Ferat Sahin

A survey on feature selection methods

Plenty of feature selection methods are available in literature due to the availability of data with hundreds of variables leading to data with very high dimension. Feature selection methods provides us a way of reducing computation time, improving prediction performance, and a better understanding of the data in machine learning or pattern recognition applications. In this paper we provide an overview of some of the methods present in literature. The objective is to provide a generic introduction to variable elimination which can be applied to a wide array of machine learning problems. We focus on Filter, Wrapper and Embedded methods. We also apply some of the feature selection techniques on standard datasets to demonstrate the applicability of feature selection techniques.

Fault diagnosis for airplane engines using Bayesian networks and distributed particle swarm optimization

This paper presents a fault diagnosis system for airplane engines using Bayesian networks (BN) and distributed particle swarm optimization (PSO). The PSO is inherently parallel, works for large domains and does not trap into local maxima. We implemented the algorithm on a computer cluster with 48 processors using message passing interface (MPI) in Linux. Our implementation has the advantages of being general, robust, and scalable. Unlike existing BN-based fault diagnosis methods, neither expert knowledge nor node ordering is necessary prior to the Bayesian Network discovery. The raw datasets obtained from airplane engines during actual flights are preprocessed using equal frequency binning histogram and used to generate Bayesian networks fault diagnosis for the engines. We studied the performance of the distributed PSO algorithm and generated a BN that can detect faults in the test data successfully.

A Discrete Event XML based Simulation Framework for System of Systems Architectures

System of systems (SoS) concept is essential in solving the issues in complex systems where there are heterogeneous independently operable systems. In order for these independent systems to establish an SoS, they need to understand each other through effective communication. Thus, there is a need for a common language which wraps the data that is sent and received from a system within an SoS. This paper presents the application of extensible markup language (XML) to represent data communicated among systems without underlying differences in hardware software of the individual systems. Moreover, since the operation of each system is asynchronous in nature, the entire SoS can be considered as an event driven system. This paper presents a simulation framework to simulate the structure of the systems in an event driven fashion and wraps the data with a common language. The DEVSJAVA software is used as the discrete event simulator. In addition, XML based encapsulation is created in the DEVSJAVA environment to in the SoS.

Cognitive maps in swarm robots for the mine detection application

Navigation based on cognition is seen in many instances in the animal community. Maps are very useful for navigation in unknown and complex environments. User defined and preinstalled maps can be very useful in navigation in complex environments, while adaptively built maps become very essential in unknown environments. Intelligence is bestowed in the effective utilization of data to produce decisions. In the case of navigation, intelligence is seen when information collected en-route from a source to a destination is used judiciously in reaching the destination. In this paper we deal with the foraging of a piece of terrain as a process of navigation. The application here is on mine detection. Mines are placed over a field at unknown locations and swarm intelligence based agents are deployed for demining them. The efficiency of the demining process is measured in terms of the quickness with which they can clear the mines and the assurance that the minefield is clear of all of the mines at the end of the process. Simulation results acknowledging the performance under different working conditions of the swarm robots are presented. In an endeavor to substantiate our claims in simulation we decided to build swarm robots performing the task on an artificially developed environment.

An application of human robot interaction: development of a ping-pong playing robotic arm

This paper describes the design and development of a ping-pong robotic arm as an application of robotic vision. Displaced frame difference (DFD) is utilized to segment the ball motion from background motion. 3-D ball tracking using parametric calibration of single CCD camera is explained. This visual information is temporally updated and further employed to guide a robot arm to hit the ball at a specified location. The results signify the system development based on single camera tracking. System latency is measured as a function of the camera interface, processor architecture, and robot motion. Various hardware and software parameters that influence the real time system performance are also discussed.

System of systems approach to threat detection and integration of heterogeneous independently operable systems

This paper presents a system of systems approach to threat detection through integration of heterogeneous independently operable systems. The approach is presented on a realistic situation where a human-controlled base robot, swarm robot(s), and sensors work together to obtain a decision about a possible threat in the environment. The base robot is remotely operated by a human using a haptic control system. The swarm robot(s) are autonomous and can accept directives from the base robot. Finally, sensors directly communicate with (report to) the base robot. In this scenario, heterogeneous systems and human interact in a system of systems architecture. With the inclusion of human expert and sensor verification of swarm robots, the system can successfully perform the threat detection and reduce the false alarms. Finally, a system of systems simulation framework including a base robot, a swarm robot, and two sensors is presented in addition to an experimental evaluation of the proposed SoS architecture.

