Computational Intelligence and Neuroscience The latest articles from Hindawi Publishing Corporation © 2015 , Hindawi Publishing Corporation . All rights reserved. Optimism in Active Learning Mon, 23 Nov 2015 07:45:32 +0000 Active learning is the problem of interactively constructing the training set used in classification in order to reduce its size. It would ideally successively add the instance-label pair that decreases the classification error most. However, the effect of the addition of a pair is not known in advance. It can still be estimated with the pairs already in the training set. The online minimization of the classification error involves a tradeoff between exploration and exploitation. This is a common problem in machine learning for which multiarmed bandit, using the approach of Optimism int the Face of Uncertainty, has proven very efficient these last years. This paper introduces three algorithms for the active learning problem in classification using Optimism in the Face of Uncertainty. Experiments lead on built-in problems and real world datasets demonstrate that they compare positively to state-of-the-art methods. Timothé Collet and Olivier Pietquin Copyright © 2015 Timothé Collet and Olivier Pietquin. All rights reserved. MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning Sun, 22 Nov 2015 12:16:02 +0000 Artificial neural networks (ANNs) have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation. Yang Liu, Jie Yang, Yuan Huang, Lixiong Xu, Siguang Li, and Man Qi Copyright © 2015 Yang Liu et al. All rights reserved. Recent Advances in Learning Theory Mon, 16 Nov 2015 13:29:34 +0000 Weihui Dai, Wlodzislaw Duch, Abdul Hanan Abdullah, Dongrong Xu, and Ye-Sho Chen Copyright © 2015 Weihui Dai et al. All rights reserved. Real-Time Control of a Video Game Using Eye Movements and Two Temporal EEG Sensors Sun, 15 Nov 2015 14:21:59 +0000 EEG-controlled gaming applications range widely from strictly medical to completely nonmedical applications. Games can provide not only entertainment but also strong motivation for practicing, thereby achieving better control with rehabilitation system. In this paper we present real-time control of video game with eye movements for asynchronous and noninvasive communication system using two temporal EEG sensors. We used wavelets to detect the instance of eye movement and time-series characteristics to distinguish between six classes of eye movement. A control interface was developed to test the proposed algorithm in real-time experiments with opened and closed eyes. Using visual feedback, a mean classification accuracy of 77.3% was obtained for control with six commands. And a mean classification accuracy of 80.2% was obtained using auditory feedback for control with five commands. The algorithm was then applied for controlling direction and speed of character movement in two-dimensional video game. Results showed that the proposed algorithm had an efficient response speed and timing with a bit rate of 30 bits/min, demonstrating its efficacy and robustness in real-time control. Abdelkader Nasreddine Belkacem, Supat Saetia, Kalanyu Zintus-art, Duk Shin, Hiroyuki Kambara, Natsue Yoshimura, Nasreddine Berrached, and Yasuharu Koike Copyright © 2015 Abdelkader Nasreddine Belkacem et al. All rights reserved. A Biologically Inspired Computational Model of Basal Ganglia in Action Selection Tue, 10 Nov 2015 08:09:50 +0000 The basal ganglia (BG) are a subcortical structure implicated in action selection. The aim of this work is to present a new cognitive neuroscience model of the BG, which aspires to represent a parsimonious balance between simplicity and completeness. The model includes the 3 main pathways operating in the BG circuitry, that is, the direct (Go), indirect (NoGo), and hyperdirect pathways. The main original aspects, compared with previous models, are the use of a two-term Hebb rule to train synapses in the striatum, based exclusively on neuronal activity changes caused by dopamine peaks or dips, and the role of the cholinergic interneurons (affected by dopamine themselves) during learning. Some examples are displayed, concerning a few paradigmatic cases: action selection in basal conditions, action selection in the presence of a strong conflict (where the role of the hyperdirect pathway emerges), synapse changes induced by phasic dopamine, and learning new actions based on a previous history of rewards and punishments. Finally, some simulations show model working in conditions of altered dopamine levels, to illustrate pathological cases (dopamine depletion in parkinsonian subjects or dopamine hypermedication). Due to its parsimonious approach, the model may represent a straightforward tool to analyze BG functionality in behavioral experiments. Chiara Baston and Mauro Ursino