| 期刊全称 | Advances in Computational Intelligence | | 影响因子2023 | Wen Yu,Edgar N. Sanchez | | 视频video | http://file.papertrans.cn/148/147138/147138.mp4 | | 发行地址 | Presents latest research in Computational Intelligence.Proceedings of IWACI‘09 Workshop: 22nd-23th June, 2009 held in Mexico City | | 学科分类 | Advances in Intelligent and Soft Computing | | 图书封面 |  | | 影响因子 | This book constitutes the proceedings of the second International Workshop on Advanced Computational Intelligence (IWACI 2009), with a sequel of IWACI 2008 successfully held in Macao, China. IWACI 2009 provided a high-level international forum for scientists, engineers, and educators to present state-of-the-art research in computational intelligence and related fields. Over the past decades, computational intelligence community has witnessed t- mendous efforts and developments in all aspects of theoretical foundations, archit- tures and network organizations, modelling and simulation, empirical study, as well as a wide range of applications across different domains. IWACI 2009 provided a great platform for the community to share their latest research results, discuss critical future research directions, stimulate innovative research ideas, as well as facilitate inter- tional multidisciplinary collaborations. IWACI 2009 received 146 submissions from about 373 authors in 26 countries and regions (Australia, Brazil, Canada, China, Chile, Hong Kong, India, Islamic Republic of Iran, Japan, Jordan, Macao, Malaysia, Mexico, Pakistan, Philippines, Qatar, Republic of Korea, Singapore, South | | Pindex | Conference proceedings 2009 |
| 1 |
Front Matter |
|
|
Abstract
|
| 2 |
Multi Lingual Speaker Recognition Using Artificial Neural Network |
Prateek Agrawal,Anupam Shukla,Ritu Tiwari |
|
Abstract
This paper describes a method for speaker identification in multiple languages that is based on Back Propagation Algorithm (BPA). The identification process goes through recording the speech utterances of different speakers in different languages, features extraction, data clustering and system training using BPA. Our database contains one sentence in 8 different Indian regional languages i.e. Hindi, English, Assami, Telugu, Punjabi, Rajasthani, Marathi & Bengali, spoken by 32 speakers in each language. With total size of 904 speech utterances, the Average performance of the system is 95.354%. These applications are mainly used in speaker Authentication, in telephony applications where the conversations can be of short durations and the language could change from one conversation to another etc.
|
| 3 |
Modeling Huntington’s Disease Considering the Theory of Central Pattern Generators (CPG) |
Masood Banaie,Yashar Sarbaz,Mohammad Pooyan,Shahriar Gharibzadeh,Farzad Towhidkhah |
|
Abstract
In this study, we present a novel model for Huntington’s disease (HD) gait disorder. We consider the mathematical relations between blocks. The number of inputs and outputs of each block are designated due to the physiological findings. The connection types between blocks are modeled by gains. Inner structure of each block is modeled using a central pattern generator neural network. Our model is able to simulate the normal and HD strides time intervals and shows how diazepam is able to ameliorate the gait disorder; however, we believe that this treatment is somehow irrational. Using GABA blockers recovers the symptoms but it means omitting BG from motor control loop. Our model shows that increment of GABA aggravates the gait disorder. Our novel idea about BG treatment is to reduce glutamate. Experimental studies are needed for evaluating this novel treatment. This validation would implement a milestone in treatment of such a debilitating disease. It seems that synchronization of a number of neurons is the major disturbance in HD. The synchronization was modeled as CPG (Central Pattern Generator) structure. We supposed that the disorder will recover if the wrong synchronization of t
|
| 4 |
Prophetia: Artificial Intelligence for TravelBox® Technology |
R. Chulaka Gunasekara,B. B. Akila Geethal,Mafaz Hassan,C. D. Tharindu Mathew,A. Shehan Perera,Harsha |
|
Abstract
In today’s fiercely competitive and dynamic market scenario, business enterprises are facing many problems due to increasing complexity of the decision making process. Besides, the amount of data to be analyzed has increased substantially. This has resulted in Artificial Intelligence stepping into decision making to make better business decisions, reduce latency and enhance revenue opportunities. Prophetia is a research project carried out to integrate Artificial Intelligence capabilities into TravelBox. technology – a range of solutions developed by Codegen International for Travel Industry. This research paper discusses three areas that were researched for the above purpose. These are, Probability Prediction – the use of Neural Networks for calculating the selling probability of a particular vacation package, Package Recognition – the use of Self Organizing Maps for recognizing patterns in past vacation package records, and Customer Interest Prediction – the use of association rule mining for determining the influence of customer characteristics on the vacation destination.
