Neural Navigation Approach for Intelligent Autonomous Vehicles (IAV) in Partially Structured Environments

The use of Neural Networks (NN) is necessary to bring the behavior of Intelligent Autonomous Vehicles (IAV) near the human one in recognition, learning, decision-making, and action. First, current navigation approaches based on NN are discussed. Indeed, these current approaches remedy insufficiencies of classical approaches related to real-time,autonomy , and intelligence. Second, a neural navigation approach essentially based on pattern classification to acquire target localization and obstacle avoidance behaviors is suggested. This approach must provide vehicles with capability, after supervised Gradient Backpropagation learning, to recognize both six (06) target location and thirty (30) obstacle avoidance situations using NN1 and NN2 classifiers, respectively. Afterwards, the decision-making and action consist of two association stages, carried out by reinforcement Trial and Error learning, and their coordination using a NN3. Then, NN3 allows to decide among five (05) actions (move towards 30°, move towards 60°, move towards 90°, move towards 120°, and move towards 150°). Third, simulation results which display the ability of theneural approach to provide IAV with capability to intelligently navigate in partially structured environments are presented. Finally, a discussion dealing with the suggested approach and how it relates to some other works is given.     

进化操作行为学习模型及在移动机器人避障上的应用

针对移动机器人避障上存在的自适应能力较差的问题,结合遗传算法(GA)的进化思想,以自适应启发评价(AHC)学习和操作条件反射(OC)理论为基础,提出了一种基于进化操作行为学习模型(EOBLM)的移动机器人学习避障行为的方法。该方法是一种改进的AHC学习模式,评价单元采用多层前向神经网络来实现,利用TD算法和梯度下降法进行权值更新,这一阶段学习用来生成取向性信息,作为内在动机决定进化的方向;动作选择单元主要用来优化操作行为以实现状态到动作的最佳映射。优化过程分两个阶段来完成,第一阶段通过操作条件反射学习算法得到的信息熵作为个体适应度,执行GA学习算法搜索最优个体;第二阶段由OC学习算法选择最优个体内的最优操作行为,并得到新的信息熵值。通过移动机器人避障仿真实验,结果表明所设计的EOBLM能使机器人通过不断与外界未知环境进行交互主动学会避障的能力,与传统的AHC方法相比其自学习自适应的能力得到加强。     

Soft computing in medicine

Soft computing (SC) is not a new term; we have gotten used to reading and hearing about it daily. Nowadays, the term is used often in computer science and information technology. It is possible to define SC in different ways. Nonetheless, SC is a consortium of methodologies which works synergistically and provides, in one form or another, flexible information processing capability for handling real life ambiguous situations. Its aim is to exploit the tolerance for imprecision, uncertainty, approximate reasoning and partial truth in order to achieve tractability, robustness and low-cost solutions. SC includes fuzzy logic (FL), neural networks (NNs), and genetic algorithm (GA) methodologies. SC combines these methodologies as FL and NN (FL–NN), NN and GA (NN–GA) and FL and GA (FL–GA). Recent years have witnessed the phenomenal growth of bio-informatics and medical informatics by using computational techniques for interpretation and analysis of biological and medical data. Among the large number of computational techniques used, SC, which incorporates neural networks, evolutionary computation, and fuzzy systems, provides unmatched utility because of its demonstrated strength in handling imprecise information and providing novel solutions to hard problems.The aim of this paper is to introduce briefly the various SC methodologies and to present various applications in medicine between the years 2000 and 2008. The scope is to demonstrate the possibilities of applying SC to medicine-related problems. The recent published knowledge about use of SC in medicine is researched in MEDLINE. This study detects which methodology or methodologies of SC are used frequently together to solve the special problems of medicine. According to MEDLINE database searches, the rates of preference of SC methodologies in medicine were found as 68% of FL–NN, 27% of NN–GA and 5% of FL–GA. So far, FL–NN methodology was significantly used in medicine. The rates of using FL–NN in clinical science, diagnostic science and basic science were found as %83, %71 and %48, respectively. On the other hand NN–GA and FL–GA methodologies were mostly preferred by basic science of medicine.Another message emerging from this survey is that the number of papers which used NN–GA methodology has continuously risen until today. Also search results put the case clearly that FL–GA methodology has not applied well enough to medicine yet. Undeniable interest in studying SC methodologies in genetics, physiology, radiology, cardiology, and neurology disciplines proves that studying SC is very fruitful in these disciplines and it is expected that future researches in medicine will use SC more than it is used today to solve more complex problems.     

