Computational Intelligence and Neuroscience The latest articles from Hindawi Publishing Corporation © 2016 , Hindawi Publishing Corporation . All rights reserved. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification Wed, 22 Jun 2016 12:15:53 +0000 The latest generation of convolutional neural networks (CNNs) has achieved impressive results in the field of image classification. This paper is concerned with a new approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. Novel way of training and the methodology used facilitate a quick and easy system implementation in practice. The developed model is able to recognize 13 different types of plant diseases out of healthy leaves, with the ability to distinguish plant leaves from their surroundings. According to our knowledge, this method for plant disease recognition has been proposed for the first time. All essential steps required for implementing this disease recognition model are fully described throughout the paper, starting from gathering images in order to create a database, assessed by agricultural experts. Caffe, a deep learning framework developed by Berkley Vision and Learning Centre, was used to perform the deep CNN training. The experimental results on the developed model achieved precision between 91% and 98%, for separate class tests, on average 96.3%. Srdjan Sladojevic, Marko Arsenovic, Andras Anderla, Dubravko Culibrk, and Darko Stefanovic Copyright © 2016 Srdjan Sladojevic et al. All rights reserved. EOG-sEMG Human Interface for Communication Tue, 21 Jun 2016 12:11:37 +0000 The aim of this study is to present electrooculogram (EOG) and surface electromyogram (sEMG) signals that can be used as a human-computer interface. Establishing an efficient alternative channel for communication without overt speech and hand movements is important for increasing the quality of life for patients suffering from amyotrophic lateral sclerosis, muscular dystrophy, or other illnesses. In this paper, we propose an EOG-sEMG human-computer interface system for communication using both cross-channels and parallel lines channels on the face with the same electrodes. This system could record EOG and sEMG signals as “dual-modality” for pattern recognition simultaneously. Although as much as 4 patterns could be recognized, dealing with the state of the patients, we only choose two classes (left and right motion) of EOG and two classes (left blink and right blink) of sEMG which are easily to be realized for simulation and monitoring task. From the simulation results, our system achieved four-pattern classification with an accuracy of 95.1%. Hiroki Tamura, Mingmin Yan, Keiko Sakurai, and Koichi Tanno Copyright © 2016 Hiroki Tamura et al. All rights reserved. Optimizing NEURON Simulation Environment Using Remote Memory Access with Recursive Doubling on Distributed Memory Systems Mon, 20 Jun 2016 11:41:20 +0000 Increase in complexity of neuronal network models escalated the efforts to make NEURON simulation environment efficient. The computational neuroscientists divided the equations into subnets amongst multiple processors for achieving better hardware performance. On parallel machines for neuronal networks, interprocessor spikes exchange consumes large section of overall simulation time. In NEURON for communication between processors Message Passing Interface (MPI) is used. MPI_Allgather collective is exercised for spikes exchange after each interval across distributed memory systems. The increase in number of processors though results in achieving concurrency and better performance but it inversely affects MPI_Allgather which increases communication time between processors. This necessitates improving communication methodology to decrease the spikes exchange time over distributed memory systems. This work has improved MPI_Allgather method using Remote Memory Access (RMA) by moving two-sided communication to one-sided communication, and use of recursive doubling mechanism facilitates achieving efficient communication between the processors in precise steps. This approach enhanced communication concurrency and has improved overall runtime making NEURON more efficient for simulation of large neuronal network models. Danish Shehzad and Zeki Bozkuş Copyright © 2016 Danish Shehzad and Zeki Bozkuş. All rights reserved. A Fast Framework for Abrupt Change Detection Based on Binary Search Trees and Kolmogorov Statistic Thu, 16 Jun 2016 08:03:37 +0000 Change-Point (CP) detection has attracted considerable attention in the fields of data mining and statistics; it is very meaningful to discuss how to quickly and efficiently detect abrupt change from large-scale bioelectric signals. Currently, most of the existing methods, like Kolmogorov-Smirnov (KS) statistic and so forth, are time-consuming, especially for