Search results for: kernel methods

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 107

Authors: Baha Eddine Aissou, Aichouche Belhadj Aissa

Abstract:

Light detection and ranging (LiDAR) is an active remote sensing technology used for several applications. Airborne LiDAR is becoming an important technology for the acquisition of a highly accurate dense point cloud. A classification of airborne laser scanning (ALS) point cloud is a very important task that still remains a real challenge for many scientists. Support vector machine (SVM) is one of the most used statistical learning algorithms based on kernels. SVM is a non-parametric method, and it is recommended to be used in cases where the data distribution cannot be well modeled by a standard parametric probability density function. Using a kernel, it performs a robust non-linear classification of samples. Often, the data are rarely linearly separable. SVMs are able to map the data into a higher-dimensional space to become linearly separable, which allows performing all the computations in the original space. This is one of the main reasons that SVMs are well suited for high-dimensional classification problems. Only a few training samples, called support vectors, are required. SVM has also shown its potential to cope with uncertainty in data caused by noise and fluctuation, and it is computationally efficient as compared to several other methods. Such properties are particularly suited for remote sensing classification problems and explain their recent adoption. In this poster, the SVM classification of ALS LiDAR data is proposed. Firstly, connected component analysis is applied for clustering the point cloud. Secondly, the resulting clusters are incorporated in the SVM classifier. Radial basic function (RFB) kernel is used due to the few numbers of parameters (C and γ) that needs to be chosen, which decreases the computation time. In order to optimize the classification rates, the parameters selection is explored. It consists to find the parameters (C and γ) leading to the best overall accuracy using grid search and 5-fold cross-validation. The exploited LiDAR point cloud is provided by the German Society for Photogrammetry, Remote Sensing, and Geoinformation. The ALS data used is characterized by a low density (4-6 points/m²) and is covering an urban area located in residential parts of the city Vaihingen in southern Germany. The class ground and three other classes belonging to roof superstructures are considered, i.e., a total of 4 classes. The training and test sets are selected randomly several times. The obtained results demonstrated that a parameters selection can orient the selection in a restricted interval of (C and γ) that can be further explored but does not systematically lead to the optimal rates. The SVM classifier with hyper-parameters is compared with the most used classifiers in literature for LiDAR data, random forest, AdaBoost, and decision tree. The comparison showed the superiority of the SVM classifier using parameters selection for LiDAR data compared to other classifiers.

Keywords: classification, airborne LiDAR, parameters selection, support vector machine

Procedia PDF Downloads 120

Authors: Ahlem Mougaida, Hedi Bel Hadj Salah

Abstract:

Several methods are suggested to improve the numerical integration in Galerkin weak form for Meshless methods. In fact, integrating without taking into account the characteristics of the shape functions reproduced by Meshless methods (rational functions, with compact support etc.), causes a large integration error that influences the PDE’s approximate solution. Comparisons between different methods of numerical integration for rational functions are discussed and compared. The algorithms are implemented in Matlab. Finally, numerical results were presented to prove the efficiency of our algorithms in improving results.

Keywords: adaptive methods, meshless, numerical integration, rational quadrature

Procedia PDF Downloads 319

Authors: Mehrnaz Alibeikloo, Hadi Khabbaz, Behzad Fatahi

Abstract:

The spectral random field method is one of the widely used methods to obtain more reliable and accurate results in geotechnical problems involving material variability. Karhunen-Loeve (K-L) expansion method was applied to perform random field discretization of cross-correlated creep parameters. Karhunen-Loeve expansion method is based on eigenfunctions and eigenvalues of covariance function adopting Kernel integral solution. In this paper, the accuracy of Karhunen-Loeve expansion was investigated to predict long-term settlement of soft soils adopting elastic visco-plastic creep model. For this purpose, a parametric study was carried to evaluate the effect of K-L expansion terms and spatial correlation length on the reliability of results. The results indicate that small values of spatial correlation length require more K-L expansion terms. Moreover, by increasing spatial correlation length, the coefficient of variation (COV) of creep settlement increases, confirming more conservative and safer prediction.

