Christophe Escriba

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.

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.

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.

Structural health monitoring using noninvasive methods is one of the major challenges that aerospace manufacturers face in this decade. Our work in this field focuses on the development and the system integration of millimetric piezoelectric sensors/ actuators to generate and measure specific guided waves. The aim of the application is to detect mechanical flaws on complex composite and alloy structures to quantify efficiently the global structures’ reliability. The study begins by a physical and analytical analysis of a piezoelectric patch. To preserve the structure’s integrity, the transducers are directly pasted onto the surface which leads to a critical issue concerning the interfacing layer. In order to improve the reliability and mitigate the influence of the interfacing layer, the global equations of piezoelectricity are coupled with a load transfer model. Thus we can determine precisely the shear strain developed on the surface of the structure. To exploit the generated signal, a high precision analog charge amplifier coupled to a double T notch filter were designed and scaled. Finally, a novel joined time-frequency analysis based on a wavelet decomposition algorithm is used to extract relevant structures signatures. Finally, this paper provides examples of application on aircraft structure specimens and the feasibility of the system is thus demonstrated.

The largest variable cost to aircraft’s manufacturers and flying companies is unscheduled maintenance. Therefore, developing efficient and modular PHM system capable to scale different architectures topologies for in flight and on ground health monitoring could be cost effective, since it brings indication and warning prior to damage occurring.In this paper, we propose an innovative diagnostic and prognostic health system based on a combination of modular acquisitions interfaces and processing units.An embedded JTFA (Joined Time-Frequency Analysis) method based on STFT (Short-Time Fourier Transform) or Wigner-Ville transforms are used to extract a relevant signature. The proposed algorithms and PHM system technology are applied for diagnosis of mechanical flows in a high speed rotating gear of a demonstrator machine. A detailed description of data management and rooting from vibration sensors to the processing unit will be exposed.Finally, a proof-of-concept experiment will be designed to demonstrate the integration of all the described system elements to detect any damage or anomaly into the monitored structure.

The work reported on this paper describes a new methodology implementation for active structural health monitoring of recent aircraft parts made from carbon-fiber-reinforced polymer. This diagnosis is based on a new embedded method that is capable of measuring the local high frequency impedance spectrum of the structure through the calculation of the electro-mechanical impedance of a piezoelectric patch pasted non-permanently onto its surface. This paper involves both the laboratory based E/M impedance method development, its implementation into a CPU with limited resources as well as a comparison with experimental testing data needed to demonstrate the feasibility of flaw detection on composite materials and answer the question of the method reliability. The different development steps are presented and the integration issues are discussed. Furthermore, we present the unique advantages that the reconfigurable electronics through System-on-Chip (SoC) technology brings to the system scaling and flexibility. At the end of this article, we demonstrate the capability of a basic network of sensors mounted onto a real composite aircraft part specimen to capture its local impedance spectrum signature and to diagnosis different delamination sizes using a comparison with a baseline.

This work focus on the structural health monitoring of aircrafts parts specimen structures made of 2024 Aluminum alloys. In this paper we demonstrate the feasibility of a new non destructive control method capable to probe very large structures within a short time. The method we developed is based through a wide piezoelectric sensors network on a smart comparison between two acoustic signatures: the healthy structure response captured before the commissioning of the plane and “an after flight” response. The sensors network exploits the capability of piezoelectric patches to generate/measure specific Lamb wave’s modes. The system is therefore dynamically configured to localize mechanicals flaws using an algorithm that operates using different techniques like pitch-catch and pulse-echo. An analytic study is performed and tests to prove the proposed method feasibility on corroded structures specimens are provided at the end of this paper.

This presents work done on the project “Blade Parameters Recording Microsystem” funded by the French research program FUI. It resulted in a fully operational recorder that can be embedded on a plane. This system allows blade monitoring to be conducted using computing algorithms. Using a top-down modelling method, this recorder can be adapted to any kind of blade. Herein, recorder was devised for a Transall plane blade. This device was used to record data in order to subsequently compute a real-time blade monitoring algorithm. The algorithm takes several blade parameters into account. The top-down modelling easily allows the algorithm parameters to be adapted to various blades.