large-scale datasets. In this paper, we propose a fast framework for abrupt change detection based on binary search trees (BSTs) and a modified KS statistic, named BSTKS (binary search trees and Kolmogorov statistic). In this method, first, two binary search trees, termed as BSTcA and BSTcD, are constructed by multilevel Haar Wavelet Transform (HWT); second, three search criteria are introduced in terms of the statistic and variance fluctuations in the diagnosed time series; last, an optimal search path is detected from the root to leaf nodes of two BSTs. The studies on both the synthetic time series samples and the real electroencephalograph (EEG) recordings indicate that the proposed BSTKS can detect abrupt change more quickly and efficiently than KS, -statistic (), and Singular-Spectrum Analyses (SSA) methods, with the shortest computation time, the highest hit rate, the smallest error, and the highest accuracy out of four methods. This study suggests that the proposed BSTKS is very helpful for useful information inspection on all kinds of bioelectric time series signals. Jin-Peng Qi, Jie Qi, and Qing Zhang Copyright © 2016 Jin-Peng Qi et al. All rights reserved. A Methodology for the Hybridization Based in Active Components: The Case of cGA and Scatter Search Tue, 14 Jun 2016 11:28:24 +0000 This work presents the results of a new methodology for hybridizing metaheuristics. By first locating the active components (parts) of one algorithm and then inserting them into second one, we can build efficient and accurate optimization, search, and learning algorithms. This gives a concrete way of constructing new techniques that contrasts the spread ad hoc way of hybridizing. In this paper, the enhanced algorithm is a Cellular Genetic Algorithm (cGA) which has been successfully used in the past to find solutions to such hard optimization problems. In order to extend and corroborate the use of active components as an emerging hybridization methodology, we propose here the use of active components taken from Scatter Search (SS) to improve cGA. The results obtained over a varied set of benchmarks are highly satisfactory in efficacy and efficiency when compared with a standard cGA. Moreover, the proposed hybrid approach (i.e., cGA+SS) has shown encouraging results with regard to earlier applications of our methodology. Andrea Villagra, Enrique Alba, and Guillermo Leguizamón Copyright © 2016 Andrea Villagra et al. All rights reserved. Novel Virtual Environment for Alternative Treatment of Children with Cerebral Palsy Tue, 14 Jun 2016 09:36:21 +0000 Cerebral palsy is a severe condition usually caused by decreased brain oxygenation during pregnancy, at birth or soon after birth. Conventional treatments for cerebral palsy are often tiresome and expensive, leading patients to quit treatment. In this paper, we describe a virtual environment for patients to engage in a playful therapeutic game for neuropsychomotor rehabilitation, based on the experience of the occupational therapy program of the Nucleus for Integrated Medical Assistance (NAMI) at the University of Fortaleza, Brazil. Integration between patient and virtual environment occurs through the hand motion sensor “Leap Motion,” plus the electroencephalographic sensor “MindWave,” responsible for measuring attention levels during task execution. To evaluate the virtual environment, eight clinical experts on cerebral palsy were subjected to a questionnaire regarding the potential of the experimental virtual environment to promote cognitive and motor rehabilitation, as well as the potential of the treatment to enhance risks and/or negatively influence the patient’s development. Based on the very positive appraisal of the experts, we propose that the experimental virtual environment is a promising alternative tool for the rehabilitation of children with cerebral palsy. Juliana M. de Oliveira, Rafael Carneiro G. Fernandes, Cristtiano S. Pinto, Plácido R. Pinheiro, Sidarta Ribeiro, and Victor Hugo C. de Albuquerque Copyright © 2016 Juliana M. de Oliveira et al. All rights reserved. A Review of Surrogate Assisted Multiobjective Evolutionary Algorithms Sun, 12 Jun 2016 07:37:28 +0000 Multiobjective evolutionary algorithms have incorporated surrogate models in order to reduce the number of required evaluations to approximate the Pareto front of computationally expensive multiobjective optimization problems. Currently, few works have reviewed the state of the art in this topic. However, the existing reviews have focused on classifying the evolutionary multiobjective optimization algorithms with respect to the type of underlying surrogate model. In this paper, we center our focus on classifying multiobjective evolutionary algorithms with respect to their integration with surrogate models. This interaction has led