Skip to main content
It has always been important to know where we are in the world. In the past we used maps and compasses to find our way but today we are using GPS devices when travelling by foot, car or bike. The developments in location-based techniques... more
It has always been important to know where we are in the world. In the past we used maps and compasses to find our way but today we are using GPS devices when travelling by foot, car or bike. The developments in location-based techniques and the growing usefulness of ubiquitous computing and context-dependent information have resulted in an increase business interest in location-based applications and services. Currently, there are many applications requiring precise location or real-time tracking of humans, animals or other things inside buildings. The current global positioning system is unreliable for interior spaces. Therefore, demand for indoor localization services is becoming a key requirement.This paper makes an analysis of recent developments in wireless indoor localization methods and systems, to have a better understanding of the state of the art and to inspire new scientific initiatives in this promising area.In order to achieve the purpose of the paper, the existing wireless localization systems and location methods are reviewed, and also comparing the related techniques and systems with future trends.
We propose a natural, 3D immersive and real-time representation of the mental state acquired through EEG. Unlike most other neurofeedback methods currently in use, which are mostly simplistic, synthetic representations, our approach will... more
We propose a natural, 3D immersive and real-time representation of the mental state acquired through EEG. Unlike most other neurofeedback methods currently in use, which are mostly simplistic, synthetic representations, our approach will make use of rich natural visual metaphors, presented immersivity and user-centric. This powerful approach will stimulate deep neurofeedback-based learning and opens a wide range of applications, from the personal training of various mental capabilities (relaxation, focus, etc.) to psychological or psychiatric treatment. In this paper, we present the general concept of the system (acquiring the EEG data, it’s processing, mapping, and rendering) and discuss one of its most promising applications - in stimulating users’ creativity. There is detailed a training protocol to enhance neurological processes related to the creative activity, based on researched studies.
Nowadays, neurorehabilitation has started to benefit from the evolution of technology – from robotics to motion recognition and virtual reality, the complex procedures needed to recover lost functionalities after a neurological condition... more
Nowadays, neurorehabilitation has started to benefit from the evolution of technology – from robotics to motion recognition and virtual reality, the complex procedures needed to recover lost functionalities after a neurological condition can be improved and made more accessible for a wide range of patients. Parkinson’s Disease is a disorder which can benefit greatly from the adaptability of the virtual environments. Our paper analyzes Parkinson’s Disease as a medical disorder and the currently existing classical and technological treatments. We then present our own system, including specially designed exercises for training specific competencies which were lost or affected by the neurological disorder.
The field of affective computing has significantly emerged over the recent years, either we talk about systems that recognize and interpret human emotions or applications with assistive or therapeutic purposes that aim to treat various... more
The field of affective computing has significantly emerged over the recent years, either we talk about systems that recognize and interpret human emotions or applications with assistive or therapeutic purposes that aim to treat various psychological disorders. Our goal is to design and develop a system that would aid people suffering of a common anxiety disorder of our times - the phobia. Thus, we propose a system for treating acrophobia - fear of heights - that exposes the patients in a Virtual Reality scenario depicting a mountain landscape, while their physiological signals (electrodermal activity, heart rate and respiration rate) are continuously recorded. However, during exposure, certain artefacts can appear, caused by head or hand movements, controller or mouse clicks, body rotations - and thus affect the quality of the recording. As artefact identification is a fundamental step in obtaining clean data, in this paper we present a method of recognizing artefact patterns in the signals recorded during gameplay sessions, which consists of aligning the data segments corresponding to the moments when the users performed head/hand/body movements with the artefact signals recorded during a reference procedure. The results obtained in pilot experiment with 5 users showed that the bias is lower on the perfectly aligned segments than on the segments located a few steps before and after the moment when the user introduced the artefact in the game signal, but without statistical significance. In addition, we propose a new method of estimating respiration rate based on the distance between two HTC Vive trackers placed on an elastic band, on the chest and on the upper back torso of the user.
