ABOUT ME

In the field of passive Brain–computer Interfaces (BCI), the need to develop systems that require rapid setup, suitable for use outside of laboratories is a fundamental challenge, especially now, that the market is flooded with novel EEG headsets with a good quality. However, the lack of control in operational conditions can compromise the performance of the machine learning model behind the BCI system. First, this study focuses on evaluating the performance loss of the BCI system, induced by a different positioning of the EEG headset (and of course sensors), so generating a variation in the control features used to calibrate the machine learning algorithm. This phenomenon is called covariate shift. Detecting covariate shift occurrences in advance allows for preventive measures, such as informing the user to adjust the position of the headset or applying specific corrections in new coming data. We used in this study an unsupervised Machine Learning model, the Isolation Forest, to detect covariate shift occurrence in new coming data. We tested the method on two different datasets, one in a controlled setting (9 participants), and the other in a more realistic setting (10 participants). In the controlled dataset, we simulated the movement of the EEG cap using different channel and reference configurations. For each test configuration, we selected a set of electrodes near the control electrodes. Regarding the realistic dataset, we aimed to simulate the use of the cap outside the laboratory, mimicking the removal and repositioning of the cap by a non-expert user. In both datasets, we recorded multiple test sessions for each configuration while executing a set of Workload tasks. The results obtained using the Isolation Forest model allowed the identification of covariate shift in the data, even with a 15-s recording sample. Moreover, the results showed a strong and significant negative correlation between the percentage of covariate shift detected by the method, and the accuracy of the passive BCI system (p-value < 0.01). This novel approach opens new perspectives for developing more robust and flexible BCI systems, with the potential to move these technologies towards out-of-the-lab use, without the need for supervision for use by a non-expert user.

The need of safe and livable indoor environments has intensified recently, given the great amount of time people spend indoor. In addition, the recent COVID-19 pandemic has moved the interest from the outdoor to indoor spaces. To guarantee an optimal indoor environmental quality, monitoring and regulating many variables (such as indoor and outdoor temperature, pollutants concentration, noise, and brightness) is necessary. In this context, we have developed AIR SAFE, an IoT and AI based infrastructure to monitor and control environmental quality in closed spaces. AIR SAFE uses Machine Learning models to make predictions of temperature, relative humidity, and CO₂ concentration. These predictions, together with data from a network of IoT sensors, are used to take actions on windows and air conditioning system with the aim of modifying for the better the room environment. We show the results of the AI model we have developed for predicting indoor concentration of CO₂, relative humidity, and temperature. Our Long Short Term Memory (LSTM) model has been tested against literature models using simulated data at first, and then testing the best models on real data. Using real data, the LSTM network performs best at forecasting temperature and relative humidity, while Random Forest is the best CO₂ concentration predictor.

Technologies like passive brain-computer interfaces (BCI) can enhance human-machine interaction. Anyhow, there are still shortcomings in terms of easiness of use, reliability, and generalizability that prevent passive-BCI from entering real-life situations. The current work aimed to technologically and methodologically design a new gel-free passive-BCI system for out-of-the-lab employment. The choice of the water-based electrodes and the design of a new lightweight headset met the need for easy-to-wear, comfortable, and highly acceptable technology. The proposed system showed high reliability in both laboratory and realistic settings, performing not significantly different from the gold standard based on gel electrodes. In both cases, the proposed system allowed effective discrimination (AUC > 0.9) between low and high levels of workload, vigilance, and stress even for high temporal resolution (<10 s). Finally, the generalizability of the proposed system has been tested through a cross-task calibration. The system calibrated with the data recorded during the laboratory tasks was able to discriminate the targeted human factors during the realistic task reaching AUC values higher than 0.8 at 40 s of temporal resolution in case of vigilance and workload, and 20 s of temporal resolution for the stress monitoring. These results pave the way for ecologic use of the system, where calibration data of the realistic task are difficult to obtain.

Driver's stress affects decision-making and the probability of risk occurrence, and it is therefore a key factor in road safety. This suggests the need for continuous stress monitoring. This work aims at validating a stress neurophysiological measure—a Neurometric—for out-of-the-lab use obtained from lightweight EEG relying on two wet sensors, in real-time, and without calibration. The Neurometric was tested during a multitasking experiment and validated with a realistic driving simulator. Twenty subjects participated in the experiment, and the resulting stress Neurometric was compared with the Random Forest (RF) model, calibrated by using EEG features and both intra-subject and cross-task approaches. The Neurometric was also compared with a measure based on skin conductance level (SCL), representing one of the physiological parameters investigated in the literature mostly correlated with stress variations. We found that during both multitasking and realistic driving experiments, the Neurometric was able to discriminate between low and high levels of stress with an average Area Under Curve (AUC) value higher than 0.9. Furthermore, the stress Neurometric showed higher AUC and stability than both the SCL measure and the RF calibrated with a cross-task approach. In conclusion, the Neurometric proposed in this work proved to be suitable for out-of-the-lab monitoring of stress levels.

Despite the technological advancements, the employment of passive brain computer interface (BCI) out of the laboratory context is still challenging. This is largely due to methodological reasons. On the one hand, machine learning methods have shown their potential in maximizing performance for user mental states classification. On the other hand, the issues related to the necessary and frequent calibration of algorithms and to the temporal resolution of the measurement (i.e. how long it takes to have a reliable state measure) are still unsolved. This work explores the performances of a passive BCI system for mental effort monitoring consisting of three frontal electroencephalographic (EEG) channels. In particular, three calibration approaches have been tested: an intra-subject approach, a cross-subject approach, and a free-calibration procedure based on the simple average of theta activity over the three employed channels. A Random Forest model has been employed in the first two cases. The results obtained during multi-tasking have shown that the cross-subject approach allows the classification of low and high mental effort with an AUC higher than 0.9, with a related time resolution of 45 seconds. Moreover, these performances are not significantly different from the intra-subject approach although they are significantly higher than the calibration-free approach. In conclusion, these results suggest that a light (three EEG channels) passive BCI system based on a Random Forest algorithm and cross-subject calibration could be a simple and reliable tool for out-of-the-lab employment.