Publications

Smoldering fires are characterized by the production of early gas emissions that can include high levels of CO and Volatile Organic Compounds (VOCs) due to pyrolysis or thermal degradation. Nowadays, standalone CO sensors, smoke detectors, or a combination of these, are standard components for fire alarm systems. While gas sensor arrays together with pattern recognition techniques are a valuable alternative for early fire detection, in practice they have certain drawbacks-they can detect early gas emissions, but can show low immunity to nuisances, and sensor time drift can render calibration models obsolete. In this work, we explore the performance of a gas sensor array for detecting smoldering and plastic fires while ensuring the rejection of a set of nuisances. We conducted variety of fire and nuisance experiments in a validated standard fire room (240 m(3)). Using PLS-DA and SVM, we evaluate the performance of different multivariate calibration models for this dataset. We show that calibration models remain predictive after several months, but perfect performance is not achieved. For example, 4 months after calibration, a PLS-DA model provides 100% specificity and 85% sensitivity since the system has difficulties in detecting plastic fires, whose signatures are close to nuisance scenarios. Nevertheless, our results show that systems based on gas sensor arrays are able to provide faster fire alarm response than conventional smoke-based fire alarms. We also propose the use of small-scale fire experiments to increase the number of calibration conditions at a reduced cost. Our results show that this is an effective way to increase the performance of the model, even when evaluated on a standard fire room. Finally, the acquired datasets are made publicly available to the community (doi: 10.5281/zenodo.5643074).

JTD Keywords: Calibration, Chemical sensors, Co2, Early fire, Early fire detection, En-54, Fire alarm, Fire detection, Fire room, Fires, Gas detectors, Gas emissions, Gas sensors, Pattern recognition, Public dataset, Sensor arrays, Sensors array, Signatures, Smoke, Smoke detector, Smoke detectors, Standard fire, Standard fire room, Support vector machines, Temperature, Toxicity, Volatile organic compounds

Indoor fire detection using gas chemical sensing has been a subject of investigation since the early nineties. This approach leverages the fact that, for certain types of fire, chemical volatiles appear before smoke particles do. Hence, systems based on chemical sensing can provide faster fire alarm responses than conventional smoke-based fire detectors. Moreover, since it is known that most casualties in fires are produced from toxic emissions rather than actual burns, gas-based fire detection could provide an additional level of safety to building occupants. In this line, since the 2000s, electrochemical cells for carbon monoxide sensing have been incorporated into fire detectors. Even systems relying exclusively on gas sensors have been explored as fire detectors. However, gas sensors respond to a large variety of volatiles beyond combustion products. As a result, chemical-based fire detectors require multivariate data processing techniques to ensure high sensitivity to fires and false alarm immunity. In this paper, we the survey toxic emissions produced in fires and defined standards for fire detection systems. We also review the state of the art of chemical sensor systems for fire detection and the associated signal and data processing algorithms. We also examine the experimental protocols used for the validation of the different approaches, as the complexity of the test measurements also impacts on reported sensitivity and specificity measures. All in all, further research and extensive test under different fire and nuisance scenarios are still required before gas-based fire detectors penetrate largely into the market. Nevertheless, the use of dynamic features and multivariate models that exploit sensor correlations seems imperative

JTD Keywords: Fire detection, Gas sensor, Pattern recognition, Sensor fusion, Machine learning, Toxicants, Carbon monoxide, Hydrogen cyanide, Standard test fires, Transducers, Smoke

Over the last two decades, electronic nose research has produced thousands of research works. Many of them were describing the ability of the e-nose technology to solve diverse applications in domains ranging from food technology to safety, security, or health. It is, in fact, in the biomedical field where e-nose technology is finding a research niche in the last years. Although few success stories exist, most described applications never found the road to industrial or clinical exploitation. Most described methodologies were not reliable and were plagued by numerous problems that prevented practical application beyond the lab. This work emphasizes the need of external validation in machine olfaction. I describe some statistical and methodological pitfalls of the e-nose practice and I give some best practice recommendations for researchers in the field.

