Giuseppe Andreoni

A robust and self-paced BCI system based on a four class SSVEP paradigm: algorithms and protocols for a high-transfer-rate direct brain communication

In this paper, we present, with particular focus on the adopted processing and identification chain and protocol-related solutions, a whole self-paced brain-computer interface system based on a 4-class steady-state visual evoked potentials (SSVEPs) paradigm. The proposed system incorporates an automated spatial filtering technique centred on the common spatial patterns (CSPs) method, an autoscaled and effective signal features extraction which is used for providing an unsupervised biofeedback, and a robust self-paced classifier based on the discriminant analysis theory. The adopted operating protocol is structured in a screening, training, and testing phase aimed at collecting user-specific information regarding best stimulation frequencies, optimal sources identification, and overall system processing chain calibration in only a few minutes. The system, validated on 11 healthy/pathologic subjects, has proven to be reliable in terms of achievable communication speed (up to 70 bit/min) and very robust to false positive identifications.

A Wearable Home BCI system: preliminary results with SSVEP protocol

This paper presents and discusses the realization and the performances of a wearable system for EEG-based BCI applications. The system (called Kimera) consists of a two-layer hardware architecture (the wireless acquisition and transmission board based on a BluetoothregARM chip, and a low power miniaturized biosignal acquisition analog front end) together with a software suite (called Bellerophonte) for the graphic user interface management, protocol execution, data recording, transmission and processing. The implemented BCI system was based on the SSVEP protocol, applied to a two state selection by using standards display/monitor with a couple of high efficiency LEDs. The frequency features of the signal were computed and used in the intention detection. The BCI algorithm is based on a supervised classifier implemented through a multi-class canonical discriminant analysis (CDA) with a continuous real-time feedback based on the mahalanobis distance parameter. Five healthy subjects participated in the first phase for a preliminary device validation. The obtained results are very interesting and promising, being lined out to the most recent performance reported in literature with a significant improvement both in system and in classification capabilities. The user-friendliness and low cost of the Kimera & Bellerophonte platform make it suitable for the development of home BCI applications

Modeling and driving a reduced human mannequin through motion captured data: a neural network approach

One of the major problems which arises in the field of virtual design is the realization of virtual mannequins able to move in a human like way. This work focuses on the analysis of the human sitting working posture, which is described by a 30-DOF mannequin, modeling the upper part of the body (pelvis, trunk, arms, and head). Trajectories formation in point to point reaching movements represents the main topic. Our approach is based on the acquisition of real human kinematics data, collected by means of an automatic motion analyzer. Starting from the kinematics database of one subject, sit in front of a desk, a neural network was trained in order to generate the movements of the virtual mannequin. The work is divided into four parts: mannequin modeling, 3D human data collection, data preprocessing according to the biomechanical model, and design and training of a multilayer perceptron neural network.

A four command BCI system based on the SSVEP protocol.

This paper discusses the development of a four command BCI system. This system is composed of a wearable electroencephalogram acquisition unit interfaced to a computer by a wireless Bluetoothreg (BT) connection. The implemented system relies on the steady-state visual evoked potential (SSVEP) protocol applied to a four selection system. In order to achieve the maximum reliability against false positives a five class classifier was used considering the idle state as an independent class. In order to maximize the usability of the system a two channel solution was tested and adopted. The BCI algorithm was based on a supervised multi-class classifier implemented by combining different binary regularized linear discriminant analysis (RLDA) classifiers. The biofeedback was evaluated by combining the resultant time signed distance with quality index related to the number of coherent identification obtained with the one-vs-all approach

Prototype of a wearable system for remote fetal monitoring during pregnancy

Fetal Heart Rate (FHR) monitoring gives important information about the fetus health state during pregnancy. This paper presents a new prototype for remote fetal monitoring. The device will allow to monitor FHR in a domiciliary context and to send fetal ECG traces to a hospital facility, where clinicians can interpret them. In this way the mother could receive prompt feedback about fetal wellbeing. The system is characterized by two units: (i) a wearable unit endowed with textile electrodes for abdominal ECG recordings and with a Field Programmable Gate Array (FPGA) board for fetal heart rate (FHR) extraction; (ii) a dock station for the transmission of the data through the telephone line. The system will allow to reduce costs in fetal monitoring, improving the assessment of fetal conditions. The device is actually in development state. In this paper, the most crucial aspects behind its fulfillment are discussed.

