In the last few decades, while the sensory evaluation of edible products has been leveraged to make strategic decisions about many domains, the traditional descriptive analysis performed by a skilled sensory panel has been seen to be too complex and time-consuming for the industry needs, making it largely unsustainable in most cases. In this context, the study of the effectiveness of different methods for sensory training on panel performances represents a new trend in research activity. With this purpose, wearable sensors are applied to study physiological signals (ECG and skin conductance) concerned with the emotions in a cohort of volunteers undergoing a short, two-day (16 h) sensory training period related to wine tasting. The results were compared with a previous study based on a conventional three-month (65 h) period of sensory training. According to what was previously reported for long panel training, it was seen that even short, intensive sensory training modulated the ANS activity toward a less sympathetically mediated response as soon as odorous compounds become familiar. A large-scale application of shorter formative courses in this domain appears possible without reducing the effectiveness of the training, thus leading to money saving for academia and scientific societies, and challenging dropout rates that might affect longer courses.

The present article proposes an ECG simulator that advances modeling of arrhythmias and noise by introducing time-varying signal characteristics. The simulator is built around a discrete-time Markov chain model for simulating atrial and ventricular arrhythmias of particular relevance when analyzing atrial fibrillation (AF). Each state is associated with statistical information on episode duration and heartbeat characteristics. Statistical, time-varying modeling of muscle noise, motion artifacts, and the influence of respiration is introduced to increase the complexity of simulated ECGs, making the simulator well suited for data augmentation in machine learning. Modeling of how the PQ and QT intervals depend on heart rate is also introduced. The realism of simulated ECGs is assessed by three experienced doctors, showing that simulated ECGs are difficult to distinguish from real ECGs. Simulator usefulness is illustrated in terms of AF detection performance when either simulated or real ECGs are used to train a neural network for signal quality control. The results show that both types of training lead to similar performance.

Heartbeat detection is the first step in automatic analysis of the electrocardiogram (ECG). For mobile and wearable devices, the detection process should be both accurate and computationally efficient. In this paper, we present a QRS detection algorithm based on moving average filters, which affords a simple yet robust signal processing technique. The decision logic considers the rhythmic and morphological features of the QRS complex. QRS enhancing is performed with channel-specific moving average cascades selected from a pool of derivative systems we designed. We measured the effectiveness of our algorithm on well-known benchmark databases, reporting F1 scores, sensitivity on abnormal beats and processing time. We also evaluated the performances of other available detectors for a direct comparison with the same criteria. The algorithm we propose achieved satisfying performances on par with or higher than the other QRS detectors. Despite the performances we report are not the highest that have been published so far, our approach to QRS detection enhances computational efficiency while maintaining high accuracy.

Spices and aromatic herbs are important components of everyday nutrition in several countries and cultures, thanks to their capability to enhance the flavor of many dishes and convey significant emotional contributions by themselves. Indeed, spices as well as aromatic herbs are to be considered not only for their important values of antimicrobial agents or flavor enhancers everybody knows, but also, thanks to their olfactory and gustatory spectrum, as drivers to stimulate the consumers’ memories and, in a stronger way, emotions. Considering these unique characteristics, spices and aromatic herbs have caught the attention of consumer scientists and experts in sensory analysis for their evaluation using semi-quantitative approaches, with interesting evidence. In this pilot study as a first step, each studied botanical, belonging to Piperaceae or aromatic herbs, has been subjected to headspace solid phase micro-extraction (HS-SPME) coupled with gas-chromatography mass spectrometry (GC-MS) analysis to assess their spontaneous volatile emission, representing the complex chemical pattern, which encounters the consumers’ olfactory perception. Furthermore, the present investigation, performed on 12 individuals, outlines the administration of a pilot study, merging the typical sensory analysis with emotional data collection and the innovative contribution related to the study around the Autonomic and Central Nervous System activation in consumers, performed using wearable technologies and related signal processing. The results obtained by our study, beyond demonstrating the feasibility of the approach, confirmed, both in terms of emotional responses and biomedical signals, the significant emotional potential of spices and aromatic herbs, most of which featuring an overall positive valence, yet with inter-subjects’ variations. Future investigations should aim to increase the number of volunteers evaluated with such an approach to draw more stable conclusions and attempting a customization of product preferences based on both implicit and explicit sensory responses.

Wearable devices provide reliable biometric measurements in different contexts, and AI algorithms are increasingly being used to analyze this data. The objective of this review is to examine the use of wearable devices to collect biometric data combined with AI algorithms in an educational setting. A systematic review was conducted through the PRISMA methodology, by searching the Scopus database for works that included wearables, biometrics, and AI algorithms. A total of 43 studies were included and examined. The objectives, the type of collected data, and the methodologies of the included studies were investigated. Most articles utilized machine learning and deep learning algorithms for classification tasks, such as detecting stress or attention. Other applications included human activity recognition (HAR) for classroom orchestration and emotional or cognitive state detection. Many of the studies applied knowledge from previous works to the educational context, resembling exploratory research. Conversely, some authors developed tasks and methodologies tailored to the educational context. The strengths and weaknesses of the presented studies were discussed to propose future research directions. The main findings of this review highlight the advantages of the combination of multimodal sensing and predictive modeling in education with the eventual prospect of personalization. The absence of standardized acquisition and reporting remains the main barrier to replication, benchmarking, and synthesis across studies.