|
| 5 |
Application Research of Local Support Vector Machines in Condition Trend Prediction of Reactor Coola |
Guohua Yan,Yongsheng Zhu |
|
Abstract
The difficulty in parameters selection of support vector machines (SVMs), which determines the performance of SVMs, limits the application of SVMs. In this paper, a directly determination (DD) method, which combines the existing practical approach used to compute parameters . and . with another method used to compute ., is introduced. This method determines the values of parameters directly from analyzing training data without running SVMs training process. The results show it gets better performance than usual grid search method in terms of predicting accuracy. Moreover, it reduces the spent time to a minimum. For predicting the condition trend of reactor coolant pump (RCP), a forecasting model which combines Local SVMs, whose parameters are determined by DD method, and Time Series is used. The results of experiments show that the model is able to predict the developing trend of time series of features reflecting the pump running condition preferably.
|
| 6 |
Asymptotic Synchronization for Pulse-Coupled Oscillators with Delayed Excitatory Coupling Is Impossi |
Wei Wu,Tianping Chen |
|
Abstract
Fireflies, as one of the most spectacular examples of synchronization in nature, have been investigated widely. Mirollo and Strogatz (1990) proposed a pulse-coupled oscillator model to explain the synchronization of South East Asian fireflies (.). However, transmission delays were not considered in their model. In fact, when transmission delays are introduced, the dynamic behaviors of pulse-coupled networks change a lot. In this paper, pulse-coupled oscillator networks with delayed excitatory coupling are studied. A concept of synchronization, named weak asymptotic synchronization, which is weaker than asymptotic synchronization, is proposed. We prove that for pulse-coupled oscillator networks with delayed excitatory coupling, weak asymptotic synchronization cannot occur.
|
| 7 |
Missing Data Imputation Through the Use of the Random Forest Algorithm |
Adam Pantanowitz,Tshilidzi Marwala |
|
Abstract
This paper presents a comparison of different paradigms used for missing data imputation. The data set used is HIV seroprevalence data from an antenatal clinic study survey performed in 2001. Data imputation is performed through five methods: Random Forests; auto-associative neural networks with genetic algorithms; auto-associative neuro-fuzzy configurations; and two random forest and neural network based hybrids. Results indicate that Random Forests are superior in imputing missing data for the given data set in terms of accuracy and in terms of computation time, with accuracy increases of up to 32 % on average for certain variables when compared with auto-associative networks. While the concept of hybrid systems has promise, the presented systems appear to be hindered by their auto-associative neural network components.
|
| 8 |
Ubiquitous Middleware Using Mobility Prediction Based on Neuro-Association Mining for Adaptive Distr |
Romeo Mark A. Mateo,Malrey Lee,Jaewan Lee |
|
Abstract
This paper proposes a ubiquitous middleware for the adaptive distributed object system to consider the mobility support of application services in distributed environment. To ensure the seamless connectivity of a moving client, a prediction based on association mining of mobility patterns is used to perform the replication of services in the next base station. The proposed neuro-association mining is based on Apriori to generate rules for prediction and these rules become nodes for the structure of multilayer perceptron (MLP) to classify the next location and replicate the resource currently serving the mobile client. We present our simulation environment for the ubiquitous middleware and a classification performance evaluation where the proposed algorithm shows more accurate and provide more comprehensive structure compared to neural network based classifiers.
|
| 9 |
A Growing Algorithm for RBF Neural Network |
Han Honggui,Qiao Junfei |
|
Abstract
This paper presents a growing algorithm to design the architecture of RBF neural network called growing RBF neural network algorithm (GRBF). The GRBF starts from a single prototype randomly initialized in the feature space; the whole algorithm consists of two major parts: the structure learning phase and parameter adjusting phase. In the structure algorithm, the growing strategy is used to judge when and where the RBF neural network should be grown in the hidden layer based on the sensitivity analysis of the network output. In the parameter adjusting strategy, the whole weights of the RBF should be adjusted for improving the whole capabilities of the GRBF. In the end, the proposed GRBF network is employed to track non-linear functions. The computational complexity analysis and the results of the simulations confirm the efficiency of the proposed algorithm.