Copyright © 2015 Chiara Baston and Mauro Ursino. All rights reserved. Emotion Analysis of Telephone Complaints from Customer Based on Affective Computing Sun, 08 Nov 2015 13:57:58 +0000 Customer complaint has been the important feedback for modern enterprises to improve their product and service quality as well as the customer’s loyalty. As one of the commonly used manners in customer complaint, telephone communication carries rich emotional information of speeches, which provides valuable resources for perceiving the customer’s satisfaction and studying the complaint handling skills. This paper studies the characteristics of telephone complaint speeches and proposes an analysis method based on affective computing technology, which can recognize the dynamic changes of customer emotions from the conversations between the service staff and the customer. The recognition process includes speaker recognition, emotional feature parameter extraction, and dynamic emotion recognition. Experimental results show that this method is effective and can reach high recognition rates of happy and angry states. It has been successfully applied to the operation quality and service administration in telecom and Internet service company. Shuangping Gong, Yonghui Dai, Jun Ji, Jinzhao Wang, and Hai Sun Copyright © 2015 Shuangping Gong et al. All rights reserved. Information Dissemination of Public Health Emergency on Social Networks and Intelligent Computation Mon, 02 Nov 2015 07:51:29 +0000 Due to the extensive social influence, public health emergency has attracted great attention in today’s society. The booming social network is becoming a main information dissemination platform of those events and caused high concerns in emergency management, among which a good prediction of information dissemination in social networks is necessary for estimating the event’s social impacts and making a proper strategy. However, information dissemination is largely affected by complex interactive activities and group behaviors in social network; the existing methods and models are limited to achieve a satisfactory prediction result due to the open changeable social connections and uncertain information processing behaviors. ACP (artificial societies, computational experiments, and parallel execution) provides an effective way to simulate the real situation. In order to obtain better information dissemination prediction in social networks, this paper proposes an intelligent computation method under the framework of TDF (Theory-Data-Feedback) based on ACP simulation system which was successfully applied to the analysis of A (H1N1) Flu emergency. Hongzhi Hu, Huajuan Mao, Xiaohua Hu, Feng Hu, Xuemin Sun, Zaiping Jing, and Yunsuo Duan Copyright © 2015 Hongzhi Hu et al. All rights reserved. An Enhanced Differential Evolution Algorithm Based on Multiple Mutation Strategies Sun, 01 Nov 2015 10:06:22 +0000 Differential evolution algorithm is a simple yet efficient metaheuristic for global optimization over continuous spaces. However, there is a shortcoming of premature convergence in standard DE, especially in DE/best/1/bin. In order to take advantage of direction guidance information of the best individual of DE/best/1/bin and avoid getting into local trap, based on multiple mutation strategies, an enhanced differential evolution algorithm, named EDE, is proposed in this paper. In the EDE algorithm, an initialization technique, opposition-based learning initialization for improving the initial solution quality, and a new combined mutation strategy composed of DE/current/1/bin together with DE/pbest/bin/1 for the sake of accelerating standard DE and preventing DE from clustering around the global best individual, as well as a perturbation scheme for further avoiding premature convergence, are integrated. In addition, we also introduce two linear time-varying functions, which are used to decide which solution search equation is chosen at the phases of mutation and perturbation, respectively. Experimental results tested on twenty-five benchmark functions show that EDE is far better than the standard DE. In further comparisons, EDE is compared with other five state-of-the-art approaches and related results show that EDE is still superior to or at least equal to these methods on most of benchmark functions. Wan-li Xiang, Xue-lei Meng, Mei-qing An, Yin-zhen Li, and Ming-xia Gao Copyright © 2015 Wan-li Xiang et al. All rights reserved. Explore Awareness of Information Security: Insights from Cognitive Neuromechanism Mon, 26 Oct 2015 08:10:14 +0000 With the rapid development of the internet and information technology, the increasingly diversified portable mobile terminals, online shopping, and social media have facilitated information exchange, social communication, and financial payment