The integration of digital technologies in sports assets is unlocking novel possibilities for managing sports facilities and enhancing learning support. This paper introduces the development of an innovative batteryless sensor system, the Autonomous Ski Deflection Sensor (ASDS), designed to monitor ski wear and assess skier performance. This new system is based on a piezoelectric energy harvester that uses the energy from the ski’s deformation and vibrations to power the electronics, avoiding the use of batteries. It integrates minimalist electronics to perform measurements of the ski solicitations in turns (directly correlated to the energy harvested), store the data in memory and send them in real time to a smartphone via Bluetooth Low Energy. The ski level of the user is evaluated thanks to data fusion between the measurements from ASDS and the inertial measurement unit (IMU) of a smartphone. For this purpose, 14 measurement campaigns (200 downhill runs) were carried out to generate the database for the machine learning algorithms for ski level classification. A public experimentation phase has been scheduled during the 2023 FIS Alpine World Ski Championships, proposing 40 pairs of skis equipped with TRL7 ASDS prototypes to participants. This initiative has allowed the evaluation of the system’s reliability, and demonstrated its potential benefits for diverse range of endusers within the skiing community. This ASDS system has the potential to enhance the skiing experience for users by providing insights to improve safety, performance, and enjoyment on the slopes. Alternatively, based on the monitoring of the ski usage/health, such system could promote new services and business models based on circular economy principles.

The low-power sensing platform proposed by the Convergence project is foreseen as a wireless, low-power and multifunctional wearable system empowered by energy-efficient technologies. This will allow meeting the strict demands of life-style and healthcare applications in terms of autonomy for quasi-continuous collection of data for early-detection strategies. The system is compatible with different kinds of sensors, able to monitor not only health indicators of individual person (physical activity, core body temperature and biomarkers) but also the environment with chemical composition of the ambient air (NOx, COx, NHx particles) returning meaningful information on his/her exposure to dangerous (safety) or pollutant agents. In this article, we introduce the specifications and the design of the low-power sensing platform and the different sensors developed in the project, with a particular focus on pollutant sensing capabilities and specifically on NO2 sensor based on graphene and CO sensor based on polyaniline ink.

This article addresses the question of passengers’ experience through different transport modes. It presents the main results of a pilot study, for which stress levels experienced by a traveller were assessed and predicted over two long journeys. Accelerometer measures and several physiological signals (electrodermal activity, blood volume pulse and skin temperature) were recorded using a smart wristband while travelling from Grenoble to Bilbao. Based on user’s feedback, three events of high stress and one period of moderate activity with low stress were identified offline. Over these periods, feature extraction and machine learning were performed from the collected sensor data to build a personalized regressive model, with user’s stress levels as output. A smartphone application has been developed on its basis, in order to record and visualize a timely estimated stress level using traveler’s physiological signals. This setting was put on test during another travel from Grenoble to Brussels, where the same user’s stress levels were predicted in real time by the smartphone application. The number of correctly classified stress-less time windows ranged from 92.6% to 100%, depending on participant’s level of activity. By design, this study represents a first step for real-life, ambulatory monitoring of passenger’s stress while travelling.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. Features relevance analysis for emotion classification with physiological sensors Christelle Godin, Fabrice Prost-Boucle, Aurélie Campagne, Sylvie Charbonnier, Stéphane Bonnet, Audrey Vidal

With the development of wearable physiological sensors, emotion estimation becomes a hot topic in the literature. Databases of physiological signals recorded during emotional stimulation are acquired and machine learning algorithms are used. Yet, which are the most relevant signals to detect emotions is still a question to be answered. In order to better understand the contribution of each signal, and thus sensor, to the emotion estimation problem, several feature selection algorithms were implemented on two databases freely available to the research community (DEAP and MANHOB-HCI). Both databases manipulate emotions by showing participants short videos (video clips or part of movies respectively). Features extracted from Galvanic Skin response were found to be relevant for arousal estimation in both databases. Other relevant features were eye closing rate for arousal, variance of zygomatic EMG for valence (those features being only available for DEAP). The hearth rate variability power in three frequency bands also appeared to be very relevant, but only for MANHOB-HCI database where heat rate was measured using ECG (whereas DEAP used PPG). This suggests that PPG is not accurate enough to estimate HRV precisely. Finally we showed on DEAP database that emotion classifiers need just a few well selected features to obtain similar performances to literature classifiers using more features.

Structural Health Monitoring methods may be divided into two major categories depending on the type of data used during the damage identification: static or dynamic. In this paper, it is shown that both analyses can be performed with the same instrumentation composed only of Micro Electro Mechanical System (MEMS) accelerometers. The latter has the capability to measure static and dynamic data. In very low frequency, accelerometers are used as inclination sensors to estimate static deflection. In higher frequency, accelerometers are used as vibration sensors to perform modal analysis. Both analyses are illustrated in the case of a real footbridge. Static deflections and modal flexibility-based deflections are compared in operational conditions, including pedestrian loads and temperature changes, and in artificially-introduced damage conditions. Very good agreements are obtained showing the relevance of the two approaches. Static and dynamic analyses could be used in a complementary way and provide additional information in order to reinforce the confidence and the accuracy of the damage identification.