Search results for: Log-likelihood Maximization

Authors: Norwati Mustapha, Manijeh Jalali, Abolghasem Bozorgniya, Mehrdad Jalali

Abstract:

Web usage mining algorithms have been widely utilized for modeling user web navigation behavior. In this study we advance a model for mining of user-s navigation pattern. The model makes user model based on expectation-maximization (EM) algorithm.An EM algorithm is used in statistics for finding maximum likelihood estimates of parameters in probabilistic models, where the model depends on unobserved latent variables. The experimental results represent that by decreasing the number of clusters, the log likelihood converges toward lower values and probability of the largest cluster will be decreased while the number of the clusters increases in each treatment.

Keywords: Web Usage Mining, Expectation maximization, navigation pattern mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1578

Authors: Abdullah A. AlShaher

Abstract:

In this paper, we demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2^nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We then proceed by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.

Keywords: Shape recognition, Arabic handwritten characters, regression curves, expectation maximization algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 713

Authors: Gkolfo I. Smani, Vasileios Megalooikonomou

Abstract:

Influence and influence diffusion have been studied extensively in social networks. However, most existing literature on this task are limited on static networks, ignoring the fact that the interactions between users change over time. In this paper, the problem of maximizing influence diffusion in dynamic social networks, i.e., the case of networks that change over time is studied. The DM algorithm is an extension of Matrix Influence (MATI) algorithm and solves the Influence Maximization (IM) problem in dynamic networks and is proposed under the Linear Threshold (LT) and Independent Cascade (IC) models. Experimental results show that our proposed algorithm achieves a diffusion performance better by 1.5 times than several state-of-the-art algorithms and comparable results in diffusion scale with the Greedy algorithm. Also, the proposed algorithm is 2.4 times faster than previous methods.

Keywords: Influence maximization, dynamic social networks, diffusion, social influence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 415

Authors: Divyesh Patel, Tanuja Srivastava

Abstract:

This paper considers the NP-hard problem of reconstructing binary matrices satisfying exactly-1-4-adjacency constraint from its row and column projections. This problem is formulated into a maximization problem. The objective function gives a measure of adjacency constraint for the binary matrices. The maximization problem is solved by the simulated annealing algorithm and experimental results are presented.

Keywords: Discrete Tomography, exactly-1-4-adjacency, simulated annealing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2457

Authors: Li Ni, Pen ManMan, Li KenLi

Abstract:

Clustering is an intensive research for some years because of its multifaceted applications, such as biology, information retrieval, medicine, business and so on. The expectation maximization (EM) is a kind of algorithm framework in clustering methods, one of the ten algorithms of machine learning. Traditionally, optimization of objective function has been the standard approach in EM. Hence, research has investigated the utility of evolutionary computing and related techniques in the regard. Chemical Reaction Optimization (CRO) is a recently established method. So the property embedded in CRO is used to solve optimization problems. This paper presents an algorithm framework (EM-CRO) with modified CRO operators based on EM cluster problems. The hybrid algorithm is mainly to solve the problem of initial value sensitivity of the objective function optimization clustering algorithm. Our experiments mainly take the EM classic algorithm:k-means and fuzzy k-means as an example, through the CRO algorithm to optimize its initial value, get K-means-CRO and FKM-CRO algorithm. The experimental results of them show that there is improved efficiency for solving objective function optimization clustering problems.

Keywords: Chemical reaction optimization, expectation maximization, initial, objective function clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1293

Authors: Jain-Shing Liu

Abstract:

In this paper, we present a matrix game-theoretic cross-layer optimization formulation to maximize the network lifetime in wireless ad hoc networks with network coding. To this end, we introduce a cross-layer formulation of general NUM (network utility maximization) that accommodates routing, scheduling, and stream control from different layers in the coded networks. Specifically, for the scheduling problem and then the objective function involved, we develop a matrix game with the strategy sets of the players corresponding to hyperlinks and transmission modes, and design the payoffs specific to the lifetime. In particular, with the inherit merit that matrix game can be solved with linear programming, our cross-layer programming formulation can benefit from both game-based and NUM-based approaches at the same time by cooperating the programming model for the matrix game with that for the other layers in a consistent framework. Finally, our numerical example demonstrates its performance results on a well-known wireless butterfly network to verify the cross-layer optimization scheme.