us to classify similar approaches and identify advantages and disadvantages of each class. Alan Díaz-Manríquez, Gregorio Toscano, Jose Hugo Barron-Zambrano, and Edgar Tello-Leal Copyright © 2016 Alan Díaz-Manríquez et al. All rights reserved. Adaptive Shape Kernel-Based Mean Shift Tracker in Robot Vision System Thu, 09 Jun 2016 06:38:57 +0000 This paper proposes an adaptive shape kernel-based mean shift tracker using a single static camera for the robot vision system. The question that we address in this paper is how to construct such a kernel shape that is adaptive to the object shape. We perform nonlinear manifold learning technique to obtain the low-dimensional shape space which is trained by training data with the same view as the tracking video. The proposed kernel searches the shape in the low-dimensional shape space obtained by nonlinear manifold learning technique and constructs the adaptive kernel shape in the high-dimensional shape space. It can improve mean shift tracker performance to track object position and object contour and avoid the background clutter. In the experimental part, we take the walking human as example to validate that our method is accurate and robust to track human position and describe human contour. Chunmei Liu, Yirui Wang, and Shangce Gao Copyright © 2016 Chunmei Liu et al. All rights reserved. Metaheuristic Algorithms for Convolution Neural Network Wed, 08 Jun 2016 12:06:02 +0000 A typical modern optimization technique is usually either heuristic or metaheuristic. This technique has managed to solve some optimization problems in the research area of science, engineering, and industry. However, implementation strategy of metaheuristic for accuracy improvement on convolution neural networks (CNN), a famous deep learning method, is still rarely investigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial intelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this paper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential evolution, and harmony search, to optimize CNN. The performances of these metaheuristic methods in optimizing CNN on classifying MNIST and CIFAR dataset were evaluated and compared. Furthermore, the proposed methods are also compared with the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been improved (up to 7.14 percent). L. M. Rasdi Rere, Mohamad Ivan Fanany, and Aniati Murni Arymurthy Copyright © 2016 L. M. Rasdi Rere et al. All rights reserved. Neural Net Gains Estimation Based on an Equivalent Model Sun, 05 Jun 2016 13:36:54 +0000 A model of an Equivalent Artificial Neural Net (EANN) describes the gains set, viewed as parameters in a layer, and this consideration is a reproducible process, applicable to a neuron in a neural net (NN). The EANN helps to estimate the NN gains or parameters, so we propose two methods to determine them. The first considers a fuzzy inference combined with the traditional Kalman filter, obtaining the equivalent model and estimating in a fuzzy sense the gains matrix and the proper gain into the traditional filter identification. The second develops a direct estimation in state space, describing an EANN using the expected value and the recursive description of the gains estimation. Finally, a comparison of both descriptions is performed; highlighting the analytical method describes the neural net coefficients in a direct form, whereas the other technique requires selecting into the Knowledge Base (KB) the factors based on the functional error and the reference signal built with the past information of the system. Karen Alicia Aguilar Cruz, José de Jesús Medel Juárez, José Luis Fernández Muñoz, and Midory Esmeralda Vigueras Velázquez Copyright © 2016 Karen Alicia Aguilar Cruz et al. All rights reserved. An Analysis of the Effects of Smartphone Push Notifications on Task Performance with regard to Smartphone Overuse Using ERP Sun, 05 Jun 2016 09:00:31 +0000 Smartphones are used ubiquitously worldwide and are essential tools in modern society. However, smartphone overuse is an emerging social issue, and limited studies have objectively assessed this matter. The majority of previous studies have included surveys or behavioral observation studies. Since a previous study demonstrated an association between increased push notifications and smartphone overuse, we investigated the effects of push notifications on task performance. We detected changes in brainwaves generated by smartphone push notifications using the N200 and P300 components of event-related potential (ERP) to investigate both concentration and cognitive ability. ERP assessment indicated that, in both risk and nonrisk groups, the lowest N200 amplitude and the longest latency during task performance were found when push notifications were delivered. Compared to the nonrisk group, the risk