Institut National des Sciences Appliquées Centre Val de Loire

Three-dimensional (3D) bioprinting, an additive manufacturing based technique of biomaterials fabrication, is an innovative and auspicious strategy in medical and pharmaceutical fields. The ability of producing regenerative tissues and organs has made this technology a pioneer to the creation of artificial multi-cellular tissues/organs. A broad variety of biomaterials is currently being utilized in 3D bioprinting as well as multiple techniques employed by researchers. In this review, we demonstrate the most common and novel biomaterials in 3D bioprinting technology further with introducing the related techniques that are commonly taking into account by researchers. In addition, an attempt has been accomplished to hand over the most relevant application of 3D bioprinting techniques such as tissue regeneration, cancer investigations, etc. by presenting the most important works. The main aim of this review paper is to emphasis on strengths and limitations of existence biomaterials and 3D bioprinting techniques in order to carry out a comparison through them.

In recent years, weeds have been responsible for most agricultural yield losses. To deal with this threat, farmers resort to spraying the fields uniformly with herbicides. This method not only requires huge quantities of herbicides but impacts the environment and human health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, unmanned aerial vehicles (UAVs) are becoming an interesting acquisition system for weed localization and management due to their ability to obtain images of the entire agricultural field with a very high spatial resolution and at a low cost. However, despite significant advances in UAV acquisition systems, the automatic detection of weeds remains a challenging problem because of their strong similarity to the crops. Recently, a deep learning approach has shown impressive results in different complex classification problems. However, this approach needs a certain amount of training data, and creating large agricultural datasets with pixel-level annotations by an expert is an extremely time-consuming task. In this paper, we propose a novel fully automatic learning method using convolutional neuronal networks (CNNs) with an unsupervised training dataset collection for weed detection from UAV images. The proposed method comprises three main phases. First, we automatically detect the crop rows and use them to identify the inter-row weeds. In the second phase, inter-row weeds are used to constitute the training dataset. Finally, we perform CNNs on this dataset to build a model able to detect the crop and the weeds in the images. The results obtained are comparable to those of traditional supervised training data labeling, with differences in accuracy of 1.5% in the spinach field and 6% in the bean field.

Bacteria‐inspired magnetic helical micro‐/nanoswimmers can be actuated and steered in a fuel‐free manner using a low‐strength rotating magnetic field, generating remotely controlled 3D locomotion with high precision in a variety of biofluidic environments. They are therefore envisioned for biomedical applications related to targeted diagnosis and therapy. In this article, a porous hollow microswimmer possessing an outer shell aggregated by mesoporous spindle‐like magnetite nanoparticles (NPs) and a helical‐shaped inner cavity is proposed. The fabrication is straightforward via a cost‐effective mass‐production process of biotemplated synthesis using helical microorganisms. Here, Spirulina ‐based fabrication is demonstrated as an example. The fabricated microswimmers are superparamagnetic and exhibit low cytotoxicity. They are also capable of performing structural disassembly to form individual NPs using ultrasound when needed. For the first time in the literature of helical microswimmers, a porous hollow architecture is successfully constructed, achieving an ultrahigh specific surface area for surface functionalization and enabling diffusion‐based cargo loading/release. Furthermore, experimental and analytical results indicate better swimming performance of the microswimmers than the existing non‐hollow helical micromachines of comparable sizes and dimensions. These characteristics of the as‐proposed microswimmers suggest a novel microrobotic tool with high loading capacity for targeted delivery of therapeutic/imaging agents in vitro and in vivo.

Crop diseases constitute a serious issue in agriculture, affecting both quality and quantity of agriculture production. Disease control has been a research object in many scientific and technologic domains. Technological advances in sensors, data storage, computing resources and artificial intelligence have shown enormous potential to control diseases effectively. A growing body of literature recognizes the importance of using data from different types of sensors and machine learning approaches to build models for detection, prediction, analysis, assessment, etc. However, the increasing number and diversity of research studies requires a literature review for further developments and contributions in this area. This paper reviews state-of-the-art machine learning methods that use different data sources, applied to plant disease detection. It lists traditional and deep learning methods associated with the main data acquisition modalities, namely IoT, ground imaging, unmanned aerial vehicle imaging and satellite imaging. In addition, this study examines the role of data fusion for ongoing research in the context of disease detection. It highlights the advantage of intelligent data fusion techniques, from heterogeneous data sources, to improve plant health status prediction and presents the main challenges facing this field. The study concludes with a discussion of several current issues and research trends.

Monitoring crops and weeds is a major challenge in agriculture and food production today. Weeds compete directly with crops for moisture, nutrients, and sunlight. They therefore have a significant negative impact on crop yield if not sufficiently controlled. Weed detection and mapping is an essential step in weed control. Many existing research studies recognize the importance of remote sensing systems and machine learning algorithms in weed management. Deep learning approaches have shown good performance in many agriculture-related remote sensing tasks, such as plant classification, disease detection, etc. However, despite the success of these approaches, they still face many challenges such as high computation cost, the need of large labelled datasets, intra-class discrimination (in growing phase weeds and crops share many attributes similarity as color, texture, and shape), etc. This paper aims to show that the attention-based deep network is a promising approach to address the forementioned problems, in the context of weeds and crops recognition with drone system. The specific objective of this study was to investigate visual transformers (ViT) and apply them to plant classification in Unmanned Aerial Vehicles (UAV) images. Data were collected using a high-resolution camera mounted on a UAV, which was deployed in beet, parsley and spinach fields. The acquired data were augmented to build larger dataset, since ViT requires large sample sets for better performance, we also adopted the transfer learning strategy. Experiments were set out to assess the effect of training and validation dataset size, as well as the effect of increasing the test set while reducing the training set. The results show that with a small labeled training dataset, the ViT models outperform state-of-the-art models such as EfficientNet and ResNet. The results of this study are promising and show the potential of ViT to be applied to a wide range of remote sensing image analysis tasks.