Keywords: Karhunen-Loeve expansion, long-term settlement, reliability analysis, spatial correlation length

Procedia PDF Downloads 124

Authors: A. Satty, H. Mwambi

Abstract:

Much clinical trials data-based research are characterized by the unavoidable problem of dropout as a result of missing or erroneous values. This paper aims to review some of the various techniques to address the dropout problems in longitudinal clinical trials. The fundamental concepts of the patterns and mechanisms of dropout are discussed. This study presents five general techniques for handling dropout: (1) Deletion methods; (2) Imputation-based methods; (3) Data augmentation methods; (4) Likelihood-based methods; and (5) MNAR-based methods. Under each technique, several methods that are commonly used to deal with dropout are presented, including a review of the existing literature in which we examine the effectiveness of these methods in the analysis of incomplete data. Two application examples are presented to study the potential strengths or weaknesses of some of the methods under certain dropout mechanisms as well as to assess the sensitivity of the modelling assumptions.

Keywords: incomplete longitudinal clinical trials, missing at random (MAR), imputation, weighting methods, sensitivity analysis

Procedia PDF Downloads 377

Authors: Mohammed Idaan Hassan Al-Majidi

Abstract:

An analysis of twenty one assorted brands of vegetable oils in Babylon Iraq, reveals varying levels of cholesterol content. Cholesterol was found to be present in most of the oil brands sampled using three standard methods. Cholesterol was detected in seventeen of the vegetable oil brands with concentration of less than 1 mg/ml while seven of the oil brands had cholesterol concentrations ranging between 1-4 mg/ml. Low iodine values were obtained in four of the vegetable oil brands and three of them had high acid values. High performance liquid chromatography (HPLC) confirmed the presence of cholesterol at varying concentrations in all the oil brands and gave the lowest detectable cholesterol values in all the oil brands. The Laser brand made from rapeseed had the highest cholesterol concentration of 3.2 mg/ml while Grand brand made from groundnuts had the least concentration (0.12 mg/ml) of cholesterol using HPLC analysis. Leibermann-Burchard method showed that Gino brand from palm kernel had the least concentration of cholesterol (3.86 mg/ml ±0.032) and the highest concentration of 3.996 mg/ml ±0.0404 was obtained in Sesame seed oil brand. This report is important in view of health implications of cholesterol in our diets. Consequently, we have been able to show that there is no cholesterol free oil in the market as shown on the vegetable oil brand labels. Therefore, companies producing and marketing vegetable oils are enjoined to desist from misleading the public by labeling their products as “cholesterol free”. They should indicate the amount of cholesterol present in the vegetable oil, no matter how small the quantity may be.

Keywords: vegetable oils, heart diseases, leibermann-burchard, cholesterol

Procedia PDF Downloads 219

Authors: Carlos Oliveira

Abstract:

This paper is a criticism of the traditional model of teaching and presents alternative teaching methods, different from the traditional lecture. These methods are accompanied by reports of experience of their application in a class. It was concluded that in the lecture, the student has a low learning rate and that other methods should be used to make the most engaging learning environment for the student, contributing (or facilitating) his learning process. However, the teacher should not use a single method, but rather a range of different methods to ensure the learning experience does not become repetitive and fatiguing for the student.

Keywords: educational practices, experience report, IT in education, teaching methods

Procedia PDF Downloads 361

Authors: Mohammed Husein Mohammad Rashid

Abstract:

For a bounded linear operator T acting on a complex infinite dimensional Hilbert space ℋ, we say that T is ∗-class A operator (abbreviation T∈A*) if |T²|≥ |T*|². In this article, we prove the following assertions:(i) we establish some conditions which imply the normality of ∗-class A; (ii) we consider ∗-class A operator T ∈ ℬ(ℋ) with reducing kernel such that TX = XS for some X ∈ ℬ(K, ℋ) and prove the Fuglede-Putnam type theorem when adjoint of S ∈ ℬ(K) is dominant operators; (iii) furthermore, we extend the asymmetric Putnam-Fuglede theorem the class of ∗-class A operators.

Keywords: fuglede-putnam theorem, normal operators, ∗-class a operators, dominant operators

Procedia PDF Downloads 50

Authors: Waqas Ahmed Khan Afridi, Subhas Chandra Mukhopadhyay, Bandita Mainali

Abstract:

The research paper presents a unique approach to evapotranspiration (ET) prediction using a Support Vector Machine (SVM) learning algorithm. The study leverages real-time sensor node data to develop an accurate and adaptable prediction model, addressing the inherent challenges of traditional ET estimation methods. The integration of the SVM algorithm with real-time sensor node data offers great potential to improve spatial and temporal resolution in ET predictions. In the model development, key input features are measured and computed using mathematical equations such as Penman-Monteith (FAO56) and soil water balance (SWB), which include soil-environmental parameters such as; solar radiation (Rs), air temperature (T), atmospheric pressure (P), relative humidity (RH), wind speed (u2), rain (R), deep percolation (DP), soil temperature (ST), and change in soil moisture (∆SM). The one-year field data are split into combinations of three proportions i.e. train, test, and validation sets. While kernel functions with tuning hyperparameters have been used to train and improve the accuracy of the prediction model with multiple iterations. This paper also outlines the existing methods and the machine learning techniques to determine Evapotranspiration, data collection and preprocessing, model construction, and evaluation metrics, highlighting the significance of SVM in advancing the field of ET prediction. The results demonstrate the robustness and high predictability of the developed model on the basis of performance evaluation metrics (R2, RMSE, MAE). The effectiveness of the proposed model in capturing complex relationships within soil and environmental parameters provide insights into its potential applications for water resource management and hydrological ecosystem.

Keywords: evapotranspiration, FAO56, KNIME, machine learning, RStudio, SVM, sensors

Procedia PDF Downloads 28

Authors: Qing Wu, Fei-Yan Li, Heng-Chang Zhang

Abstract:

Multitask learning support vector machines (SVMs) have recently attracted increasing research attention. Given several related tasks, the single-task learning methods trains each task separately and ignore the inner cross-relationship among tasks. However, multitask learning can capture the correlation information among tasks and achieve better performance by training all tasks simultaneously. In addition, the asymmetric squared loss function can better improve the generalization ability of the models on the most asymmetric distributed data. In this paper, we first make two assumptions on the relatedness among tasks and propose two multitask learning proximal support vector machine algorithms, named MTL-a-PSVM and EMTL-a-PSVM, respectively. MTL-a-PSVM seeks a trade-off between the maximum expectile distance for each task model and the closeness of each task model to the general model. As an extension of the MTL-a-PSVM, EMTL-a-PSVM can select appropriate kernel functions for shared information and private information. Besides, two corresponding special cases named MTL-PSVM and EMTLPSVM are proposed by analyzing the asymmetric squared loss function, which can be easily implemented by solving linear systems. Experimental analysis of three classification datasets demonstrates the effectiveness and superiority of our proposed multitask learning algorithms.

Keywords: multitask learning, asymmetric squared loss, EMTL-a-PSVM, classification

Procedia PDF Downloads 78

Authors: Jai Prakash Verma, Khushboo Verma

Abstract:

In the present paper, a pair of Mond-Weir type non-differentiable multiobjective second-order programming problems, involving two kernel functions, where each of the objective functions contains support function, is formulated. We prove weak, strong and converse duality theorem for the second-order symmetric dual programs under η-pseudoinvexity conditions.

Keywords: non-differentiable multiobjective programming, second-order symmetric duality, efficiency, support function, eta-pseudoinvexity

Procedia PDF Downloads 218

Authors: David F. Nettleton, Elodie Bugnicourt, Christian Wasiak, Alejandro Rosales

Abstract:

In this presentation, preliminary results are given for the modeling and calibration of two different industrial winding MIMO (Multiple Input Multiple Output) processes using machine learning techniques. In contrast to previous approaches which have typically used ‘black-box’ linear statistical methods together with a definition of the mechanical behavior of the process, we use non-linear machine learning algorithms together with a ‘white-box’ rule induction technique to create a supervised model of the fitting error between the expected and real force measures. The final objective is to build a precise model of the winding process in order to control de-tension of the material being wound in the first case, and the friction of the material passing through the die, in the second case. Case 1, Tension Control of a Winding Process. A plastic web is unwound from a first reel, goes over a traction reel and is rewound on a third reel. The objectives are: (i) to train a model to predict the web tension and (ii) calibration to find the input values which result in a given tension. Case 2, Friction Force Control of a Micro-Pullwinding Process. A core+resin passes through a first die, then two winding units wind an outer layer around the core, and a final pass through a second die. The objectives are: (i) to train a model to predict the friction on die2; (ii) calibration to find the input values which result in a given friction on die2. Different machine learning approaches are tested to build models, Kernel Ridge Regression, Support Vector Regression (with a Radial Basis Function Kernel) and MPART (Rule Induction with continuous value as output). As a previous step, the MPART rule induction algorithm was used to build an explicative model of the error (the difference between expected and real friction on die2). The modeling of the error behavior using explicative rules is used to help improve the overall process model. Once the models are built, the inputs are calibrated by generating Gaussian random numbers for each input (taking into account its mean and standard deviation) and comparing the output to a target (desired) output until a closest fit is found. The results of empirical testing show that a high precision is obtained for the trained models and for the calibration process. The learning step is the slowest part of the process (max. 5 minutes for this data), but this can be done offline just once. The calibration step is much faster and in under one minute obtained a precision error of less than 1x10-3 for both outputs. To summarize, in the present work two processes have been modeled and calibrated. A fast processing time and high precision has been achieved, which can be further improved by using heuristics to guide the Gaussian calibration. Error behavior has been modeled to help improve the overall process understanding. This has relevance for the quick optimal set up of many different industrial processes which use a pull-winding type process to manufacture fibre reinforced plastic parts. Acknowledgements to the Openmind project which is funded by Horizon 2020 European Union funding for Research & Innovation, Grant Agreement number 680820

