Alexandr Stefek

Benchmarking of heuristic optimization methods

It is short history when many heuristic optimization methods appear. As example Particle swarm optimization method (PSO) or Repulsive particle swarm optimization method (RPSO), Gravitational search algorithm (GSA), Central force optimization (CFO), Harmony search algorithm (HAS) etc. Those methods are working differently but all of them can optimize same problems. There is general question: Exists any standard benchmark which can be used for individual methods comparing? It is a bit hard to answer this question because it is possible to find some optimization problems which are widely used along some papers but in fact there does not exists summary which can be uses for standard evaluation of optimization process. This paper will describe set of benchmarks which can be used for evaluation of optimization process. As a part of paper some results of optimization and utilization of optimization methods will be included.

Evaluation of relationship between the activity of upper limb and the piloting precision

Flying an aircraft requires a significant degree of coordination of upper and lower limbs. Such movements tend to be rather uncoordinated in the case of inexperienced pilots which results in inaccurate piloting. The aim of this study is to prove or disprove the dependence of the upper limb activity in relation to the aircraft steering during various actions which are required for precise maneuvering. We also deal with the design of a method to determine the degree of correlation between the movement of the hand and the airplane. The study was conducted on 8 subjects with the same level of experience during 11 hours of flight training on the simulator of type TRD40 and aircraft of type DA40. Subjects performed 14 maneuvers in total. Between takeoff and landing a recurring cycle of four maneuvers has been carried out by the subjects. Repeated maneuvers were in the order from the straight-and-level flight, horizontal turn by 360°, ascend turn by 180°, and descent turn by 180°. Recorded data except for basic flight data (magnetic course, banked and altitude) have been variables depicting the activity of the pilots upper limb. The activity was measured using triaxial accelerometer located on the dorsal side of the distal end of the forearm. The correlation coefficient proved relationship between the upper limb movement and aircraft steering both at bank and altitude. It testifies that change of bank and altitude of aircraft is directly connected with upper limb movements. Resultant activity standard deviation relation correlation coefficient is 0.7.

Wearable systems for monitoring the health condition of soldiers: Review and application

From the second half of the 1990s, thanks to more affordable and more powerful technology and systems for recording based on miniaturized sensors, we can observe a more intensive development of a system that monitors the physical and psychological conditions of soldiers. Systems for measuring of physical and medical data for the diagnostics of physical and psychological state has significantly spread. This study, however, examines the current technologies and usage of the wearable monitoring systems in military. The article can serve as a guide for choosing suitable and affordable systems of quantitative evaluation of physical and psychological conditions of soldiers. In addition, the innovative telemetry monitoring system (FlexiGuard system) composed of appropriate sensors is introduced. Based on previous researches and tests, FlexiGuard system and its sensors are recommended for use in military practice.

Myoelectric arm using artificial neural networks to reduce cognitive load of the user

Today’s multiple degree-of-freedom myoelectric prosthesis relies only on direct control by the processed electromyographic signal. However, it is difficult for the wearer to learn unnatural muscle contractions in order to wield more than three DoFs of the arm. This makes it almost impossible to use more complex prostheses with a larger number of actuators. Methods based on sensor–actuator loop and artificial intelligence may reduce cognitive load of the user by removing low level control, and an intelligent control system would make it needless to micromanage every action. For this purpose, sensor system for body segments motion capture was developed, as well as sensor system for prosthetic limb’s environment motion capture. Neural networks were designed to process data from the sensor systems. For the identification of the knee angle, orientation trackers were used. Neural network predictor of arm positions predicts the shoulder angle using the information about movement of the lower limb. In the case of the periodic/cyclic movements of the legs, such as walking, the control unit uses typical movement patterns of the healthy upper limb. Ultrasonic range sensors are used to create 3D map of objects in the environment around the arm. Neural network predictor of object positions predicts collisions. If the potential collisions are identified, the control unit stops arm movement. The new methods were verified by MATLAB and are designed as a part of assistive technology for disabled people and are to be understood as an original contribution to the investigation of new prosthesis control units and international debate on the design of new myoelectric prostheses.

Low cost 3D mapping for indoor navigation

This article focuses on the ability to use a robot with a low cost 3D Scanner (Kinect) in an indoor environment to do a mapping of different rooms in a building and to be able to localize itself when going back to the same room. This method uses SIFT points (points of interest in images) to be able to reconstruct the environment in 3D and uses these SIFT points to identify the localization of the robot.

UAV assisted landing on moving UGV

The paper presents a method to assist the landing of an Unmanned Aerial Vehicle (UAV) on a moving Unmanned Ground Vehicle (UGV). The measurement of the relative position of the UAV and the UGV is carried out by a cheap USB camera. The paper deals with the list of the difficulties of such a system which have to be taken into account and develop ideas on how to overcome them. The solution of the key problems is implemented and tested by experiments.

Multi-agent system as operational center support

Civilian or military operational centers are typical for their specific set of activities according to solved problems. Operational personnel have to perform procedural as well as positive kind of control of its controlled entities. To help these personnel with their decisions, we propose to build an automated system based on knowledge structure. This paper deals with procedural reasoning multi agent system designed to take over certain kind of task at operational center like firefighting operational center or military air operations center.

Utilization of optimization methods cooperation for the improvement of optimization process

The article deals with the proposal of new methods combinations that are designed to solve general optimization problems. These methods tackle the problems without constraints and therefore can be utilized in most fields of human activity. Issues dealing with solution of optimization problems that are focused especially on three basic optimization algorithms are presented and theoretically analyzed in this paper. An important part is the description of the parameters that have a significant influence on the process of finding extremes. The attention is also paid to the basic optimization methods and to inclusion of different methods into the overall concept of optimization. As a result, there are proposed algorithms that solve the cooperation of optimization methods. The optimization process improvements reached by using newly developed composite methods is proved by comparing achieved values obtained from series of tests with the values of the basic versions of used algorithms.

General Implementation of the Ant colony optimization on .NET platform

The paper presents an appropriate tool for testing and tuning algorithms based on the Ant colony optimization methods. Setting up a set of parameters of these methods is an essential and also very complex issue and in this way could be the presented implementation very beneficial. Suggested implementation depicted how to encapsulate mathematical algorithm into an generalized instrument which can be used for testing and evaluating all required inputs and moreover be user-friendly as much as possible. The implementation is built up on the .NET framework using all of its features as object oriented architecture and functional programming which can be very handy in practical experiments.

Contribution to Determination of Target Angular Position by Single Visual Camera at Indoor Close Environs

This paper is a follow-up to issued results of the Research Intention at the Department of Air Defence Systems that were performed and published in period 2011 and 2013. The paper deals with practical experiments which have been performed in order to bring some evidences about possibilities estimating angular positions of the stationary target by using visual odometry. The single visual camera and the target have been used to estimate angular position and angle of rotation of the target in the laboratory conditions at short distances. Mainly the paper describes the results of performed experiments and possibilities reduction of errors caused by optical system of camera (e.g. field deflection).