Training fuzzy logic based software components by combining adaptation algorithms

 A training framework of an effective method for off-line training of a class of control software components (e.g., for first-order nonlinear feedback control systems) using combinations of three kinds of adaptation algorithms is presented. Each control software component is represented at the abstract level by means of a set of adaptive fuzzy logic (FL) rules and at the concrete level by means of fuzzy membership functions (MBFs). At the concrete representation level adaptation algorithms specified for use in adapting MBFs are: genetic algorithms, neural net algorithms, and Monte Carlo algorithms. We specify effective combinations of these three existing adaptation algorithms to train a faulty FL rule-based software component for the tracker problem. In the framework, training consists of two phases: testing and adapting. In the testing phase, a test driver generates an effective fault scenario ( fs) and locates the faulty fuzzy elements (FFEs) by using each or a combination of three adaptation algorithms. In the adapting phase, for each fault scenario adaptation algorithms and their combinations are used to modify the MBFs of the component. Effectiveness of the two phase training is determined in terms of testability, flexibility, adaptability, and stability. An initial design of the simulation environment is presented. In the experiment, for a given circumstance (environment and fuzzy rules) we apply a combination of a genetic algorithm GA) and a neural network (NN) with an error back-propagation algorithm (BP) in the testing phase for generating fault scenarios. Then we apply GA-only method in the adapting phase for adapting the faulty software component. Simulation results on effectiveness and efficiency are discussed.     

Decentralized Control of Autonomous Swarm Systems Using Artificial Potential Functions: Analytical Design Guidelines

This paper presents a framework for decentralized control of self-organizing swarm systems based on the artificial potential functions (APFs). In this scheme, multiple agents in a swarm self-organize to flock and achieve formation control through attractive and repulsive forces among themselves using APFs. In particular, this paper presents a set of analytical guidelines for designing potential functions to avoid local minima for a number of representative scenarios. Specifically the following cases are addressed: 1) A non-reachable goal problem (a case that the potential of the goal is overwhelmed by the potential of an obstacle, 2) an obstacle collision problem (a case that the potential of the obstacle is overwhelmed by the potential of the goal), 3) an obstacle collision problem in swarm (a case that the potential of the obstacle is overwhelmed by potential of other robots in a group formation) and 4) an inter-robot collision problem (a case that the potential of the robot in a formation is overwhelmed by potential of the goal). The simulation results showed that the proposed scheme can effectively construct a self-organized swarm system with the capability of group formation, navigation and migration in the presence of obstacles.Category (5) – Intelligent Systems/Intelligent Control/Fuzzy Control/Prosthetics/Robot Motion Planning     

A Wheelchair Steered through Voice Commands and Assisted by a Reactive Fuzzy-Logic Controller

This paper describes new results with a Reactive Shared-Control system that enables a semi-autonomous navigation of a wheelchair in unknown and dynamic environments. The purpose of the reactive shared controller is to assist wheelchair users providing an easier and safer navigation. It is designed as a fuzzy-logic controller and follows a behaviour-based architecture. The implemented behaviours are three: intelligent obstacle avoidance, collision detection and contour following. Intelligent obstacle avoidance blends user commands, from voice or joystick, with an obstacle avoidance behaviour. Therefore, the user and the vehicle share the control of the wheelchair. The reactive shared control was tested on the RobChair powered wheelchair prototype [6] equipped with a set of ranging sensors. Experimental results are presented demonstrating the effectiveness of the controller.     