Keywords: data model, machine learning, industrial winding, calibration

Procedia PDF Downloads 209

Authors: Payel Das, Gnaneshwar Nelakanti

Abstract:

In this paper we analyse the iterated discrete Legendre Galerkin method for Fredholm-Hammerstein integral equations with smooth kernel. Using sufficiently accurate numerical quadrature rule, we obtain superconvergence rates for the iterated discrete Legendre Galerkin solutions in both infinity and $L^2$-norm. Numerical examples are given to illustrate the theoretical results.

Keywords: hammerstein integral equations, spectral method, discrete galerkin, numerical quadrature, superconvergence

Procedia PDF Downloads 439

Authors: J. P. Chollom, G. M. Kumleng, S. Longwap

Abstract:

The search for higher order A-stable linear multi-step methods has been the interest of many numerical analysts and has been realized through either higher derivatives of the solution or by inserting additional off step points, supper future points and the likes. These methods are suitable for the solution of stiff differential equations which exhibit characteristics that place a severe restriction on the choice of step size. It becomes necessary that only methods with large regions of absolute stability remain suitable for such equations. In this paper, high order block implicit multi-step methods of the hybrid form up to order twelve have been constructed using the multi-step collocation approach by inserting one or more off step points in the multi-step method. The accuracy and stability properties of the new methods are investigated and are shown to yield A-stable methods, a property desirable of methods suitable for the solution of stiff ODE’s. The new High Order Block Implicit Multistep methods used as block integrators are tested on stiff differential systems and the results reveal that the new methods are efficient and compete favourably with the state of the art Matlab ode23 code.

Keywords: block linear multistep methods, high order, implicit, stiff differential equations

Procedia PDF Downloads 327

Authors: Andrey V. Timofeev

Abstract:

The paper presents new results concerning selection of optimal information fusion formula for ensembles of C-OTDR channels. The goal of information fusion is to create an integral classificator designed for effective classification of seismoacoustic target events. The LPBoost (LP-β and LP-B variants), the Multiple Kernel Learning, and Weighing of Inversely as Lipschitz Constants (WILC) approaches were compared. The WILC is a brand new approach to optimal fusion of Lipschitz Classifiers Ensembles. Results of practical usage are presented.

Keywords: Lipschitz Classifier, classifiers ensembles, LPBoost, C-OTDR systems

Procedia PDF Downloads 426

Authors: Gustavo G. Shimamoto, Matthieu Tubino

Abstract:

The characterization and the quality of biodiesel samples are checked by determining several parameters. Considering a large number of analysis to be performed, as well as the disadvantages of the use of toxic solvents and waste generation, multivariate calibration is suggested to reduce the number of tests. In this work, hydrogen nuclear magnetic resonance (1H NMR) spectra were used to build multivariate models, from partial least squares (PLS) regression, in order to determine simultaneously six important characterizing and/or quality parameters of biodiesels: density at 20 ºC, kinematic viscosity at 40 ºC, iodine value, acid number, oxidative stability, and water content. Biodiesels from twelve different oils sources were used in this study: babassu, brown flaxseed, canola, corn, cottonseed, macauba almond, microalgae, palm kernel, residual frying, sesame, soybean, and sunflower. 1H NMR reflects the structures of the compounds present in biodiesel samples and showed suitable correlations with the six parameters. The PLS models were constructed with latent variables between 5 and 7, the obtained values of r(cal) and r(val) were greater than 0.994 and 0.989, respectively. In addition, the models were considered suitable to predict all the six parameters for external samples, taking into account the analytical speed to perform it. Thus, the alliance between 1H NMR and PLS showed to be appropriate to characterize and evaluate the quality of biodiesels, reducing significantly analysis time, the consumption of reagents/solvents, and waste generation. Therefore, the proposed methods can be considered to adhere to the principles of green chemistry.