group demonstrated lower P300 amplitudes and longer latencies. In addition, the risk group featured a higher rate of error in the Go-Nogo task, due to the negative influence of smartphone push notifications on performance in both risk and nonrisk groups. Furthermore, push notifications affected subsequent performance in the risk group. Seul-Kee Kim, So-Yeong Kim, and Hang-Bong Kang Copyright © 2016 Seul-Kee Kim et al. All rights reserved. PWC-ICA: A Method for Stationary Ordered Blind Source Separation with Application to EEG Thu, 02 Jun 2016 11:28:44 +0000 Independent component analysis (ICA) is a class of algorithms widely applied to separate sources in EEG data. Most ICA approaches use optimization criteria derived from temporal statistical independence and are invariant with respect to the actual ordering of individual observations. We propose a method of mapping real signals into a complex vector space that takes into account the temporal order of signals and enforces certain mixing stationarity constraints. The resulting procedure, which we call Pairwise Complex Independent Component Analysis (PWC-ICA), performs the ICA in a complex setting and then reinterprets the results in the original observation space. We examine the performance of our candidate approach relative to several existing ICA algorithms for the blind source separation (BSS) problem on both real and simulated EEG data. On simulated data, PWC-ICA is often capable of achieving a better solution to the BSS problem than AMICA, Extended Infomax, or FastICA. On real data, the dipole interpretations of the BSS solutions discovered by PWC-ICA are physically plausible, are competitive with existing ICA approaches, and may represent sources undiscovered by other ICA methods. In conjunction with this paper, the authors have released a MATLAB toolbox that performs PWC-ICA on real, vector-valued signals. Kenneth Ball, Nima Bigdely-Shamlo, Tim Mullen, and Kay Robbins Copyright © 2016 Kenneth Ball et al. All rights reserved. An Application of Self-Organizing Map for Multirobot Multigoal Path Planning with Minmax Objective Thu, 02 Jun 2016 06:10:07 +0000 In this paper, Self-Organizing Map (SOM) for the Multiple Traveling Salesman Problem (MTSP) with minmax objective is applied to the robotic problem of multigoal path planning in the polygonal domain. The main difficulty of such SOM deployment is determination of collision-free paths among obstacles that is required to evaluate the neuron-city distances in the winner selection phase of unsupervised learning. Moreover, a collision-free path is also needed in the adaptation phase, where neurons are adapted towards the presented input signal (city) to the network. Simple approximations of the shortest path are utilized to address this issue and solve the robotic MTSP by SOM. Suitability of the proposed approximations is verified in the context of cooperative inspection, where cities represent sensing locations that guarantee to “see” the whole robots’ workspace. The inspection task formulated as the MTSP-Minmax is solved by the proposed SOM approach and compared with the combinatorial heuristic GENIUS. The results indicate that the proposed approach provides competitive results to GENIUS and support applicability of SOM for robotic multigoal path planning with a group of cooperating mobile robots. The proposed combination of approximate shortest paths with unsupervised learning opens further applications of SOM in the field of robotic planning. Jan Faigl Copyright © 2016 Jan Faigl. All rights reserved. Mitigation of Effects of Occlusion on Object Recognition with Deep Neural Networks through Low-Level Image Completion Wed, 01 Jun 2016 13:18:54 +0000 Heavily occluded objects are more difficult for classification algorithms to identify correctly than unoccluded objects. This effect is rare and thus hard to measure with datasets like ImageNet and PASCAL VOC, however, owing to biases in human-generated image pose selection. We introduce a dataset that emphasizes occlusion and additions to a standard convolutional neural network aimed at increasing invariance to occlusion. An unmodified convolutional neural network trained and tested on the new dataset rapidly degrades to chance-level accuracy as occlusion increases. Training with occluded data slows this decline but still yields poor performance with high occlusion. Integrating novel preprocessing stages to segment the input and inpaint occlusions is an effective mitigation. A convolutional network so modified is nearly as effective with more than 81% of pixels occluded as it is with no occlusion. Such a network is also more accurate on unoccluded images than an otherwise identical network that has been trained with only unoccluded images. These results depend on successful segmentation. The