Nowadays, engineers have to face a lot of challenges before going to a job interview. Introversion, insecurity or lack of experience are some of the reasons that can lead to poor interview performances. Through training, such difficulties... more
Nowadays, engineers have to face a lot of challenges before going to a job interview. Introversion, insecurity or lack of experience are some of the reasons that can lead to poor interview performances. Through training, such difficulties can be overcome, leading to significant skill improvement. Our paper presents the advantages of using emerging technologies to facilitate job interview training. Our proposed model for a training system is based on virtual reality and chatterbots. Hard skills and soft skills training, various 3D virtual environments and domains modularity could ensure the personalization of the system for any job
Virtual Training Environments (VTE) are crucial for the testing and development of Sensory Substitution Devices (SSD) in a safe, controlled manner. User Analytics serve to collect and analyze user behavior, to provide clear design... more
Virtual Training Environments (VTE) are crucial for the testing and development of Sensory Substitution Devices (SSD) in a safe, controlled manner. User Analytics serve to collect and analyze user behavior, to provide clear design decisions for improving SSdev development and implementation. We implemented an analytics framework capable of tracking user behavior, map real-time paths and aggregate data over multiple nominal testing sessions. Aggregated data is used to reveal patterns of use and match them to individual abilities and user groups.
One of the important non-verbal human communication along with other form like postures and gestures, is emotional facial expression. Facial expression, carries a huge amount of information which represent the emotional feelings of... more
One of the important non-verbal human communication along with other form like postures and gestures, is emotional facial expression. Facial expression, carries a huge amount of information which represent the emotional feelings of humanity, and by observing people’s facial expressions with its cunning and moment movements can help us to understand what the face tell us because its reflect an immediate indicator of affective dispositions in other people. All the action and the reaction in the human body is controlled by the brain, and because of the major emotional significance of facial expression, many studies have used emotional faces to identify neural substrates of emotional processing. These studies have found that brain areas generally involved in the processing of emotional information are also activated during the processing of facial emotion. Microsoft company provides a new device technology for image and video acquisition with great high resolution for capturing the faci...
Back pain is among the most common causes of missing work and contributes to about 93 million lost workdays and $5 billion in health care costs every year. Sitting in an office chair for long periods of time can create lower back pain and... more
Back pain is among the most common causes of missing work and contributes to about 93 million lost workdays and $5 billion in health care costs every year. Sitting in an office chair for long periods of time can create lower back pain and can worsen problems that already exist. There are a number of factors that affect back pain, including level of movement, schedule, and desk set-up. Posture is a key factor that can induce pain over time; this includes sitting in the same position for too long or leaning too close to the screen. One may be able to avoid back pain or prevent its recurrence by improving the physical condition and learning and practicing proper body mechanics. We propose an efficient and time-effective tool to support the maintenance of a healthy position a smart pillow. This pillow will track one’s sitting posture on the chair, provides alerts when you don’t have a right posture, provide you tips for exercises based on your posture, allow you to set up goals regardin...
The current paper presents a state of the art of medical e-learning, highlighting the main features of existent applications, the technologies used to develop them, as well as the challenges they had to overcome in order to maximize the... more
The current paper presents a state of the art of medical e-learning, highlighting the main features of existent applications, the technologies used to develop them, as well as the challenges they had to overcome in order to maximize the value of educational activities. Although e-learning is a well-known practice of enhancing education, the research question here is whether it is fully adapted and exploited in the medical field. Based on the pros and cons of each analyzed tool, a new model to leverage medical e-learning is proposed. As a trend, most applications in medical e-learning target a certain medical specialization, very few being applicable for any medical discipline. Furthermore, certain areas pose specific limitations: for example, physical examination in clinical practice can't be taught in an e-learning environment, thus e-learning should complement but not replace the traditional medical education. Medical imaging and surgery are the medical fields highly supported by e-learning applications, followed by medical ethics, medical biochemistry, pediatrics. Some applications are merely customizations of well-known e-learning platforms (e.g. Moodle or Dokeos), others exploit advanced technologies such as virtual reality, 3D graphics, multimedia technologies, physical simulations or artificial intelligence. We consider that a major drawback of current medical e-learning platforms is the insufficiency of didactic material: most applications present didactical case studies (real or virtual), but their amount is far from enough. Thus, we propose an e-learning model which incorporates a medical atlas containing a large volume of expertly-annotated real cases, easily accessible and searchable, for various medical specializations. The repository will " self-evolve " , by allowing participants to upload their own materials. A formative learning module will be available. Also, group work will be allowed when putting diagnostics, thus collaborative learning techniques will be exploited in order to increase the information retention rate among users. We claim that the e-learning tool based on our model will be useful not only for undergraduate medical students, but also for continuous medical education.
