencies’ values. By using the first-order perturbation method, the expression of sensitivity, which depends only on the selected vibration modes, is established to determine the deficiency of foundations stiffnesses. The solutions are obtained by using the singular value decomposition method for the regularization of the inverse problem. The propagation of uncertainties is also calculated to verify the efficiency of the inverse problem method. Numerical simulations describing different scenarios of scour are investigated on a simplified model of a real composite steel-concrete bridge located in France. The results of the modal analysis show that the modes corresponding to in-plane and out-of-plane piers vibrations are sensitive to the loss of foundation stiffness. While the deck bending modes are not affected by this damage.

Keywords: bridge’s piers, inverse problems, modal sensitivity, scour detection, vibration analysis

Procedia PDF Downloads 66

Authors: Ariungerel Jargal

Abstract:

: Cave mining is a bulk underground mining method, which allows large low-grade deposits to be mined underground. This method involves undermining the orebody to make it collapse under its own weight into a series of chambers from which the ore extracted. It is a useful technique to extend the life of large deposits previously mined by open pits, and it is a method increasingly proposed for new mines around the world. We plan to conduct a feasibility study using Electrical impedance tomography (EIT) technology to show how much subsidence there is at the intersection with the cave mining surface. EIT is an imaging technique which uses electrical measurements at electrodes attached on the body surface to yield a cross-sectional image of conductivity changes within the object. EIT has been developed in several different applications areas as a simpler, cheaper alternative to many other imaging methods. A low frequency current is injected between pairs of electrodes while voltage measurements are collected at all other electrode pairs. In the difference EIT, images are reconstructed of the change in conductivity distribution (σ) between the acquisition of the two sets of measurements. Image reconstruction in EIT requires the solution of an ill-conditioned nonlinear inverse problem on noisy data, typically requiring make simpler assumptions or regularization. It is noted that the ratio of current to voltage represents a complex value according to Ohm’s law, and that it is theoretically possible to re-express EIT. The results of the experiment were presented on the simulation, and it was concluded that it is possible to conduct further real experiments. Drill a certain number of holes in the top wall of the cave to attach the electrodes, flow a current through them, and measure and acquire the potential through these electrodes. Appropriate values should be selected depending on the distance between the holes, the frequency and duration of the measurements, the surface characteristics and the size of the study area using an EIT device.

Keywords: impedance tomography, cave mining, soil, EIT device

Procedia PDF Downloads 78

Authors: Hung-Sheng Lin, Cheng-Hsuan Li

Abstract:

Over the past few years, kernel-based algorithms have been widely used to extend some linear feature extraction methods such as principal component analysis (PCA), linear discriminate analysis (LDA), and nonparametric weighted feature extraction (NWFE) to their nonlinear versions, kernel principal component analysis (KPCA), generalized discriminate analysis (GDA), and kernel nonparametric weighted feature extraction (KNWFE), respectively. These nonlinear feature extraction methods can detect nonlinear directions with the largest nonlinear variance or the largest class separability based on the given kernel function. Moreover, they have been applied to improve the target detection or the image classification of hyperspectral images. The double nearest proportion feature extraction (DNP) can effectively reduce the overlap effect and have good performance in hyperspectral image classification. The DNP structure is an extension of the k-nearest neighbor technique. For each sample, there are two corresponding nearest proportions of samples, the self-class nearest proportion and the other-class nearest proportion. The term “nearest proportion” used here consider both the local information and other more global information. With these settings, the effect of the overlap between the sample distributions can be reduced. Usually, the maximum likelihood estimator and the related unbiased estimator are not ideal estimators in high dimensional inference problems, particularly in small data-size situation. Hence, an improved estimator by shrinkage estimation (regularization) is proposed. Based on the DNP structure, LDA is included as a special case. In this paper, the kernel method is applied to extend DNP to kernel-based DNP (KDNP). In addition to the advantages of DNP, KDNP surpasses DNP in the experimental results. According to the experiments on the real hyperspectral image data sets, the classification performance of KDNP is better than that of PCA, LDA, NWFE, and their kernel versions, KPCA, GDA, and KNWFE.