for people more and more than ever before. In the meantime, information security and privacy protection have been meeting with new severe challenges. Although we have taken a variety of information security measures in both management and technology, the actual effectiveness depends firstly on people’s awareness of information security and the cognition of potential risks. In order to explore the new technology for the objective assessment of people’s awareness and cognition on information security, this paper takes the online financial payment as example and conducts an experimental study based on the analysis of electrophysiological signals. Results indicate that left hemisphere and beta rhythms of electroencephalogram (EEG) signal are sensitive to the cognitive degree of risks in the awareness of information security, which may be probably considered as the sign to assess people’s cognition of potential risks in online financial payment. Dongmei Han, Yonghui Dai, Tianlin Han, and Xingyun Dai Copyright © 2015 Dongmei Han et al. All rights reserved. Feed-Forward Neural Network Soft-Sensor Modeling of Flotation Process Based on Particle Swarm Optimization and Gravitational Search Algorithm Sun, 25 Oct 2015 13:14:07 +0000 For predicting the key technology indicators (concentrate grade and tailings recovery rate) of flotation process, a feed-forward neural network (FNN) based soft-sensor model optimized by the hybrid algorithm combining particle swarm optimization (PSO) algorithm and gravitational search algorithm (GSA) is proposed. Although GSA has better optimization capability, it has slow convergence velocity and is easy to fall into local optimum. So in this paper, the velocity vector and position vector of GSA are adjusted by PSO algorithm in order to improve its convergence speed and prediction accuracy. Finally, the proposed hybrid algorithm is adopted to optimize the parameters of FNN soft-sensor model. Simulation results show that the model has better generalization and prediction accuracy for the concentrate grade and tailings recovery rate to meet the online soft-sensor requirements of the real-time control in the flotation process. Jie-Sheng Wang and Shuang Han Copyright © 2015 Jie-Sheng Wang and Shuang Han. All rights reserved. CyberPsychological Computation on Social Community of Ubiquitous Learning Mon, 19 Oct 2015 09:34:38 +0000 Under the modern network environment, ubiquitous learning has been a popular way for people to study knowledge, exchange ideas, and share skills in the cyberspace. Existing research findings indicate that the learners’ initiative and community cohesion play vital roles in the social communities of ubiquitous learning, and therefore how to stimulate the learners’ interest and participation willingness so as to improve their enjoyable experiences in the learning process should be the primary consideration on this issue. This paper aims to explore an effective method to monitor the learners’ psychological reactions based on their behavioral features in cyberspace and therefore provide useful references for adjusting the strategies in the learning process. In doing so, this paper firstly analyzes the psychological assessment of the learners’ situations as well as their typical behavioral patterns and then discusses the relationship between the learners’ psychological reactions and their observable features in cyberspace. Finally, this paper puts forward a CyberPsychological computation method to estimate the learners’ psychological states online. Considering the diversity of learners’ habitual behaviors in the reactions to their psychological changes, a BP-GA neural network is proposed for the computation based on their personalized behavioral patterns. Xuan Zhou, Genghui Dai, Shuang Huang, Xuemin Sun, Feng Hu, Hongzhi Hu, and Mirjana Ivanović Copyright © 2015 Xuan Zhou et al. All rights reserved. A Neuroeconomics Analysis of Investment Process with Money Flow Information: The Error-Related Negativity Sun, 18 Oct 2015 08:52:54 +0000 This investigation is among the first ones to analyze the neural basis of an investment process with money flow information of financial market, using a simplified task where volunteers had to choose to buy or not to buy stocks based on the display of positive or negative money flow information. After choosing “to buy” or “not to buy,” participants were presented with feedback. At the same time, event-related potentials (ERPs) were used to record investor’s brain activity and capture the event-related negativity (ERN) and feedback-related negativity (FRN) components. The results of ERN suggested that there might be a higher risk and more conflict when buying stocks with negative net money flow information than positive net money flow information, and the inverse was