Search

Piezoelectric transducers can be used to both harvest biomechanical energy and to detect gait cycle events. Several designing factors influence the efficiency of the energy harvesting system, such as the location of the transducers, their mechanical/electrical parameters and the correct matching of the load resistor. In this research, a piezoelectric polyvinylidene fluoride (PVDF) film — LDT4-028k — is simultaneously used as energy harvester for recovering energy associated with human walking, and as an active sensor to detect stance and swing phases of human gait. The PVDF transducer was placed on the back of the knee through an elastic cotton leotard, which allowed obtaining an output power of 1.45 μW during walking. Moreover, we presented a patterns' comparison between the signals of the PVDF transducer with a gyroscope. By using the output signal of the PVDF transducer we were able to distinguish the two phases of gait cycle with a difference in time of about 15 ms as compared to the events estimated through a gyroscope placed on the shank.

We propose an event-based dynamic segmentation technique for the classification of locomotion activities, able to detect the mid-swing, initial contact and end contact events. This technique is based on the use of a shank-mounted inertial sensor incorporating a tri-axial accelerometer and a tri-axial gyroscope, and it is tested on four different locomotion activities: walking, stair ascent, stair descent and running. Gyroscope data along one component are used to dynamically determine the window size for segmentation, and a number of features are then extracted from these segments. The event-based segmentation technique has been compared against three different fixed window size segmentations, in terms of classification accuracy on two different datasets, and with two different feature sets. The dynamic event-based segmentation showed an improvement in terms of accuracy of around 5% (97% vs. 92% and 92% vs. 87%) and 1-2% (89% vs. 87% and 97% vs. 96%) for the two dataset, respectively, thus confirming the need to incorporate an event-based criterion to increase performance in the classification of motion activities.

Eight elderly adults were requested to perform circle movements with the hand through a commercial haptic platform, in two different conditions: with visual feedback, and with a facilitating force field produced by the machine. A measure of movement regularity (the mean square jerk in its normalized form) were captured to determine the effect of these feedbacks on hand kinematics. Regularity was higher when haptics feedback was given alone (MSJratio 6.48 +/- 0.15), as compared to combining it with visual feedback (MSJratio 7.46 +/- 0.18). We interpreted these differences as the ability to process visual information in trajectory tracking conditions as higher than the one to cope with external force fields, also when provided as a hypothetically facilitating one.

"Eight elderly adults and eight young adults were requested to perform circular movements with the hand through a commercial haptic platform, under different conditions in an ecological setting: with visual feedback, and with a force field produced by the machine. Measures of kinematics and movement regularity (maximum velocity, duration, mean square jerk, and its normalized form) were captured to determine the effect of these feedbacks on hand kinematics. In the elderly group, regularity was lower when haptic feedback was given in combination with visual feedback as compared to providing haptic feedback alone. This effect appeared also in the group of young adults, and outlines the possibility that the ability to integrate different feedbacks may need more time to be learned, even if the feedbacks are generated to facilitate movements."

Heart disease diagnosis is considered as one of the complicated tasks in medical field. In order to perform heart disease diagnosis an accurate and efficient automation system can be very helpful. In this research, we propose a classifier ensemble method to improve the decision of the classifiers for heart disease diagnosis. Homogeneous ensemble is applied for heart disease classification and finally results are optimized by using Genetic algorithm. Data is evaluated by using 10-fold cross validation and performance of the system is evaluated by classifiers accuracy, sensitivity and specificity to check the feasibility of our system. Comparison of our methodology with existing ensemble technique has shown considerable improvements in terms of classification accuracy.