occlusions in our dataset are deliberately easy to segment from the figure and background. Achieving similar results on a more challenging dataset would require finding a method to split figure, background, and occluding pixels in the input. Benjamin Chandler and Ennio Mingolla Copyright © 2016 Benjamin Chandler and Ennio Mingolla. All rights reserved. Gender and Age Related Effects While Watching TV Advertisements: An EEG Study Thu, 26 May 2016 06:30:27 +0000 The aim of the present paper is to show how the variation of the EEG frontal cortical asymmetry is related to the general appreciation perceived during the observation of TV advertisements, in particular considering the influence of the gender and age on it. In particular, we investigated the influence of the gender on the perception of a car advertisement (Experiment ) and the influence of the factor age on a chewing gum commercial (Experiment ). Experiment results showed statistically significant higher approach values for the men group throughout the commercial. Results from Experiment showed significant lower values by older adults for the spot, containing scenes not very enjoyed by them. In both studies, there was no statistical significant difference in the scene relative to the product offering between the experimental populations, suggesting the absence in our study of a bias towards the specific product in the evaluated populations. These evidences state the importance of the creativity in advertising, in order to attract the target population. Giulia Cartocci, Patrizia Cherubino, Dario Rossi, Enrica Modica, Anton Giulio Maglione, Gianluca di Flumeri, and Fabio Babiloni Copyright © 2016 Giulia Cartocci et al. All rights reserved. Stratification-Based Outlier Detection over the Deep Web Wed, 25 May 2016 09:32:55 +0000 For many applications, finding rare instances or outliers can be more interesting than finding common patterns. Existing work in outlier detection never considers the context of deep web. In this paper, we argue that, for many scenarios, it is more meaningful to detect outliers over deep web. In the context of deep web, users must submit queries through a query interface to retrieve corresponding data. Therefore, traditional data mining methods cannot be directly applied. The primary contribution of this paper is to develop a new data mining method for outlier detection over deep web. In our approach, the query space of a deep web data source is stratified based on a pilot sample. Neighborhood sampling and uncertainty sampling are developed in this paper with the goal of improving recall and precision based on stratification. Finally, a careful performance evaluation of our algorithm confirms that our approach can effectively detect outliers in deep web. Xuefeng Xian, Pengpeng Zhao, Victor S. Sheng, Ligang Fang, Caidong Gu, Yuanfeng Yang, and Zhiming Cui Copyright © 2016 Xuefeng Xian et al. All rights reserved. An Artificial Intelligence System to Predict Quality of Service in Banking Organizations Sun, 22 May 2016 13:10:18 +0000 Quality of service, that is, the waiting time that customers must endure in order to receive a service, is a critical performance aspect in private and public service organizations. Providing good service quality is particularly important in highly competitive sectors where similar services exist. In this paper, focusing on banking sector, we propose an artificial intelligence system for building a model for the prediction of service quality. While the traditional approach used for building analytical models relies on theories and assumptions about the problem at hand, we propose a novel approach for learning models from actual data. Thus, the proposed approach is not biased by the knowledge that experts may have about the problem, but it is completely based on the available data. The system is based on a recently defined variant of genetic programming that allows practitioners to include the concept of semantics in the search process. This will have beneficial effects on the search process and will produce analytical models that are based only on the data and not on domain-dependent knowledge. Mauro Castelli, Luca Manzoni, and Aleš Popovič Copyright © 2016 Mauro Castelli et al. All rights reserved. A Hybrid Neural Network Model for Sales Forecasting Based on ARIMA and Search Popularity of Article Titles Sun, 22 May 2016 11:24:22 +0000 Enhancing sales and operations planning through forecasting analysis and business intelligence is demanded in many industries and enterprises. Publishing industries usually pick attractive titles and headlines for their stories to increase sales, since popular article titles and headlines can attract readers to buy magazines. In this paper, information retrieval techniques are adopted to extract words from article