also true for the “not to buy” stocks option. The FRN component evoked by the bad outcome of a decision was more negative than that by the good outcome, which reflected the difference between the values of the actual and expected outcome. From the research, we could further understand how investors perceived money flow information of financial market and the neural cognitive effect in investment process. Cuicui Wang, João Paulo Vieito, and Qingguo Ma Copyright © 2015 Cuicui Wang et al. All rights reserved. Two Different Points of View through Artificial Intelligence and Vector Autoregressive Models for Ex Post and Ex Ante Forecasting Tue, 13 Oct 2015 07:40:32 +0000 The ANN method has been applied by means of multilayered feedforward neural networks (MLFNs) by using different macroeconomic variables such as the exchange rate of USD/TRY, gold prices, and the Borsa Istanbul (BIST) 100 index based on monthly data over the period of January 2000 and September 2014 for Turkey. Vector autoregressive (VAR) method has also been applied with the same variables for the same period of time. In this study, different from other studies conducted up to the present, ENCOG machine learning framework has been used along with JAVA programming language in order to constitute the ANN. The training of network has been done by resilient propagation method. The ex post and ex ante estimates obtained by the ANN method have been compared with the results obtained by the econometric forecasting method of VAR. Strikingly, our findings based on the ANN method reveal that there is a possibility of financial distress or a financial crisis in Turkey starting from October 2017. The results which were obtained with the method of VAR also support the results of ANN method. Additionally, our results indicate that the ANN approach has more superior prediction performance than the VAR method. Alev Dilek Aydin and Seyma Caliskan Cavdar Copyright © 2015 Alev Dilek Aydin and Seyma Caliskan Cavdar. All rights reserved. P300 and Decision Making under Risk and Ambiguity Sun, 11 Oct 2015 08:14:01 +0000 Our study aims to contrast the neural temporal features of early stage of decision making in the context of risk and ambiguity. In monetary gambles under ambiguous or risky conditions, 12 participants were asked to make a decision to bet or not, with the event-related potentials (ERPs) recorded meantime. The proportion of choosing to bet in ambiguous condition was significantly lower than that in risky condition. An ERP component identified as P300 was found. The P300 amplitude elicited in risky condition was significantly larger than that in ambiguous condition. The lower bet rate in ambiguous condition and the smaller P300 amplitude elicited by ambiguous stimuli revealed that people showed much more aversion in the ambiguous condition than in the risky condition. The ERP results may suggest that decision making under ambiguity occupies higher working memory and recalls more past experience while decision making under risk mainly mobilizes attentional resources to calculate current information. These findings extended the current understanding of underlying mechanism for early assessment stage of decision making and explored the difference between the decision making under risk and ambiguity. Lei Wang, Jiehui Zheng, Shenwei Huang, and Haoye Sun Copyright © 2015 Lei Wang et al. All rights reserved. An Opinion Interactive Model Based on Individual Persuasiveness Mon, 05 Oct 2015 09:44:15 +0000 In order to study the formation process of group opinion in real life, we put forward a new opinion interactive model based on Deffuant model and its improved models in this paper because current models of opinion dynamics lack considering individual persuasiveness. Our model has following advantages: firstly persuasiveness is added to individual’s attributes reflecting the importance of persuasiveness, which means that all the individuals are different from others; secondly probability is introduced in the course of interaction which simulates the uncertainty of interaction. In Monte Carlo simulation experiments, sensitivity analysis including the influence of randomness, initial persuasiveness distribution, and number of individuals is studied at first; what comes next is that the range of common opinion based on the initial persuasiveness distribution can be predicted. Simulation experiment results show that when the initial values of agents are fixed, no matter how many times independently replicated experiments, the common opinion will converge at a certain point; however the number of iterations will not always be the same; the range of common opinion can be predicted when initial distribution of opinion and persuasiveness are given. As a result, this model can reflect and interpret some