Keywords: Cross-layer design, Lifetime maximization, Matrix game, Network coding

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1694

Authors: Refaat M Mohamed, Ayman El-Baz, Aly A. Farag

Abstract:

This paper presents a new approach for the prob-ability density function estimation using the Support Vector Ma-chines (SVM) and the Expectation Maximization (EM) algorithms.In the proposed approach, an advanced algorithm for the SVM den-sity estimation which incorporates the Mean Field theory in the learning process is used. Instead of using ad-hoc values for the para-meters of the kernel function which is used by the SVM algorithm,the proposed approach uses the EM algorithm for an automatic optimization of the kernel. Experimental evaluation using simulated data set shows encouraging results.

Keywords: Density Estimation, SVM, Learning Algorithms, Parameters Estimation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2505

Authors: Ho Yuan-Hong, Hunag Chiung-Ju

Abstract:

This study conducts simulation analyses to find the optimal debt ceiling of Taiwan, while factoring in welfare maximization under a dynamic stochastic general equilibrium framework. The simulation is based on Taiwan's 2001 to 2011 economic data and shows that welfare is maximized at a debt/GDP ratio of 0.2, increases in the debt/GDP ratio leads to increases in both tax and interest rates and decreases in the consumption ratio and working hours. The study results indicate that the optimal debt ceiling of Taiwan is 20% of GDP, where if the debt/GDP ratio is greater than 40%, the welfare will be negative and result in welfare loss.

Keywords: Debt sustainability, optimal debt ceiling, dynamic stochastic general equilibrium, welfare maximization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2390

Authors: Tugrul Oktay, Mehmet Konar, Mustafa Soylak, Firat Sal, Murat Onay, Orhan Kizilkaya

Abstract:

In this paper, autonomous performance of a small manufactured unmanned helicopter is tried to be increased. For this purpose, a small unmanned helicopter is manufactured in Erciyes University, Faculty of Aeronautics and Astronautics. It is called as ZANKA-Heli-I. For performance maximization, autopilot parameters are determined via minimizing a cost function consisting of flight performance parameters such as settling time, rise time, overshoot during trajectory tracking. For this purpose, a stochastic optimization method named as simultaneous perturbation stochastic approximation is benefited. Using this approach, considerable autonomous performance increase (around %23) is obtained.

Keywords: Small helicopters, hierarchical control, stochastic optimization, autonomous performance maximization, autopilots.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1636

Authors: R.Sukesh Kumar, Abhisek Verma, Jasprit Singh

Abstract:

In this work a novel approach for color image segmentation using higher order entropy as a textural feature for determination of thresholds over a two dimensional image histogram is discussed. A similar approach is applied to achieve multi-level thresholding in both grayscale and color images. The paper discusses two methods of color image segmentation using RGB space as the standard processing space. The threshold for segmentation is decided by the maximization of conditional entropy in the two dimensional histogram of the color image separated into three grayscale images of R, G and B. The features are first developed independently for the three ( R, G, B ) spaces, and combined to get different color component segmentation. By considering local maxima instead of the maximum of conditional entropy yields multiple thresholds for the same image which forms the basis for multilevel thresholding.

Keywords: conditional entropy, multi-level thresholding, segmentation, two dimensional image histogram

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2997

Authors: Frank Emmert Streib

Abstract:

The classification of the protein structure is commonly not performed for the whole protein but for structural domains, i.e., compact functional units preserved during evolution. Hence, a first step to a protein structure classification is the separation of the protein into its domains. We approach the problem of protein domain identification by proposing a novel graph theoretical algorithm. We represent the protein structure as an undirected, unweighted and unlabeled graph which nodes correspond the secondary structure elements of the protein. This graph is call the protein graph. The domains are then identified as partitions of the graph corresponding to vertices sets obtained by the maximization of an objective function, which mutually maximizes the cycle distributions found in the partitions of the graph. Our algorithm does not utilize any other kind of information besides the cycle-distribution to find the partitions. If a partition is found, the algorithm is iteratively applied to each of the resulting subgraphs. As stop criterion, we calculate numerically a significance level which indicates the stability of the predicted partition against a random rewiring of the protein graph. Hence, our algorithm terminates automatically its iterative application. We present results for one and two domain proteins and compare our results with the manually assigned domains by the SCOP database and differences are discussed.

