Valerio F. Annese

Designing a Cyber–Physical System for Fall Prevention by Cortico–Muscular Coupling Detection

The authors present wearable noninvasive electronics that prevent a human from falling. It deducts a probable fall from EEG and EMG information and provides a real-time alarm signal for protection.

Gait analysis for fall prediction using EMG triggered movement related potentials

Abnormal gait is an usual feature in neurodegenerative disease (i.e.: Huntington Chorea, Parkinson and Alzheimer), while the capability to maintain a stable posture and fluid walking is progressive impaired in aging. Monitoring and correcting the insurgence of abnormal dynamic balance opens new scenarios in the cure of these diseases and falls prevention. In this work, we present a study based on EEG time-frequency analysis to identify the correlation between synchronized EEG and EMG signals for gait analysis. Several tools for gait analysis are developed and experimented i.e. EMG trigger generation with dynamic threshold, EMG co-contraction, EEG movement related potentials (MRPs) and EEG event related desynchronizations (ERDs). This work particularly focus on gait analysis indexes implementation and experimentally obtained results based on a large dataset, including different type of gait i.e. normal gait, perturbed gait and gait during a second cognitive task (DT). A weighted average on the calculated indexes are exploited to quantify the falling risk.

Remote Neuro-Cognitive Impairment Sensing Based on P300 Spatio-Temporal Monitoring

A novel mobile healthcare solution for remotely monitoring neuro-cognitive efficiency is here presented. The method is based on the spatio-temporal characterization of a specific event-related potential, called P300, induced in our brain by a target stimulus. P300 analysis is used as a biomarker: the amplitude and latency of the signal are quality indexes of the brain activity. Up to now, the P300 characterization has been performed in hospital through EEG analysis and it has not been experimented an algorithm that can work remotely and learn from the subject performance. The proposed m-health service allows remote EEG monitoring of P300 through a “plug and play” system based on the video game reaction of the subject under test. The signal processing is achieved by tuned residue iteration decomposition (t-RIDE). The methodology has been tested on the parietal-cortex area (Pz, Fz, and Cz) of 12 subjects involved in three different cognitive tasks with increasing difficulty. For the set of considered subjects, a P300 deviation has been detected: the amplitude ranges around 2.8-8 μV and latency around 300-410 ms. To demonstrate the improvement achieved by the proposed algorithm respect the state of the art, a comparison between t-RIDE, RIDE, independent component analysis (ICA) approaches, and grand average method is here reported. t-RIDE and ICA analyses report the same results (0.1% deviation) using the same data set (game with a detection of 40 targets). Nevertheless, t-RIDE is 1.6 times faster than ICA since converges in 79 iterations (i.e., t-RIDE: 1.95s against ICA: 3.1s). Furthermore, t-RIDE reaches 80% of accuracy after only 13 targets (task time can be reduced to 65s); differently from ICA, t-RIDE can be performed even on a single channel. The procedure shows fast diagnosis capability in cognitive deficit, including mild and heavy cognitive impairment.

FPGA based architecture for fall-risk assessment during gait monitoring by synchronous EEG/EMG

One out of three subjects older than 65 years falls. Despite extensive research, existing assessment tools for fall risk have been insufficient for predicting falls since the phenomenology is complex and there is no equipment on the market that allows everyday life monitoring. In this paper we present a novel approach for fall-risk on-line assessment based on: i) clinical condition of the subject, ii) environmental conditions, iii) electromyographic (EMG) co-contraction analysis and iv) electroencephalographic (EEG) analysis based on Movement Related Potentials (MRPs) and μ-rhythm event related desynchronizations (μ-ERDs) occurrence. This fall-risk assessment approach is implemented by a complete cyber-physical system made up by EEG and EMG wearable recording systems interfaced to an FPGA on-line performing the needed real-time processing for indexes extraction. The results present a fall-risk assessment case study on healthy subjects walking showing detectable fall-risk increasing (+1.5%) when obstacles are overcome.