phenomena of opinion interaction in realistic society. Xin Zhou, Bin Chen, Liang Liu, Liang Ma, and Xiaogang Qiu Copyright © 2015 Xin Zhou et al. All rights reserved. An Efficient Robust Eye Localization by Learning the Convolution Distribution Using Eye Template Sun, 04 Oct 2015 06:49:26 +0000 Eye localization is a fundamental process in many facial analyses. In practical use, it is often challenged by illumination, head pose, facial expression, occlusion, and other factors. It remains great difficulty to achieve high accuracy with short prediction time and low training cost at the same time. This paper presents a novel eye localization approach which explores only one-layer convolution map by eye template using a BP network. Results showed that the proposed method is robust to handle many difficult situations. In experiments, accuracy of 98% and 96%, respectively, on the BioID and LFPW test sets could be achieved in 10 fps prediction rate with only 15-minute training cost. In comparison with other robust models, the proposed method could obtain similar best results with greatly reduced training time and high prediction speed. Xuan Li, Yong Dou, Xin Niu, Jiaqing Xu, and Ruorong Xiao Copyright © 2015 Xuan Li et al. All rights reserved. Neural Cognition and Affective Computing on Cyber Language Mon, 28 Sep 2015 09:10:56 +0000 Characterized by its customary symbol system and simple and vivid expression patterns, cyber language acts as not only a tool for convenient communication but also a carrier of abundant emotions and causes high attention in public opinion analysis, internet marketing, service feedback monitoring, and social emergency management. Based on our multidisciplinary research, this paper presents a classification of the emotional symbols in cyber language, analyzes the cognitive characteristics of different symbols, and puts forward a mechanism model to show the dominant neural activities in that process. Through the comparative study of Chinese, English, and Spanish, which are used by the largest population in the world, this paper discusses the expressive patterns of emotions in international cyber languages and proposes an intelligent method for affective computing on cyber language in a unified PAD (Pleasure-Arousal-Dominance) emotional space. Shuang Huang, Xuan Zhou, Ke Xue, Xiqiong Wan, Zhenyi Yang, Duo Xu, Mirjana Ivanović, and Xueer Yu Copyright © 2015 Shuang Huang et al. All rights reserved. Neural Basis of Intrinsic Motivation: Evidence from Event-Related Potentials Sun, 27 Sep 2015 07:01:35 +0000 Human intrinsic motivation is of great importance in human behavior. However, although researchers have focused on this topic for decades, its neural basis was still unclear. The current study employed event-related potentials to investigate the neural disparity between an interesting stop-watch (SW) task and a boring watch-stop task (WS) to understand the neural mechanisms of intrinsic motivation. Our data showed that, in the cue priming stage, the cue of the SW task elicited smaller N2 amplitude than that of the WS task. Furthermore, in the outcome feedback stage, the outcome of the SW task induced smaller FRN amplitude and larger P300 amplitude than that of the WS task. These results suggested that human intrinsic motivation did exist and that it can be detected at the neural level. Furthermore, intrinsic motivation could be quantitatively indexed by the amplitude of ERP components, such as N2, FRN, and P300, in the cue priming stage or feedback stage. Quantitative measurements would also be convenient for intrinsic motivation to be added as a candidate social factor in the construction of a machine learning model. Jia Jin, Liping Yu, and Qingguo Ma Copyright © 2015 Jia Jin et al. All rights reserved. Intelligent Context-Aware and Adaptive Interface for Mobile LBS Sun, 20 Sep 2015 09:49:05 +0000 Context-aware user interface plays an important role in many human-computer Interaction tasks of location based services. Although spatial models for context-aware systems have been studied extensively, how to locate specific spatial information for users is still not well resolved, which is important in the mobile environment where location based services users are impeded by device limitations. Better context-aware human-computer interaction models of mobile location based services are needed not just to predict performance outcomes, such as whether people will be able to find the information needed to complete a human-computer interaction task, but to understand human processes that interact in spatial query, which will in turn inform the detailed design of better user interfaces in mobile location based services. In this study, a context-aware adaptive model for mobile location based services interface is proposed, which