{"title":"A Neuro Fuzzy Decision Tree Model for Predicting the Risk in Coronary Artery Disease","authors":"O. G. Kochurani, S. Aji, M. D. Kaimal","doi":"10.1109/ISIC.2007.4450879","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450879","url":null,"abstract":"The application of a neuro fuzzy model, typically a TSK model that incorporates rule structures obtained from the classical ID3 approach of decision trees in predicting the degree of risks from the information obtained through clinical observations in coronary artery disease patients is discussed in this paper. In recent years, numerous attempts have been made to use knowledge structures represented by fuzzy systems and artificial neural networks in various applications particularly in decision-making models. The utility of fuzzy systems lies in their ability for modeling uncertain or ambiguous, multi-parameter data often encountered in complex situations like medical diagnosis. This paper proposes a new model for medical decision making situations.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126462872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Universal Approximation for Takagi-Sugeno Fuzzy Systems Using Dynamically Constructive Method-SISO Cases","authors":"F. Sun, Ni Zhao","doi":"10.1109/ISIC.2007.4450876","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450876","url":null,"abstract":"In this paper, a dynamically constructive method is proposed for proving the universal approximation for single input/single output (SISO) Takagi-Sugeno (T-S) fuzzy systems, which is superior to the existing constructive methods only considering the global property of the function to be approximated and also unrelated to the membership functions of fuzzy sets. The dynamically constructive method proposed not only considers the different property of the nonlinear function in different areas, but also the membership functions of fuzzy sets in fuzzy rules. As a result, the number of rules in the constructed T-S model is greatly reduced. Finally some simulation examples confirm that the T-S fuzzy model constructed by our method with small size rule base can approximate the given nonlinear functions at high accuracy as compared with some typical methods.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127624892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Architecture and Algorithm for a Laboratory Vehicle Collision Avoidance System","authors":"C. Robinson, H. Schuetz, G. Baliga, P. Kumar","doi":"10.1109/ISIC.2007.4450855","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450855","url":null,"abstract":"In this paper we describe the application architecture for a collision avoidance system developed for a fleet of sensorless mobile vehicles. The system has been deployed in the IT Convergence Lab in the Coordinated Science Laboratory at the University of Illinois at Urbana-Champaign, which is a testbed for studying system architecture for networked embedded control systems. We describe several factors that a well designed collision avoidance algorithm needs to address, and discuss some of the tradeoffs and design decisions that need to be made. The solution that we have developed has a minimal effect on existing components for higher level functionality, as well their interfaces. The architecture and algorithm provide a low level safety guarantee regardless of higher level objectives. The architecture exploits the infrastructure and services provided by the control domain middleware, called Etherware, which has been developed in the laboratory. Indeed, the development of the collision avoidance system shows the usefulness of the specific services and abstractions that Etherware provides to the application designer in facilitating rapid system design and deployment.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132262337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Polar Polynomial Curve for Smooth, Collision-free Path Generation Between Two Arbitrary Configurations for Nonholonomic Robots","authors":"X. Lai, A. Mamun, S. Ge","doi":"10.1109/ISIC.2007.4450861","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450861","url":null,"abstract":"This paper studies a geometric-based method for smooth path generation for nonholonomic mobile robots, which are subject to dynamic and curvature constraints. It first studies polar polynomial curve and its properties for it to be used in curvature-smooth transition. In the design of such a path, it is examinable whether the robot constraints and curvature requirement are satisfied. Then, connection using such a curve is extended to the case that the robot is performing rotation at its start position. Next, a computationally efficient way is proposed for collision test of the curve in order to achieve realtime path planning. Finally, extensive simulation experiments are carried out to verify the proposed method.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132368823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient solution for compositional design problems by Multi-stage Genetic Algorithm","authors":"Masakazu Suzuki, Y. Hiyama, H. Yamada","doi":"10.1109/ISIC.2007.4450958","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450958","url":null,"abstract":"The Multi-stage Genetic Algorithm, MGA, is introduced to solve a class of compositional design problems. The problem with complicated constraints is formulated as a set of local subproblems with simple constraints and a supervising problem. Every subproblem is solved by GA to generate a set of suboptimal solutions. And in the supervising problem, the elements of each set are optimally combined by GA to yield the optimal solution for the original problem. The method is a learning method where the empirical knowledge obtained by solving the problem is effectively utilized to solve similar problems efficiently. Extended knapsack problems are solved to demonstrate the proposed method, and the efficiency of the method is shown. In addition, the method is successfully applied to optimal realization of cooperative robot soccer behaviors.