Giovanni Mezzina

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.

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.

Brain-computer interface using P300: a gaming approach for neurocognitive impairment diagnosis

This paper proposes a novel mobile healthcare system for remotely monitoring neuro-cognitive functions of impaired subjects and proposing possible treatments. Currently, only hospital centers perform similar analyses through fixed and wired electroencephalography (EEG) inspection. The solution proposed here works wirelessly and improves its accuracy learning by performances of the subject playing a game/test. The system is based on spatio-temporal detection and characterization of a specific brain potential named P300. It includes: i) a wearable wireless EEG device; ii) a gateway (tablet or smartphone) processing gathered data, also providing the test/game to the user. Given the above hardware settings, a new algorithm, named tuned-Residue Iteration Decomposition (t-RIDE), provides spatiotemporal features of P300s and a semantic-based reasoner allows taking into account factors which could modify the test if performed in non-standard conditions. The system has been adopted with 12 subjects involved in three different cognitive tasks with increasing difficulty. Fast diagnosis of cognitive deficits is reached, including mild and heavy impairments cases: t-RIDE processing is performed in 1.95s (after 79 iterations for convergence) whereas semantic matchmaking routine requires 2.5ms in the worst case. A case study for an Alzheimer injured patient is reported to corroborate and clarify the proposed approach.

Gait analysis and quantitative drug effect evaluation in Parkinson disease by jointly EEG-EMG monitoring

This work addresses the rising need for a diagnostic tool for the evaluation of the effectiveness of a drug treatment in Parkinson disease, allowing the physician to monitor of the patient gait at home and to shape the treatment on the individual peculiarity. In aim, we present a cyber-physical system for real-time processing EEG and EMG signals. The wearable and wireless system extracts the following indexes: (i) typical activation and deactivation timing of single muscles and the duty cycle in a single step (ii) typical and maximum co-contractions, as well as number of co-contraction/s. The indexes are validated by using Movement Related Potentials (MRPs). The signal processing stage is implemented on Altera Cyclone V FPGA. In the paper, we show in vivo measurements by comparing responses before and after the drug (Levodopa) treatment. The system quantifies the effect of the Levodopa treatment detecting: (i) a 17% reduction in typical agonist-antagonist co-contractions time (ii) 23.6% decrease in the maximum co-contraction time (iii) 33% decrease in number of critical co-contraction. Brain implications shows a mean reduction of 5% on the evaluated potentials.

An embedded system remotely driving mechanical devices by P300 brain activity

In this paper we present a P300-hased Brain Computer Interface (BCI) for the remote control of a mechatronic actuator, such as wheelchair, or even a car, driven by EEG signals to be used hy tetraplegic and paralytic users or just for safe drive in case of car. The P300 signal, an Evoked Related Potential (ERP) devoted to the cognitive brain activity, is induced for purpose by visual stimulation. The EEG data are collected by 6 smart wireless electrodes from the parietal-cortex area and online classified by a linear threshold classifier, basing on a suitable stage of Machine Learning (ML). The ML is implemented on a μPC dedicated to the system and where the data acquisition and processing is performed. The main improvement in remote driving car by EEG, regards the approach used for the intentions recognition. In this work, the classification is based on the P300 and not just on the average of more not well identify potentials. This approach reduces the number of electrodes on the EEG helmet. The ML stage is based on a custom algorithm (t-RIDE) which tunes the following classification stage on the users “cognitive chronometry”. The ML algorithm starts with a fast calibration phase (just ∼190s for the first learning). Furthermore, the BCI presents a functional approach for time-domain features extraction, which reduces the amount of data to be analyzed, and then the system response times. In this paper, a proof of concept of the proposed BCI is shown using a prototype car, tested on 5 subjects (aged 26 ± 3). The experimental results show that the novel ML approach allows a complete P300 spatio-temporal characterization in 1.95s using 38 target brain visual stimuli (for each direction of the car path). In free-drive mode, the BCI classification reaches 80.5 ± 4.1% on single-trial detection accuracy while the worst-case computational time is 19.65ms ± 10.1. The BCI system here described can be also used on different mechatronic actuators, such as robots.

Real-time muscle fiber conduction velocity tracker for diabetic neuropathy monitoring

This paper describes the architecture of a wearable, wireless embedded system for the Diabetic Peripheral Neuropathy (DPN) assessment in ordinary dynamic movements, such as a fluid gait. In this context, the EMG analysis can provide information about the nerves status by estimating the linked Muscle Fiber Conduction Velocity (MFCV). The system operates with synchronized and digitized data samples from 4 EMG channels, which are positioned on each leg of the person under test, exploiting the guidelines provided by an embedded positional scanning algorithm. This work presents a novel algorithm for the estimation of MFCV that is based on the classic 2-electrodes comparative measurement principle. The system uses dynamic thresholds bit-stream conversion of the EMG signals and a low computational solution for the implementation of the bitstream cross-correlator. The entire system fully operates on Altera Cyclone V FPGA. The experimental results on 3 subjects demonstrate the ability of the proposed method for matching the physiological MFCV values, as reported in medical literature. In particular, comparing the medical values, obtained in controlled environments, with the system extracted MFCV, in the same experimental conditions: the absolute error is, on average, 0.2m/s. The system returns a probability of invalid real-time measures below of 4% (worst case).