titles. The popularity measures of article titles are then analyzed by using the search indexes obtained from Google search engine. Backpropagation Neural Networks (BPNNs) have successfully been used to develop prediction models for sales forecasting. In this study, we propose a novel hybrid neural network model for sales forecasting based on the prediction result of time series forecasting and the popularity of article titles. The proposed model uses the historical sales data, popularity of article titles, and the prediction result of a time series, Autoregressive Integrated Moving Average (ARIMA) forecasting method to learn a BPNN-based forecasting model. Our proposed forecasting model is experimentally evaluated by comparing with conventional sales prediction techniques. The experimental result shows that our proposed forecasting method outperforms conventional techniques which do not consider the popularity of title words. Hani Omar, Van Hai Hoang, and Duen-Ren Liu Copyright © 2016 Hani Omar et al. All rights reserved. A General Fuzzy Cerebellar Model Neural Network Multidimensional Classifier Using Intuitionistic Fuzzy Sets for Medical Identification Thu, 19 May 2016 09:00:55 +0000 The diversity of medical factors makes the analysis and judgment of uncertainty one of the challenges of medical diagnosis. A well-designed classification and judgment system for medical uncertainty can increase the rate of correct medical diagnosis. In this paper, a new multidimensional classifier is proposed by using an intelligent algorithm, which is the general fuzzy cerebellar model neural network (GFCMNN). To obtain more information about uncertainty, an intuitionistic fuzzy linguistic term is employed to describe medical features. The solution of classification is obtained by a similarity measurement. The advantages of the novel classifier proposed here are drawn out by comparing the same medical example under the methods of intuitionistic fuzzy sets (IFSs) and intuitionistic fuzzy cross-entropy (IFCE) with different score functions. Cross verification experiments are also taken to further test the classification ability of the GFCMNN multidimensional classifier. All of these experimental results show the effectiveness of the proposed GFCMNN multidimensional classifier and point out that it can assist in supporting for correct medical diagnoses associated with multiple categories. Jing Zhao, Lo-Yi Lin, and Chih-Min Lin Copyright © 2016 Jing Zhao et al. All rights reserved. A Novel Quantum-Behaved Bat Algorithm with Mean Best Position Directed for Numerical Optimization Wed, 18 May 2016 14:16:21 +0000 This paper proposes a novel quantum-behaved bat algorithm with the direction of mean best position (QMBA). In QMBA, the position of each bat is mainly updated by the current optimal solution in the early stage of searching and in the late search it also depends on the mean best position which can enhance the convergence speed of the algorithm. During the process of searching, quantum behavior of bats is introduced which is beneficial to jump out of local optimal solution and make the quantum-behaved bats not easily fall into local optimal solution, and it has better ability to adapt complex environment. Meanwhile, QMBA makes good use of statistical information of best position which bats had experienced to generate better quality solutions. This approach not only inherits the characteristic of quick convergence, simplicity, and easy implementation of original bat algorithm, but also increases the diversity of population and improves the accuracy of solution. Twenty-four benchmark test functions are tested and compared with other variant bat algorithms for numerical optimization the simulation results show that this approach is simple and efficient and can achieve a more accurate solution. Binglian Zhu, Wenyong Zhu, Zijuan Liu, Qingyan Duan, and Long Cao Copyright © 2016 Binglian Zhu et al. All rights reserved. A Guiding Evolutionary Algorithm with Greedy Strategy for Global Optimization Problems Wed, 18 May 2016 11:33:50 +0000 A Guiding Evolutionary Algorithm (GEA) with greedy strategy for global optimization problems is proposed. Inspired by Particle Swarm Optimization, the Genetic Algorithm, and the Bat Algorithm, the GEA was designed to retain some advantages of each method while avoiding some disadvantages. In contrast to the usual Genetic Algorithm, each individual in GEA is crossed with the current global best one instead of a randomly selected individual. The current best individual served as a guide to attract offspring to its region of genotype space. Mutation was added to offspring according to a dynamic mutation probability. To increase the capability of exploitation, a local search mechanism was applied to new individuals according to a dynamic