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133421275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Toward A Practical Multi-agent System for Integrated Control and Asset Management of Petroleum Production Facilities","authors":"Atalla F. Sayda, James H. Taylor","doi":"10.1109/ISIC.2007.4450938","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450938","url":null,"abstract":"This paper addresses a practical intelligent multi-agent system for asset management for the petroleum industry, which is crucial for profitable oil and gas facilities operations and maintenance. A research project was initiated to study the feasibility of an intelligent asset management system. Having proposed a conceptual model, architecture, and implementation plan for such a system in previous work [1], [2], [3], we define the autonomy, communications, and artificial intelligence (AI) requirements of the component agents of such a system. We also discuss the software implementation of such agents. Furthermore, we describe a simple system prototype, and conduct a real time simulation experiment to analyze the prototype performance. Simulation results reveal that MATLAB can be used to build high performance real-time multi-agent systems, which can be used for many applications.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130225774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Algorithm for variational inequality problems based on a gradient dynamical system designed using a control Liapunov function","authors":"F. Pazos, A. Bhaya","doi":"10.1109/ISIC.2007.4450953","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450953","url":null,"abstract":"We present an algorithm to find the optimal point of a variational inequality problem. The domain of the function that defines the variational inequality is a convex set, determined by convex inequality constraints and affine equality constraints. The algorithm is based on a discrete variable structure closed-loop control system which presents sliding mode trajectories on the boundary of the feasible set until the optimal point is reached. The update law is designed using control Liapunov function (CLF), which guarantees the decrease of a discrete Liapunov function inside and outside the feasible set. The step size is optimized using Liapunov optimizing control (LOC).","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114454368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Supervisory Control Methodology for a New Pneumatic Cart-Seesaw System","authors":"Jonqlan Lin, J. Zhan, Julian Chang","doi":"10.1109/ISIC.2007.4450932","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450932","url":null,"abstract":"This paper describes mechanical configuration and control environment for a new cart-seesaw system. The system consists of a cart, which slides on the pneumatic rodless cylinder. The rodless cylinder is a double-acting one with carrier bracket on which a cart has been pinion mechanism to tracks. The task of the cart-seesaw system is to bring the cart to from any initial position to a desired position on the seesaw by applying an appropriate force to the cart and thereby changing the angle of the seesaw. The position of a cart represents the first degree of freedom, which is activated by a pneumatic proportional valve and the angle of the seesaw represents the second degree of freedom that is not actuated. Consequently, the proposed new pneumatic cart-seesaw system is simple to construct and direct to operate in different scenarios of performance. A state feedback controller is applied for stabilization of the equilibrium point of the system. Moreover, this work adds a supervisory controller that takes control action in extreme situations. Thus, the test results show excellent characteristics in control performance. Finally, the proposed product in this research can be extensively application in SAMS and pneumatic control for control laboratory.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114634266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Model-Free H-Infinity Load-Frequency Controller Design for Power Systems","authors":"A. Al-Tamimi, F. Lewis, Youyi Wang","doi":"10.1109/ISIC.2007.4450871","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450871","url":null,"abstract":"In this paper, an H-infinity load-frequency controller for a power system generator will be designed without the knowledge of the system model. Uncertainty in the system model is a common problem in power systems. In this paper the strategies for discrete-time linear system quadratic zero-sum games related to the H-infinity optimal control problem are solved forward in time without knowing the system dynamical model. The idea is to solve for an action dependent value function Q(x,u,w) of the zero-sum game instead of solving for the state dependent value function V(x) which satisfies a corresponding game algebraic Riccati equation (GARE). The result is model-free approach that solves the zero-sum game forward in time; i.e. it finds an H-infinity controller without knowing the dynamical system. It is proven that the algorithm is equivalent to a model-free iterative algorithm to solve the underlying (GARE) of the linear quadratic discrete-time zero-sum game.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131826319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Unit-Gain D-type Iterative Learning Control Scheme: Application to a 6-DOF Robot Manipulator","authors":"Y. Ye, Abdelhamid Tayebi, P. X. Liu","doi":"10.1109/ISIC.2007.4450892","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450892","url":null,"abstract":"In this paper, a novel method to realize a unit-gain feature in iterative learning control (ILC) is proposed, using both forward and backward filtering. Based on this method, a unit-gain derivative is proposed as a remedy to the undesirable high gain feature of the conventional derivative at high frequency. The scheme is equivalent to an all-pass unit-gain phase shifter; the forward altering uses a 0.5-order derivative and the backward filtering employs a 0.5-order integral. The all-pass phase shifter is then deployed in a unit-gain D-type ILC. For implementation, frequency-band synthesis of non-integer differentiator is introduced. The effectiveness of the unit-gain D-type ILC is demonstrated by experimental results on a 6 DOF robot manipulator.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133422720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}