Showing papers in "Neural Computing and Applications in 2014"
TL;DR: Cuckoo search (CS) is a relatively new algorithm, developed by Yang and Deb in 2009, and the same has been found to be efficient in solving global optimization problems.
Abstract: Cuckoo search (CS) is a relatively new algorithm, developed by Yang and Deb in 2009, and the same has been found to be efficient in solving global optimization problems. In this paper, we review the fundamental ideas of cuckoo search and the latest developments as well as its applications. We analyze the algorithm and gain insight into its search mechanisms and find out why it is efficient. We also discuss the essence of algorithms and its link to self-organizing systems, and finally, we propose some important topics for further research.
582 citations
[...]
TL;DR: The proposed binary bat algorithm (BBA) is able to significantly outperform others on majority of the benchmark functions and there is a real application of the proposed method in optical engineering called optical buffer design that evidence the superior performance of BBA in practice.
Abstract: Bat algorithm (BA) is one of the recently proposed heuristic algorithms imitating the echolocation behavior of bats to perform global optimization. The superior performance of this algorithm has been proven among the other most well-known algorithms such as genetic algorithm (GA) and particle swarm optimization (PSO). However, the original version of this algorithm is suitable for continuous problems, so it cannot be applied to binary problems directly. In this paper, a binary version of this algorithm is proposed. A comparative study with binary PSO and GA over twenty-two benchmark functions is conducted to draw a conclusion. Furthermore, Wilcoxon's rank-sum nonparametric statistical test was carried out at 5 % significance level to judge whether the results of the proposed algorithm differ from those of the other algorithms in a statistically significant way. The results prove that the proposed binary bat algorithm (BBA) is able to significantly outperform others on majority of the benchmark functions. In addition, there is a real application of the proposed method in optical engineering called optical buffer design at the end of the paper. The results of the real application also evidence the superior performance of BBA in practice.
549 citations
TL;DR: A review of the state of the art of information-theoretic feature selection methods can be found in this paper, where the concepts of feature relevance, redundance, and complementarity are clearly defined, as well as Markov blanket.
Abstract: In this work, we present a review of the state of the art of information-theoretic feature selection methods. The concepts of feature relevance, redundance, and complementarity (synergy) are clearly defined, as well as Markov blanket. The problem of optimal feature selection is defined. A unifying theoretical framework is described, which can retrofit successful heuristic criteria, indicating the approximations made by each method. A number of open problems in the field are presented.
479 citations
TL;DR: An improved and discrete version of the Cuckoo Search (CS) algorithm is presented to solve the famous traveling salesman problem (TSP), an NP-hard combinatorial optimisation problem.
Abstract: In this paper, we present an improved and discrete version of the Cuckoo Search (CS) algorithm to solve the famous traveling salesman problem (TSP), an NP-hard combinatorial optimisation problem. CS is a metaheuristic search algorithm which was recently developed by Xin-She Yang and Suash Deb in 2009, inspired by the breeding behaviour of cuckoos. This new algorithm has proved to be very effective in solving continuous optimisation problems. We now extend and improve CS by reconstructing its population and introducing a new category of cuckoos so that it can solve combinatorial problems as well as continuous problems. The performance of the proposed discrete cuckoo search (DCS) is tested against a set of benchmarks of symmetric TSP from the well-known TSPLIB library. The results of the tests show that DCS is superior to some other metaheuristics.
403 citations
TL;DR: An approach is developed to solve the multiple attribute decision-making problems with SVNNs based on the SVNNWBM operator to demonstrate its practicality and effectiveness.
Abstract: In this paper, we proposed a single-valued neutrosophic normalized weighted Bonferroni mean (SVNNWBM) operator on the basis of Bonferroni mean, the weighted Bonferroni mean (WBM), and the normalized WBM. Firstly, the definition, operational laws, characteristics, and comparing method of single-valued neutrosophic numbers (SVNNs) are introduced. Then, the SVNNWBM operator is developed, and some properties and special cases of this operator are analyzed. Furthermore, an approach is developed to solve the multiple attribute decision-making problems with SVNNs based on the SVNNWBM operator. Finally, an illustrative example is given to verify the developed approach and to demonstrate its practicality and effectiveness.