简化的广义多层感知机模型及其学习算法

提出了简化的广义多层感知机模型(SGMLP模型)，并针对SGMLP模型给出了两种学习算法：广义误差反向传播算法(GBP算法)和基于遗传算法(GA)的学习算法。两个典型算例的实验结果表明，该模型及其学习算法是可行和有效的。     

Using kNN model for automatic text categorization

An investigation is conducted on two well-known similarity-based learning approaches to text categorization: the k-nearest neighbors (kNN) classifier and the Rocchio classifier. After identifying the weakness and strength of each technique, a new classifier called the kNN model-based classifier (kNN Model) is proposed. It combines the strength of both kNN and Rocchio. A text categorization prototype, which implements kNN Model along with kNN and Rocchio, is described. An experimental evaluation of different methods is carried out on two common document corpora: the 20-newsgroup collection and the ModApte version of the Reuters-21578 collection of news stories. The experimental results show that the proposed kNN model-based method outperforms the kNN and Rocchio classifiers, and is therefore a good alternative for kNN and Rocchio in some application areas. This work was partly supported by the European Commission project ICONS, project no. IST-2001-32429.     

Recognition of driving postures by multiwavelet transform and multilayer perceptron classifier

To develop Human-centric Driver Assistance Systems (HDAS) for automatic understanding and charactering of driver behaviors, an efficient feature extraction of driving postures based on Geronimo–Hardin–Massopust (GHM) multiwavelet transform is proposed, and Multilayer Perceptron (MLP) classifiers with three layers are then exploited in order to recognize four pre-defined classes of driving postures. With features extracted from a driving posture dataset created at Southeast University (SEU), the holdout and cross-validation experiments on driving posture classification are conducted by MLP classifiers, compared with the Intersection Kernel Support Vector Machines (IKSVMs), the k-Nearest Neighbor (kNN) classifier and the Parzen classifier. The experimental results show that feature extraction based on GHM multwavelet transform and MLP classifier, using softmax activation function in the output layer and hyperbolic tangent activation function in the hidden layer, offer the best classification performance compared to IKSVMs, kNN and Parzen classifiers. The experimental results also show that talking on a cellular phone is the most difficult one to classify among four predefined classes, which are 83.01% and 84.04% in the holdout and cross-validation experiments respectively. These results show the effectiveness of the feature extraction approach using GHM multiwavelet transform and MLP classifier in automatically understanding and characterizing driver behaviors towards Human-centric Driver Assistance Systems (HDAS).     

Evolutionary fuzzy hybrid neural network for project cash flow control

This paper develops an evolutionary fuzzy hybrid neural network (EFHNN) to enhance project cash flow management. The developed EFHNN combines neural networks (NN) and high order neural networks (HONN) into a hybrid neural network (HNN), which acts as the major inference engine and operates with alternating linear and nonlinear NN layer connections. Fuzzy logic is employed to sandwich the HNN between a fuzzification and defuzzification layer. The authors developed and applied the EFHNN to sequential cash flow trend problems by fusing HNN, FL, and GA. Results show that the proposed EFHNN can be deployed effectively to sequential cash flow estimation. The performance of linear and nonlinear (high order) neuron layer connectors in the EFHNN was significantly better than the performance achieved by previous models that used singular linear NN. Trained results were used for the prediction and strategic management of project cash flow. The proposed strategy can assist project managers to control project cash flows within the banana envelope of the S-curve to enhance project success.     

计算智能在移动机器人路径规划中的应用综述

移动机器人路径规划是建立在机器人定位与避障研究之上,进一步对机器人行为的深入.在给出人工神经网络(ANN)、模糊逻辑(FL)、遗传算法(GA)等计算智能原理性方法的基础上,从一般意义讨论了各类计算智能方法用于路径规划的切入点,研究了各类算法的实现机理与设计思想.最后结合目前的技术发展趋势,对路径规划问题未来可能的研究发展方向进行了探讨.     