contains three major sections: purpose, adjustment, and adaptation. Based on this model we try to describe the process of user operation and interface adaptation clearly through the dynamic interaction between users and the interface. Then we show how the model applies users’ demands in a complicated environment and suggested the feasibility by the experimental results. Jiangfan Feng and Yanhong Liu Copyright © 2015 Jiangfan Feng and Yanhong Liu. All rights reserved. The Large Scale Machine Learning in an Artificial Society: Prediction of the Ebola Outbreak in Beijing Sun, 20 Sep 2015 09:39:42 +0000 Ebola virus disease (EVD) distinguishes its feature as high infectivity and mortality. Thus, it is urgent for governments to draw up emergency plans against Ebola. However, it is hard to predict the possible epidemic situations in practice. Luckily, in recent years, computational experiments based on artificial society appeared, providing a new approach to study the propagation of EVD and analyze the corresponding interventions. Therefore, the rationality of artificial society is the key to the accuracy and reliability of experiment results. Individuals’ behaviors along with travel mode directly affect the propagation among individuals. Firstly, artificial Beijing is reconstructed based on geodemographics and machine learning is involved to optimize individuals’ behaviors. Meanwhile, Ebola course model and propagation model are built, according to the parameters in West Africa. Subsequently, propagation mechanism of EVD is analyzed, epidemic scenario is predicted, and corresponding interventions are presented. Finally, by simulating the emergency responses of Chinese government, the conclusion is finally drawn that Ebola is impossible to outbreak in large scale in the city of Beijing. Peng Zhang, Bin Chen, Liang Ma, Zhen Li, Zhichao Song, Wei Duan, and Xiaogang Qiu Copyright © 2015 Peng Zhang et al. All rights reserved. Exploiting Language Models to Classify Events from Twitter Mon, 14 Sep 2015 08:30:25 +0000 Classifying events is challenging in Twitter because tweets texts have a large amount of temporal data with a lot of noise and various kinds of topics. In this paper, we propose a method to classify events from Twitter. We firstly find the distinguishing terms between tweets in events and measure their similarities with learning language models such as ConceptNet and a latent Dirichlet allocation method for selectional preferences (LDA-SP), which have been widely studied based on large text corpora within computational linguistic relations. The relationship of term words in tweets will be discovered by checking them under each model. We then proposed a method to compute the similarity between tweets based on tweets’ features including common term words and relationships among their distinguishing term words. It will be explicit and convenient for applying to k-nearest neighbor techniques for classification. We carefully applied experiments on the Edinburgh Twitter Corpus to show that our method achieves competitive results for classifying events. Duc-Thuan Vo, Vo Thuan Hai, and Cheol-Young Ock Copyright © 2015 Duc-Thuan Vo et al. All rights reserved. Design of Automatic Extraction Algorithm of Knowledge Points for MOOCs Sun, 13 Sep 2015 13:33:37 +0000 In recent years, Massive Open Online Courses (MOOCs) are very popular among college students and have a powerful impact on academic institutions. In the MOOCs environment, knowledge discovery and knowledge sharing are very important, which currently are often achieved by ontology techniques. In building ontology, automatic extraction technology is crucial. Because the general methods of text mining algorithm do not have obvious effect on online course, we designed automatic extracting course knowledge points (AECKP) algorithm for online course. It includes document classification, Chinese word segmentation, and POS tagging for each document. Vector Space Model (VSM) is used to calculate similarity and design the weight to optimize the TF-IDF algorithm output values, and the higher scores will be selected as knowledge points. Course documents of “C programming language” are selected for the experiment in this study. The results show that the proposed approach can achieve satisfactory accuracy rate and recall rate. Haijian Chen, Dongmei Han, Yonghui Dai, and Lina Zhao Copyright © 2015 Haijian Chen et al. All rights reserved. Operating Comfort Prediction Model of Human-Machine Interface Layout for Cabin Based on GEP Thu, 10 Sep 2015 11:03:42 +0000 In view of the evaluation and decision-making problem of human-machine interface layout design for cabin, the operating comfort prediction model is proposed based on GEP (Gene Expression Programming), using operating comfort to evaluate layout