Keywords: biodiesel, multivariate calibration, nuclear magnetic resonance, quality parameters

Procedia PDF Downloads 492

Authors: Jay N. Vyas, Sachin Daxini

Abstract:

Numerical simulation techniques are widely used now in product development and testing instead of expensive, time-consuming and sometimes dangerous laboratory experiments. Numerous numerical methods are available for performing simulation of physical problems of different engineering fields. Grid based methods, like Finite Element Method, are extensively used in performing various kinds of static, dynamic, structural and non-structural analysis during product development phase. Drawbacks of grid based methods in terms of discontinuous secondary field variable, dealing fracture mechanics and large deformation problems led to development of a relatively a new class of numerical simulation techniques in last few years, which are popular as Meshless methods or Meshfree Methods. Meshless Methods are expected to be more adaptive and flexible than Finite Element Method because domain descretization in Meshless Method requires only nodes. Present paper introduces Meshless Methods and differentiates it with Finite Element Method in terms of following aspects: Shape functions used, role of weight function, techniques to impose essential boundary conditions, integration techniques for discrete system equations, convergence rate, accuracy of solution and computational effort. Capabilities, benefits and limitations of Meshless Methods are discussed and concluded at the end of paper.

Keywords: numerical simulation, Grid-based methods, Finite Element Method, Meshless Methods

Procedia PDF Downloads 355

Authors: Sabina Hublova, Kristyna Hrabova, Petr Cikrle

Abstract:

Sustainable development and preservation of existing buildings are becoming increasingly important worldwide. In order to reduce the amount of CO2 emissions in the air and to reduce the amount of waste from building structures, we can predict an increasing demand for maintenance of some existing buildings in the future. The use of modern diagnostic methods, which allow detailed determination of the properties of structures, the identification of critical points, could be the great importance for the better assessment of existing structures. Non-destructive methods could be one of the options. From these methods, ultrasonic appears to be a highly perspective method, thanks to which we are able to identify critical points of an element or a structure. The experiment will focus on the use of electroacoustic methods for defectoscopy in reinforced concrete columns.

Keywords: sustainability, defectoscopy, ultrasonic method, non-destructive methods, electroacoustic methods

Procedia PDF Downloads 121

Authors: T. A. Biala

Abstract:

This paper deals with the numerical integration of the general second order multipoint boundary value problems. This has been achieved by the development of a continuous linear multistep method (LMM). The continuous LMM is used to construct a main discrete method to be used with some initial and final methods (also obtained from the continuous LMM) so that they form a discrete analogue of the continuous second order boundary value problems. These methods are used as boundary value methods and adapted to cope with the integration of the general second order multipoint boundary value problems. The convergence, the use and the region of absolute stability of the methods are discussed. Several numerical examples are implemented to elucidate our solution process.

Keywords: linear multistep methods, boundary value methods, second order multipoint boundary value problems, convergence

Procedia PDF Downloads 347

Authors: Marasovic Branka, Aljinovic Zdravka, Poklepovic Tea

Abstract:

Numerical methods like binomial and trinomial trees and finite difference methods can be used to price a wide range of options contracts for which there are no known analytical solutions. American options are the most famous of that kind of options. Besides numerical methods, American options can be valued with the approximation formulas, like Bjerksund-Stensland formulas from 1993 and 2002. When the value of American option is approximated by Bjerksund-Stensland formulas, the computer time spent to carry out that calculation is very short. The computer time spent using numerical methods can vary from less than one second to several minutes or even hours. However to be able to conduct a comparative analysis of numerical methods and Bjerksund-Stensland formulas, we will limit computer calculation time of numerical method to less than one second. Therefore, we ask the question: Which method will be most accurate at nearly the same computer calculation time?