|
| 10 |
Fault Tolerance Based on Neural Networks for the Intelligent Distributed Framework |
Michael Angelo G. Salvo,Jaewan Lee,Jung-sik Lee |
|
Abstract
Current studies on the intelligent distributed framework in distributed systems use multi-agents which include replication agents, grouping agents, locator agents, and load balancing agents among others which work systematically to provide quality of service. This research aims to improve that quality of service by implementing a neural network in the fault tolerant scheme. Incase of an object failure or disconnection, the properties of that object will be used as input data in the multilayer perceptron (MLP) to select an alternate object. The fault tolerant scheme then chooses a new object by training these properties using the backpropagation algorithm. Results show that the proposed algorithm recorded the highest accuracy rate compared to the ZeroR, Simple Logistic, and J48 algorithms.
|
| 11 |
Learning RNN-Based Gene Regulatory Networks for Robot Control |
Wei-Po Lee,Tsung-Hsien Yang |
|
Abstract
With the unique characteristic of orchestrating gene expression level in cellular metabolism during the development of living organisms, gene regulatory networks can be modeled as reliable and robust control mechanisms for robots. In this work we devise a recurrent neural network-based GRN model to control robots. To simulate the regulatory effects and make our model inferable from time-series data, we develop an enhanced learning algorithm, coupled with some heuristic techniques of data processing for performance improvement. We also establish a method of programming by demonstration to collect behavior sequence data of the robot as the expression profiles, and then employ our framework to infer controllers automatically. To verify the proposed approach, experiments have been conducted and the results show that our regulatory model can be inferred for robot control successfully.
|
| 12 |
Fault Detection for Networked Control Systems via Minimum Error Entropy Observer |
Jianhua Zhang,Lei Cai,Hong Wang |
|
Abstract
In this paper, a novel fault detection scheme is presented for networked control systems with random delays and noises. Since the random noises and delays existed in networked control system are probably non-Gaussian, the extended Luenberger observer under minimum error entropy frame is utilized to generate residual so as to detect faults in networked control systems. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed method.
|
| 13 |
Discrete-Time Reduced Order Neural Observers |
Alma Y. Alanis,Edgar Nelson Sanchez |
|
Abstract
A nonlinear discrete-time reduced order neural observer for the state estimation of a discrete-time unknown nonlinear system, in presence of external and internal uncertainties is presented. The observer is based on a discrete-time recurrent high order neural network (RHONN) trained with an extended Kalman filter (EKF)-based algorithm. This observer estimates the state of the unknown discrete-time nonlinear system, using a parallel configuration. To illustrate the applicability simulation results are included.
|
| 14 |
A New Neural Observer for an Anaerobic Wastewater Treatment Process |
Rubén Belmonte-Izquierdo,Salvador Carlos-Hernández,Edgar Nelson Sanchez |
|
Abstract
In this paper, a recurrent high order neural observer (RHONO) for anaerobic processes is proposed. The main objective is to estimate biomass and substrate in a completely stirred tank reactor.The recurrent high order neural network (RHONN) structure is based on hyperbolic tangent as activation function. The learning algorithm is based on an extended Kalman filter. The applicability of the proposed scheme is illustrated via simulation. Thus, this observer can be successfully implemented for control purposes.
|
| 15 |
Prediction of Protein Subcellular Multi-localization by Using a Min-Max Modular Support Vector Machi |
Yang Yang,Bao-Liang Lu |
|
Abstract
Prediction of protein subcellular location is an important issue in computational biology because it provides important clues for characterization of protein function. Currently, much effort has been dedicated to developing automatic prediction tools. However, most of them focus on mono-locational proteins. It should be noted that many proteins bear multi-locational characteristics, and they carry out crucial functions in biological processes. This work aims to develop a general pattern classifier for predicting multiple subcellular locations of proteins. We used an ensemble classifier, called min-max modular support vector machine (M.-SVM), to solve protein subcellular multi-localization problem, and proposed a task decomposition method based on gene ontology (GO) semantic information for the M.-SVM. We applied our method to a high-quality multi-locational protein data set. The M.-SVMs showed better performance than traditional SVMs using the same feature vectors. And the GO decomposition also helped improve the prediction accuracy with more stable performance than random decomposition.