scheme. Through joint angles to describe operating posture of upper limb, the joint angles are taken as independent variables to establish the comfort model of operating posture. Factor analysis is adopted to decrease the variable dimension; the model’s input variables are reduced from 16 joint angles to 4 comfort impact factors, and the output variable is operating comfort score. The Chinese virtual human body model is built by CATIA software, which will be used to simulate and evaluate the operators’ operating comfort. With 22 groups of evaluation data as training sample and validation sample, GEP algorithm is used to obtain the best fitting function between the joint angles and the operating comfort; then, operating comfort can be predicted quantitatively. The operating comfort prediction result of human-machine interface layout of driller control room shows that operating comfort prediction model based on GEP is fast and efficient, it has good prediction effect, and it can improve the design efficiency. Li Deng, Guohua Wang, and Bo Chen Copyright © 2015 Li Deng et al. All rights reserved. Deep Neural Networks with Multistate Activation Functions Thu, 10 Sep 2015 10:02:59 +0000 We propose multistate activation functions (MSAFs) for deep neural networks (DNNs). These MSAFs are new kinds of activation functions which are capable of representing more than two states, including the N-order MSAFs and the symmetrical MSAF. DNNs with these MSAFs can be trained via conventional Stochastic Gradient Descent (SGD) as well as mean-normalised SGD. We also discuss how these MSAFs perform when used to resolve classification problems. Experimental results on the TIMIT corpus reveal that, on speech recognition tasks, DNNs with MSAFs perform better than the conventional DNNs, getting a relative improvement of 5.60% on phoneme error rates. Further experiments also reveal that mean-normalised SGD facilitates the training processes of DNNs with MSAFs, especially when being with large training sets. The models can also be directly trained without pretraining when the training set is sufficiently large, which results in a considerable relative improvement of 5.82% on word error rates. Chenghao Cai, Yanyan Xu, Dengfeng Ke, and Kaile Su Copyright © 2015 Chenghao Cai et al. All rights reserved. Nonlinear Inertia Weighted Teaching-Learning-Based Optimization for Solving Global Optimization Problem Wed, 02 Sep 2015 13:05:21 +0000 Teaching-learning-based optimization (TLBO) algorithm is proposed in recent years that simulates the teaching-learning phenomenon of a classroom to effectively solve global optimization of multidimensional, linear, and nonlinear problems over continuous spaces. In this paper, an improved teaching-learning-based optimization algorithm is presented, which is called nonlinear inertia weighted teaching-learning-based optimization (NIWTLBO) algorithm. This algorithm introduces a nonlinear inertia weighted factor into the basic TLBO to control the memory rate of learners and uses a dynamic inertia weighted factor to replace the original random number in teacher phase and learner phase. The proposed algorithm is tested on a number of benchmark functions, and its performance comparisons are provided against the basic TLBO and some other well-known optimization algorithms. The experiment results show that the proposed algorithm has a faster convergence rate and better performance than the basic TLBO and some other algorithms as well. Zong-Sheng Wu, Wei-Ping Fu, and Ru Xue Copyright © 2015 Zong-Sheng Wu et al. All rights reserved. Improved Quantum Artificial Fish Algorithm Application to Distributed Network Considering Distributed Generation Tue, 01 Sep 2015 08:23:04 +0000 An improved quantum artificial fish swarm algorithm (IQAFSA) for solving distributed network programming considering distributed generation is proposed in this work. The IQAFSA based on quantum computing which has exponential acceleration for heuristic algorithm uses quantum bits to code artificial fish and quantum revolving gate, preying behavior, and following behavior and variation of quantum artificial fish to update the artificial fish for searching for optimal value. Then, we apply the proposed new algorithm, the quantum artificial fish swarm algorithm (QAFSA), the basic artificial fish swarm algorithm (BAFSA), and the global edition artificial fish swarm algorithm (GAFSA) to the simulation experiments for some typical test functions, respectively. The simulation results demonstrate that the proposed algorithm can escape from the local extremum effectively and has higher convergence speed and better accuracy. Finally, applying IQAFSA to distributed network problems and the simulation results for 33-bus radial distribution network system show that IQAFSA can get the