Francisco R. Ortega

Implementing a Sensor Fusion Algorithm for 3D Orientation Detection with Inertial/Magnetic Sensors

In this paper a sensor fusion algorithm is developed and implemented for detecting orientation in three dimensions. Tri-axis MEMS inertial sensors and tri-axis magnetometer outputs are used as input to the fusion system. A Kalman filter is designed to compensate the inertial sensors errors by combining accelerometer and gyroscope data. A tilt compensation unit is designed to calculate the heading of the system.

Off-line and on-line stress detection through processing of the pupil diameter signal.

The pupil diameter (PD), controlled by the autonomic nervous system, seems to provide a strong indication of affective arousal, as found by previous research, but it has not been investigated fully yet. In this study, new approaches based on monitoring and processing the PD signal for off-line and on-line “relaxation” vs. “stress” differentiation are proposed. For the off-line approach, wavelet denoising, Kalman filtering, data normalization, and feature extraction are sequentially utilized. For the on-line approach, a hard threshold, a moving average window and three stress detection steps are implemented. In order to use only the most reliable data, two types of data selection methods (paired t test based on galvanic skin response (GSR) data and subject self-evaluation) are applied, achieving average classification accuracies up to 86.43 and 87.20% for off-line and 72.30 and 73.55% for on-line algorithms, with each set of selected data, respectively. The GSR was also monitored and processed in our experiments for comparison purposes, with the highest classification rate achieved being only 63.57% (based on the off-line processing algorithm). The overall results show that the PD signal is more effective and robust for differentiating “relaxation” vs. “stress,” in comparison with the traditionally used GSR signal.

Measuring the effort for creating and using domain-specific models

The use of domain-specific modeling languages (DSMLs) results in higher productivity during the development process. This is accomplished by raising the level of abstraction during design and focusing on domain concepts rather than low-level implementation details. Unlike other development paradigms, little work has been done in determining and measuring the claimed benefits of using DSMLs. In this paper, we propose a new approach to determine the effort involved in creating and using DSML models to develop applications and to manage the behavior of applications at runtime. The approach involves a classification of the effort involved, and definition of relevant metrics to measure the effort for each category. A case study is presented that shows how we applied the proposed metrics during the development and execution of an application using three different DSMLs.

Eberos GML2D: a graphical domain-specific language for modeling 2D video games

The complexity of game development has increased in the past 30 years, from a task that could almost be entirely handled by a single programmer to an endeavor requiring a large team. To reduce this complexity, we have developed a Domain-Specific Language (DSL) targeting the modeling of two-dimensional (2D) games. We call this language Eberos Game Modeling Language 2D (Eberos GML2D). By raising the level of abstraction through modeling, we allowed a simpler specification of the game, and reduced the time and programming efforts. In order to evaluate our approach, we modeled two games and compared the difference between the amount of work required to write the game from scratch and the amount required using our proposed language. These evaluations yielded promising results of 86.4% savings on programming effort, and 82.3% savings on programming time.

Bio-sensing for Emotional Characterization without Word Labels

In this article, we address some of the issues concerning emotion recognition from processing physiological signals captured by bio-sensors. We discuss some of our preliminary results, and propose future directions for emotion recognition based on our lessons learned.

Interaction Design for 3D User Interfaces: The World of Modern Input Devices for Research, Applications, and Game Development

In this new era of computing, where the iPhone, iPad, Xbox Kinect, and similar devices have changed the way to interact with computers, many questions arised of how modern input devices can be used for a more intuitive user interaction. This book, Interaction Design for 3D User Interfaces, addressed this paradigm shift. The book looks at user interfaces with an input perspective. This book is divided in four parts (I) Theory of input devices and user interfaces with an emphasis on multi-touch interaction; (II) Advanced topics that helps reduced noise on input devices; (III) Hands-on approach to allow the reader gain experience with some of the new devices mention on this book. (IV) A case study that shows how a complete solution, using speech as input. This book provides current state-of-the-art, which allows researchers, developers, and students to understand the direction on the field of input devices and user interaction

Gesture elicitation for 3D travel via multi-touch and mid-Air systems for procedurally generated pseudo-universe

With the introduction of new input devices, a series of questions have been raised in regard to making user interaction more intuitive - in particular, preferred gestures for different tasks. Our study looks into how to find a gesture set for 3D travel using a multi-touch display and a mid-air device to improve user interaction. We conducted a user study with 30 subjects, concluding that users preferred simple gestures for multi-touch. In addition, we found that multi-touch user legacy carried over mid-Air interaction. Finally, we propose a gesture set for both type of interactions.

CircGR: Interactive Multi-Touch Gesture Recognition using Circular Measurements

CircGR is a multi-touch non-symbolic gesture recognition algorithm, which utilizes circular statistic measures to implement linearithmic (O(n log n)) template-based matching. CircGR provides a solution to gesture designers, which allows for building complex multi-touch gestures with high-confidence accuracy. We demonstrated the algorithm and described a user study with 60 subjects and over 12,000 gestures collected for an original gesture set of 36. The accuracy is over 99% with the Matthews correlation coefficient of 0.95. In addition, early gesture detection was successful in CircGR as well.

Exploring modeling language for multi-touch systems using petri nets

The motivation in this research endeavor is to design a flexible and compact modeling language for multi-touch gesture recognition using Petri Nets. The findings demonstrated that a Petri Net can be used effectively for gesture detection, with the potential for such a model to be composed of many Petri Nets for faster and user friendly applications.

HandMagic: Towards user interaction with inertial measuring units

We present a method of gesture recognition designed to be used with inertial measurement units (IMUs) for 3D user interaction. We provide a drone simulator environment to validate our work. It is important to use motion sensors for user interaction as other devices provide challenges not present in motion-sensors. It is also important since the current field of user interaction is moving towards a multi-modal paradigm and IMUs have been under studied for this field. This work presents the functionality of IMUs with a 6-axis model. We discussed our pilot study and its results, which were satisfactory.