New classification techniques for electroencephalogram (EEG) signals and a real-time EEG control of a robot

This paper studies the state-of-the-art classification techniques for electroencephalogram (EEG) signals. Fuzzy Functions Support Vector Classifier, Improved Fuzzy Functions Support Vector Classifier and a novel technique that has been designed by utilizing Particle Swarm Optimization and Radial Basis Function Networks (PSO-RBFN) have been studied. The classification performances of the techniques are compared on standard EEG datasets that are publicly available and used by brain–computer interface (BCI) researchers. In addition to the standard EEG datasets, the proposed classifier is also tested on non-EEG datasets for thorough comparison. Within the scope of this study, several data clustering algorithms such as Fuzzy C-means, K-means and PSO clustering algorithms are studied and their clustering performances on the same datasets are compared. The results show that PSO-RBFN might reach the classification performance of state-of-the art classifiers and might be a better alternative technique in the classification of EEG signals for real-time application. This has been demonstrated by implementing the proposed classifier in a real-time BCI application for a mobile robot control.

Pattern recognition with surface EMG signal based wavelet transformation

EMG based input device is a natural means of human computer interface (HCI) because the electrical activity induced by the humans arm muscle movements can be interpreted and transformed into computers control commands. In this paper, we describe an approach for classifying electromyography (EMG) signals using a multilayer perceptron neural network (MLP) and Bayesian classifier (BC) with the wavelet transformation technique for feature selection to discriminate 6 classes of motions to control a mouse. Wavelet Transformation (WT) was applied to raw EMG data and in order to decrease the dimension of the feature sets, principle component analysis (PCA) and sequential forward selection (SFS) were utilized.

Intelligent Control Systems with an Introduction to System of Systems Engineering

Apply NASA SoS Innovations to Your Own Work From aeronautics and manufacturing to healthcare and disaster management, systems engineering (SE) now focuses on designing applications that ensure performance optimization, robustness, and reliability while combining an emerging group of heterogeneous systems to realize a common goal. Use SoS to Revolutionize Management of Large Organizations, Factories, and Systems Intelligent Control Systems with an Introduction to System of Systems Engineering integrates the fundamentals of artificial intelligence and systems control in a framework applicable to both simple dynamic systems and large-scale system of systems (SoS). For decades, NASA has used SoS methods, and major manufacturersincluding Boeing, Lockheed-Martin, Northrop-Grumman, Raytheon, BAE Systemsnow make large-scale systems integration and SoS a key part of their business strategies, dedicating entire business units to this remarkably efficient approach. Simulate Novel Robotic Systems and ApplicationsTranscending theory, this book offers a complete and practical review of SoS and some of its fascinating applications, including: Manipulation of robots through neural-based network control Use of robotic swarms, based on ant colonies, to detect mines Other novel systems in which intelligent robots, trained animals, and humans cooperate to achieve humanitarian objectives Training engineers to integrate traditional systems control theory with soft computing techniques further nourishes emerging SoS technology. With this in mind, the authors address the fundamental precepts at the core of SoS, which uses human heuristics to model complex systems, providing a scientific rationale for integrating independent, complex systems into a single coordinated, stabilized, and optimized one. They provide readers with MATLAB code, which can be downloaded from the publishers website to simulate presented results and projects that offer practical, hands-on experience using concepts discussed throughout the book.

A swarm intelligence based approach to the mine detection problem

In this paper, we have applied a swarm intelligence based technique to a mine detection problem. Swarm intelligence techniques are used to model robotic agents to solve the problem. Studies made on the ant colonies, which is a typical member of the family of swarms, are applied in devising the techniques for the agents. Ant colony models bestow intelligence not only at the individual level, but more at the collective level (the interactions produced by the individual members in trying to solve a common problem). An analysis of the results obtained with a computer simulation of the mine detection is also presented.