Georges Soto-Romero

Beehive health monitoring has gained interest in the study of bees in biology, ecology, and agriculture. As audio sensors are less intrusive, a number of audio datasets (mainly labeled with the presence of a queen in the hive) have appeared in the literature, and interest in their classification has been raised. All studies have exhibited good accuracy, and a few have questioned and revealed that classification cannot be generalized to unseen hives. To increase the number of known hives, a review of open datasets is described, and a merger in the form of the “BeeTogether” dataset on the open Kaggle platform is proposed. This common framework standardizes the data format and features while providing data augmentation techniques and a methodology for measuring hives’ extrapolation properties. A classical classifier is proposed to benchmark the whole dataset, achieving the same good accuracy and poor hive generalization as those found in the literature. Insight into the role of the frequency of the classification of the presence of a queen is provided, and it is shown that this frequency mostly depends on a colony’s belonging. New classifiers inspired by contrastive learning are introduced to circumvent the effect of colony belonging and obtain both good accuracy and hive extrapolation abilities when learning changes in labels. A process for obtaining absolute labels was prototyped on an unsupervised dataset. Solving hive extrapolation with a common open platform and contrastive approach can result in effective applications in agriculture.

This paper presents the development of an electronic system that converts an electrically assisted bicycle into an intelligent health monitoring system, allowing people who are not athletic or who have a history of health issues to progressively start the physical activity by following a medical protocol (e.g., max heart rate and power output, training time). The developed system aims to monitor the health state of the rider, analyze data in real-time, and provide electric assistance, thus diminishing muscular exertion. Furthermore, such a system can recover the same physiological data used in medical centers and program it into the e-bike to track the patient’s health. System validation is conducted by replicating a standard medical protocol used in physiotherapy centers and hospitals, typically conducted in indoor conditions. However, the presented work differentiates itself by implementing this protocol in outdoor environments, which is impossible with the equipment used in medical centers. The experimental results show that the developed electronic prototypes and the algorithm effectively monitored the subject’s physiological condition. Moreover, when necessary, the system can change the training load and help the subject remain in their prescribed cardiac zone. This system allows whoever needs to follow a rehabilitation program to do so not only in their physician’s office, but whenever they want, including while commuting.

Dans le cadre du cursus de 1ere année cycle ingénieur santé à ISIS Castres, les étudiants sont amenés à approfondir leurs connaissances en électronique dans le domaine des capteurs biomédicaux. En faisant du reverse engineering, ils identifient les étapes de mesure de plusieurs dispositifs médicaux (vues dans des cours précédents), et avec quelques bases en électronique embarquée et IoT (Internet of Things), ils utilisent une approche Do It Yourself (DIY), pour construire leurs propres prototypes d’oxymètres de pouls, et comparer ceux-ci avec les oxymètres du commerce disponibles dans la salle de Travaux Pratiques.

This paper aims to provide a review of the electrically assisted bicycles (also known as e-bikes) used for recovery of the rider’s physical and physiological information, monitoring of their health state, and adjusting the “medical” assistance accordingly. E-bikes have proven to be an excellent way to do physical activity while commuting, thus improving the user’s health and reducing air pollutant emissions. Such devices can also be seen as the first step to help unhealthy sedentary people to start exercising with reduced strain. Based on this analysis, the need to have e-bikes with artificial intelligence (AI) systems that recover and processe a large amount of data is discussed in depth. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were used to complete the relevant papers’ search and selection in this systematic review.

A large number of power meters have become commercially available during the last decades to provide power output (PO) measurement. Some of these power meters were evaluated for validity in the literature. This study aimed to perform a review of the available literature on the validity of cycling power meters. PubMed, SPORTDiscus, and Google Scholar have been explored with PRISMA methodology. A total of 74 studies have been extracted for the reviewing process. Validity is a general quality of the measurement determined by the assessment of different metrological properties: Accuracy, sensitivity, repeatability, reproducibility, and robustness. Accuracy was most often studied from the metrological property (74 studies). Reproducibility was the second most studied (40 studies) property. Finally, repeatability, sensitivity, and robustness were considerably less studied with only 7, 5, and 5 studies, respectively. The SRM power meter is the most used as a gold standard in the studies. Moreover, the number of participants was very different among them, from 0 (when using a calibration rig) to 56 participants. The PO tested was up to 1700 W, whereas the pedalling cadence ranged between 40 and 180 rpm, including submaximal and maximal exercises. Other exercise conditions were tested, such as torque, position, temperature, and vibrations. This review provides some caveats and recommendations when testing the validity of a cycling power meter, including all of the metrological properties (accuracy, sensitivity, repeatability, reproducibility, and robustness) and some exercise conditions (PO range, sprint, pedalling cadence, torque, position, participant, temperature, vibration, and field test).

Modern agriculture imposes the need for better knowledge of the soil moisture content to rationalize the amount of water needed to irrigate farmlands. In this context, since current technological solutions do not correspond to the cost or use criteria, this paper presents a design for a new original capacitive bi-functional sensor to measure soil moisture and salinity. In this paper, we outline the design stages from simulation to finished elements of the optimal design to deployment in the fields, considering the mechanical integration constraints necessary for industrialization. The measurement electronics were developed based on the sensor’s electric model to obtain a double measurement. An on-site (field lot) measurement program was then carried out to validate the system’s good performance in real-time. Finally, this performance was matched with that of leading commercially available sensors on the market. This work demonstrates that, after deployment of the sensors, the overall system makes it possible to obtain a precise image of cultivated soil’s hydric condition, with the best response time.

The GIBIC research team, from UdeA, and S4M from LAAS-CNRS, designed a glove with inertial sensors (IMU) for quantifying surgeons’ dexterity. A previous study validated its capacity to accurately rank participants, compared to a video evaluation, during neurosurgery training. The objective of this work is to check this validity for laparoscopic surgery, compared with a “gold-standard” simulator, the LapSim (Surgical Science^®). For this purpose, the inertial basic data of the sensors were processed into quantified score comparable with the LapSim scores. A trial was designed and conducted during one month with nine students training on specific LapSim tasks.

The traditional neurosurgical apprenticeship scheme includes the assessment of trainee’s manual skills carried out by experienced surgeons. However, the introduction of surgical simulation technology presents a new paradigm where residents can refine surgical techniques on a simulator before putting them into practice in real patients. Unfortunately, in this new scheme, an experienced surgeon will not always be available to evaluate trainee’s performance. For this reason, it is necessary to develop automatic mechanisms to estimate metrics for assessing manual dexterity in a quantitative way. Authors have proposed some hardware-software approaches to evaluate manual dexterity on surgical simulators. This paper presents IGlove, a wearable device that uses inertial sensors embedded on an elastic glove to capture hand movements. Metrics to assess manual dexterity are estimated from sensors signals using data processing and information analysis algorithms. It has been designed to be used with a neurosurgical simulator called Daubara NS Trainer, but can be easily adapted to another benchtop- and manikin-based medical simulators. The system was tested with a sample of 14 volunteers who performed a test that was designed to simultaneously evaluate their fine motor skills and the IGlove’s functionalities. Metrics obtained by each of the participants are presented as results in this work; it is also shown how these metrics are used to automatically evaluate the level of manual dexterity of each volunteer.