Keywords: Graph partitioning, unweighted graph, protein domains.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1355

Authors: Endrick Barnacin, Jean-Luc Henry, Jack Molinié, Jimmy Nagau, Hélène Delatte, Gérard Lebreton

Abstract:

Palynology is a field of interest for many disciplines. It has multiple applications such as chronological dating, climatology, allergy treatment, and even honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time-consuming task that requires the intervention of experts in the field, which is becoming increasingly rare due to economic and social conditions. So, the automation of this task is a necessity. Pollen slides analysis is mainly a visual process as it is carried out with the naked eye. That is the reason why a primary method to automate palynology is the use of digital image processing. This method presents the lowest cost and has relatively good accuracy in pollen retrieval. In this work, we propose a system combining recognition and grouping of pollen. It consists of using a Logistic Model Tree to classify pollen already known by the proposed system while detecting any unknown species. Then, the unknown pollen species are divided using a cluster-based approach. Success rates for the recognition of known species have been achieved, and automated clustering seems to be a promising approach.

Keywords: Pollen recognition, logistic model tree, expectation-maximization, local binary pattern.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 770

Authors: Fariba Azizi, Firoozeh Haghighi, Viliam Makis

Abstract:

In this paper, we propose a method to model the relationship between failure time and degradation for a simple step stress test where underlying degradation path is linear and different causes of failure are possible. It is assumed that the intensity function depends only on the degradation value. No assumptions are made about the distribution of the failure times. A simple step-stress test is used to shorten failure time of products and a tampered failure rate (TFR) model is proposed to describe the effect of the changing stress on the intensities. We assume that some of the products that fail during the test have a cause of failure that is only known to belong to a certain subset of all possible failures. This case is known as masking. In the presence of masking, the maximum likelihood estimates (MLEs) of the model parameters are obtained through an expectation-maximization (EM) algorithm by treating the causes of failure as missing values. The effect of incomplete information on the estimation of parameters is studied through a Monte-Carlo simulation. Finally, a real example is analyzed to illustrate the application of the proposed methods.

Keywords: Expectation-maximization (EM) algorithm, cause of failure, intensity, linear degradation path, masked data, reliability function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1073

Authors: R. Vedhapriya Vadhana, Ruba Soundar, K. G. Jothi Shalini

Abstract:

We address the problem of interference over all the channels in multiuser MIMO-OFDM systems. This paper contributes three beamforming strategies designed for multiuser multiple-input and multiple-output by way of orthogonal frequency division multiplexing, in which the transmit and receive beamformers are acquired repetitious by secure-form stages. In the principal case, the transmit (TX) beamformers remain fixed then the receive (RX) beamformers are computed. This eradicates one interference span for every user by means of extruding the transmit beamformers into a null space of relevant channels. Formerly, by gratifying the orthogonality condition to exclude the residual interferences in RX beamformer for every user is done by maximizing the signal-to-noise ratio (SNR). The second case comprises mutually optimizing the TX and RX beamformers from controlled SNR maximization. The outcomes of first case is used here. The third case also includes combined optimization of TX-RX beamformers; however, uses the both controlled SNR and signal-to-interference-plus-noise ratio maximization (SINR). By the standardized channel model for IEEE 802.11n, the proposed simulation experiments offer rapid beamforming and enhanced error performance.

Keywords: Beamforming, interference channels, MIMO-OFDM, multi-objective optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1126

Authors: FH. Sarieddeen, R. El Berbari, S. Imad, J. Abdel Baki, M. Hamad, R. Blanc, A. Nakib, Y.Chenoune

Abstract:

Brain ArterioVenous Malformation (BAVM) is an abnormal tangle of brain blood vessels where arteries shunt directly into veins with no intervening capillary bed which causes high pressure and hemorrhage risk. The success of treatment by embolization in interventional neuroradiology is highly dependent on the accuracy of the vessels visualization. In this paper the performance of clustering techniques on vessel segmentation from 3- D rotational angiography (3DRA) images is investigated and a new technique of segmentation is proposed. This method consists in: preprocessing step of image enhancement, then K-Means (KM), Fuzzy C-Means (FCM) and Expectation Maximization (EM) clustering are used to separate vessel pixels from background and artery pixels from vein pixels when possible. A post processing step of removing false-alarm components is applied before constructing a three-dimensional volume of the vessels. The proposed method was tested on six datasets along with a medical assessment of an expert. Obtained results showed encouraging segmentations.