Globally, rehabilitation in healthcare systems requires major improvements so that affordable, high-quality services will become available to a larger scale. Rehabilitation benefits both individuals and the entire community from an... more
Globally, rehabilitation in healthcare systems requires major improvements so that affordable, high-quality services will become available to a larger scale. Rehabilitation benefits both individuals and the entire community from an economic and social point of view. There are different types of rehabilitation, for a wide range of medical conditions, and each type requires a series of specific procedures performed by the patient, under therapist's guidance. Unfortunately, classical rehabilitation techniques have severe limitations in terms of results and large-scale availability, due to costs and lack of specialists. It is thus necessary to use the advantages of modern technologies, such as robotics, sensors or virtual reality in order to improve the results and make them accessible to many patients. In this paper, first we analyze the medical conditions that need specific neurorehabilitation procedures and their classical, currently used therapies. Then, we point out the potenti...
This paper proposes a real-time Virtual Reality game for treating acrophobia that automatically tailors in-game exposure to heights to the players’ individual characteristics – affective state and physiological features. The elements of... more
This paper proposes a real-time Virtual Reality game for treating acrophobia that automatically tailors in-game exposure to heights to the players’ individual characteristics – affective state and physiological features. The elements of novelty are the automatic estimation of fear and the prediction of the next game level based on the electroencephalogram (EEG) and biophysical data – Galvanic Skin Response (GSR) and Heart Rate (HR). Two neural networks have been trained with the data recorded in an experiment where 4 subjects have been in-vivo and virtually exposed to various heights. In order to test the validity of the approach, the same users played the acrophobia game, using two modalities of ex-pressing fear level. After completing a game level, the EEG and biophysical data were averaged and one neural network estimated the current fear score, while the other predicted the next game level. A measure of similarity between the self-estimated fear level during a game epoch and the fear level predicted by the first neural network showed an accuracy rate of 73% and 42% respectively for the two modalities of expressing fear level. 3 out of 4 users succeeded to obtain a fear level of 0 (complete relaxation) in the final game epoch
We propose a new method for segmenting indoor scenes captured with RGBD or depth cameras with a simple and fast iterative CPU segmentation. The segmentation consists of three main steps. In the first stage, regions grow by adding new... more
We propose a new method for segmenting indoor scenes captured with RGBD or depth cameras with a simple and fast iterative CPU segmentation. The segmentation consists of three main steps. In the first stage, regions grow by adding new pixels based on depth information and normal vectors. Next, multiple regions are merged into bigger surfaces based on adjacency and region statistics. The last stage of the method ensures interframe consistency based on a cost function between regions from subsequent frames. The planar segmentation can be used both for identifying indoor objects, which in general have planar faces, as well as for estimating the camera motion and then reconstructing the environment.
Introduction As the number of people with visual impairments (that is, those who are blind or have low vision) is continuously increasing, rehabilitation and engineering researchers have identified the need to design sensory-substitution... more
Introduction As the number of people with visual impairments (that is, those who are blind or have low vision) is continuously increasing, rehabilitation and engineering researchers have identified the need to design sensory-substitution devices that would offer assistance and guidance to these people for performing navigational tasks. Auditory and haptic cues have been shown to be an effective approach towards creating a rich spatial representation of the environment, so they are considered for inclusion in the development of assistive tools that would enable people with visual impairments to acquire knowledge of the surrounding space in a way close to the visually based perception of sighted individuals. However, achieving efficiency through a sensory substitution device requires extensive training for visually impaired users to learn how to process the artificial auditory cues and convert them into spatial information. Methods Considering all the potential advantages game-based l...