JTD Keywords: Chemical sensor arrays, Pattern recognition, Chemometrics, Electronic noses, Robustness, Signal and data processing

Stroke is a major cause of disability, usually causing hemiplegic damage on the motor abilities of the patient. Stroke rehabilitation seeks restoring normal motion on the affected limb. However, normality’ of movements is usually assessed by clinical and functional tests, without considering how the motor system responds to therapy. We hypothesized that electromyographic (EMG) recordings could provide useful information for evaluating the outcome of rehabilitation from a neuromuscular perspective. Four healthy subjects were asked to perform 14 different functional movements simulating the action of reaching over a table. Each movement was defined according to the starting and target positions that the subject had to connect using linear trajectories. Bipolar recordings of EMG signals were taken from biceps and triceps muscles, and spectral and temporal characteristics were extracted for each movement. Using pattern recognition techniques we found that only two EMG channels were sufficient to accurately determine the spatial characteristics of motor activity: movement direction, length and execution zone. Our results suggest that muscles may fire in a patterned way depending on the specific characteristics of the movement and that EMG signals may codify such detailed information. These findings may be of great value to quantitatively assess post-stroke rehabilitation and to compare the neuromuscular activity of the affected and unaffected limbs, from a physiological perspective. Furthermore, disturbed movements could be characterized in terms of the muscle function to identify, which is the spatial characteristic that fails, e.g. movement direction, and guide personalized rehabilitation to enhance the training of such characteristic.

JTD Keywords: EMG, Movement spatial characteristics, Pattern recognition, Stroke rehabilitation, Upper-limb

Statistical analysis, power spectral density, and Lempel Ziv complexity, are used in a multi-parameter approach to analyze four temporal series obtained from the Electrocardiographic and Respiratory Flow signals of 126 patients on weaning trials. In which, 88 patients belong to successful group (SG), and 38 patients belong to failure group (FG), i.e. failed to maintain spontaneous breathing during trial. It was found that mean values of cardiac inter-beat and breath durations give higher values for SG than for FG; Kurtosis coefficient of the spectrum of the rapid shallow breathing index is higher for FG; also Lempel Ziv complexity mean values associated with the respiratory flow signal are bigger for FG. Patients were then classified with a pattern recognition neural network, obtaining 80% of correct classifications (81.6% for FG and 79.5% for SG).

JTD Keywords: Electrocardiography, Medical signal processing, Neural nets, Pattern recognition, Pneumodynamics, Signal classification, Statistical analysis, ECG, Kurtosis coefficient, Lempel Ziv complexity, Breath durations, Cardiac interbeat durations, Electrocardiography, Multiparameter analysis, Pattern recognition neural network, Power spectral density, Respiratory flow signals, Signal classification, Spontaneous breathing, Statistical analysis, Weaning trials

A first step towards the multidetection of anabolic androgenic steroids by Enzyme-linked immunosorbent assays (ELISA) has been performed in this study. This proposal combines an array of classical ELISA assays with different selectivities and multivariate data analysis techniques. Data has been analyzed by principal component analysis in conjunction with a k-nearest line classifier has been used. This proposal allows to detect simultaneously four different compounds in the range of concentration from 10(-1.5) to 10(3) mM with a total rate of 90.6% of correct detection.

JTD Keywords: Immunoarray, Anabolic androgenic steroid, Multidetection, Pattern recognition, K-nearlest line

In this paper we compare three different spectral estimation techniques for the classification of mental tasks. These techniques are the standard periodogram, the Welch periodogram and the Burg method, applied to electroencephalographic (EEG) signals. For each one of these methods we compute two parameters: the mean power and the root mean square (RMS), in various frequency bands. The classification of the mental tasks was conducted with a linear discriminate analysis. The Welch periodogram and the Burg method performed better than the standard periodogram. The use of the RMS allows better classification accuracy than the obtained with the power of EEG signals.

JTD Keywords: Adult, Algorithms, Artificial Intelligence, Cognition, Electroencephalography, Female, Humans, Male, Pattern Recognition, Automated, Reproducibility of Results, Sensitivity and Specificity, Task Performance and Analysis, User-Computer Interface