Fast-forward solver for inhomogeneous media using machine learning methods: artificial neural network,support vector machine and fuzzy logic

Encountering with a nonlinear second-order differential equation including ϵ _r and μ _r spatial distributions, while computing the fields inside inhomogeneous media, persuaded us to find their known distributions that give exact solutions. Similarities between random distributions of electric properties and known functions lead us to estimate them using three mathematical tools of artificial neural networks (ANNs), support vector machines (SVMs) and Fuzzy Logic (FL). Assigning known functions after fitting with minimum error to arbitrary inputs using results of machine learning networks leads to achieve an approximate solution for the field inside materials considering boundary conditions. A comparative study between the methods according to the complexity of the structures as well as the accuracy and the calculation time for testing of unforeseen inputs, including classification, prediction and regression is presented. We examined the extracted pairs of ϵ _r and μ _r with ANN, SVM networks and FL and got satisfactory outputs with detailed results. The application of the presented method in zero reflection subjects is exemplified.

     

Developing hybrid intelligent tutoring and hypertext systems

Abstract

The objective of this paper is to present an alternative paradigm to the traditional Knowledge Based Expert Systems Paradigm for developing a full-scale Intelligent Tutoring System that has dominated for years Intelligent Tutoring Systems development. This alternative paradigm which integrates Minsky's Frames with hypertext has been successfully deployed so far in the development of PEDRO, an Intelligent Tutoring System for foreign language learning, SONATA, an Intelligent Tutoring System for music theory learning and INTUITION, an Intelligent Tutoring System for Gaming-Simulation.     

Design of an H ∞ PID controller using particle swarm optimization

This paper proposes a novel method to designing an H _∞ PID controller with robust stability and disturbance attenuation. This method uses particle swarm optimization algorithm to minimize a cost function subject to H _∞-norm to design robust performance PID controller. We propose two cost functions to design of a multiple-input, multiple-output (MIMO) and single-input, single-output (SISO) robust performance PID controller. We apply this method to a SISO flexible-link manipulator and a MIMO super maneuverable F18/HARV fighter aircraft system as two challenging examples to illustrate the design procedure and to verify performance of the proposed PID controller design methodology. It is shown with the MIMO super maneuverable F18/HARV fighter system that PSO performs well for parametric optimization functions and performance of the PSO-based method without prior domain knowledge is superior to those of existing GA-based and OSA-based methods for designing H _∞ PID controllers. Recommended by Editorial Board member Jietae Lee under the direction of Editor Young-Hoon Joo. This work was supported by the Iranian Telecommunication Research Center (ITRC) under Grant T500-11629. Majid Zamani received the B.Sc. and M.Sc. degrees in Electrical Engineering in 2005 and 2007 from Isfahan University of Technology, and Sharif University of Technology, Iran, respectively. Currently, He is a Ph.D. student in Electrical Engineer-ing Department of University of California, Los Angeles, U.S.A. Nasser Sadati was born in Iran in 1960. He received the B.S. degree from Oklahoma State University, Stillwater, in 1982, and the M.S. and Ph.D. degrees from Cleveland State University, Cleveland, OH, USA, in 1985 and 1989, respectively, all in Electrical Engineering. From 1986 to 1987, he was with the NASA Lewis Research Center, Cleveland, to study the albedo effects on space station solar array. In 1989, he conducted postgraduate research at Case Western Reserve University, Cleveland, OH. Since 1990, he has been with the Sharif University of Technology, Tehran, Iran, where he is currently a Full Professor in the Department of Electrical Engineering, the Head of Control Group, and the Director of the Intelligent Systems Laboratory and the Co-Director of Robotics and Machine Vision Laboratory. He was the first to introduce the subject of fuzzy logic and intelligent control as course work in the universities engineering program in Iran. He has published two books in Persian and over 200 technical papers in peer-reviewed journals and conference proceedings, and is currently working on two more books in English (Intelligent Control of Large-Scale Systems) and Persian (Neural Networks). His research interests include intelligent control and soft computing, large-scale systems, robotics and pattern recognition. Dr. Sadati was the recipient of the Academic Excellence Award for 1998–1999 from the Sharif University of Technology. He is a Founding Member of the Iranian Journal of Fuzzy Systems (IJFS). He is the Founder and Chairman of the First Symposiums on Fuzzy Logic, and Intelligent Control and Soft Computing in Iran. He is the editorial board members of International Journal of Advances in Fuzzy Mathematics (AFM) and the Journal of Iranian Association of Electrical and Electronics Engineers (IAEEE). He also has served as the Co-Chair of the First International Conference on Intelligent and Cognitive Systems (ICICS’96). Dr. Sadati is a Founding Member of the Center of Excellence in Power System Management and Control (CEPSMC), Sharif University of Technology, Tehran, Iran and the Foreign Member of the Institute of Control, Robotics, and Systems (ICROS), Korea. Masoud Karimi Ghartemani received the B.Sc. and M.Sc. in Electrical Engineering in 1993 and 1995 from Isfahan University of Technology, Iran, where he continued to work as a Teaching and Research Assistant until 1998. He received the Ph.D. degree in Electrical Engineering from University of Toronto in 2004. He was a Research Associate and a Post-doctoral Researcher in the Department of Electrical and Computer Engineering of the University of Toronto from 1998 to 2001 and from 2004 to 2005, respectively. He joined Sharif University of Technology, Tehran, Iran, in 2005 as a Faculty Member. His research topics include nonlinear and optimal control, novel control and signal processing techniques/algorithms for control and protection of modern power systems, power electronics, power system stability and control, and power quality.     