341 citations
TL;DR: An intelligent model for predicting phishing attacks based on artificial neural network particularly self-structuring neural networks is proposed that shows high acceptance for noisy data, fault tolerance and high prediction accuracy.
Abstract: Internet has become an essential component of our everyday social and financial activities. Nevertheless, internet users may be vulnerable to different types of web threats, which may cause financial damages, identity theft, loss of private information, brand reputation damage and loss of customer's confidence in e-commerce and online banking. Phishing is considered as a form of web threats that is defined as the art of impersonating a website of an honest enterprise aiming to obtain confidential information such as usernames, passwords and social security number. So far, there is no single solution that can capture every phishing attack. In this article, we proposed an intelligent model for predicting phishing attacks based on artificial neural network particularly self-structuring neural networks. Phishing is a continuous problem where features significant in determining the type of web pages are constantly changing. Thus, we need to constantly improve the network structure in order to cope with these changes. Our model solves this problem by automating the process of structuring the network and shows high acceptance for noisy data, fault tolerance and high prediction accuracy. Several experiments were conducted in our research, and the number of epochs differs in each experiment. From the results, we find that all produced structures have high generalization ability.
257 citations
TL;DR: This study utilises ten chaotic maps to enhance the performance of the biogeography-based optimisation algorithm and demonstrates that the combination of chaotic selection and emigration operators results in the highest performance.
Abstract: The biogeography-based optimisation (BBO) algorithm is a novel evolutionary algorithm inspired by biogeography. Similarly, to other evolutionary algorithms, entrapment in local optima and slow convergence speed are two probable problems it encounters in solving challenging real problems. Due to the novelty of this algorithm, however, there is little in the literature regarding alleviating these two problems. Chaotic maps are one of the best methods to improve the performance of evolutionary algorithms in terms of both local optima avoidance and convergence speed. In this study, we utilise ten chaotic maps to enhance the performance of the BBO algorithm. The chaotic maps are employed to define selection, emigration, and mutation probabilities. The proposed chaotic BBO algorithms are benchmarked on ten test functions. The results demonstrate that the chaotic maps (especially Gauss/mouse map) are able to significantly boost the performance of BBO. In addition, the results show that the combination of chaotic selection and emigration operators results in the highest performance.
256 citations
TL;DR: Experimental results indicate that the proposed algorithm performs better than or at least comparable with state-of-the-art approaches from literature when considering the quality of the solution obtained.
Abstract: In this paper, we intend to propose a new heuristic optimization method, called animal migration optimization algorithm. This algorithm is inspired by the animal migration behavior, which is a ubiquitous phenomenon that can be found in all major animal groups, such as birds, mammals, fish, reptiles, amphibians, insects, and crustaceans. In our algorithm, there are mainly two processes. In the first process, the algorithm simulates how the groups of animals move from the current position to the new position. During this process, each individual should obey three main rules. In the latter process, the algorithm simulates how some animals leave the group and some join the group during the migration. In order to verify the performance of our approach, 23 benchmark functions are employed. The proposed method has been compared with other well-known heuristic search methods. Experimental results indicate that the proposed algorithm performs better than or at least comparable with state-of-the-art approaches from literature when considering the quality of the solution obtained.
245 citations
TL;DR: It is demonstrated that the performance of this hybrid meta-heuristic optimization approach HS/KH is superior to, or at least highly competitive with, the standard KH and other population-based optimization methods, such as ACO, BBO, DE, ES, GA, HS, KH, PSO, and SGA.