Wearable platform for automatic recognition of Parkinson Disease by muscular implication monitoring

The need for diagnostic tools for the characterization of progressive movement disorders — as the Parkinson Disease (PD) — aiming to early detect and monitor the pathology is getting more and more impelling. The parallel request of wearable and wireless solutions, for the real-time monitoring in a non-controlled environment, has led to the implementation of a Quantitative Gait Analysis platform for the extraction of muscular implications features in ordinary motor action, such as gait. The here proposed platform is used for the quantification of PD symptoms. Addressing the wearable trend, the proposed architecture is able to define the real-time modulation of the muscular indexes by using 8 EMG wireless nodes positioned on lower limbs. The implemented system “translates” the acquisition in a 1-bit signal, exploiting a dynamic thresholding algorithm. The resulting 1-bit signals are used both to define muscular indexes both to drastically reduce the amount of data to be analyzed, preserving at the same time the muscular information. The overall architecture has been fully implemented on Altera Cyclone V FPGA. The system has been tested on 4 subjects: 2 affected by PD and 2 healthy subjects (control group). The experimental results highlight the validity of the proposed solution in Disease recognition and the outcomes match the clinical literature results.

Spatio-Temporal Optimization of Perishable Goods’ Shelf Life by a Pro-Active WSN-Based Architecture

The waste in the perishable goods supply-chain has prompted many global organizations (e.g., FAO and WHO), to develop the Hazard Analysis and Critical Control Points (HACCP) protocol that ensures a high degree of food quality, minimizing the losses in all the stages of the farm-to-fork chain. It has been proven that good warehouse management practices improve the average life of perishable goods. The advances in wireless sensors network (WSN) technology offers the possibility of a “smart” storage organization. In this paper, a low cost reprogrammable WSN-based architecture for functional warehouse management is proposed. The management is based on the continuous monitoring of environmental parameters (i.e., temperature, light exposure and relative humidity), and on their combination to extract a spatial real-time prediction of the product shelf life. For each product, the quality decay is computed by using a 1st order kinetic Arrhenius model to the whole storage site area. It strives to identify, in a way compatible with the other products’ shelf lives, the position within the warehouse that maximizes the food expiration date. The shelf life computing and the “first-expired first-out” logistic problem are entrusted to a Raspberry Pi-based central unit, which manages a set of automated pallet transporters for the displacement of products, according to the computed shelf lives. The management unit supports several commercial light/temperature/humidity sensor solutions, implementing ZigBee, Bluetooth and HTTP-request interfaces. A proof of concept of the presented pro-active WSN-based architecture is also shown. Comparing the proposed monitoring system for the storage of e.g., agricultural products, with a typical one, the experimental results show an improvement of the expected expiration date of about 1.2 ± 0.5 days, for each pallet, when placed in a non-refrigerated environment. In order to stress the versatility of the WSN solution, a section is dedicated to the implemented system user interfaces that highlight detecting critical situations and allow timely automatic or human interventions, minimizing the latter.

FPGA Implementation of a Single Step MFCV Estimator Based on EMG in Diabetic Neuropathy

This paper details the design and the hardware implementation of a real-time diagnostic system based on FPGA for the muscle fibre conduction velocity estimation (MFCV). The MFCV is considered as a principal monitoring index for diabetic neuropathy (DPN), as well as in muscle fatigue assessment, to evaluate the muscle fibre status. The FPGA platform evaluates the MFCV during dynamic contractions (e.g., gait), by exploiting a multichannel sensing system composed of 4 wireless surface EMG electrodes, placed in pair on each leg. Raw data are digitized and made binary to create two bitstreams for each monitored limb. Then, a comparison between the two-bit streamed EMGs extracted from the same leg is carried out. The comparison, which allows extracting the MFCV, exploits a computationally light version of the cross-correlation method. The overall architecture implemented and validated on an Altera Cyclone V FPGA is HPS-free and exploits 22.5% ALMs, 10,874 ALUTs, 9.81% registers, 3.36% block memory, and subjects evaluated). On average, the same MFCV estimation has been extracted on 1184/1250 contractions (standard deviation of 11 contractions), reaching an accuracy of 94.7%. These estimations fully match the physiological value range reported in literature.

Real-time P300-based BCI in mechatronic control by using a multi-dimensional approach

This study presents a P300-based brain-computer interface (BCI) for mechatronic device driving, i.e. without the need for any physical control. The technique is based on a machine learning (ML) algorithm, which exploits a spatio-temporal characterization of the P300, analyses all the discrimination scenarios through a multiclass classification problem. The BCI is composed of the acquisition unit, the processing unit and the navigation unit. The acquisition unit is a wireless 32-channel electroencephalography headset collecting data from six electrodes. The processing unit is a dedicated µPC performing stimuli delivery, ML and classification, leading to the user intention interpretation. The ML stage is based on a custom algorithm (tuned residue iteration decomposition) which trains the classifier on the user-tuned P300 features. The extracted features undergo a dimensionality reduction and are used to define decision boundaries for the real-time classification. The real-time classification performs a functional approach for the features extraction, reducing the amount of data to be analyzed. The Raspberry-based navigation unit actuates the received commands, supporting the wheelchair motion. The experimental results, based on a dataset of seven subjects, demonstrate that the classification chain is performed in 8.16 ms with an accuracy of 84.28 ± 0.87%, allowing the real-time control of the wheelchair.