Kimon P. Valavanis

Surveying stock market forecasting techniques - Part II: Soft computing methods

The key to successful stock market forecasting is achieving best results with minimum required input data. Given stock market model uncertainty, soft computing techniques are viable candidates to capture stock market nonlinear relations returning significant forecasting results with not necessarily prior knowledge of input data statistical distributions. This paper surveys more than 100 related published articles that focus on neural and neuro-fuzzy techniques derived and applied to forecast stock markets. Classifications are made in terms of input data, forecasting methodology, performance evaluation and performance measures used. Through the surveyed papers, it is shown that soft computing techniques are widely accepted to studying and evaluating stock market behavior.

Evolutionary algorithm based offline/online path planner for UAV navigation

An evolutionary algorithm based framework, a combination of modified breeder genetic algorithms incorporating characteristics of classic genetic algorithms, is utilized to design an offline/online path planner for unmanned aerial vehicles (UAVs) autonomous navigation. The path planner calculates a curved path line with desired characteristics in a three-dimensional (3-D) rough terrain environment, represented using B-spline curves, with the coordinates of its control points being the evolutionary algorithm artificial chromosome genes. Given a 3-D rough environment and assuming flight envelope restrictions, two problems are solved: i) UAV navigation using an offline planner in a known environment, and, ii) UAV navigation using an online planner in a completely unknown environment. The offline planner produces a single B-Spline curve that connects the starting and target points with a predefined initial direction. The online planner, based on the offline one, is given on-board radar readings which gradually produces a smooth 3-D trajectory aiming at reaching a predetermined target in an unknown environment; the produced trajectory consists of smaller B-spline curves smoothly connected with each other. Both planners have been tested under different scenarios, and they have been proven effective in guiding an UAV to its final destination, providing near-optimal curved paths quickly and efficiently.

Analytical design of intelligent machines

Abstract The problem of designing “intelligent machines” operating in uncertain environments with minimum supervision or interaction with a human operator is examined. The structure of an “intelligent machine” is defined to be the structure of a Hierarchically Intelligent Control System, composed of three levels hierarchically ordered according to the principle of “increasing precision with decreasing intelligence”, namely: the organizational level, performing general information processing tasks in association with a long-term memory, the coordination level, dealing with specific information processing tasks with a short-term memory, and the control level, which performs the execution of various tasks through hardware using feedback control methods. The behavior of such a machine may be managed by controls with special considerations and its “intelligence” is directly related to the derivation of a compatible measure that associates the intelligence of the higher levels with the concept of entropy, which is a sufficient analytic measure that unifies the treatment of all the levels of an “intelligent machine” as the mathematical problem of finding the right sequence of internal decisions and controls for a system structured in the order of intelligence and inverse order of precision such that it minimizes its total entropy. A case study on the automatic maintenance of a nuclear plant illustrates the proposed approach.

On the Measurement of Enterprise Agility

Agility metrics are difficult to define in general, mainly due to the multidimensionality and vagueness of the concept of agility itself. In this paper, a knowledge-based framework is proposed and presented as a candidate solution for the measurement and assessment of manufacturing agility. Given an enterprise, in order to calculate its overall agility, a set of quantitatively defined agility parameters is proposed and grouped into production, market, people and information infrastructures. The combined, resulting, measure incorporates the individual and grouped infrastructure agility parameters and their variations into one calculated value of the overall agility. The necessary expertise used to quantitatively determine and measure individual agility parameters is represented via fuzzy logic terminology that allows for human-like knowledge representation and reasoning. An example demonstrates the feasibility and applicability of the proposed approach.

Control architectures for autonomous underwater vehicles

Autonomous underwater vehicles (AUVs) share common control problems with other air, land, and water unmanned vehicles. In addition to requiring high-dimensional and computationally intensive sensory data for real-time mission execution, power and communication limitations in an underwater environment make it more difficult to develop a control architecture for an AUV. In this article, the four types of control architectures being used for AUVs (hierarchical, heterarchical, subsumption, and hybrid architecture) are reviewed. A summary of 25 existing AUVs and a review of 11 AUV control architecture systems present a flavor of the state of the art in AUV technology. A new sensor-based embedded AUV control system architecture is also described and its implementation is discussed.

Autonomous vehicle navigation utilizing electrostatic potential fields and fuzzy logic

An electrostatic potential field (EPF) path planner is combined with a two-layered fuzzy logic inference engine and implemented for real-time mobile robot navigation in a 2-D dynamic environment. The environment is first mapped into a resistor network; an electrostatic potential field is then created through current injection into the network. The path of maximum current through the network corresponds to the approximately optimum path in the environment. The first layer of the fuzzy logic inference engine performs sensor fusion from sensor readings into a fuzzy variable, collision, providing information about possible collisions in four directions, front, back, left and right. The second layer guarantees collision avoidance with dynamic obstacles while following the trajectory generated by the electrostatic potential field. The proposed approach is experimentally tested using the Nomad 200 mobile robot.

A Novel Nonlinear Backstepping Controller Design for Helicopters Using the Rotation Matrix

This brief presents a backstepping controller design for helicopters. The controller objective is for the helicopter to autonomously track predefined position and yaw reference trajectories. The incorporation of nested saturation feedback functions in the backstepping design preserves the helicopters motion and power physical constraints. The intermediate control signals related to the attitude dynamics exploit the structural properties of the rotation matrix and are enhanced with terms that guarantee that the helicopter will not overturn while tracking the desired position trajectory. The attitude dynamics are rendered exponentially stable while the translational dynamics are globally asymptotically stable. Numerical simulations illustrate the applicability of the proposed design.

Unmanned Aircraft Systems

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

On the hierarchical modeling analysis and simulation of flexible manufacturing systems with extended Petri nets

A class of Petri nets, called extended Petri nets, with multiple types of places, multiple classes of tokens and multiple arcs is proposed. It is utilized for the hierarchical modeling of flexible manufacturing systems, ensuring a priori that the extended Petri net system model obtained is live, bounded, consistent and error free. The proposed method views the operation of the flexible manufacturing system as a process that is decomposed into operations with specified precedence relations. For each operation the required resources are identified, and on the basis of these requirements the overall system is decomposed into a set of finite subsystems. The operation of each subsystem is modeled as an event graph representing a single resource activity cycle. The extended Petri net system model is synthesized from these component nets using certain synthesis rules. A software package has been developed to simulate the execution of the model obtained. >

Mobile robot navigation in 2-D dynamic environments using an electrostatic potential field

Proposes a solution to the two-dimensional (2-D) collision fee path planning problem for an autonomous mobile robot utilizing an electrostatic potential field (EPF) developed through a resistor network, derived to represent the environment. No assumptions are made about the amount of information contained in the a priori environment map (it may be completely empty) or the shape of the obstacles. The well-formulated and well-known laws of electrostatic fields are used to prove that the proposed approach generates an approximately optimal path (based on cell resolution) in a real-time frame. It is also proven through the classical laws of electrostatics that the derived potential function is a global navigation function (as defined by Rimon and Koditschek, 1992), that the field is free of all local minima and that all paths necessarily lead to the goal position. The complexity of the EPF generated path is shown to be O(mn/sub M/), where m is the total number of polygons in the environment and n/sub M/ is the maximum number of sides of a polygonal object. The method is tested both by simulation and experimentally on a Nomad200 mobile robot platform equipped with a ring of sixteen sonar sensors.