Abstract: Recently, Gandomi and Alavi proposed a robust meta-heuristic optimization algorithm, called Krill Herd (KH), for global optimization. To improve the performance of the KH algorithm, harmony search (HS) is applied to mutate between krill during the process of krill updating instead of physical diffusion used in KH. A novel hybrid meta-heuristic optimization approach HS/KH is proposed to solve global numerical optimization problem. HS/KH combines the exploration of harmony search (HS) with the exploitation of KH effectively, and hence, it can generate the promising candidate solutions. The detailed implementation procedure for this improved meta-heuristic method is also described. Fourteen standard benchmark functions are applied to verify the effects of these improvements, and it is demonstrated that, in most cases, the performance of this hybrid meta-heuristic method (HS/KH) is superior to, or at least highly competitive with, the standard KH and other population-based optimization methods, such as ACO, BBO, DE, ES, GA, HS, KH, PSO, and SGA. The effect of the HS/FA parameters is also analyzed.
188 citations
TL;DR: The principle and algorithm of extreme learning machine (ELM), a novel learning algorithm for single-hidden-layer feedforward neural networks (SLFNs), are described, which provides extremely faster learning speed, better generalization performance and with least human intervention.
Abstract: Recently, a novel learning algorithm for single-hidden-layer feedforward neural networks (SLFNs) named extreme learning machine (ELM) was proposed by Huang et al. The essence of ELM is that the learning parameters of hidden nodes, including input weights and biases, are randomly assigned and need not be tuned while the output weights can be analytically determined by the simple generalized inverse operation. The only parameter needed to be defined is the number of hidden nodes. Compared with other traditional learning algorithms for SLFNs, ELM provides extremely faster learning speed, better generalization performance and with least human intervention. This paper firstly introduces a brief review of ELM, describing the principle and algorithm of ELM. Then, we put emphasis on the improved methods or the typical variants of ELM, especially on incremental ELM, pruning ELM, error-minimized ELM, two-stage ELM, online sequential ELM, evolutionary ELM, voting-based ELM, ordinal ELM, fully complex ELM, and symmetric ELM. Next, the paper summarized the applications of ELM on classification, regression, function approximation, pattern recognition, forecasting and diagnosis, and so on. In the last, the paper discussed several open issues of ELM, which may be worthy of exploring in the future.
187 citations
TL;DR: This paper aims at proposing a quantitative microscopic approach toward the discrimination of lymphoblasts (malignant) from lymphocytes (normal) in stained blood smear and bone marrow samples and to assist in the development of a computer-aided screening of ALL.
Abstract: Leukemia is a malignant neoplasm of the blood or bone marrow that affects both children and adults and remains a leading cause of death around the world. Acute lymphoblastic leukemia (ALL) is the most common type of leukemia and is more common among children and young adults. ALL diagnosis through microscopic examination of the peripheral blood and bone marrow tissue samples is performed by hematologists and has been an indispensable technique long since. However, such visual examinations of blood samples are often slow and are also limited by subjective interpretations and less accurate diagnosis. The objective of this work is to improve the ALL diagnostic accuracy by analyzing morphological and textural features from the blood image using image processing. This paper aims at proposing a quantitative microscopic approach toward the discrimination of lymphoblasts (malignant) from lymphocytes (normal) in stained blood smear and bone marrow samples and to assist in the development of a computer-aided screening of ALL. Automated recognition of lymphoblasts is accomplished using image segmentation, feature extraction, and classification over light microscopic images of stained blood films. Accurate and authentic diagnosis of ALL is obtained with the use of improved segmentation methodology, prominent features, and an ensemble classifier, facilitating rapid screening of patients. Experimental results are obtained and compared over the available image data set. It is observed that an ensemble of classifiers leads to 99 % accuracy in comparison with other standard classifiers, i.e., naive Bayesian (NB), K-nearest neighbor (KNN), multilayer perceptron (MLP), radial basis functional network (RBFN), and support vector machines (SVM).
TL;DR: The experimental results reveal that these SVM classifiers achieve very fast, simple, and efficient breast cancer diagnosis and strongly suggest that LPSVM can aid in the diagnosis of breast cancer.