A digital processor architecture for combined EEG/EMG falling risk prediction

The brain signal anticipates the voluntary movement with patterns that can be detected even 500ms before the occurrence. This paper presents a digital signal processing unit which implements a real-time algorithm for falling risk prediction. The system architecture is designed to operate with digitized data samples from 8 EMG (limbs) and 8 EEG (motor-cortex) channels and, through their combining, provides 1 bit outputs for the early detection of unintentional movements. The digital architecture is validated on an FPGA to determine resources utilization, related timing constraints and performance figures of a dedicated real-time ASIC implementation for wearable applications. The system occupies 85.95% ALMs, 43283 ALUTs, 73.0% registers, 9.9% block memory of an Altera Cyclone V FPGA for a processing latency lower than 1ms. Outputs are available in 56ms, within the time limit of 300ms, enabling decision taking for active control. Comparisons between Matlab (used as golden reference) and measured FPGA outputs outline a very low residual numerical error of about 0.012% (worst case) despite the higher float precision of Matlab simulations and losses due to mandatory dataset conversion for validation.

Fall-risk assessment by combined movement related potentials and co-contraction index monitoring

In this paper we propose a novel approach for online fall-risk assessment based on concurrent EEG and EMG monitoring. The fall-risk evaluation is based on: i) clinical condition of the individual, ii) environment, iii) EMG agonist-antagonist co-contraction analysis and iv) Movement Related Potentials and event related desynchronizations occurrence/absence. The fall-risk assessment evaluation algorithm has been implemented on a FPGA (Altera Cyclone V SE 5CSEMA5F31C6N) in order to realize an autonomous and stand-alone fall prevention tool. The experimental results (based on a dataset of 10 individuals) are described and demonstrate the validity of the algorithm and its FPGA implementation, which responds in 41ms, well within the 300ms time limit according to a study on 45 fallers and 80 non-fallers (with 74 years average age).

Combining EEG and EMG Signals in a Wireless System for Preventing Fall in Neurodegenerative Diseases

We present an innovative wireless wearable, low power, noninvasive neuroprosthetic system that is geared towards detecting and preventing falls. The system allows continuous monitoring of EEG/EMG, detecting in particular pre-motor potentials to prevent falls of elder and motor-impaired patients by introducing a feedback action to stabilize gait.

The truth machine of involuntary movement: FPGA based cortico-muscular analysis for fall prevention

Voluntary movements are managed by movement related potentials (MRPs) which are brain activity patterns detectable even 500ms before the movement itself. The cortico-muscular matching between brain (EEG) and muscles (EMG) activity allows the assessment of the intentionality of the performed movement. Basing on this knowledge, a real-time algorithm for falling risk prediction based on EMG/EEG coupled analysis is presented. The system architecture involves 8 EMG (limbs) and 8 EEG (motor-cortex) channels wirelessly collected by a FPGA (gateway) that contextually performs the real-time processing based on an event triggered time-frequency approach. The digital architecture is validated on the FPGA to determine resources utilization, related timing constraints and performance figures of a dedicated real-time ASIC implementation for wearable applications. The system resource utilization is 85.95% ALMs, 43283 ALUTs, 73.0% registers, 9.9% block memory of an Altera Cyclone V FPGA. The processing latency is lower than 1ms and the output are available in 56ms, respecting the time limit of 300ms. Outputs enables decision-taking for feedback delivering.

The ultimate IoT application: A cyber-physical system for ambient assisted living

We propose a novel approach that integrates wireless, non-invasive devices with fast, real-time algorithms for large data analysis and biofeedback reaction, to discern the voluntariness of human movement through direct sensing of brain potentials combined with muscular action signal monitoring. The system has been tested in real situations.

Towards mobile health care: Neurocognitive impairment monitoring by BCI-based game

A mobile-health solution for neuro-cognitive impairment monitoring based on P300 spatio-temporal characterization achieved by tuned Residue Iteration Decomposition (t-RIDE) is here presented. It allows remote monitoring of neuro-cognitive impairment through a domestic game-test by physician which can interact with it. Data collection is allowed by cloud bridging. It has been validated on 10 subjects: P300 amplitude and latency ranges are 2.8pV-8pV and 300ms-410ms (on Pz, Fz, Cz, EEG electrodes) in total agreement with the medical references. The methodology shows fast diagnosis of cognitive deficit, including mild and heavy cognitive impairment: t-RIDE convergence is reached in 79 iteration (i.e. 1.95s) giving 80% accuracy in P300 amplitude evaluation with only 13 trials on a single EEG channel.