Several strategies have been proposed to improve patient motivation and exercise intensity during robot-aided stroke rehabilitation. One relatively unexplored possibility is two-player gameplay, allowing subjects compete or cooperate with each other achieve a common goal. In order explore the potential of such games, we designed game played using two ARMin arm rehabilitation robots.The was an air-hockey task displayed on computer monitor controlled shoulder movements in robot. Three modes...

Journal Article A survey of methods for data fusion and system adaptation using autonomic nervous responses in physiological computing Get access Domen Novak, Novak * Faculty Electrical Engineering, University Ljubljana, Trzaska cesta 25, 1000 Slovenia Corresponding author. Tel.: +386 14768373 (O), mobile: 41969753; fax: 14768239. E-mail addresses:domen.novak@robo.fe.uni-lj.si (D. Novak), matjaz.mihelj@robo.fe.uni-lj.si (M. Mihelj), marko@robo.fe.uni-lj.si Munih). Search other works by this...

People with chronic arm impairment should exercise intensely to regain their abilities, but frequently lack motivation, leading poor rehabilitation outcome. One promising way increase motivation is through interpersonal games, which allow patients compete or cooperate together other people. However, such games have mainly been evaluated unimpaired subjects, and little known about how they affect intensity in people impairment. We designed four different that are played by a person friend,...

This paper presents a novel multimodal virtual rehabilitation environment. Its design and implementation are based on principles related to intrinsic motivation game design. The system consists of visual, acoustic, haptic modalities. Elements contributing carefully joined in the three modalities increase patients' during long process rehabilitation. message bottle (MIB) scenario is designed allow interplay between motor cognitive challenges exercising patient. user first needs perform action...

Cognitively challenging training sessions during robot-assisted gait after stroke were shown to be key requirements for the success of rehabilitation. Despite a broad variability cognitive impairments amongst population, current rehabilitation environments do not adapt capabilities patient, as load cannot objectively assessed in real-time. We provided healthy subjects and patients with virtual task training, which allowed modulating by adapting difficulty level task. quantified using...

People with neurological injuries such as stroke should exercise frequently and intensely to regain their motor abilities, but are generally hindered by lack of motivation. One way increase motivation in rehabilitation is through competitive exercises, exercises have only been tested single brief sessions usually did not adapt difficulty the patient's abilities. We designed a arm game for two players that dynamically adapts its both players' This was evaluated participant groups: 15...

This paper presents the analysis of four psychophysiological responses in post-stroke upper extremity rehabilitation. The goal was to determine which would provide most reliable information about subjects' psychological states during Heart rate, skin conductance, respiration, and temperature were recorded a stroke group control two difficulty levels pick-and-place task performed virtual environment using haptic robot cognitive task. Psychophysiological measurements correlated with results...

This paper examines the usefulness of psychophysiological measurements in a biocooperative feedback loop that adjusts difficulty an upper extremity rehabilitation task. Psychophysiological (heart rate, skin conductance, respiration, and temperature) were used both by themselves combination with task performance biomechanics. Data fusion was performed discriminant analysis, special adaptive version implemented can gradually adapt to subject. Both healthy subjects hemiparetic patients...

Previous studies have presented algorithms for detection of turns during gait using wearable sensors, but those were not built real-time use. This paper therefore investigates the optimal approach planned inertial measurement units. Several different sensor positions (head, back and legs) three criteria (orientation, angular velocity both) are compared with regard to their ability correctly detect turn onset. Furthermore, predict direction amplitude. The evaluation was performed on ten...

SUMMARY Psychophysiological measurements, which serve as objective indicators of psychological state, have recently been introduced into human–robot interaction. However, their usefulness in haptic interaction is uncertain, since they are influenced by physical workload. This study analyses psychophysiological responses to a task with three different difficulty levels and two load. Four physiological were recorded: heart rate, skin conductance, respiratory rate temperature. Results show that...

We present an automated segmentation method based on the analysis of plantar pressure signals recorded from two synchronized wireless foot insoles. Given strict limits computational power and consumption typical wearable electronic components, our aim is to investigate capability a Hidden Markov Model machine-learning method, detect gait phases with different levels complexity in processing sensors signals. Therefore three datasets are developed: raw voltage values, calibrated sensor...

We present an automated gait segmentation method based on the analysis of foot plantar pressure patterns elaborated from two wireless pressure-sensitive insoles. The 64 signals recorded by each device are to extract 10 feature variables which used segment cycle into 6 sub-phases following a simplified version Perry's model. is Hidden Markov Model with minimum phase length constraint and univariate Gaussian emission model, decoded using classic Viterbi algorithm. tested pool 5 healthy young...

Rapid recognition of voluntary motions is crucial in human-computer interaction, but few studies compare the predictive abilities different sensing technologies. This paper thus compares performances technologies when predicting targets human reaching motions: electroencephalography (EEG), electrooculography, camera-based eye tracking, electromyography (EMG), hand position, and user's preferences. Supervised machine learning used to make predictions at points time (before during limb motion)...

This paper uses physiological measurements to estimate human workload and effort in physical human–robot interaction. Ten subjects performed 19 consecutive task periods using the ARMin robot while difficulty was varied along two scales. Three modalities were measured: electroencephalography, autonomic nervous system (ANS) responses (electrocardiography, skin conductance, respiration, temperature) eye tracking. After each period, reference values collected NASA Task Load Index. Machine...

Among the methods used to increase enjoyment and performance in serious games, reward schedules, i.e., determining when in-game rewards should be given, have not been sufficiently explored. In present study, we designed a simple memory training game compared two of scheduling rewards, both based on paradigm positive reinforcement: fixed ratio schedule, which were given after number correct responses, variable an unpredictable responses. To account for variability player preference...

Drivers' hazardous physical and mental states (e.g. distraction, fatigue, stress high workload) have a major effect on driving performance strongly contribute to 25-50% of all traffic accidents. They are caused by numerous factors, such as cell phone use or lack sleep. However, while significant research has been done detecting states, most studies not tried identify the causes states. Such information would be very useful, it allow intelligent vehicles better respond detected state. Thus,...

This paper presents a new approach to benchmarking brain-computer interfaces (BCIs) outside the lab. A computer game was created that mimics real-world application of assistive BCIs, with main outcome metric being time needed complete game. used at Cybathlon 2016, competition for people disabilities who use technology achieve tasks. The summarizes technical challenges describes design game, then rules acceptable hardware, software and inclusion human pilots in BCI Cybathlon. 11 participating...