probability of local search. Experimental results show that GEA outperformed the other three typical global optimization algorithms with which it was compared. Leilei Cao, Lihong Xu, and Erik D. Goodman Copyright © 2016 Leilei Cao et al. All rights reserved. Course Control of Underactuated Ship Based on Nonlinear Robust Neural Network Backstepping Method Wed, 18 May 2016 08:27:33 +0000 The problem of course control for underactuated surface ship is addressed in this paper. Firstly, neural networks are adopted to determine the parameters of the unknown part of ideal virtual backstepping control, even the weight values of neural network are updated by adaptive technique. Then uniform stability for the convergence of course tracking errors has been proven through Lyapunov stability theory. Finally, simulation experiments are carried out to illustrate the effectiveness of proposed control method. Junjia Yuan, Hao Meng, Qidan Zhu, and Jiajia Zhou Copyright © 2016 Junjia Yuan et al. All rights reserved. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks Wed, 18 May 2016 08:20:12 +0000 In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. Jie Wang, Jun Wang, Wen Fang, and Hongli Niu Copyright © 2016 Jie Wang et al. All rights reserved. Biologically Inspired Methods for Imaging, Cognition, Vision, and Intelligence Wed, 18 May 2016 07:32:30 +0000 Yufeng Zheng, Erik Blasch, and Adel S. Elmaghraby Copyright © 2016 Yufeng Zheng et al. All rights reserved. Human Action Recognition Using Improved Salient Dense Trajectories Tue, 17 May 2016 13:22:17 +0000 Human action recognition in videos is a topic of active research in computer vision. Dense trajectory (DT) features were shown to be efficient for representing videos in state-of-the-art approaches. In this paper, we present a more effective approach of video representation using improved salient dense trajectories: first, detecting the motion salient region and extracting the dense trajectories by tracking interest points in each spatial scale separately and then refining the dense trajectories via the analysis of the motion saliency. Then, we compute several descriptors (i.e., trajectory displacement, HOG, HOF, and MBH) in the spatiotemporal volume aligned with the trajectories. Finally, in order to represent the videos better, we optimize the framework of bag-of-words according to the motion salient intensity distribution and the idea of sparse coefficient reconstruction. Our architecture is trained and evaluated on the four standard video actions datasets of KTH, UCF sports, HMDB51, and UCF50, and the experimental results show that our approach performs competitively comparing with the state-of-the-art results. Qingwu Li, Haisu Cheng, Yan Zhou, and Guanying Huo Copyright © 2016 Qingwu Li et al. All rights reserved. A New Modified Artificial Bee Colony Algorithm with Exponential Function Adaptive Steps Tue, 17 May 2016 10:01:22 +0000 As one of the most recent popular swarm intelligence techniques, artificial bee colony algorithm is poor at exploitation and has some defects such as slow search speed, poor population diversity, the stagnation in the working process, and being trapped into the local optimal solution. The purpose of this paper is to develop a new modified artificial bee colony algorithm in view of the initial population structure, subpopulation groups, step updating, and population elimination. Further, depending on opposition-based learning theory and the new modified algorithms, an improved -type grouping method is proposed and the original way of roulette wheel selection is substituted through sensitivity-pheromone way. Then, an adaptive step with exponential functions is designed for replacing the original random step. Finally, based on the new test function versions CEC13, six benchmark functions with the dimensions and are chosen and applied in the experiments for analyzing and comparing the iteration speed and accuracy of the new modified algorithms. The experimental results show that the new modified algorithm has faster and more stable searching and can quickly increase poor population diversity and bring out the global optimal solutions. Wei Mao, Heng-you Lan, and Hao-ru Li Copyright © 2016 Wei Mao et al. All rights reserved. BrainK for Structural Image Processing: Creating Electrical Models of the Human Head Mon, 16 May 2016 11:45:34 +0000 BrainK is a set of automated procedures for characterizing the tissues of the human head from MRI, CT, and photogrammetry images. The tissue segmentation and cortical surface extraction support the primary goal of modeling the propagation of electrical currents through head tissues with a finite difference model (FDM) or finite element model (FEM) created from the BrainK geometries. The electrical head model is necessary for accurate