The paper summarizes a number of audio-related studies conducted by the Sound of Vision consortium, which focuses on the construction of a new prototype electronic travel aid for the blind. Different solutions for spatial audio were... more
The paper summarizes a number of audio-related studies conducted by the Sound of Vision consortium, which focuses on the construction of a new prototype electronic travel aid for the blind. Different solutions for spatial audio were compared by testing sound localization accuracy in a number of setups, comparing plain stereo panning with generic and individual HRTFs, as well as testing different types of stereo headphones vs custom designed quadrophonic proximaural headphones. A number of proposed sonification approaches were tested by sighted and blind volunteers for accuracy and efficiency in representing simple virtual environments.
The Hospital Acquired Infection (HAI), also known as nosocomial infection is an infection acquired by the patient during his stay in the health care facilities due to a completely different reason than the original entry reason. The HAI... more
The Hospital Acquired Infection (HAI), also known as nosocomial infection is an infection acquired by the patient during his stay in the health care facilities due to a completely different reason than the original entry reason. The HAI problem is classified as one of the main problems in health care facilities nowadays, due to the increased mortality, prolonging the duration of stay in hospitals, and then increased financial burden. In this article we highlight the infection problem with clear statistics from many countries, the infection causes in details, especially the contaminated hands, which are a critical issue. We clarify the role of healthcare workers (HCWs) and the hospital management for infection prevention. The aim of our research is to propose an information system dedicated to the prevention of hospital acquired infections. This paper presents an analysis of both the traditional and the latest ICT solutions dedicated to HAI prevention. The paper reveals that the traditional methods are far from enough to solve the problem, and that ICT solutions could contribute to solve the HAI problem to a much larger extent. In particular, we analyzed the integrated ICT systems used for monitoring the compliance with hand hygiene in details, and found that they give the highest rate of compliance with hand hygiene, thus fighting an important rate of infection.
3D Massively Multiplayer Online (MMO) applications have in present a large number of registered and active users that can reach up to even several millions for the most popular ones. These types of applications that include 3D games,... more
3D Massively Multiplayer Online (MMO) applications have in present a large number of registered and active users that can reach up to even several millions for the most popular ones. These types of applications that include 3D games, virtual life simulations, educational environments, museums, etc. are already considered by many as the new generation of human computer interface and human computer mediated communication; they continue to grow in size and integrate or even replace traditional ones (web browsers, instant messengers, social portals, etc.). The main problems of current 3D MMO server architectures are related to their scalability because they need to accommodate a large number of concurrent users and the number of operations that need to be executed can get very high in moments of peak usage. These problems of scalability are mainly due to the necessity to achieve real time low latency interaction in the 3D virtual worlds, at the same time ensuring their consistency and persistence. The owners of such virtual worlds need to handle a high operational cost due to the software and hardware complexity of current server architectures. In this paper we present and evaluate the 3D MMO server architectures already used in production and we also expand our previous work, presenting an overview of a solution that uses GPGPU (General Purpose computing on Graphics Processing Units) processing in order to alleviate the scalability and costs of current architectures. Preliminary results and tests with a functional prototype sustain the feasibility of our solution.
In recent years, the assistive technologies and stroke rehabilitation methods have been empowered by the use of virtual reality environments and the facilities offered by brain computer interface systems and functional electrical... more
In recent years, the assistive technologies and stroke rehabilitation methods have been empowered by the use of virtual reality environments and the facilities offered by brain computer interface systems and functional electrical stimulators. In this paper, a therapy system for stroke rehabilitation based on these revolutionary techniques is presented. Using a virtual reality Oculus Rift device, the proposed system ushers the patient in a virtual scenario where a virtual therapist coordinates the exercises aimed at restoring brain function. The electrical stimulator helps the patient to perform rehabilitation exercises and the brain computer interface system and an electrooculography device are used to determine if the exercises are executed properly. Laboratory tests on healthy people led to system validation from technical point of view. The clinical tests are in progress, but the preliminary results of the clinical tests have highlighted the good satisfaction degree of patients, ...
Photorealism has become a growing requirement for real-time graphics applications. Among the components needed to obtain photorealism, one of the most important is the simulation of the light transport, the result of which is called... more
Photorealism has become a growing requirement for real-time graphics applications. Among the components needed to obtain photorealism, one of the most important is the simulation of the light transport, the result of which is called global illumination. With the growing interest in the research in this field, the need to develop a learning approach for the methods that produce real-time global illumination and a technological basis have become important topics. In this paper, we present a framework for the rapid development and testing of such methods. The framework itself does not contain their implementations, but contains a set of components that underlie them. It has been developed with a multi-pass architecture that allows the reuse of pass implementations in several technique pipelines. Moreover, this framework can be used in the process of learning real-time global illumination methods thanks to an editor with graphical user interface (GUI) that offers a rich amount of inform...