Kinematics of head-trunk movements while entering and exiting a car

The study of free and natural accessibility movements for a medium-sized car was carried out, recording the motor performances of ten participants by means of a motion analysis system. The experimental protocol used passive markers to implement a two-segment biomechanical model for the analysis of the head-trunk complex. The kinematic variables quantify the motor patterns, and showed specific features that can be related to the individual anthropometric characteristics and to the car geometry differences: tall participants used a neck flexion and a leftwards bending of the head, while short participants extended the neck and bent the head to the right. The different seat positions (short participants move forwards the seat) along with the principal need to avoid any body interference with the car, can explain the observed strategies. From the wider analysis of the movements in relation to the vehicles features and to the anthropometric size of the participants, this approach could lead to an extension of the design criteria for those structural components of the car which have been demonstrated to significantly influence the human – machine interaction.

Telefetalcare: A first prototype of a wearable fetal electrocardiograph

Fetal heart rate monitoring is fundamental to infer information about fetal health state during pregnancy. The cardiotocography (CTG) is the most common antepartum monitoring technique. Abdominal ECG recording represents the most valuable alternative to cardiotocography, as it allows passive, non invasive and long term fetal monitoring. Unluckily fetal ECG has low SNR and needs to be extracted from abdominal recordings using ad hoc algorithms. This work describes a prototype of a wearable fetal ECG electrocardiograph. The system has flat band frequency response between 1–60Hz and guarantees good signal quality. It was tested on pregnant women between the 30th and 34th gestational week. Several electrodes configurations were tested, in order to identify the best solution. Implementation of a simple algorithm for FECG extraction permitted the reliable detection of maternal and fetal QRS complexes. The system will allow continuative and deep screening of fetal heart rate, introducing the possibility of home fetal monitoring.

Method for Movement and Gesture Assessment (MMGA) in Ergonomics

We present a technique for the ergonomic assessment of motor tasks and postures. It is based on movement analysis and it integrates the perceived discomfort scores for joints motions and the time involvement of the different body districts. It was tested on 8 subjects performing reaching movements. The experimental protocol was designed to have an a priori expected comfort ranking, namely, higher values in presence of more uncomfortable tasks. The validation of the Method for Movement and Gesture Assessment (MMGA) in the ergonomic evaluation of a reaching task gave promising results and showed the effectiveness of the index. Possible applications of the method might be the integration into CAD tools and human motion simulation to provide an early comparative evaluation of the ergonomics of the prototyping process and workplace redesign in industry.

Densitometric Quantification of Neuronal Viability by Computerized Image Analysis

A new method is presented for the quantification of cell viability based on densitometry with computerized image analysis. Neuronal cells were stained with crystal violet and densitometric analysis was performed with an IBAS 2.0 image analyzer (Kontron/ Zeiss), using specially implemented dedicated software which integrates the optical density of the culture in each well with the area covered by the stained cells. To test the reliability of the densitometric method cortical cells were plated at different concentrations (5 x 10(4)-10(6)/ml); the standard curve obtained by analysis of crystal violet staining showed a linear proportion between cell number and optical density signal. The validation and accuracy of the method were assessed and compared with other methods using rat cortical cells cultured in vitro for 10 days and exposed to kainic acid (250 microM) for 24 h. Neuronal viability was reduced by 40-50% and comparison with direct cell counting, MTT assay, and spectrophotometric analysis confirmed that the method is simple, quick, and reliable.

Cognitive ability assessment by Brain–Computer Interface: Validation of a new assessment method for cognitive abilities

Brain-Computer Interfaces (BCIs) are systems which can provide communication and environmental control to people with severe neuromuscular diseases. The current study proposes a new BCI-based method for psychometric assessment when traditional or computerized testing cannot be used owing to the subjects output impairment. This administration protocol was based on, and validated against, a widely used clinical test (Raven Colored Progressive Matrix) in order to verify whether BCI affects the brain in terms of cognitive resource with a misstatement result. The operating protocol was structured into two phases: phase 1 was aimed at configuring the BCI system on the subjects features and train him/her to use it; during phase 2 the BCI system was reconfigured and the test performed. A step-by-step checking procedure was adopted to verify progressive inclusion/exclusion criteria and the underpinning variables. The protocol was validated on 19 healthy subjects and the BCI-based administration was compared with a paper-based administration. The results obtained by both methods were correlated as known for traditional assessment of a similarly culture free and reasoning based test. Although our findings need to be validated on pathological participants, in our healthy population the BCI-based administration did not affect performance and added a further control of the response due to the several variables included and analyzed by the computerized task.