Abstract: Support vector machine (SVM) is a supervised machine learning approach that was recognized as a statistical learning apotheosis for the small-sample database. SVM has shown its excellent learning and generalization ability and has been extensively employed in many areas. This paper presents a performance analysis of six types of SVMs for the diagnosis of the classical Wisconsin breast cancer problem from a statistical point of view. The classification performance of standard SVM (St-SVM) is analyzed and compared with those of the other modified classifiers such as proximal support vector machine (PSVM) classifiers, Lagrangian support vector machines (LSVM), finite Newton method for Lagrangian support vector machine (NSVM), Linear programming support vector machines (LPSVM), and smooth support vector machine (SSVM). The experimental results reveal that these SVM classifiers achieve very fast, simple, and efficient breast cancer diagnosis. The training results indicated that LSVM has the lowest accuracy of 95.6107 %, while St-SVM performed better than other methods for all performance indices (accuracy = 97.71 %) and is closely followed by LPSVM (accuracy = 97.3282). However, in the validation phase, the overall accuracies of LPSVM achieved 97.1429 %, which was superior to LSVM (95.4286 %), SSVM (96.5714 %), PSVM (96 %), NSVM (96.5714 %), and St-SVM (94.86 %). Value of ROC and MCC for LPSVM achieved 0.9938 and 0.9369, respectively, which outperformed other classifiers. The results strongly suggest that LPSVM can aid in the diagnosis of breast cancer.
TL;DR: From the results, the proposed methods are able to find more accurate solution than the KH and other methods and the robustness of the DEKH algorithm and the influence of the initial population size on convergence and performance are investigated.
Abstract: In order to overcome the poor exploitation of the krill herd (KH) algorithm, a hybrid differential evolution KH (DEKH) method has been developed for function optimization. The improvement involves adding a new hybrid differential evolution (HDE) operator into the krill, updating process for the purpose of dealing with optimization problems more efficiently. The introduced HDE operator inspires the intensification and lets the krill perform local search within the defined region. DEKH is validated by 26 functions. From the results, the proposed methods are able to find more accurate solution than the KH and other methods. In addition, the robustness of the DEKH algorithm and the influence of the initial population size on convergence and performance are investigated by a series of experiments.
TL;DR: The best mass is archived and utilised to accelerate the exploitation phase, ameliorating this weakness of the GSA, and the results of benchmark and classical engineering problems demonstrate the performance of the proposed method.
Abstract: One heuristic evolutionary algorithm recently proposed is the gravitational search algorithm (GSA), inspired by the gravitational forces between masses in nature. This algorithm has demonstrated superior performance among other well-known heuristic algorithms such as particle swarm optimisation and genetic algorithm. However, slow exploitation is a major weakness that might result in degraded performance when dealing with real engineering problems. Due to the cumulative effect of the fitness function on mass in GSA, masses get heavier and heavier over the course of iteration. This causes masses to remain in close proximity and neutralise the gravitational forces of each other in later iterations, preventing them from rapidly exploiting the optimum. In this study, the best mass is archived and utilised to accelerate the exploitation phase, ameliorating this weakness. The proposed method is tested on 25 unconstrained benchmark functions with six different scales provided by CEC 2005. In addition, two classical, constrained, engineering design problems, namely welded beam and tension spring, are also employed to investigate the efficiency of the proposed method in real constrained problems. The results of benchmark and classical engineering problems demonstrate the performance of the proposed method.
TL;DR: It is concluded that nonlinear regression can be applied as a simple method for predicting the maximum daily flow at the outlet of the Khosrow Shirin watershed in Iran.
