Low cost gaze estimation: knowledge-based solutions.

Eye tracking technology in low resolution scenarios is not a completely solved issue to date. The possibility of using eye tracking in a mobile gadget is a challenging objective that would permit to spread this technology to non-explored fields. In this paper, a knowledge based approach is presented to solve gaze estimation in low resolution settings. The understanding of the high resolution paradigm permits to propose alternative models to solve gaze estimation. In this manner, three models are presented: a geometrical model, an interpolation model and a compound model, as solutions for gaze estimation for remote low resolution systems. Since this work considers head position essential to improve gaze accuracy, a method for head pose estimation is also proposed. The methods are validated in an optimal framework, I2Head database, which combines head and gaze data. The experimental validation of the models demonstrates their sensitivity to image processing inaccuracies, critical in the case of the geometrical model. Static and extreme movement scenarios are analyzed showing the higher robustness of compound and geometrical models in the presence of user's displacement. Accuracy values of about 3° have been obtained, increasing to values close to 5° in extreme displacement settings, results fully comparable with the state-of-the-art.

Dual Task Gait Performance in Frail Individuals with and without Mild Cognitive Impairment.

BACKGROUND: Several studies have stated that frailty is associated with cognitive impairment. Based on various studies, cognition impairment has been considered as a component of frailty. Other authors have shown that physical frailty is associated with low cognitive performance. Dual task gait tests are used as a strong predictor of falls in either dementia or frailty. Consequently, it is important to investigate dual task walking tests in elderly populations including control robust oldest old, frail oldest old with mild cognitive impairment (MCI) and frail oldest old without MCI. METHODS: Dual task walking tests were carried out to examine the association between frailty and cognitive impairment in a population with advanced age. Forty-one elderly men and women participated in this study. The subjects from control, frail with MCI and frail without MCI groups, completed the 5-meter walk test at their own gait velocity. Arithmetic and verbal dual task walking performance was also assessed. Kinematic data were acquired from a unique tri-axial inertial sensor. RESULTS: The spatiotemporal and frequency parameters related to gait disorders did not show any significant differences between frail with and without MCI groups. CONCLUSIONS: The evaluation of these parameters extracted from the acceleration signals led us to conclude that these results expand the knowledge regarding the common conditions in frailty and MCI and may highlight the idea that the impairment in walking performance does not depend of frailty and cognitive status.

Gait Variability Related to Muscle Quality and Muscle Power Output in Frail Nonagenarian Older Adults.

BACKGROUND: Frailty has become the center of attention of basic, clinical, and demographic research because of its incidence level and the gravity of adverse outcomes with age. Moreover, with advanced age, motor variability increases, particularly in gait. Muscle quality and muscle power seem to be closely associated with performance on functional tests in frail populations. Insight into the relationships among muscle power, muscle quality, and functional capacity could improve the quality of life in this population. In this study, the relationship between the quality of the muscle mass and muscle strength with gait performance in a frail population was examined. METHODS: Twenty-two institutionalized frail elderly individuals (93.1 ± 3.6) participated in this study. Muscle quality was measured by segmenting areas of high- and low-density fibers as observed in computed tomography images. The assessed functional outcomes were leg strength and power, velocity of gait, and kinematic gait parameters obtained from a tri-axial inertial sensor. FINDINGS: Our results showed that a greater number of high-density fibers, specifically those of the quadriceps femoris muscle, were associated with better gait performance in terms of step time variability, regularity, and symmetry. Additionally, gait variability was associated with muscle power. In contrast, no significant relationship was observed between gait velocity and either muscle quality or muscle power. INTERPRETATION: Gait pattern disorders could be explained by a deterioration of the lower limb muscles. It is known that an impaired gait is an important predictor of falls in older populations; thus, the loss of muscle quality and power could underlie the impairments in motor control and balance that lead to falls and adverse outcomes.

Frailty assessment based on trunk kinematic parameters during walking.

BACKGROUND: Physical frailty has become the center of attention of basic, clinical and demographic research due to its incidence level and gravity of adverse outcomes with age. Frailty syndrome is estimated to affect 20 % of the population older than 75 years. Thus, one of the greatest current challenges in this field is to identify parameters that can discriminate between vulnerable and robust subjects. Gait analysis has been widely used to predict frailty. The aim of the present study was to investigate whether a collection of parameters extracted from the trunk acceleration signals could provide additional accurate information about frailty syndrome. METHODS: A total of 718 subjects from an elderly population (319 males, 399 females; age: 75.4 ± 6.1 years, mass: 71.8 ± 12.4 kg, height: 158 ± 6 cm) volunteered to participate in this study. The subjects completed a 3-m walk test at their own gait velocity. Kinematic data were acquired from a tri-axial inertial orientation tracker. FINDINGS: The spatio-temporal and frequency parameters measured in this study with an inertial sensor are related to gait disorders and showed significant differences among groups (frail, pre-frail and robust). A selection of those parameters improves frailty classification obtained to gait velocity, compared to classification model based on gait velocity solely. INTERPRETATION: Gait parameters simultaneously used with gait velocity are able to provide useful information for a more accurate frailty classification. Moreover, this technique could improve the early detection of pre-frail status, allowing clinicians to perform measurements outside of a laboratory environment with the potential to prescribe a treatment for reversing their physical decline.