source localization of dense array electroencephalographic (dEEG) measures from head surface electrodes. It is also necessary for accurate targeting of cerebral structures with transcranial current injection from those surface electrodes. BrainK must achieve five major tasks: image segmentation, registration of the MRI, CT, and sensor photogrammetry images, cortical surface reconstruction, dipole tessellation of the cortical surface, and Talairach transformation. We describe the approach to each task, and we compare the accuracies for the key tasks of tissue segmentation and cortical surface extraction in relation to existing research tools (FreeSurfer, FSL, SPM, and BrainVisa). BrainK achieves good accuracy with minimal or no user intervention, it deals well with poor quality MR images and tissue abnormalities, and it provides improved computational efficiency over existing research packages. Kai Li, Xenophon Papademetris, and Don M. Tucker Copyright © 2016 Kai Li et al. All rights reserved. Optimization Control of the Color-Coating Production Process for Model Uncertainty Tue, 10 May 2016 16:35:14 +0000 Optimized control of the color-coating production process (CCPP) aims at reducing production costs and improving economic efficiency while meeting quality requirements. However, because optimization control of the CCPP is hampered by model uncertainty, a strategy that considers model uncertainty is proposed. Previous work has introduced a mechanistic model of CCPP based on process analysis to simulate the actual production process and generate process data. The partial least squares method is then applied to develop predictive models of film thickness and economic efficiency. To manage the model uncertainty, the robust optimization approach is introduced to improve the feasibility of the optimized solution. Iterative learning control is then utilized to further refine the model uncertainty. The constrained film thickness is transformed into one of the tracked targets to overcome the drawback that traditional iterative learning control cannot address constraints. The goal setting of economic efficiency is updated continuously according to the film thickness setting until this reaches its desired value. Finally, fuzzy parameter adjustment is adopted to ensure that the economic efficiency and film thickness converge rapidly to their optimized values under the constraint conditions. The effectiveness of the proposed optimization control strategy is validated by simulation results. Dakuo He, Zhengsong Wang, Le Yang, and Zhizhong Mao Copyright © 2016 Dakuo He et al. All rights reserved. Learning to Model Task-Oriented Attention Mon, 09 May 2016 14:32:42 +0000 For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene with a particular task. Models of saliency can be used to predict fixation locations, but a large body of previous saliency models focused on free-viewing task. They are based on bottom-up computation that does not consider task-oriented image semantics and often does not match actual eye movements. To address this problem, we collected eye tracking data of 11 subjects when they performed some particular search task in 1307 images and annotation data of 2,511 segmented objects with fine contours and 8 semantic attributes. Using this database as training and testing examples, we learn a model of saliency based on bottom-up image features and target position feature. Experimental results demonstrate the importance of the target information in the prediction of task-oriented visual attention. Xiaochun Zou, Xinbo Zhao, Jian Wang, and Yongjia Yang Copyright © 2016 Xiaochun Zou et al. All rights reserved. Regularized Embedded Multiple Kernel Dimensionality Reduction for Mine Signal Processing Mon, 09 May 2016 10:54:05 +0000 Traditional multiple kernel dimensionality reduction models are generally based on graph embedding and manifold assumption. But such assumption might be invalid for some high-dimensional or sparse data due to the curse of dimensionality, which has a negative influence on the performance of multiple kernel learning. In addition, some models might be ill-posed if the rank of matrices in their objective functions was not high enough. To address these issues, we extend the traditional graph embedding framework and propose a novel regularized embedded multiple kernel dimensionality reduction method. Different from the conventional convex relaxation technique, the proposed algorithm directly takes advantage of a binary search and an alternative optimization scheme to obtain optimal solutions efficiently. The experimental results demonstrate the effectiveness of the proposed method for supervised, unsupervised, and semisupervised scenarios. Shuang Li, Bing Liu, and Chen Zhang Copyright © 2016 Shuang Li et al. All rights reserved.