Probabilistic ensemble simplified fuzzy ARTMAP for sonar target differentiation

This study investigates the processing of sonar signals with ensemble neural networks for robust recognition of simple objects such as plane, corner and trapezium surface. The ensemble neural networks can differentiate the target objects with high accuracy. The simplified fuzzy ARTMAP (SFAM) and probabilistic ensemble simplified fuzzy ARTMAP (PESFAM) are compared in terms of classification accuracy. The PESFAM implements an accurate and effective probabilistic plurality voting method to combine outputs from multiple SFAM classifiers. Five benchmark data sets have been used to evaluate the applicability of the proposed ensemble SFAM network. The PESFAM achieves good accuracy based on the twofold cross-validation results. In addition, the effectiveness of the proposed ensemble SFAM is delineated in sonar target differentiation. The experiments demonstrate the potential of PESFAM classifiers in offering an optimal solution to the data-ordering problem of SFAM implementation and also as an intelligent classification tool in mobile robot application.     

Multiclass classifiers based on dimension reduction with generalized LDA

Linear discriminant analysis (LDA) has been widely used for dimension reduction of data sets with multiple classes. The LDA has been recently extended to various generalized LDA methods that are applicable regardless of the relative sizes between the data dimension and the number of data items. In this paper, we propose several multiclass classifiers based on generalized LDA (GLDA) algorithms, taking advantage of the dimension reducing transformation matrix without requiring additional training or parameter optimization. A marginal linear discriminant classifier (MLDC), a Bayesian linear discriminant classifier (BLDC), and a one-dimensional BLDC are introduced for multiclass classification. Our experimental results illustrate that these classifiers produce higher ten-fold cross validation accuracy than kNN and centroid-based classifiers in the reduced dimensional space obtained from GLDA.     

AGFS: Adaptive Genetic Fuzzy System for medical data classification

A Genetic Fuzzy System (GFS) is basically a fuzzy system augmented by a learning process based on a genetic algorithm (GA). Fuzzy systems have demonstrated their ability to solve different kinds of problems in various application domains. Currently, there is an increasing interest to augment fuzzy systems with learning and adaptation capabilities. Two of the most successful approaches to hybridize fuzzy systems with learning and adaptation methods have been made in the realm of soft computing. The GA can be merged with Fuzzy system for different purposes like rule selection, membership function optimization, rule generation, co-efficient optimization, for data classification. Here we propose an Adaptive Genetic Fuzzy System (AGFS) for optimizing rules and membership functions for medical data classification process. The primary intension of the research is 1) Generating rules from data as well as for the optimized rules selection, adapting of genetic algorithm is done and to explain the exploration problem in genetic algorithm, introduction of new operator, called systematic addition is done, 2) Proposing a simple technique for scheming of membership function and Discretization, and 3) Designing a fitness function by allowing the frequency of occurrence of the rules in the training data. Finally, to establish the efficiency of the proposed classifier the presentation of the anticipated genetic-fuzzy classifier is evaluated with quantitative, qualitative and comparative analysis. From the outcome, AGFS obtained better accuracy when compared to the existing systems.     