Technology has reached a level most people could not even imagine a couple of decades ago. "eLearning" has become a hot topic all over the world. However, in many countries, including Romania ,the educational system has not... more
Technology has reached a level most people could not even imagine a couple of decades ago. "eLearning" has become a hot topic all over the world. However, in many countries, including Romania ,the educational system has not evolved the same way as technology. In most elementary and middle schools, the educational process does not differ much from the one established ten or even twenty years ago. Many students have access to smartphones, tablets, laptops, but they still use traditional paper textbooks and solve classical problems exercises in school. We propose an improvement to the current education system, which solves some major issues in the actual socio-economic context: a modern eLearning interactive math platform. Our team, composed of renowned math teachers and dedicated researchers in the technical field, has developed an online math platform for 5th grade pupils, characterized by attractiveness, interaction, animation, student-centered learning, gamification and o...
Order independent transparency represents a class of graphics algorithms in which the final result is independent of the order of primitive rasterization. The complexity of this class is given by the fact that the fragments generated by... more
Order independent transparency represents a class of graphics algorithms in which the final result is independent of the order of primitive rasterization. The complexity of this class is given by the fact that the fragments generated by the rasterized geometry need to be sorted and stored on a per pixel basis-a computational and a memory bandwidth problem. In this paper we present a novel real time single pass algorithm that uses fragment culling in order to decrease the memory usage by an average of 12.5% while still performing virtually correct transparency.
Massively Multiplayer Online (MMO) virtual worlds are nowadays one of the most widespread and fast growing types of online interactive applications with a user base that can reach up to millions of users. The most popular type of MMOs is... more
Massively Multiplayer Online (MMO) virtual worlds are nowadays one of the most widespread and fast growing types of online interactive applications with a user base that can reach up to millions of users. The most popular type of MMOs is represented by 3D MMO games but there are also other types of MMO applications such as virtual online virtual life simulations, educational virtual spaces, virtual exhibitions, etc. In this paper, we will present the current technologies that are being used for the functioning of MMOs in optimal conditions and also we will introduce a novel taxonomy for MMOs classification based on the following criteria: type of MMOs, architectures used for simulation of virtual worlds, communication protocol and monetization.
Office work related pain is very common nowadays and it is generally agreed that it is associated with complex physical and psychosocial factors. Spending extended periods of time in front of the computer and doing sedentary work severely... more
Office work related pain is very common nowadays and it is generally agreed that it is associated with complex physical and psychosocial factors. Spending extended periods of time in front of the computer and doing sedentary work severely affects human health. We have decided to seriously consider this aspect in the context of virtual reality and to develop computer-based interfaces that will enable monitoring human health in real time, based on certain physiological parameters. In this way, we aim to create a healthier working environment. We will show all the components of the virtual reality environment and each time the worker deviates from the normal posture the program will react in the most realistic way.
This paper is intended to define a new concept, the Dynamic Management of Distributed Cases-DMDC, and to describe it in the context of its implementation in the automation of processes put in execution by liberal professions. It also... more
This paper is intended to define a new concept, the Dynamic Management of Distributed Cases-DMDC, and to describe it in the context of its implementation in the automation of processes put in execution by liberal professions. It also makes an inventory of existing systems' shortcomings and identifies the minimal set of standards for process formalization and data exchange as well as re-usable components for a DMDC-type solution.
Getting an infection inside the hospital from the environment or from persons such as patients, physicians or visitors is known as the Hospital Acquired Infection (HAI). HAI is classified as one of the main issues which hospitals face... more
Getting an infection inside the hospital from the environment or from persons such as patients, physicians or visitors is known as the Hospital Acquired Infection (HAI). HAI is classified as one of the main issues which hospitals face nowadays that increases the mortality rate within hospitals. It also requires a large financial budget to be combated. In this paper, we propose a system dedicated to monitoring the hand hygiene rules within a hospital room, by tracking the positions of both physicians and patients, and by measuring the hand hygiene duration.