Abstract: Flood prediction is an important for the design, planning and management of water resources systems. This study presents the use of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), multiple linear regression (MLR) and multiple nonlinear regression (MNLR) for forecasting maximum daily flow at the outlet of the Khosrow Shirin watershed, located in the Fars Province of Iran. Precipitation data from four meteorological stations were used to develop a multilayer perceptron topology model. Input vectors for simulations included the original precipitation data, an area-weighted average precipitation and antecedent flows with one- and two-day time lags. Performances of the models were evaluated with the RMSE and the R 2. The results showed that the area-weighted precipitation as an input to ANNs and MNLR and the spatially distributed precipitation input to ANFIS and MLR lead to more accurate predictions (e.g., in ANNs up to 2.0 m3 s−1 reduction in RMSE). Overall, the MNLR was shown to be superior (R 2 = 0.81 and RMSE = 0.145 m3 s−1) to ANNs, ANFIS and MLR for prediction of maximum daily flow. Furthermore, models including antecedent flow with one- and two-day time lags significantly improve flow prediction. We conclude that nonlinear regression can be applied as a simple method for predicting the maximum daily flow.
TL;DR: The experimental results confirm better performance of BPSOGSA compared with binary gravitational search algorithm (BGSA), binary particle swarm optimization (BPSO), and genetic algorithm in terms of avoiding local minima and convergence rate.
Abstract: The PSOGSA is a novel hybrid optimization algorithm, combining strengths of both particle swarm optimization (PSO) and gravitational search algorithm (GSA). It has been proven that this algorithm outperforms both PSO and GSA in terms of improved exploration and exploitation. The original version of this algorithm is well suited for problems with continuous search space. Some problems, however, have binary parameters. This paper proposes a binary version of hybrid PSOGSA called BPSOGSA to solve these kinds of optimization problems. The paper also considers integration of adaptive values to further balance exploration and exploitation of BPSOGSA. In order to evaluate the efficiencies of the proposed binary algorithm, 22 benchmark functions are employed and divided into three groups: unimodal, multimodal, and composite. The experimental results confirm better performance of BPSOGSA compared with binary gravitational search algorithm (BGSA), binary particle swarm optimization (BPSO), and genetic algorithm in terms of avoiding local minima and convergence rate.
TL;DR: Experimental results with the lithium-ion battery test data from NASA and CALCE show that the proposed fusion prognostic approach can effectively predict the battery RUL with more accurate forecasting result and uncertainty representation of probability density distribution.
Abstract: The lithium-ion battery cycle life prediction with particle filter (PF) depends on the physical or empirical model. However, in observation equation based on model, the adaptability and accuracy for individual battery under different operating conditions are not fully considered. Therefore, a novel fusion prognostic framework is proposed, in which the data-driven time series prediction model is adopted as observation equation, and combined to PF algorithm for lithium-ion battery cycle life prediction. Firstly, the nonlinear degradation feature of the lithium-ion battery capacity degradation is analyzed, and then, the nonlinear accelerated degradation factor is extracted to improve prediction ability of linear AR model. So an optimized nonlinear degradation autoregressive (ND---AR) time series model for remaining useful life (RUL) estimation of lithium-ion batteries is introduced. Then, the ND---AR model is used to realize multi-step prediction of the battery capacity degradation states. Finally, to improve the uncertainty representation ability of the standard PF algorithm, the regularized particle filter is applied to design a fusion RUL estimation framework of lithium-ion battery. Experimental results with the lithium-ion battery test data from NASA and CALCE (The Center for Advanced Life Cycle Engineering, the University of Maryland) show that the proposed fusion prognostic approach can effectively predict the battery RUL with more accurate forecasting result and uncertainty representation of probability density distribution (pdf).
TL;DR: The basic concepts of graph theory are introduced and main matrix representations of the graph are reviewed, then the objective functions of typical graph cut methods are compared, and the nature of spectral clustering algorithm is explored.