Human-centered ontology engineering: The HCOME methodology

The fast emergent and continuously evolving areas of the Semantic Web and Knowledge Management make the incorporation of ontology engineering tasks in knowledge-empowered organizations and in the World Wide Web more than necessary. In such environments, the development and evolution of ontologies must be seen as a dynamic process that has to be supported through the entire ontology life cycle, resulting to living ontologies. The aim of this paper is to present the Human-Centered Ontology Engineering Methodology (HCOME) for the development and evaluation of living ontologies in the context of communities of knowledge workers. The methodology aims to empower knowledge workers to continuously manage their formal conceptualizations in their day-to-day activities and shape their information space by being actively involved in the ontology life cycle. The paper also demonstrates the Human Centered ONtology Engineering Environment, HCONE, which can effectively support this methodology. George VOUROS (B.Sc. Ph.D.) holds a B.Sc. in Mathematics, and a Ph.D. in Artificial Intelligence all from the University of Athens, Greece. Currently he is a Professor and Head of the Department of Information and Communication Systems Engineering, University of the Aegean, Greece, Director of the AI Lab and head of the Intelligent and Cooperative Systems Group (InCoSys). He has done research in the areas of Expert Systems, Knowledge management, Collaborative Systems, Ontologies, and Agent-based Systems. His published scientific work includes more than 80 book chapters, journal and national and international conference papers in the above-mentioned themes. He has served as program chair and chair and member of organizing committees of national and international conferences on related topics. Konstantinos KOTIS (B.Sc. Ph.D.) holds a B.Sc. in Computation from the University of Manchester, UK (1995), and a Ph.D. in Information Management from University of the Aegean, Greece (May, 2005). Currently, he is a member of the Intelligent and Cooperative Systems Group (InCoSys) and director of the Information Technology Department of the Prefecture of Samos, Greece. His research and published work concerns Knowledge management, Ontology Engineering and Semantic Web. He has lectured in several IT seminars and has served as member of program committees in international workshops.     

Neural network approach to acquiring free-gait motion of quadruped robots in obstacle avoidance

In obstacle avoidance by a legged mobile robot, it is not necessary to avoid all of the obstacles by turning only, because it can climb or stride over some of them, depending on the obstacle configuration and the state of the robot, unlike a wheel-type or a crawler-type robot. It is thought that mobility efficiency to a destination is improved by crawling over or striding over obstacles. Moreover, if robots have many legs, like 4-legged or 6-legged types, then the robot's movement range is affected by the order of the swing leg. In this article a neural network (NN) is used to determine the action of a quadruped robot in an obstacle-avoiding situation by using information about the destination, the obstacle configuration, and the robot's self-state. To acquire a free gait in static walking, the order of the swing leg is realized using an alternative NN whose inputs are the amount of movement and the robot's self-state. The design parameters of the former NN are adjusted by a genetic algorithm (GA) off-line. This work was presented in part at the 9th International Symposium on Artificial Life and Robotics, Oita, Japan, January 28–30, 2004     

Self-Configuration of Network Services with Biologically Inspired Learning and Adaptation

This paper proposes a self-organizing scheme based on ant metaheuristics to optimize the operation of multiple classes of managed elements on an Operations Support Systems (OSSs) for mobile pervasive communications. Ant metaheuristics are characterized by learning and adaptation capabilities against dynamic environment changes and uncertainties. As an important division of swarm agent intelligence, it distinguishes itself from centralized management schemes due to its features of robustness and scalability. We have successfully applied ant metaheuristics to the network service configuration process, which is simply redefined as: the managed elements represented as graphic nodes, and ants traverse by selecting nodes with the minimum cost constraints until the eligible network elements are located along near-optimal paths—the located elements are those needed for the configuration or activation of a particular product and service. Although the configuration process is non-transparent to end users, the negotiated SLAs between users and providers affect the overall process. This proposed self-organized learning and adaptation scheme using Ant Colony Optimization (ACO) is evaluated by simulation in Java. A performance comparison is also made with a class of Genetic Algorithm known as PBIL. Finally, the simulation results show the scalability and robustness capability of autonomous ant-like agents able to adapt to dynamic networks.