Hospitals receive many patients and visitors daily, and include a large number of medical staff members, thus, hospitals are eligible environments for infection transmission. The hospital acquired infection (HAI) is situated at the top of... more
Hospitals receive many patients and visitors daily, and include a large number of medical staff members, thus, hospitals are eligible environments for infection transmission. The hospital acquired infection (HAI) is situated at the top of the reasons pyramid that lead to death. HAI means that a patient enters the hospital for some reason and gets infected because of another reason. Non compliance with hygiene protocols is a major cause of HAI. Therefore, the automatic monitoring of hospital workflows using the recent communication technologies is a vital factor for infection prevention. In this article, we highlight in details the technologies that could be investigated for monitoring the workflows in a hospital room. We describe the hospital room use case, and we analyze the suitability for each technology. The goal of this paper is to suggest a system for monitoring the clinical workflows and pveventing the HAI. Nowadays, it became possible to perform efficient automated monitorin...
The problem of blindness and other eye disabilities is highly important as it affects millions of people on the globe. In the same time, the number of modern touchscreen devices is increasing fast. They are widely spread and becoming... more
The problem of blindness and other eye disabilities is highly important as it affects millions of people on the globe. In the same time, the number of modern touchscreen devices is increasing fast. They are widely spread and becoming accessible for education purposes. For those who suffer from congenital visual disabilities is very difficult to imagine the world as it is and the struggle begins from the early school stages and continues for the rest of their lives. Modern touchscreen devices, also called smart devices, represent a viable solution for people with sight problems due to their rich multimedia experience. Thus, they can be used as assistive devices. This paper describes how learning basic geometric shapes using a smartphone or a tablet can improve several important aspects like: general feeling of using touchscreen devices, perception of a basic figure’s shape by simply touching the screen, intuition on how to follow a GPS map. This methodology represents only the initia...
This paper reports research results from design and implementation of several collaborative and adaptive learning objects within a 3D experimental educational simulator on OpenSimulator platform. Our methodology was to identify and apply... more
This paper reports research results from design and implementation of several collaborative and adaptive learning objects within a 3D experimental educational simulator on OpenSimulator platform. Our methodology was to identify and apply different extensibility mechanisms of OpenSimulator that can support a flexible design and an extensible model required by an open and adaptive educational simulator. The learning objects were experimented with a small user base using different collaborative scenarios and will be further integrated into the “3DUPB” virtual campus in a Massive MultiUser Online context. The paper also discusses findings and presents conclusions and perspectives of the research.
This paper presented the assessment of cognitive load (as an effective real-time index of task difficulty) and the level of brain activation during an experiment in which eight visually impaired subjects performed two types of tasks while... more
This paper presented the assessment of cognitive load (as an effective real-time index of task difficulty) and the level of brain activation during an experiment in which eight visually impaired subjects performed two types of tasks while using the white cane and the Sound of Vision assistive device with three types of sensory input—audio, haptic, and multimodal (audio and haptic simultaneously). The first task was to identify object properties and the second to navigate and avoid obstacles in both the virtual environment and real-world settings. The results showed that the haptic stimuli were less intuitive than the audio ones and that the navigation with the Sound of Vision device increased cognitive load and working memory. Visual cortex asymmetry was lower in the case of multimodal stimulation than in the case of separate stimulation (audio or haptic). There was no correlation between visual cortical activity and the number of collisions during navigation, regardless of the type...
The technology advancements greatly improved the medical services over time with virtual reality (VR) devices and applications. Currently taking advantage of these recent advancements is the medical rehabilitation field, heavily studied... more
The technology advancements greatly improved the medical services over time with virtual reality (VR) devices and applications. Currently taking advantage of these recent advancements is the medical rehabilitation field, heavily studied in past few years as a promising VR area. VR-based rehab brings several advantages over the traditional therapy and could deliver personalized in-home treatment without the need of a permanent dedicated supervisor. A device that could make this technology possible is the Microsoft’s new Kinect v2, an improved motion capture sensor available at low prices for personal use. This promising high-tech device can track body movements without the need of additional attached devices that could prove unconformable and expensive. In order to evaluate the medical rehabilitation utility for in-home usage we conducted some research studies and practical experiments focusing on the upper-part of the body in a seated pose in front of a desk. Results indicate that t...