Keywords: Bjerksund and Stensland approximations, computational analysis, finance, options pricing, numerical methods

Procedia PDF Downloads 413

Authors: S. Krustev, V. Angelova, K. Ivanov, P. Zaprjanova

Abstract:

It is generally accepted that only about ten microelements are vitally important to all plants, and approximately ten more elements are proved to be significant for the development of some species. The main methods for their determination in soils are the atomic spectral techniques - AAS and ICP-OAS. Critical stage to obtain correct results for content of heavy metals and nutrients in the soil is the process of mineralization. A comparative study of the most widely spread methods for soil sample preparation for determination of some trace elements was carried out. Three most commonly used methods for sample preparation were used as follows: ISO11466, EPA Method 3051 and BDS ISO 14869-1. Their capabilities were assessed and their bounds of applicability in determining the levels of the most important microelements in agriculture were defined.

Keywords: analysis, copper, methods, zinc

Procedia PDF Downloads 228

Authors: Arindam Chaudhuri

Abstract:

Classification of data has been actively used for most effective and efficient means of conveying knowledge and information to users. The prima face has always been upon techniques for extracting useful knowledge from data such that returns are maximized. With emergence of huge datasets the existing classification techniques often fail to produce desirable results. The challenge lies in analyzing and understanding characteristics of massive data sets by retrieving useful geometric and statistical patterns. We propose a supervised parallel fuzzy rough support vector machine (PFRSVM) for data classification in cloud environment. The classification is performed by PFRSVM using hyperbolic tangent kernel. The fuzzy rough set model takes care of sensitiveness of noisy samples and handles impreciseness in training samples bringing robustness to results. The membership function is function of center and radius of each class in feature space and is represented with kernel. It plays an important role towards sampling the decision surface. The success of PFRSVM is governed by choosing appropriate parameter values. The training samples are either linear or nonlinear separable. The different input points make unique contributions to decision surface. The algorithm is parallelized with a view to reduce training times. The system is built on support vector machine library using Hadoop implementation of MapReduce. The algorithm is tested on large data sets to check its feasibility and convergence. The performance of classifier is also assessed in terms of number of support vectors. The challenges encountered towards implementing big data classification in machine learning frameworks are also discussed. The experiments are done on the cloud environment available at University of Technology and Management, India. The results are illustrated for Gaussian RBF and Bayesian kernels. The effect of variability in prediction and generalization of PFRSVM is examined with respect to values of parameter C. It effectively resolves outliers’ effects, imbalance and overlapping class problems, normalizes to unseen data and relaxes dependency between features and labels. The average classification accuracy for PFRSVM is better than other classifiers for both Gaussian RBF and Bayesian kernels. The experimental results on both synthetic and real data sets clearly demonstrate the superiority of the proposed technique.

Keywords: FRSVM, Hadoop, MapReduce, PFRSVM

Procedia PDF Downloads 454

Authors: Rattana Sangchan, Pattaraporn Thampradit

Abstract:

Teaching students to use a variety of reading methods in developing reading is essential for Thai university students. However, there haven’t been a lot of studies concerned about developing reading methods that are used by Thai students in the industrial education field. Therefore, this study was carried out not only to investigate the developing reading methods of Industrial Education students at King Mongkut’s Institute of Technology Ladkrabang, but also to determine if the developing reading strategies differ among the students’ reading abilities and differ gender: male and female. The research instrument used in collecting the data consisted of fourteen statements which include either metacognitive strategies, cognitive strategies or social / affective strategies. Results of this study revealed that students could develop their reading methods in moderate level (mean=3.13). Furthermore, high reading ability students had different levels of using reading methods to develop their reading from those of mid reading ability students. In addition, high reading ability students could use either metacognitive reading methods or cognitive reading methods to develop their reading much better than mid reading ability students. Interestingly, male students could develop their reading methods in great levels while female students could develop their reading methods only in moderate level. Last but not least, male students could use either metacognitive reading methods or cognitive reading methods to develop their reading much better than female students. Thus, the results of this study could indicate that most students need to apply much more reading strategies to develop their reading. At the same time, suggestions on how to motivate and train their students to apply much more appropriate effective reading strategies to better comprehend their reading were also provided.

Keywords: developing reading methods, industrial education, reading abilities, reading method classification

Procedia PDF Downloads 253

Authors: B. Sellami, Y. Laskri, M. Belloufi

Abstract:

Conjugate gradient methods are an important class of methods for unconstrained optimization, especially for large-scale problems. Recently, they have been much studied. In this paper, a new family of conjugate gradient method is proposed for unconstrained optimization. This method includes the already existing two practical nonlinear conjugate gradient methods, which produces a descent search direction at every iteration and converges globally provided that the line search satisfies the Wolfe conditions. The numerical experiments are done to test the efficiency of the new method, which implies the new method is promising. In addition the methods related to this family are uniformly discussed.