Abstract: Spectral clustering is a clustering method based on algebraic graph theory. It has aroused extensive attention of academia in recent years, due to its solid theoretical foundation, as well as the good performance of clustering. This paper introduces the basic concepts of graph theory and reviews main matrix representations of the graph, then compares the objective functions of typical graph cut methods and explores the nature of spectral clustering algorithm. We also summarize the latest research achievements of spectral clustering and discuss several key issues in spectral clustering, such as how to construct similarity matrix and Laplacian matrix, how to select eigenvectors, how to determine cluster number, and the applications of spectral clustering. At last, we propose several valuable research directions in light of the deficiencies of spectral clustering algorithms.
TL;DR: Results indicate that GMDH-type NN in comparison with fourth-order Runge–Kutta integration scheme provides an effective means of efficiently recognizing the patterns in data and accurately predicting a performance.
Abstract: Heat transfer of Cu–water nanofluid over a stretching cylinder in the presence of magnetic field has been investigated. The group method of data handling (GMDH) type neural networks (NNs) is used to calculate Nusselt number formulation. Results indicate that GMDH-type NN in comparison with fourth-order Runge–Kutta integration scheme provides an effective means of efficiently recognizing the patterns in data and accurately predicting a performance. The effects of nanoparticle volume fraction, magnetic parameter and Reynolds number on Nusselt number are studied by sensitivity analyses. The results show that Nusselt number is an increasing function of Reynolds number and volume fraction of nanoparticles while it is a decreasing function of magnetic parameter. As volume fraction of nanoparticles increases, the effect of this parameter on Nusselt number also increases, but opposite behavior is obtained for magnetic parameter and Reynolds number.
TL;DR: The results indicate that SVM could be a better alternative for predicting monthly streamflows as it provides a high degree of accuracy and reliability.
Abstract: The long-term streamflow forecasts are very significant in planing and reservoir operations. The streamflow forecasts have to deal with a complex and highly nonlinear data patterns. This study employs support vector machines (SVMs) in predicting monthly streamflows. SVMs are proved to be a good tool for forecasting the nonlinear time series. But the performance of the SVM depends solely upon the appropriate choice of parameters. Hence, particle swarm optimization technique is employed in tuning SVM parameters. The proposed SVM-PSO model is used in forecasting the streamflow values of Swan River near Bigfork and St. Regis River near Clark Fork of Montana, United States. Further SVM model with various input structures is constructed, and the best structure is determined using various statistical performances. Later, the performance of the SVM model is compared with the autoregressive moving average model (ARMA) and artificial neural networks (ANN's). The results indicate that SVM could be a better alternative for predicting monthly streamflows as it provides a high degree of accuracy and reliability.
TL;DR: A combination methodology which attempts to benefit from the strengths of both RW and ANN models, and achieves reasonably better forecasting accuracies than each of RW, FANN and EANN models in isolation for all four financial time series.
Abstract: Properly comprehending and modeling the dynamics of financial data has indispensable practical importance. The prime goal of a financial time series model is to provide reliable future forecasts which are crucial for investment planning, fiscal risk hedging, governmental policy making, etc. These time series often exhibit notoriously haphazard movements which make the task of modeling and forecasting extremely difficult. As per the research evidence, the random walk (RW) is so far the best linear model for forecasting financial data. Artificial neural network (ANN) is another promising alternative with the unique capability of nonlinear self-adaptive modeling. Numerous comparisons of the performances of RW and ANN models have also been carried out in the literature with mixed conclusions. In this paper, we propose a combination methodology which attempts to benefit from the strengths of both RW and ANN models. In our proposed approach, the linear part of a financial dataset is processed through the RW model, and the remaining nonlinear residuals are processed using an ensemble of feedforward ANN (FANN) and Elman ANN (EANN) models. The forecasting ability of the proposed scheme is examined on four real-world financial time series in terms of three popular error statistics. The obtained results clearly demonstrate that our combination method achieves reasonably better forecasting accuracies than each of RW, FANN and EANN models in isolation for all four financial time series.
TL;DR: Experimental results indicate that the proposed algorithm performs better than or at least comparable to state-of-the-art approaches from literature when considering the quality of the solution obtained.