This paper presents a human-centered methodology for designing and developing Virtual Reality Exposure Therapy (VRET) systems. By following the steps proposed by the methodology – Users analysis, Domain Analysis, Task Analysis and... more
This paper presents a human-centered methodology for designing and developing Virtual Reality Exposure Therapy (VRET) systems. By following the steps proposed by the methodology – Users analysis, Domain Analysis, Task Analysis and Representational Analysis, we developed a system for acrophobia therapy composed of 9 functional, interrelated modules which are responsible for patients, scenes, audio and graphics management, as well as for physiological monitoring and events triggering. The therapist visualizes in real time the patient’s biophysical signals and adapts the exposure scenario accordingly, as he can lower or increase the level of exposure. There are 3 scenes in the game, containing a ride by cable car, one by ski lift and a walk by foot in a mountain landscape. A reward system is implemented and emotion dimension ratings are collected at predefined points in the scenario. They will be stored and later used for constructing an automatic machine learning emotion recognition a...
Human spatial representation is determined by the interaction of a wide range of stimuli, including visual, neuromotor and acoustic information. In a virtual acoustic environment that intends to simulate the perception of sound as in... more
Human spatial representation is determined by the interaction of a wide range of stimuli, including visual, neuromotor and acoustic information. In a virtual acoustic environment that intends to simulate the perception of sound as in real-world conditions by rendering the audio stimuli over headphones, the accuracy of audio presentation is of the utmost importance. Nonetheless, a well-known problem which affects binaural audio localization is represented by the front-back confusion, a situation in which the listener perceives the sounds which come from the front as coming from the back and vice-versa. Over the years, many theoretical and practical approaches have been devised in order to reduce the incidence of front-back confusions, including head movement, source movement, sound filtering using early reflections, the simulation of reverberant environments or anthropometric estimation. This paper aims to study, review and compare the most relevant methods and experiments designed t...
The Binaural Navigation Game is a 3D audio game with hierarchical levels of difficulty that can be used by both normal sighted or visually impaired players. The purpose of the game is to test and train the sound localization skills, to... more
The Binaural Navigation Game is a 3D audio game with hierarchical levels of difficulty that can be used by both normal sighted or visually impaired players. The purpose of the game is to test and train the sound localization skills, to entertain and to provide an alternative to the common video games available on the market nowadays. The sonification technique is based on the perception of 3D binaural sounds synthesized with non-individualized Head Related Transfer Functions (HRTFs) and on the inversely proportional sound intensity encoding of distance. Furthermore, we use an original method based on the simultaneous perception of two types of noise that aims to reduce the incidence of front-back confusions. This game has been tested in an experimental procedure (comprised of a pre-test, a hapticauditory feedback based training and a post-test session) in which 10 visually impaired subjects (with a percent of residual vision ranging from 0% to 15%) have participated. This paper aims...
In this paper, we present the concept, implementation and experimentation of a 3D MMO educational game designed for interactively learning chemistry. The game is integrated into the OpenSim framework to implement immersive, real time and... more
In this paper, we present the concept, implementation and experimentation of a 3D MMO educational game designed for interactively learning chemistry. The game is integrated into the OpenSim framework to implement immersive, real time and multiuser “learning by playing” techniques that have proved to be among the most powerful learning strategies in learning science. Experimenting the game with high school students proved that virtual gaming can be a practical and effective educational tool. Results suggest that it is more powerful to support chemistry learning with virtual game technology than with the traditional learning methods.