Keywords: feature extraction, kernel method, double nearest proportion feature extraction, kernel double nearest feature extraction

Procedia PDF Downloads 296

Authors: Faiz N. K. Yusufi, Aquil Ahmed, Jamal Ahmad

Abstract:

Diabetes in India is growing at an alarming rate and the complications caused by it need to be controlled. Coronary heart disease (CHD) is one of the complications that will be discussed for prediction in this study. India has the second most number of diabetes patients in the world. To the best of our knowledge, there is no CHD risk score for Indian type 2 diabetes patients. Any form of CHD has been taken as the event of interest. A sample of 750 was determined and randomly collected from the Rajiv Gandhi Centre for Diabetes and Endocrinology, J.N.M.C., A.M.U., Aligarh, India. Collected variables include patients data such as sex, age, height, weight, body mass index (BMI), blood sugar fasting (BSF), post prandial sugar (PP), glycosylated haemoglobin (HbA1c), diastolic blood pressure (DBP), systolic blood pressure (SBP), smoking, alcohol habits, total cholesterol (TC), triglycerides (TG), high density lipoprotein (HDL), low density lipoprotein (LDL), very low density lipoprotein (VLDL), physical activity, duration of diabetes, diet control, history of antihypertensive drug treatment, family history of diabetes, waist circumference, hip circumference, medications, central obesity and history of CHD. Predictive risk scores of CHD events are designed by cox proportional hazard regression. Model calibration and discrimination is assessed from Hosmer Lemeshow and area under receiver operating characteristic (ROC) curve. Overfitting and underfitting of the model is checked by applying regularization techniques and best method is selected between ridge, lasso and elastic net regression. Youden’s index is used to choose the optimal cut off point from the scores. Five year probability of CHD is predicted by both survival function and Markov chain two state model and the better technique is concluded. The risk scores for CHD developed can be calculated by doctors and patients for self-control of diabetes. Furthermore, the five-year probabilities can be implemented as well to forecast and maintain the condition of patients.

Keywords: coronary heart disease, cox proportional hazard regression, ROC curve, type 2 diabetes Mellitus

Procedia PDF Downloads 186

Authors: Faiz N. K. Yusufi, Aquil Ahmed, Jamal Ahmad

Abstract:

Predicting the risk of diabetic retinopathy (DR) in Indian type 2 diabetes patients is immensely necessary. India, being the second largest country after China in terms of a number of diabetic patients, to the best of our knowledge not a single risk score for complications has ever been investigated. Diabetic retinopathy is a serious complication and is the topmost reason for visual impairment across countries. Any type or form of DR has been taken as the event of interest, be it mild, back, grade I, II, III, and IV DR. A sample was determined and randomly collected from the Rajiv Gandhi Centre for Diabetes and Endocrinology, J.N.M.C., A.M.U., Aligarh, India. Collected variables include patients data such as sex, age, height, weight, body mass index (BMI), blood sugar fasting (BSF), post prandial sugar (PP), glycosylated haemoglobin (HbA1c), diastolic blood pressure (DBP), systolic blood pressure (SBP), smoking, alcohol habits, total cholesterol (TC), triglycerides (TG), high density lipoprotein (HDL), low density lipoprotein (LDL), very low density lipoprotein (VLDL), physical activity, duration of diabetes, diet control, history of antihypertensive drug treatment, family history of diabetes, waist circumference, hip circumference, medications, central obesity and history of DR. Cox proportional hazard regression is used to design risk scores for the prediction of retinopathy. Model calibration and discrimination are assessed from Hosmer Lemeshow and area under receiver operating characteristic curve (ROC). Overfitting and underfitting of the model are checked by applying regularization techniques and best method is selected between ridge, lasso and elastic net regression. Optimal cut off point is chosen by Youden’s index. Five-year probability of DR is predicted by both survival function, and Markov chain two state model and the better technique is concluded. The risk scores developed can be applied by doctors and patients themselves for self evaluation. Furthermore, the five-year probabilities can be applied as well to forecast and maintain the condition of patients. This provides immense benefit in real application of DR prediction in T2DM.

