Search

IntroductionEither non-invasive somatotopic or substitute sensory feedback is capable of conveying a single modality of sensory information from prosthetic hands to amputees. However, the neurocognitive ability of amputees to integrate multi-modality sensory information for functional discrimination is unclear. The purpose of this study was to assess the fusion of non-invasive somatotopic tactile and substitute aperture feedbacks for profile perception of multiple physical features during grasping objects.MethodsTwo left transradial amputees with somatotopic evoked tactile sensation (ETS) of five fingers participated in the study. The tactile information of prosthetic hand was provided to amputees by the ETS feedback elicited on the stump projected finger map. Hand aperture information was conveyed to amputees with substitute electrotactile stimulation on the forearm or upper arm. Two types of sensory feedback were integrated to a commercial prosthetic hand. The efficacy of somatotopic ETS feedback on object length identification task was assessed with or without substitute aperture stimulation. The object size identification task was utilized to assess how ETS stimulation at the stump may affect aperture perception with stimulation on the ipsilateral upper arm or forearm. Finally, the task of identifying combined length and size was conducted to evaluate the ability of amputees to integrate the dual modalities of sensory feedback for perceiving profile features.ResultsThe study revealed that amputee subjects can effectively integrate the ETS feedback with electrotactile substitutive feedback for object profile discrimination. Specifically, ETS was robust to provide object length information with electrotactile stimulation at either the forearm or upper arm. However, electrotactile stimulation at the upper arm for aperture perception was less susceptible to the interference of ETS stimulation than at the forearm.DiscussionAmputee subjects are able to combine somatotopic ETS and aperture feedbacks for identifying multi-dimensional features in object profiling. The two sensory streams of information can be fused effectively without mutual interference for functional discrimination.

Restoring locomotion functionality of transfemoral amputees is essential for early rehabilitation treatment and for preserving mobility and independence in daily life. Research in wearable robotics fostered the development of innovative active mechatronic lower-limb prostheses designed with the goal to reduce the cognitive and physical effort of lower-limb amputees in rehabilitation and daily life activities. To ensure benefits to the users, active mechatronic prostheses are expected to be aware of the user intention and properly interact in a closed human-in-the-loop paradigm. In the state of the art various cognitive interfaces have been proposed to online decode the user's intention. Electromyography in combination with mechanical sensing such as inertial or pressure sensors is a widely adopted solution for driving active mechatronic prostheses. In this framework, researchers also explored targeted muscles re-innervation for an objective-oriented surgical amputation promoting wider usability of active prostheses. However, information kept by the neural component of the cognitive interface deteriorates in a prolonged use scenario due to electrodes-related issues, thereby undermining the correct functionality of the active prosthesis. The objective of this work is to present a novel controller for an active transfemoral prosthesis based on whole body awareness relying on a wireless distributed non-invasive sensory apparatus acting as cognitive interface. A finite-state machine controller based on signals monitored from the wearable interface performs subject-independent intention detection of functional tasks such as ground level walking, stair ascent, and sit-to-stand maneuvres and their main sub-phases. Experimental activities carried out with four transfemoral amputees (among them one dysvascular) demonstrated high reliability of the controller capable of providing 100% accuracy rate in treadmill walking even for weak subjects and low walking speeds. The minimum success rate was of 94.8% in performing sit-to-stand tasks. All the participants showed high confidence in using the transfemoral active prosthesis even without training period thanks to intuitiveness of the whole body awareness controller.

Restoring locomotion functionality of transfemoral amputees is essential for early rehabilitation treatment and for preserving mobility and independence in daily life. Research in wearable robotics fostered the development of innovative activemechatronic lower-limb prostheses designed with the goal to reduce the cognitive and physical effort of lower-limb amputees in rehabilitation and daily life activities. To ensure benefits to the users, active mechatronic prostheses are expected to be aware of the user intention and properly interact in a closed human-in-the-loop paradigm. In the state of the art various cognitive interfaces have been proposed to online decode the user's intention. Electromyography in combination with mechanical sensing such as inertial or pressure sensors is a widely adopted solution for driving active mechatronic prostheses. In this framework, researchers also explored targeted muscles re-innervation for an objective-oriented surgical amputation promoting wider usability of active prostheses. However, information kept by the neural component of the cognitive interface deteriorates in a prolonged use scenario due to electrodes-related issues, thereby undermining the correct functionality of the active prosthesis. The objective of this work is to present a novel controller for an active transfemoral prosthesis based on whole body awareness relying on a wireless distributed non-invasive sensory apparatus acting as cognitive interface. A finite-state machine controller based on signals monitored from the wearable interface performs subject-independent intention detection of functional tasks such as ground level walking, stair ascent, and sit-to-stand maneuvres and their main sub-phases. Experimental activities carried out with four transfemoral amputees (among them one dysvascular) demonstrated high reliability of the controller capable of providing 100%accuracy rate in treadmill walking even for weak subjects and low walking speeds. The minimum success rate was of 94.8% in performing sit-to-stand tasks. All the participants showed high confidence in using the transfemoral active prosthesis even without training period thanks to intuitiveness of the whole body awareness controller. [ABSTRACT FROM AUTHOR]

Deep Belief Networks (DBNs) have recently shown impressive performance on a broad range of classification problems. Their generative properties allow better understanding of the performance, and provide a simpler solution for sensor fusion tasks. However, because of their inherent need for feedback and parallel update of large numbers of units, DBNs are expensive to implement on serial computers. This paper proposes a method based on the Siegert approximation for Integrate-and-Fire neurons to map an offline-trained DBN onto an efficient event-driven spiking neural network suitable for hardware implementation. The method is demonstrated in simulation and by a real-time implementation of a 3-layer network with 2694 neurons used for visual classification of MNIST handwritten digits with input from a 128x128 Dynamic Vision Sensor (DVS) silicon retina, and sensory-fusion using additional input from a 64-channel AER-EAR silicon cochlea. The system is implemented through the open-source software in the jAER project and runs in real-time on a laptop computer. It is demonstrated that the system can recognize digits in the presence of distractions, noise, scaling, translation and rotation, and that the degradation of recognition performance by using an event-based approach is less than 1%. Recognition is achieved in an average of 5.8 ms after the onset of the presentation of a digit. By cue integration from both silicon retina and cochlea outputs we show that the system can be biased to select the correct digit from otherwise ambiguous input.

Deep Belief Networks (DBNs) have recently shown impressive performance on a broad range of classification problems. Their generative properties allow better understanding of the performance, and provide a simpler solution for sensor fusion tasks. However, because of their inherent need for feedback and parallel update of large numbers of units, DBNs are expensive to implement on serial computers. This paper proposes a method based on the Siegert approximation for Integrate-and-Fire neurons to map an offline-trained DBN onto an efficient event-driven spiking neural network suitable for hardware implementation. The method is demonstrated in simulation and by a real-time implementation of a 3-layer network with 2694 neurons used for visual classification of MNIST handwritten digits with input from a 128 × 128 Dynamic Vision Sensor (DVS) silicon retina, and sensoryfusion using additional input from a 64-channel AER-EAR silicon cochlea. The system is implemented through the open-source software in the jAER project and runs in real-time on a laptop computer. It is demonstrated that the system can recognize digits in the presence of distractions, noise, scaling, translation and rotation, and that the degradation of recognition performance by using an event-based approach is less than 1%. Recognition is achieved in an average of 5.8 ms after the onset of the presentation of a digit. By cue integration from both silicon retina and cochlea outputs we show that the system can be biased to select the correct digit from otherwise ambiguous input. [ABSTRACT FROM AUTHOR]