This paper presents an overview of 3D virtual world systems used by universities around the world to increase student engagement. Using publicly available information from the universities websites, we classified the virtual world systems... more
This paper presents an overview of 3D virtual world systems used by universities around the world to increase student engagement. Using publicly available information from the universities websites, we classified the virtual world systems they have deployed according to the type of technology used, availability and level of immersion. Using this classification, we provide a high-level view of the currently used systems and the expectations set for them by their target audience, students and prospective students. The purpose of this paper is to analyse the state of the art in the field of virtual world systems used in universities, as a start point for further improvements in this field. We also present a set of emerging technologies used in this context: augmented world through personal smartphones and virtual reality helmets. Author
Visually impaired people, completely or partially blind cannot perceive the surrounding environment as normal healthy people can. Not knowing how colors and shapes look like is a serious penalty and they have to live with it an entire... more
Visually impaired people, completely or partially blind cannot perceive the surrounding environment as normal healthy people can. Not knowing how colors and shapes look like is a serious penalty and they have to live with it an entire life. It is known that the human brain adapts and compensates with greater capabilities for hearing and touch when vision is low or missing, that is why blind people develop special skills and perform so good when it comes to music and kinetotherapy. Based on this information we are proposing a method that explains colors using vibrations. In this paper we would like to present a new way of transforming an image to vibration by using the capabilities of an Xbox gamepad. During the study on real blind volunteers, this kind of approach proved to be very effective and promising, allowing them to slightly understand how an image, painting or friend looks like. Author
This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information... more
This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method ...
The Sound of Vision project involves developing a sensory substitution device that is aimed at creating and conveying a rich auditory representation of the surrounding environment to the visually impaired. However, the feasibility of such... more
The Sound of Vision project involves developing a sensory substitution device that is aimed at creating and conveying a rich auditory representation of the surrounding environment to the visually impaired. However, the feasibility of such an approach is strongly constrained by neural flexibility, possibilities of sensory substitution and adaptation to changed sensory input. We review evidence for such flexibility from various perspectives. We discuss neuroplasticity of the adult brain with an emphasis on functional changes in the visually impaired compared to sighted people. We discuss effects of adaptation on brain activity, in particular short-term and long-term effects of repeated exposure to particular stimuli. We then discuss evidence for sensory substitution such as Sound of Vision involves, while finally discussing evidence for adaptation to changes in the auditory environment. We conclude that sensory substitution enterprises such as Sound of Vision are quite feasible in lig...
Over the past few years, computers have become indispensable in many fields. This also happened in medicine, where the need for speed and precision has led to the replacement of some human activities with those, faster and more accurate,... more
Over the past few years, computers have become indispensable in many fields. This also happened in medicine, where the need for speed and precision has led to the replacement of some human activities with those, faster and more accurate, of the computers. Nevertheless, despite the accuracy and the computing power, at this moment, for superior results, there is still a need for the human presence, to supervise and interpret the results. This is why we have developed a software application that will help doctors working in a small segment of medicine: Hip Arthroplasty.
Research Interests:
ABSTRACT Massive Multiplayer Online (MMO) applications have become extremely popular in the last years and this has led to an increase in the numbers of users that 3D MMO servers need to cope with. The current Client-Server architecture... more
ABSTRACT Massive Multiplayer Online (MMO) applications have become extremely popular in the last years and this has led to an increase in the numbers of users that 3D MMO servers need to cope with. The current Client-Server architecture that is used by the majority of MMOs introduces a severe bottleneck regarding the performance and scalability of the virtual spaces. In order to achieve the necessary level of performance for the 3D MMO servers the operators of such virtual worlds are faced with a high financial cost to maintain the system infrastructure. In this paper we describe the challenges that 3D MMO servers face, analyze the general architecture of 3D MMO servers, identify key operation that can be optimized as GPGPU (General Purpose computation on Graphical Processing Units) programs and propose adaptations for the server architecture to run GPGPU tasks. The tests that we have conducted using a prototype implementation have shown encouraging results proving that it is feasible for a 3D MMO server to offload tasks as GPGPU programs and thus reducing the overall costs.
Research Interests:
ABSTRACT
ABSTRACT We present here the results of a 3 year long nearshoring experiment, conducted in a semi-controlled academic environment. The experiment involved teams of 10-15 people from 6 European universities and proved that the biggest... more
ABSTRACT We present here the results of a 3 year long nearshoring experiment, conducted in a semi-controlled academic environment. The experiment involved teams of 10-15 people from 6 European universities and proved that the biggest issue in nearshoring lies in the difference between the 2 involved teams in terms of technical background differences.
Research Interests:

And 144 more