Keywords: Cox proportional hazard regression, diabetic retinopathy, ROC curve, type 2 diabetes mellitus

Procedia PDF Downloads 146

Authors: Rideci Farias, Haroldo Paranhos

Abstract:

The present work deals with the use of drainage geo-composite as a deep drainage and geogrid element to reinforce the base of the body of the landfill destined to the road pavement on geological faults in the stretch of the TO-342 Highway, between the cities of Miracema and Miranorte, in the State of Tocantins / TO, Brazil, which for many years was the main link between TO-010 and BR-153, after the city of Palmas, also in the state of Tocantins / TO, Brazil. For this application, geotechnical and geological studies were carried out by means of SPT percussion drilling, drilling and rotary drilling, to understand the problem, identifying the type of faults, filling material and the definition of the water table. According to the geological and geotechnical studies carried out, the area where the route was defined, passes through a zone of longitudinal fault to the runway, with strong breaking / fracturing, with presence of voids, intense alteration and with advanced argilization of the rock and with the filling up parts of the faults by organic and compressible soils leachate from other horizons. This geology presents as a geotechnical aggravating agent a medium of high hydraulic load and very low resistance to penetration. For more than 20 years, the region presented constant excessive deformations in the upper layers of the pavement, which after routine services of regularization, reconformation, re-compaction of the layers and application of the asphalt coating. The faults were quickly propagated to the surface of the asphalt pavement, generating a longitudinal shear, forming steps (unevenness), close to 40 cm, causing numerous accidents and discomfort to the drivers, since the geometric positioning was in a horizontal curve. Several projects were presented to the region's highway department to solve the problem. Due to the need for partial closure of the runway, the short time for execution, the use of geosynthetics was proposed and the most adequate solution for the problem was taken into account the movement of existing geological faults and the position of the water level in relation to several Layers of pavement and failure. In order to avoid any flow of water in the body of the landfill and in the filling material of the faults, a drainage curtain solution was used, carried out at 4.0 meters depth, with drainage geo-composite and as reinforcement element and inhibitor of the possible A geogrid of 200 kN / m of resistance was inserted at the base of the reconstituted landfill. Recent evaluations, after 13 years of application of the solution, show the efficiency of the technique used, supported by the geotechnical studies carried out in the area.

Keywords: geosynthetics, geocomposite, geogrid, road, recovery, geological failure

Procedia PDF Downloads 141

Authors: R. Di Lorenzo, S. Laneri, A. Sacchi

Abstract:

Hair surface properties affect hair texture and shine, whereas the healthy state of the hair cortex sways hair ends. Even if cosmetic treatments are intrinsically safe, there is potentially damaging action on the hair fibers. Loss of luster, frizz, split ends, and other hair problems are particularly prevalent among people who repeatedly alter the natural style of their hair or among people with intrinsically weak hair. Technological and scientific innovations in hair care thus become invaluable allies to preserve their natural well-being and shine. The study evaluated restoring keratin-like ingredients that improve hair fibers' structural integrity, increase tensile strength, improve hair manageability and moisturizing. The hair shaft is composed of 65 - 95% of keratin. It gives the hair resistance, elasticity, and plastic properties and also contributes to their waterproofing. Providing exogenous keratin is, therefore, a practical approach to protect and nourish the hair. By analyzing the amino acid composition of keratin, we find a high frequency of hydrophobic amino acids. It confirms the critical role interactions, mainly hydrophobic, between cosmetic products and hair. The active ingredient analyzed comes from vegetable proteins through an enzymatic cut process that selected only oligo- and polypeptides (> 3500 KDa) rich in amino acids with hydrocarbon side chains apolar or sulfur. These chemical components are the most expressed amino acids at the level of the capillary keratin structure, and it determines the most significant possible compatibility with the target substrate. Given the biological variability of the sources, it isn't easy to define a constant and reproducible molecular formula of the product. Still, it consists of hydroxypropiltrimonium vegetable peptides with keratin-like performances. 20 natural hair tresses (30 cm in length and 0.50 g weight) were treated with the investigated products (5 % v/v aqueous solution) following a specific protocol and compared with non-treated (Control) and benchmark-keratin-treated strands (Benchmark). Their brightness, moisture content, cortical and surface integrity, and tensile strength were evaluated and statistically compared. Keratin-like treated hair tresses showed better results than the other two groups (Control and Benchmark). The product improves the surface with significant regularization of the cuticle closure, improves the cortex and the peri-medullar area filling, gives a highly organized and tidy structure, delivers a significant amount of sulfur on the hair, and is more efficient moisturization and imbibition power, increases hair brightness. The hydroxypropyltrimonium quaternized group added to the C-terminal end interacts with the negative charges that form on the hair after washing when disheveled and tangled. The interactions anchor the product to the hair surface, keeping the cuticles adhered to the shaft. The small size allows the peptides to penetrate and give body to the hair, together with a conditioning effect that gives an image of healthy hair. Results suggest that the product is a valid ally in numerous restructuring/conditioning, shaft protection, straightener/dryer-damage prevention hair care product.