Abstract: The cuckoo search algorithm is a simple and effective global optimization algorithm. It has been successfully applied to solve a wide range of real-world optimization problem. In this paper, we use a new search strategy based on orthogonal learning strategy to enhance the exploitation ability of the basic cuckoo search algorithm. In order to verify the performance of our approach, 23 benchmark functions are employed. Experimental results indicate that the proposed algorithm performs better than or at least comparable to state-of-the-art approaches from literature when considering the quality of the solution obtained.
TL;DR: A robustness analysis based on sensitivity is shown in this article to analyze the disturbance rejection properties and the relations of the IMC parameters, obtaining a robust method for cascade controllers with better performance than sequential tuning or other frequency domain-based methods.
Abstract: In this article, an internal model control plus proportional-integral-derivative (IMC---PID) tuning procedure for cascade control systems is proposed based on the gain and phase margin specifications of the inner and outer loop. The internal model control parameters are adjusted according to the desired frequency response of each loop with a minimum interaction between the inner and outer PID controllers, obtaining a fine tuning and the desired gain and phase margins specifications due to an appropriate selection of the PID controller gains and constants. Given the design specifications for the inner and outer loop, this tuning procedure adjusts the IMC parameter of each controller independently, with no interference between the inner and outer loop obtaining a robust method for cascade controllers with better performance than sequential tuning or other frequency domain-based methods. This technique is accurate and simple, providing a convenient technique for the PID tuning of cascade control systems in different applications such as mechanical, electrical or chemical systems. The proposed tuning method explained in this article provides a flexible tuning procedure in comparison with other tuning procedures because each loop is tuned simultaneously without modifying the robustness characteristics of the inner and outer loop. Several experiments are shown to compare and validate the effectiveness of the proposed tuning procedure over other sequential or cascade tuning methods; some experiments under different conditions are done to test the performance of the proposed tuning technique. For these reasons, a robustness analysis based on sensitivity is shown in this article to analyze the disturbance rejection properties and the relations of the IMC parameters.
TL;DR: A new approach intended to provide more reliable magnetic resonance (MR) breast image segmentation that is based on adaptation to identify target objects through an optimization methodology that maintains the optimum result during iterations is presented.
Abstract: Image segmentation is vital for meaningful analysis and interpretation of the medical images. The most popular method for clustering is k-means clustering. This article presents a new approach intended to provide more reliable magnetic resonance (MR) breast image segmentation that is based on adaptation to identify target objects through an optimization methodology that maintains the optimum result during iterations. The proposed approach improves and enhances the effectiveness and efficiency of the traditional k-means clustering algorithm. The performance of the presented approach was evaluated using various tests and different MR breast images. The experimental results demonstrate that the overall accuracy provided by the proposed adaptive k-means approach is superior to the standard k-means clustering technique.
TL;DR: A joint analysis of the efficiency/efficacy trade-off provides novel insight in the concrete successful exploitation of RC for AAL tasks and for their distributed implementation into wireless sensor networks.
Abstract: In this paper, we present an introduction and critical experimental evaluation of a reservoir computing (RC) approach for ambient assisted living (AAL) applications. Such an empirical analysis jointly addresses the issues of efficiency, by analyzing different system configurations toward the embedding into computationally constrained wireless sensor devices, and of efficacy, by analyzing the predictive performance on real-world applications. First, the approach is assessed on a validation scheme where training, validation and test data are sampled in homogeneous ambient conditions, i.e., from the same set of rooms. Then, it is introduced an external test set involving a new setting, i.e., a novel ambient, which was not available in the first phase of model training and validation. The specific test-bed considered in the paper allows us to investigate the capability of the RC approach to discriminate among user movement trajectories from received signal strength indicator sensor signals. This capability can be exploited in various AAL applications targeted at learning user indoor habits, such as in the proposed indoor movement forecasting task. Such a joint analysis of the efficiency/efficacy trade-off provides novel insight in the concrete successful exploitation of RC for AAL tasks and for their distributed implementation into wireless sensor networks.
