Vidas Raudonis

Discrete eye tracking for medical applications

The novel technology, which is dedicated to assist the person with disabilities, is presented in the work. It is the discrete eye tracking system which recognizes the users command from voluntary controlled eye motion. The user wears the head mounted device, which consist of glasses with fixed on it video camera. The system was tested with three on-line applications. First — the control of the mobile robot in the maze, second, application is the text writing program “EyeWriter” and third computer game. Over 25 commands per second can be generated using presented eye tracking system.

Autonomous Mobile Robot Control Using Fuzzy Logic and Genetic Algorithm

Design of efficient control algorithms for autonomous mobile robot movement in unknown and changing environment with obstacles and walls is a difficult task. There exist different strategies to design control systems to perform the robot movement. In this article possibility to use fuzzy logic, if-then rules, and genetic algorithm for autonomous mobile robot control is presented. Control using fuzzy logic is softer and better then control using if-then rules because of absence of motors speed jumps. It is shown that the rough control system can be designed using an expert knowledge. Then genetic algorithm can be used to improve the quality of the control system.

Student progress assessment with the help of an intelligent pupil analysis system

Students and lecturers would like to know how well students have learned the study materials being taught. A formal test or exam would cause needless stress for students. To resolve this problem, the authors of this article have developed an Intelligent Pupil Analysis (IPA) System. A sufficient amount of studies worldwide prove an interrelation between pupil size and a persons cognitive load. The obtained research results are comparable with the results from other similar studies. The original contribution of this article, compared to the research results published earlier, is as follows: the IPA System developed by the authors is superior to the traditional pupil analysis research due to the integration of pupil analysis with subsystems of decision support, recommender and intelligent tutoring systems and innovative Models of the Model-base, which permit a more detailed analysis of the knowledge attained by a student. This article ends with a case study to demonstrate the practical operation of the IPA System.

Trajectory based fuzzy controller for indoor navigation

The experimental results of fuzzy based indoor navigation system are presented in this article. The system was built with simplicity in mind, employing roof mounted visual sensors and fuzzy logic for the guidance and positioning of an autonomous mobility device with real-life noisy and delayed visual data processing. The fuzzy control strategy presented bellow works on a given (predefined) trajectory principle. The position of the device in the 2D plane, the distance from the given trajectory, orientation and control tasks are evaluated according to visual data. The controller controls the angular velocities of two device drive wheels based on the distance to the segment of the given trajectory and the orientation. Paper presents the control model and algorithm of a real-life prototype, as well as the quite promising experimental evaluation of the indoor autonomous navigation capabilities.

Gender, Age, Colour, Position and Stress: How They Influence Attention at Workplace?

We explore the relationship between attention and action, and focus on human reaction to stress in the Supervisory Control and Data Acquisition (SCADA) based Human Computer Interface (HCI) environment aiming to measure the reaction time and warn against attention deficit. To provoke human reaction we simulate several provocative situations mimicking real-world accidents while working on the industrial production line. During the simulation of the industrial line control, the subjects are presented on screen with affective visual stimuli imitating the possible accident and the reaction of subjects is tracked with a gaze tracker. We measure a subjects’ response time from stimuli onset to the eye fixation (gaze time) and to the pressing of “line stop” button (press time). The reaction time patterns are analysed with respect to subject’s gender, age, colour and position of stop sign. The results confirm the significance of gender, age, sign colour and position factors.

Investigation of complexity of extraction accuracy modeling cardio signals in two ways

How to extract information intensively from cardio signals for the diagnosis of diseases and assessment of heart function is a topical subject. Heart is not a periodic oscillator under normal physiologic conditions and standard linear measures may not be able to detect subtle, but important changes in heart time series, whereas, most of nonlinear measures suffer from the curse of dimensionally. In this paper, we show the results of cardio signals identification using the proposed structure based on H rank function employment.

Are you ashamed? Can a gaze tracker tell?

Our aim was to determine the possibility of detecting cognitive emotion information (neutral, disgust, shameful, ‘‘sensory pleasure’’) by using a remote eye tracker within an approximate range of 1 meter. Our implementation was based on a self-learning ANN used for profile building, emotion status identification and recognition. Participants of the experiment were provoked with audiovisual stimuli (videos with sounds) to measure the emotional feedback. The proposed system was able to classify each felt emotion with an average of 90% accuracy (2 second measuring interval). Subjects Human-Computer Interaction, Artificial Intelligence, Computer Vision

Vision Enhancement Technique Based on Eye Tracking System

In this paper a gaze tracking system is presented that allows stress free reading for people who are paralyzed, with low vision or who have both disabilities. The system tracks the positions of the eye pupil corneal reflection and finds the point of the readers gaze. The user wears a head-mounted device (special eyeglasses) when he sits in front of the computer screen. The integrated possibility of magnification has allowed more effective working with the computer, including accurate selections of targets, faster reading and writing. The experiments have shown the usefulness of the proposed system and claim that it can not only enhance the human vision but can also increase the living quality by allowing non-contact interaction with the computer.

Application of computer vision methods in automatic analysis of embryo development

In vitro fertilization (IVF) is a process by which an egg is fertilized by sperm outside the body. This is very difficult procedure, and in the end of it, some of embryos should be selected to implant to the uterus of woman. The applied image processing methods are represented in this article, which detect and measure the embryos early development. The results of embryos detection is represented in this article also.

Intelligent Pupil Analysis of Student Progress System

Various methodologies are used in the effort to predict the knowledge of students. A sufficient amount of studies worldwide prove an interrelation between persons’ cognitive load to pupil size. The Intelligent Pupil Analysis of Student Progress (IPASP) System for assessing student progress were developed on the basis of the aforementioned methodologies, the fifteen years of experience with distance learning and the seven years of experience with technology for pupil analysis by the authors of this article. The IPASP System developed by these authors is superior to the systems due to the use of pupil analysis and special algorithm which permits a more detailed analysis of the knowledge attained by a student.