Keywords: conditioning, hair damage, hair, keratin, polarized light microscopy, scanning electron microscope, thermogravimetric analysis

Procedia PDF Downloads 101

Authors: Gabrielle Robertson, Matthew Downs, Joseph Dagher

Abstract:

Iron deposition in the brain has been linked with a host of neurological disorders such as Alzheimer’s, Parkinson’s, and Multiple Sclerosis. While some treatment options exist, there are no objective measurement tools that allow for the monitoring of iron levels in the brain in vivo. An emerging Magnetic Resonance Imaging (MRI) method has been recently proposed to deduce iron concentration through quantitative measurement of magnetic susceptibility. This is a multi-step process that involves repeated modeling of physical processes via approximate numerical solutions. For example, the last two steps of this Quantitative Susceptibility Mapping (QSM) method involve I) mapping magnetic field into magnetic susceptibility and II) mapping magnetic susceptibility into iron concentration. Process I involves solving an ill-posed inverse problem by using regularization via injection of prior belief. The end result from Process II highly depends on the model used to describe the molecular content of each voxel (type of iron, water fraction, etc.) Due to these factors, the accuracy and repeatability of QSM have been an active area of research in the MRI and medical imaging community. This work aims to estimate iron concentration in the brain via a single step. A synthetic numerical model of the human head was created by automatically and manually segmenting the human head on a high-resolution grid (640x640x640, 0.4mm³) yielding detailed structures such as microvasculature and subcortical regions as well as bone, soft tissue, Cerebral Spinal Fluid, sinuses, arteries, and eyes. Each segmented region was then assigned tissue properties such as relaxation rates, proton density, electromagnetic tissue properties and iron concentration. These tissue property values were randomly selected from a Probability Distribution Function derived from a thorough literature review. In addition to having unique tissue property values, different synthetic head realizations also possess unique structural geometry created by morphing the boundary regions of different areas within normal physical constraints. This model of the human brain is then used to create synthetic MRI measurements. This is repeated thousands of times, for different head shapes, volume, tissue properties and noise realizations. Collectively, this constitutes a training-set that is similar to in vivo data, but larger than datasets available from clinical measurements. This 3D convolutional U-Net neural network architecture was used to train data-driven Deep Learning models to solve for iron concentrations from raw MRI measurements. The performance was then tested on both synthetic data not used in training as well as real in vivo data. Results showed that the model trained on synthetic MRI measurements is able to directly learn iron concentrations in areas of interest more effectively than other existing QSM reconstruction methods. For comparison, models trained on random geometric shapes (as proposed in the Deep QSM method) are less effective than models trained on realistic synthetic head models. Such an accurate method for the quantitative measurement of iron deposits in the brain would be of important value in clinical studies aiming to understand the role of iron in neurological disease.

Keywords: magnetic resonance imaging, MRI, iron deposition, machine learning, quantitative susceptibility mapping

Procedia PDF Downloads 93

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 165