Keywords: Brain arteriovenous malformation (BAVM), 3-D rotational angiography (3DRA), K-Means (KM) clustering, Fuzzy CMeans (FCM) clustering, Expectation Maximization (EM) clustering, volume rendering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1910

Authors: Elena Ezhova, Vadim Mottl, Olga Krasotkina

Abstract:

The problem of estimating time-varying regression is inevitably concerned with the necessity to choose the appropriate level of model volatility - ranging from the full stationarity of instant regression models to their absolute independence of each other. In the stationary case the number of regression coefficients to be estimated equals that of regressors, whereas the absence of any smoothness assumptions augments the dimension of the unknown vector by the factor of the time-series length. The Akaike Information Criterion is a commonly adopted means of adjusting a model to the given data set within a succession of nested parametric model classes, but its crucial restriction is that the classes are rigidly defined by the growing integer-valued dimension of the unknown vector. To make the Kullback information maximization principle underlying the classical AIC applicable to the problem of time-varying regression estimation, we extend it onto a wider class of data models in which the dimension of the parameter is fixed, but the freedom of its values is softly constrained by a family of continuously nested a priori probability distributions.

Keywords: Time varying regression, time-volatility of regression coefficients, Akaike Information Criterion (AIC), Kullback information maximization principle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1533

Authors: J. Arneric, A. Rozga

Abstract:

In this paper usefulness of quasi-Newton iteration procedure in parameters estimation of the conditional variance equation within BHHH algorithm is presented. Analytical solution of maximization of the likelihood function using first and second derivatives is too complex when the variance is time-varying. The advantage of BHHH algorithm in comparison to the other optimization algorithms is that requires no third derivatives with assured convergence. To simplify optimization procedure BHHH algorithm uses the approximation of the matrix of second derivatives according to information identity. However, parameters estimation in a/symmetric GARCH(1,1) model assuming normal distribution of returns is not that simple, i.e. it is difficult to solve it analytically. Maximum of the likelihood function can be founded by iteration procedure until no further increase can be found. Because the solutions of the numerical optimization are very sensitive to the initial values, GARCH(1,1) model starting parameters are defined. The number of iterations can be reduced using starting values close to the global maximum. Optimization procedure will be illustrated in framework of modeling volatility on daily basis of the most liquid stocks on Croatian capital market: Podravka stocks (food industry), Petrokemija stocks (fertilizer industry) and Ericsson Nikola Tesla stocks (information-s-communications industry).

Keywords: Heteroscedasticity, Log-likelihood Maximization, Quasi-Newton iteration procedure, Volatility.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2649

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

In this paper, we propose the variational EM inference algorithm for the multi-class Gaussian process classification model that can be used in the field of human behavior recognition. This algorithm can drive simultaneously both a posterior distribution of a latent function and estimators of hyper-parameters in a Gaussian process classification model with multiclass. Our algorithm is based on the Laplace approximation (LA) technique and variational EM framework. This is performed in two steps: called expectation and maximization steps. First, in the expectation step, using the Bayesian formula and LA technique, we derive approximately the posterior distribution of the latent function indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. Second, in the maximization step, using a derived posterior distribution of latent function, we compute the maximum likelihood estimator for hyper-parameters of a covariance matrix necessary to define prior distribution for latent function. These two steps iteratively repeat until a convergence condition satisfies. Moreover, we apply the proposed algorithm with human action classification problem using a public database, namely, the KTH human action data set. Experimental results reveal that the proposed algorithm shows good performance on this data set.

Keywords: Bayesian rule, Gaussian process classification model with multiclass, Gaussian process prior, human action classification, laplace approximation, variational EM algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1758

Authors: Cheima Ben Soltane, Ittansa Yonas Kelbesa

Abstract:

Speaker Identification (SI) is the task of establishing identity of an individual based on his/her voice characteristics. The SI task is typically achieved by two-stage signal processing: training and testing. The training process calculates speaker specific feature parameters from the speech and generates speaker models accordingly. In the testing phase, speech samples from unknown speakers are compared with the models and classified. Even though performance of speaker identification systems has improved due to recent advances in speech processing techniques, there is still need of improvement. In this paper, a Closed-Set Tex-Independent Speaker Identification System (CISI) based on a Multiple Classifier System (MCS) is proposed, using Mel Frequency Cepstrum Coefficient (MFCC) as feature extraction and suitable combination of vector quantization (VQ) and Gaussian Mixture Model (GMM) together with Expectation Maximization algorithm (EM) for speaker modeling. The use of Voice Activity Detector (VAD) with a hybrid approach based on Short Time Energy (STE) and Statistical Modeling of Background Noise in the pre-processing step of the feature extraction yields a better and more robust automatic speaker identification system. Also investigation of Linde-Buzo-Gray (LBG) clustering algorithm for initialization of GMM, for estimating the underlying parameters, in the EM step improved the convergence rate and systems performance. It also uses relative index as confidence measures in case of contradiction in identification process by GMM and VQ as well. Simulation results carried out on voxforge.org speech database using MATLAB highlight the efficacy of the proposed method compared to earlier work.