|
| 16 |
Application of MultiLayer Perceptron Type Neural Network to Camera Calibration |
Dong-Min Woo,Dong-Chul Park |
|
Abstract
The objective of camera calibration is to obtain the correlation between camera image coordinate and 3D real world coordinate. In this paper, we propose a new approach which is based on the neural network model instead of the physical camera model including position, orientation, focal length, and optical center. The neural network employed in this paper is MLPNN (MultiLayer Perceptron Type Neural Network), which is primarily used as a mapper between 2D image points and points of a certain space in 3D real world. The neural network model implicitly contains all the physical parameters, some of which are very difficult to be estimated in the conventional calibration methods. In order to show the performance of the proposed method, images from two different cameras with three different camera angles were used for calibrating the cameras. The performance of the proposed neural network approach is compared with the well-known Tsai’s two stage method in terms of calibration errors. The results show that the proposed approach gives much more consistent and acceptable calibration error over Tsai’s two stage method regardless of the quality of camera and the camera angles.
|
| 17 |
Hierarchical Neural Network Model for Water Quality Prediction in Wastewater Treatment Plants |
Qiumei Cong,Wen Yu,Tianyou Chai |
|
Abstract
Water quality measurement is important for wastewater treatment plants. Up to the present moment, there are not economic on-line sensors for it. In this paper a new soft measurement method is proposed, which uses mechanism model and hierarchical neural networks to resolve a modeling accuracy problem. Since wastewater treatment plants are cascaded processes, hierarchical neural networks can match these structures and predict water quality in inner reactors. By comparing our method with the other soft measurement approaches, we find that based on mechanism model and hierarchical neural networks, the hierarchical model is effective for wastewater treatment plants.
|
| 18 |
Third Generation Neural Networks: Spiking Neural Networks |
Samanwoy Ghosh-Dastidar,Hojjat Adeli |
|
Abstract
Artificial Neural Networks (ANNs) are based on highly simplified brain dynamics and have been used as powerful computational tools to solve complex pattern recognition, function estimation, and classification problems. Throughout their development, ANNs have been evolving towards more powerful and more biologically realistic models. In the last decade, the . Spiking Neural Networks (SNNs) have been developed which comprise of . neurons. Information transfer in these neurons models the information transfer in biological neurons, i.e., via the precise timing of spikes or a sequence of spikes. Addition of the temporal dimension for information encoding in SNNs yields new insight into the dynamics of the human brain and has the potential to result in compact representations of large neural networks. As such, SNNs have great potential for solving complicated time-dependent pattern recognition problems defined by time series because of their inherent dynamic representation. This article presents an overview of the development of spiking neurons and SNNs within the context of feedforward networks, and provides insight into their potential for becoming the next generation neural networks.
|
| 19 |
Choquet Fuzzy Integral Applied to Stereovision Matching for Fish-Eye Lenses in Forest Analysis |
P. Javier Herrera,Gonzalo Pajares,María Guijarro,José J. Ruz,Jesús M. de la Cruz |
|
Abstract
This paper describes a novel stereovision matching approach based on omni-directional images obtained with fish-eye lenses in forest environments. The goal is to obtain a disparity map as a previous step for determining the volume of wood in the imaged area. The interest is focused on the trunks of the trees, due to the irregular distribution of the trunks; the most suitable features are the pixels. A set of six attributes is used for establishing the matching between the pixels in both images of the stereo pair. The final decision about the matched pixel is taken based on the Choquet Fuzzy Integral paradigm, which is a technique well tested for combining classifiers. The use and adjusting of this decision approach to our specific stereo vision matching problem makes the main finding of the paper. The procedure is based on the application of three well known matching constraints. The proposed approach is compared favourably against the usage of simple features and other fuzzy strategy that combines the simple ones.
|
| 20 |
Fuzzy OLAP: A Formal Definition |
Claudia González,Leonid Tineo,Angélica Urrutia |
|
Abstract
Real world is pervaded of imprecision and uncertainty. These characteristics are well represented in computational systems by means of fuzzy logic. Some systems produce vital data that must be stored for its posterior analysis supporting decision making through OLAP. At present time this data may involve imprecision and uncertainty, therefore fuzzy OLAP operators must be provided. We do that in this paper in a formal way, giving a rigorous definition of fuzzy logic extended OLAP operators.
|
|
|
|Archiver|手机版|小黑屋|
派博传思国际
( 京公网安备110108008328)
GMT+8, 2025-11-16 16:51
发表于 2025-3-21 16:58:12