TL;DR: This work presents a review of the state of the art of learning vector quantization (LVQ) classifiers and proposes a taxonomy which integrates the most relevant LVQ approaches to date.
Abstract: In this work, we present a review of the state of the art of learning vector quantization (LVQ) classifiers. A taxonomy is proposed which integrates the most relevant LVQ approaches to date. The main concepts associated with modern LVQ approaches are defined. A comparison is made among eleven LVQ classifiers using one real-world and two artificial datasets.
TL;DR: Magnetohydrodynamic flow in a nanofluid filled inclined enclosure is investigated numerically using the Control Volume based Finite Element Method and shows that in presence of magnetic field, velocity field retarded, and hence, convection and Nusselt number decreases.
Abstract: Magnetohydrodynamic flow in a nanofluid filled inclined enclosure is investigated numerically using the Control Volume based Finite Element Method. The cold wall of cavity is assumed to mimic a sinusoidal profile with different dimensionless amplitude, and the fluid in the enclosure is a water-based nanofluid containing Cu nanoparticles. The effective thermal conductivity and viscosity of nanofluid are calculated using the Maxwell–Garnetts and Brinkman models, respectively. Numerical simulations were performed for different governing parameters namely the Hartmann number, Rayleigh number, nanoparticle volume fraction and inclination angle of enclosure. The results show that in presence of magnetic field, velocity field retarded, and hence, convection and Nusselt number decreases. At Ra = 103, maximum value of enhancement for low Hartmann number is obtained at γ = 0°, but for higher values of Hartmann number, maximum values of E occurs at γ = 90°. Also, it can be found that for all values of Hartmann number, at Ra = 104 and 105, maximum value of E is obtained at γ = 60° and γ = 0°, respectively.
TL;DR: It is proved that the non-homogenous discrete grey model (abbreviated as NDGM) with first accumulated generating operator violates the principle of new information priority and principle of minimal information of grey system theory.
Abstract: It is proved that the non-homogenous discrete grey model (abbreviated as NDGM) with first accumulated generating operator violates the principle of new information priority and principle of minimal information of grey system theory. A new NDGM with the fractional-order accumulation is put forward. The first value is effective when the accumulation order number is not 1, and the priority of new information can be better reflected when the accumulation order number becomes smaller. Three real case studies show that the proposed grey model has higher performances not only on model fitting but also on forecasting.
TL;DR: A review of a variety of supervised neural networks with online learning capabilities, focusing on articles published in main indexed journals in the past 10 years, examines a number of key neural network architectures.
Abstract: Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003---2013). We examine a number of key neural network architectures, which include feedforward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented.
TL;DR: An intelligent approach based on the Mamdani fuzzy model was utilized to predict UCS of rock surrounding access tunnels in longwall coal mining, and it was concluded that performance of fuzzy model is considerably better than statistical model.
Abstract: Unconfined compressive strength (UCS) of rocks is one of the most important parameters in rock engineering, engineering geology, and mining projects. In the laboratory determination of UCS, high-quality samples are necessary; in which preparing of core samples has several limits, as it is difficult, expensive, and time-consuming. For this, development of predictive models to determine the UCS of rocks seems to be an attractive research. In this study, an intelligent approach based on the Mamdani fuzzy model was utilized to predict UCS of rock surrounding access tunnels in longwall coal mining. To approve the capability of this approach, the obtained results are compared to the results of statistical model. A database containing 93 rock sample records, ranging from weak to very strong rock types, was used to develop and test the models. For the evaluation of models performance, determination coefficient (R
2), root mean square error, and variance account for indices were used. Based on this comparison, it was concluded that performance of fuzzy model is considerably better than statistical model. Also, the fuzzy model results indicate very close agreement for the UCS with the laboratory measurements. Furthermore, the fuzzy model sensitivity analysis shows that Schmidt hardness and porosity are the most and least effective parameters on the UCS, respectively.