Keywords: Feature Extraction, Speaker Modeling, Feature Matching, Mel Frequency Cepstrum Coefficient (MFCC), Gaussian mixture model (GMM), Vector Quantization (VQ), Linde-Buzo-Gray (LBG), Expectation Maximization (EM), pre-processing, Voice Activity Detection (VAD), Short Time Energy (STE), Background Noise Statistical Modeling, Closed-Set Tex-Independent Speaker Identification System (CISI).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1884

Authors: Huey-Kuo Chen

Abstract:

Travel demand forecasting including four travel choices, i.e., trip generation, trip distribution, modal split and traffic assignment constructs the core of transportation planning. In its current application, travel demand forecasting has associated with three important issues, i.e., interface inconsistencies among four travel choices, inefficiency of commonly used solution algorithms, and undesirable multiple path solutions. In this paper, each of the three issues is extensively elaborated. An ideal unified framework for the combined model consisting of the four travel choices and variable demand functions is also suggested. Then, a few remarks are provided in the end of the paper

Keywords: Travel choices, B algorithm, entropy maximization, dynamic traffic assignment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2357

Authors: Krisztina Szegedi, Gyula Fülöp, Ádám Bereczk

Abstract:

The shared goal of social entrepreneurship, corporate social responsibility and social innovation is the advancement of society. The business model of social enterprises is characterized by unique strategies based on the competencies of the entrepreneurs, and is not aimed primarily at the maximization of profits, but rather at carrying out goals for the benefit of society. Corporate social responsibility refers to the active behavior of a company, by which it can create new solutions to meet the needs of society, either on its own or in cooperation with other social stakeholders. The objectives of this article are to define concepts, describe and integrate relevant theoretical models, develop a model and introduce some examples of international practice that can inspire initiatives for social development.

Keywords: Corporate social responsibility, CSR, social innovation, social entrepreneurship.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4147

Authors: A. Briseno, A, Zorrilla

Abstract:

Firms are increasingly responding to social and environmental claims from society. Practices oriented to attend issues such as poverty, work equality, or renewable energy, are being implemented more frequently by firms to address impacts on sustainability. However, questions remain on how the responses of firms vary across industries and regions between the social and the economic objectives. Using concepts from organizational theory and social network theory, this paper aims to create a theoretical framework that explains the internal and external influences that make a firm establish its objective. The framework explains why firms might have a different objective orientation in terms of its economic and social prioritization.

Keywords: Organizational identity, social network analysis, firm objective, value maximization, social responsibility.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 927

Authors: Aly Farag, Ayman El-Baz, Refaat Mohamed

Abstract:

In this paper we present a novel approach for density estimation. The proposed approach is based on using the logistic regression model to get initial density estimation for the given empirical density. The empirical data does not exactly follow the logistic regression model, so, there will be a deviation between the empirical density and the density estimated using logistic regression model. This deviation may be positive and/or negative. In this paper we use a linear combination of Gaussian (LCG) with positive and negative components as a model for this deviation. Also, we will use the expectation maximization (EM) algorithm to estimate the parameters of LCG. Experiments on real images demonstrate the accuracy of our approach.

Keywords: Logistic regression model, Expectationmaximization, Segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1732

Authors: Masato Sasaki, Masayoshi Yamamoto

Abstract:

The majority of wireless power transfer (WPT) systems transfer power in a directional manner. This paper describes a discrete exciting voltage control technique for WPT via magnetic resonant coupling with two orthogonal transmitter coils (2D omni-directional WPT system) which can maximize the power transfer efficiency in response to the change of coupling status. The theory allows the equations of the efficiency of the system to be determined at all the rate of the mutual inductance. The calculated results are included to confirm the advantage to one directional WPT system and the validity of the theory and the equations.