minimum power loss after comparing with BAFSA, GAFSA, and QAFSA. Tingsong Du, Yang Hu, and Xianting Ke Copyright © 2015 Tingsong Du et al. All rights reserved. CDMBE: A Case Description Model Based on Evidence Tue, 01 Sep 2015 06:31:50 +0000 By combining the advantages of argument map and Bayesian network, a case description model based on evidence (CDMBE), which is suitable to continental law system, is proposed to describe the criminal cases. The logic of the model adopts the credibility logical reason and gets evidence-based reasoning quantitatively based on evidences. In order to consist with practical inference rules, five types of relationship and a set of rules are defined to calculate the credibility of assumptions based on the credibility and supportability of the related evidences. Experiments show that the model can get users’ ideas into a figure and the results calculated from CDMBE are in line with those from Bayesian model. Jianlin Zhu, Xiaoping Yang, and Jing Zhou Copyright © 2015 Jianlin Zhu et al. All rights reserved. A Multilayer Naïve Bayes Model for Analyzing User’s Retweeting Sentiment Tendency Mon, 31 Aug 2015 12:05:33 +0000 Today microblogging has increasingly become a means of information diffusion via user’s retweeting behavior. Since retweeting content, as context information of microblogging, is an understanding of microblogging, hence, user’s retweeting sentiment tendency analysis has gradually become a hot research topic. Targeted at online microblogging, a dynamic social network, we investigate how to exploit dynamic retweeting sentiment features in retweeting sentiment tendency analysis. On the basis of time series of user’s network structure information and published text information, we first model dynamic retweeting sentiment features. Then we build Naïve Bayes models from profile-, relationship-, and emotion-based dimensions, respectively. Finally, we build a multilayer Naïve Bayes model based on multidimensional Naïve Bayes models to analyze user’s retweeting sentiment tendency towards a microblog. Experiments on real-world dataset demonstrate the effectiveness of the proposed framework. Further experiments are conducted to understand the importance of dynamic retweeting sentiment features and temporal information in retweeting sentiment tendency analysis. What is more, we provide a new train of thought for retweeting sentiment tendency analysis in dynamic social networks. Mengmeng Wang, Wanli Zuo, and Ying Wang Copyright © 2015 Mengmeng Wang et al. All rights reserved. On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review Mon, 31 Aug 2015 06:17:18 +0000 A comprehensive review on the problem of choosing a suitable activation function for the hidden layer of a feed forward neural network has been widely investigated. Since the nonlinear component of a neural network is the main contributor to the network mapping capabilities, the different choices that may lead to enhanced performances, in terms of training, generalization, or computational costs, are analyzed, both in general-purpose and in embedded computing environments. Finally, a strategy to convert a network configuration between different activation functions without altering the network mapping capabilities will be presented. Antonino Laudani, Gabriele Maria Lozito, Francesco Riganti Fulginei, and Alessandro Salvini Copyright © 2015 Antonino Laudani et al. All rights reserved. Fuzzy Inference System Approach for Locating Series, Shunt, and Simultaneous Series-Shunt Faults in Double Circuit Transmission Lines Sun, 30 Aug 2015 14:08:44 +0000 Many schemes are reported for shunt fault location estimation, but fault location estimation of series or open conductor faults has not been dealt with so far. The existing numerical relays only detect the open conductor (series) fault and give the indication of the faulty phase(s), but they are unable to locate the series fault. The repair crew needs to patrol the complete line to find the location of series fault. In this paper fuzzy based fault detection/classification and location schemes in time domain are proposed for both series faults, shunt faults, and simultaneous series and shunt faults. The fault simulation studies and fault location algorithm have been developed using Matlab/Simulink. Synchronized phasors of voltage and current signals of both the ends of the line have been used as input to the proposed fuzzy based fault location scheme. Percentage of error in location of series fault is within 1% and shunt fault is 5% for all the tested fault cases. Validation of percentage of error in location estimation is done using Chi square test with both 1% and 5% level of significance. Aleena Swetapadma and Anamika Yadav Copyright © 2015 Aleena Swetapadma and Anamika Yadav. All rights reserved.