Arkadiusz Kubacki

Detection of Artefacts from the Motion of the Eyelids Created During EEG Research Using Artificial Neural Network

This article shows the results of the work on the system to recognize artefacts during the EEG research. The focus is on recognizing only one but the most common artefact which is eyes blinking. Recognition was used six artificial neural networks with 1, 2, 5, 10, 100 and 1000 hidden layers. For its learn were used 16765 samples. This article is based on of Emotiv EPOC+™ system and the MATLAB environment.

Control of an Electro-Hydraulic Manipulator by Vision System Using Central Point of a Marker Estimated via Kalman Filter

In the paper, the vision system for control a electro-hydraulic manipulator is presented. The authors have proposed a Kalman Filter (KF) to estimate a central position of markers. Two different methods of initial estimation of markers position are used. First one is based on central point of marker’s mass. Second refers to a circle fitting method of binary object. These two methods theoretically give the same position of a central point of given marker, however, in case of image distortion results will have different errors. This can occur when operator is holding marker in a hand, and cover some parts of it. Therefore it is important to develop new robust method for marker tracking. Authors proposed Kalman Filter to estimate central point of a marker by making a fusion of information provided by two initial estimation methods. The conducted research proved that KF reduces total manipulator’s control error even in situation where \(30\,\%\) of marker area is invisible.

Research on Concentration Levels Depending on the Color and Blinking Frequency of the Marker Using Multiple EEG Channel

This paper presents the research on the concentration index. In the first section authors present general information on their brain-computer interfaces. They presented a system placement of the electrodes on a head and information about the human brain wave frequencies. In the next section the authors have presented the research methodology. They describe a method of carrying out three tests and equipment which they had used during the test. In the next chapter they presented the results of the tests. They have verified which electrodes must be taken into consideration when examining the concentration index. They showed how it affects the color and the frequency blinking marker change on the test results. The authors determined the best frequency for this type of research.

Development of Low Cost Speech System for Patient Suffer on the Amyotrophic Lateral Sclerosis

The article describes design of low cost speech system for patient suffer on the amyotrophic lateral sclerosis (ALS). The authors performed a literature overview concerning on the piezoelectric sensors, the ALS disease and construction systems supporting speech. The system was built with piezo sensor, which was triggered by the mimic face movements. The read signals is transmit to the extern application via USB interface, allowing patient to construction of words and phrases. The system has been tested, that allowed to choose the optimal location of the sensor on the head. Performed research is the starting point for building fully mobile speech system.

Design of The Test Stand for Hydraulic Active Heave Compensation System

Abstract The article presented here described the design of a test stand for hydraulic active heave compensation system. The simulation of sea waves is realized by the use of hydraulic cylinder. A hydraulic motor is used for sea waves compensation. The hydraulic cylinder and the hydraulic motor are controlled by electrohydraulic servo valves. For the measurements Authors used displacement sensor and incremental encoder. Control algorithm is implemented on the PLC. The performed tests included hydraulic actuator and hydraulic motor step responses.

Detection of facial gestures artefacts created during an EEG research using artificial neural networks

The article concerns detecting artefacts created by facial expressions in an EEG with the use of artificial neural networks. During the EEG research may appear some interferences which are called artefacts caused for example by muscle activity. This article will focus on some of them, namely eyeballs movements to the right and left, opening the mouth, smile, lifting eyebrows, opening and closing eyes. In order to record the electrical activity of the brain a device called Emotiv EPOC+™ was used. One of the aims of the research was to find a suitable activation function for the artificial neural networks.

Controlling the Direction of Rotation of the Motor Using Brain Waves via Ethernet POWERLINK Protocol

The paper presents preliminary results of the work with the Emotiv EPOC+™ system, which enabled in binary way control of objects. The system reads the brain waves from 14 plus 2 references electrodes. The controlled object was stepper motor with encoder released by the B&R company. For communication between the PC and engine control module was used Ethernet POWERLINK protocol, which allows data transfer with a minimum cycle time of 200 μs. Completely omitted PLC controller, which function was taken over the PC.

Design of Control System for an Electrohydraulic Drive Based on the Valve with PMSM Motor

The article describes design of control system and test stand for an electrohydraulic drive based on the new kind proportional valve with synchronous motor type PMSM (Permanent Magnets Synchronous Motor). In the second part, the chosen laboratory investigations of proposed valve with PMSM are presented. The study included the test of the basic characteristics of the drive such as step response and temperature of oil impact.

Development of Experimental Design for Hydraulic Active Heave Compensation Systems

The article presented here describes the development of test stand for hydraulic active heave compensation system. For measurements, actual position of hydraulic cylinder was used displacement sensors by the authors. They measured actual position of hydraulic motor by means incremental encoder. The test stand was built with the use of force sensor and 3 DOF accelerometer and gyroscope. During experimental tests force, acceleration and rotations (Pitch and Roll) were measured. Authors used two servo valves for the controlled position of hydraulic cylinder and hydraulic motor. The control system was based on PLC controller type Power Panel 500. The performed test included step response of hydraulic motor and hydraulic cylinder for sine signal.

Development of a Speech System Using BCI Based on ERD/ERS for Patients Suffering from Amyotrophic Lateral Sclerosis

The article describes the design process for a speech synthesis system based on ERD/ERS for patients suffering from amyotrophic lateral sclerosis (ALS) and for other patients with significantly reduced mobility. The authors performed a literature overview concerning the disease and the systems currently supporting speaking. The method described here is based on ERD/ERS technology. The system was built with the use of bioactive sensors mounted on the head, triggered by a signal known as MI tasks. The raw signals are transmitted to the external application via VRPN server and, after filtering, is allowed to build the words and phrases. The device has been tested so that the optimal location of the sensor on the head could be chosen.