Keywords: Wireless power transfer, orthogonal, omni-directional, efficiency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 942

Authors: E. S. Gower, M. O. J. Hawksford

Abstract:

An algorithm for learning an overcomplete dictionary using a Cauchy mixture model for sparse decomposition of an underdetermined mixing system is introduced. The mixture density function is derived from a ratio sample of the observed mixture signals where 1) there are at least two but not necessarily more mixture signals observed, 2) the source signals are statistically independent and 3) the sources are sparse. The basis vectors of the dictionary are learned via the optimization of the location parameters of the Cauchy mixture components, which is shown to be more accurate and robust than the conventional data mining methods usually employed for this task. Using a well known sparse decomposition algorithm, we extract three speech signals from two mixtures based on the estimated dictionary. Further tests with additive Gaussian noise are used to demonstrate the proposed algorithm-s robustness to outliers.

Keywords: expectation-maximization, Pitman estimator, sparsedecomposition

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1947

Authors: F. Alborzi, H. Vafaei, M.H. Gholami, M.M. S. Esfahani

Abstract:

In this article, the design of a Supply Chain Network (SCN) consisting of several suppliers, production plants, distribution centers and retailers, is considered. Demands of retailers are considered stochastic parameters, so we generate amounts of data via simulation to extract a few demand scenarios. Then a mixed integer two-stage programming model is developed to optimize simultaneously two objectives: (1) minimization the fixed and variable cost, (2) maximization the service level. A weighting method is utilized to solve this two objective problem and a numerical example is made to show the performance of the model.

Keywords: Mixed Integer Programming, Multi-objective Optimization, Stochastic Demand, Supply Chain Design, Two Stage Programming

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2321

Authors: Fatemeh Azimi, Razeeh Sadat Aboutalebi, Amir Abbas Najafi

Abstract:

In this paper the multi-mode resource-constrained project scheduling problem with discounted cash flows is considered. Minimizing the makespan and maximization the net present value (NPV) are the two common objectives that have been investigated in the literature. We apply one evolutionary algorithm named multiobjective particle swarm optimization (MOPSO) to find Pareto front solutions. We used standard sets of instances from the project scheduling problem library (PSPLIB). The results are computationally compared respect to different metrics taken from the literature on evolutionary multi-objective optimization.

Keywords: Evolutionary multi-objective optimization makespan, multi-mode, resource constraint, net present value.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2293

Authors: Soma Roychowdhury

Abstract:

This paper deals with a periodic-review substitutable inventory system for a finite and an infinite number of periods. Here an upward substitution structure, a substitution of a more costly item by a less costly one, is assumed, with two products. At the beginning of each period, a stochastic demand comes for the first item only, which is quality-wise better and hence costlier. Whenever an arriving demand finds zero inventory of this product, a fraction of unsatisfied customers goes for its substitutable second item. An optimal ordering policy has been derived for each period. The results are illustrated with numerical examples. A sensitivity analysis has been done to examine how sensitive the optimal solution and the maximum profit are to the values of the discount factor, when there is a large number of periods.

Keywords: Multi-period model, inventory, random demand, upward substitution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1438

Authors: Chutchada Nusai, Yoshimi Suzuki, Haruaki Yamazaki

Abstract:

Selecting the word translation from a set of target language words, one that conveys the correct sense of source word and makes more fluent target language output, is one of core problems in machine translation. In this paper we compare the 3 methods of estimating word translation probabilities for selecting the translation word in Thai – English Machine Translation. The 3 methods are (1) Method based on frequency of word translation, (2) Method based on collocation of word translation, and (3) Method based on Expectation Maximization (EM) algorithm. For evaluation we used Thai – English parallel sentences generated by NECTEC. The method based on EM algorithm is the best method in comparison to the other methods and gives the satisfying results.

Keywords: Machine translation, EM algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1678

Authors: Geeta Sikka, Arvinder Kaur Takkar, Moin Uddin

Abstract:

Missing data is a persistent problem in almost all areas of empirical research. The missing data must be treated very carefully, as data plays a fundamental role in every analysis. Improper treatment can distort the analysis or generate biased results. In this paper, we compare and contrast various imputation techniques on missing data sets and make an empirical evaluation of these methods so as to construct quality software models. Our empirical study is based on NASA-s two public dataset. KC4 and KC1. The actual data sets of 125 cases and 2107 cases respectively, without any missing values were considered. The data set is used to create Missing at Random (MAR) data Listwise Deletion(LD), Mean Substitution(MS), Interpolation, Regression with an error term and Expectation-Maximization (EM) approaches were used to compare the effects of the various techniques.

Keywords: Missing data, Imputation, Missing Data Techniques.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1666