Keywords: conjugate gradient method, global convergence, line search, unconstrained optimization

Procedia PDF Downloads 374

Authors: Eiman Kattan, Hong Wei

Abstract:

In using Convolutional Neural Network (CNN) for classification, there is a set of hyperparameters available for the configuration purpose. This study aims to evaluate the impact of a range of parameters in CNN architecture i.e. AlexNet on land cover classification based on four remotely sensed datasets. The evaluation tests the influence of a set of hyperparameters on the classification performance. The parameters concerned are epoch values, batch size, and convolutional filter size against input image size. Thus, a set of experiments were conducted to specify the effectiveness of the selected parameters using two implementing approaches, named pertained and fine-tuned. We first explore the number of epochs under several selected batch size values (32, 64, 128 and 200). The impact of kernel size of convolutional filters (1, 3, 5, 7, 10, 15, 20, 25 and 30) was evaluated against the image size under testing (64, 96, 128, 180 and 224), which gave us insight of the relationship between the size of convolutional filters and image size. To generalise the validation, four remote sensing datasets, AID, RSD, UCMerced and RSCCN, which have different land covers and are publicly available, were used in the experiments. These datasets have a wide diversity of input data, such as number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in both training and testing. The results have shown that increasing the number of epochs leads to a higher accuracy rate, as expected. However, the convergence state is highly related to datasets. For the batch size evaluation, it has shown that a larger batch size slightly decreases the classification accuracy compared to a small batch size. For example, selecting the value 32 as the batch size on the RSCCN dataset achieves the accuracy rate of 90.34 % at the 11th epoch while decreasing the epoch value to one makes the accuracy rate drop to 74%. On the other extreme, setting an increased value of batch size to 200 decreases the accuracy rate at the 11th epoch is 86.5%, and 63% when using one epoch only. On the other hand, selecting the kernel size is loosely related to data set. From a practical point of view, the filter size 20 produces 70.4286%. The last performed image size experiment shows a dependency in the accuracy improvement. However, an expensive performance gain had been noticed. The represented conclusion opens the opportunities toward a better classification performance in various applications such as planetary remote sensing.

Keywords: CNNs, hyperparamters, remote sensing, land cover, land use

Procedia PDF Downloads 137

Authors: Mouhamadou Dosso

Abstract:

This paper presents methods of spectral dichotomy of a matrix which compute spectral projectors on the subspace associated with the eigenvalues external to the parabolas described by a general equation. These methods are modifications of the one proposed in [A. N. Malyshev and M. Sadkane, SIAM J. MATRIX ANAL. APPL. 18 (2), 265-278, 1997] which uses the spectral dichotomy method of a matrix with respect to the imaginary axis. Theoretical and algorithmic aspects of the methods are developed. Numerical results obtained by applying methods presented on matrices are reported.

Keywords: spectral dichotomy method, spectral projector, eigensubspaces, eigenvalue

Procedia PDF Downloads 56

Authors: Marija Milašinović-Šeremešić, Valentina Semenčenko, Milica Radosavljević, Dušanka Terzić, Ljiljana Mojović, Ljubica Dokić

Abstract:

Maize (Zea mays L.) is one of the most important cereal crops, and as such, one of the most significant naturally renewable carbohydrate raw materials for the production of energy and multitude of different products. The main goal of the present study was to investigate a suitability of selected maize hybrids of different genetic background produced in Maize Research Institute ‘Zemun Polje’, Belgrade, Serbia, for starch, bioethanol and animal feed production. All the hybrids are commercial and their detailed characterization is important for the expansion of their different uses. The starches were isolated by using a 100-g laboratory maize wet-milling procedure. Hydrolysis experiments were done in two steps (liquefaction with Termamyl SC, and saccharification with SAN Extra L). Starch hydrolysates obtained by the two-step hydrolysis of the corn flour starch were subjected to fermentation by S. cerevisiae var. ellipsoideus under semi-anaerobic conditions. The digestibility based on enzymatic solubility was performed by the Aufréré method. All investigated ZP maize hybrids had very different physical characteristics and chemical composition which could allow various possibilities of their use. The amount of hard (vitreous) and soft (floury) endosperm in kernel is considered one of the most important parameters that can influence the starch and bioethanol yields. Hybrids with a lower test weight and density and a greater proportion of soft endosperm fraction had a higher yield, recovery and purity of starch. Among the chemical composition parameters only starch content significantly affected the starch yield. Starch yields of studied maize hybrids ranged from 58.8% in ZP 633 to 69.0% in ZP 808. The lowest bioethanol yield of 7.25% w/w was obtained for hybrid ZP 611k and the highest by hybrid ZP 434 (8.96% w/w). A very significant correlation was determined between kernel starch content and the bioethanol yield, as well as volumetric productivity (48h) (r=0.66). Obtained results showed that the NDF, ADF and ADL contents in the whole maize plant of the observed ZP maize hybrids varied from 40.0% to 60.1%, 18.6% to 32.1%, and 1.4% to 3.1%, respectively. The difference in the digestibility of the dry matter of the whole plant among hybrids (ZP 735 and ZP 560) amounted to 18.1%. Moreover, the differences in the contents of the lignocelluloses fraction affected the differences in dry matter digestibility. From the results it can be concluded that genetic background of the selected maize hybrids plays an important part in estimation of the technological value of maize hybrids for various purposes. Obtained results are of an exceptional importance for the breeding programs and selection of potentially most suitable maize hybrids for starch, bioethanol and animal feed production.

Keywords: bioethanol, biomass quality, maize, starch

Procedia PDF Downloads 187

Authors: Alexander P. Smirnov, Sergey A. Matveev, Dmitry A. Zheltkov, Eugene E. Tyrtyshnikov

Abstract:

We propose a new computational technique for multidimensional (multicomponent) Smoluchowski coagulation equation. Using low-rank approximations in Tensor Train format of both the solution and the coagulation kernel, we accelerate the classical finite-difference Runge-Kutta scheme keeping its level of accuracy. The complexity of the taken finite-difference scheme is reduced from O(N^2d) to O(d^2 N log N ), where N is the number of grid nodes and d is a dimensionality of the problem. The efficiency and the accuracy of the new method are demonstrated on concrete problem with known analytical solution.

Keywords: tensor train decomposition, multicomponent Smoluchowski equation, runge-kutta scheme, convolution

Procedia PDF Downloads 383

Authors: Musoke Ivan, Birungi Racheal

Abstract:

The construction trend is characterized by increased use of modern methods yet traditional methods are cheaper in terms of costs, in addition to the benefits it offers to the construction sector, like providing more jobs that could have been worked with the intensive machines. The purpose of this research was to assess the influence of using Traditional methods of construction (TMC) on the costs and quality of building structures and determine the different ways. Traditional methods of construction (TMC) can be applicable and integrated into the construction trend, and propose ways how this can be a success. The study adopted a quantitative method approach targeting various construction professionals like Architects, Quantity surveyors, Engineers, and Construction Managers. Questionnaires and analyses of literature were used to obtain research data and findings. Simple random sampling was used to select 40 construction professionals to which questionnaires were administered. The data was then analyzed using Microsoft Excel. The findings of the research indicate that Traditional methods of construction (TMCs) in Uganda are cheaper in terms of costs, but the quality is still low. This is attributed to a lack of skilled labour and efficient supervision while undertaking tasks leading to low quality. The study identifies strategies that would improve Traditional methods of construction (TMC), which include the employment of skilled manpower and effective supervision. It also identifies the need by stakeholders like the government, clients, and professionals to appreciate Traditional methods of construction (TMCs) and allow for a levelled ground for Traditional Methods of Construction and Modern methods of construction (MMCs).

Keywords: traditional methods of construction, integration, cost, quality

Procedia PDF Downloads 21

Authors: Hassan Eshkiki, Benjamin Mora

Abstract:

The Neighbor Migrating Generator is a simple and efficient approach to finding the closest potential neighbor(s) with a different label for a given instance and so without the need to calibrate any kernel settings at all. This allows determining and explaining the most important features that will influence an AI model. It can be used to either migrate a specific sample to the class decision boundary of the original model within a close neighborhood of that sample or identify global features that can help localising neighbor classes. The proposed technique works by minimizing a loss function that is divided into two components which are independently weighted according to three parameters α, β, and ω, α being self-adjusting. Results show that this approach is superior to past techniques when detecting the smallest changes in the feature space and may also point out issues in models like over-fitting.

Keywords: explainable AI, EX AI, feature importance, counterfactual explanations

Procedia PDF Downloads 112