After decades of development, microrobots have exhibited great application potential in the biomedical field, such as minimally invasive surgery, drug delivery, and bio‐sensing. Compared with conventional medical robotic systems, microrobots may be capable of reaching more narrow and vulnerable regions in the human body with minimal damage. However, limited by the small scale of microrobots, microprocessors, power supplies, and sensors can hardly be integrated on‐board. Thus, new strategies for the actuation and feedback for microrobots need to be explored. Furthermore, the open‐loop control method accomplished by operators may lack accuracy, and long‐duration operation could bring a severe physical challenge in many applications. Consequently, the automatic control of microrobots with the aid of control theories is developed to improve the control efficiency and precision. To further promote the automation level of microrobots, machine learning algorithms are expected to provide a solution to let microrobots adapt to more dynamic environments and undertake more complex medical tasks. Herein, a systematic introduction of the manipulation of microrobots from open‐loop to closed‐loop control is given in this review. It is envisioned that microrobots will play an important role in future biomedical applications.

Nowadays, the development of robots and smart tractors for the automation of sowing, harvesting, weeding etc. is transforming agriculture. Farmers are moving from an agriculture where everything is applied uniformly to a much more targeted farming. This new kind of farming is commonly referred to as precision agriculture. However for autonomous guidance of these agricultural machines and even sometimes for weed detection an accurate detection of crop rows is required. In this paper we propose a new method called CRowNet which uses a convolutional neural network (CNN) and the Hough transform to detect crop rows in images taken by an unmanned aerial vehicle (UAV). The method consists of a model formed with SegNet (S-SegNet) and a CNN based Hough transform (HoughCNet). The performance of the proposed method was quantitatively compared to traditional approaches and it showed the best and most robust result. A good crop row detection rate of 93.58% was obtained with an IoU score per crop row above 70%. Moreover the model trained on a given crop field is able to detect rows in images of different types of crops.

On 16 March 2020, as a result of the unprecedented global health crisis linked to the emergence of a new form of coronavirus (COVID-19), the 74 universities of France closed their doors, forcing nearly 1.6 million students, as well as their teachers, to find solutions and initiatives that could ensure continuity in teaching. In the reliance on videoconferencing tools, chat, the sharing of documents/tutorials/videos/podcasts, and the use of social networks, many ideas have emerged, but no consensus has developed nor has a common way of doing things been adopted by a majority of teachers. Some software tools, such as Zoom, have also been questioned over data security issues or excessive intrusion into the student learning process. Nevertheless, in these uncertain times, much had to be done so that students can acquire the requisite knowledge, develop skills, and build on what they have learned. How can we ensure that the learning process is as smooth as possible for everyone involved? How can we evaluate knowledge and skills learned at a distance, and their relevance? Four groups of electronic and electrical engineering students in France were monitored during the containment period in order to provide answers to these questions. Lectures, tutorials, practical work, and projects were carried out using the Microsoft Teams and Zoom video conferencing and chat tools to complement activities made available through the digital work environment. In order to ensure equity among all students, especially in view of the digital divide, open access tools/software/applications have been promoted. In the various surveys completed, the engineering students asserted their complete satisfaction with the learning process, the use of distance tools, and the level of mastery of these tools by their teachers. The results of the various knowledge tests show that, for the same course, distance learning does not reduce the performance of the engineering students. Indeed, they obtained local grades similar to those expected in face-to-face teaching. The results presented in this article are not intended to highlight the virtues of distance education, but rather to open up a debate and reflect more widely on the sustainability of this transformation of education in universities.

Round 4 Submission to the NIST post quantum standardization process

We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES (79.6%). With only 212k parameters, our approach is up to 200 times more compact than other state-of-the-art models while maintaining similar performance. Furthermore, our model can be trained on a single GPU in 3 hours for a fold of the S3DIS dataset, which is 7× to 70× fewer GPU-hours than the best-performing methods. Our code and models are accessible at github.com/drprojects/superpoint_transformer.

Abstract The last decade has seen the rapid development of untethered mobile micro‐ and nanorobots able to navigate liquids by means of external power sources or by harvesting chemicals from their surrounding media. These tiny devices hold great promise for applications in the biomedical field including targeted drug delivery, localized diagnostics, microsurgery, and cell stimulation. However, to translate small‐scale robots from the laboratory to the clinic, many challenges remain. A major obstacle is the lack of imaging technologies that will allow for precise tracking of the devices in vivo. Here, the current progress, challenges, and future possibilities in the monitoring and tracking of biomedical micro‐ and nanomachines using established as well as less conventional imaging technologies are reviewed.

As an integral part of patient care, nursing is required to constantly adapt to changes in the healthcare system, as well as the wider financial and societal environment. Among the key factors driving these changes is the aging of population. Combined with an existing shortage of nursing and caregiving professionals, accommodating for the patients and elderly needs within hospitals, elderly-care facilities and at a home setting, becomes a societal challenge. Amongst the technological solutions that have evolved in response to these developments, nursing and assistive robotics claim a pivotal role. The objective of the present study is to provide an overview of today's landscape in nursing and assistive robotics, highlighting the benefits associated with adopting such solutions in standard clinical practice. At the same time, to identify existing challenges and limitations that essentially outline the area's future directions. Beyond technological innovation, the manuscript also investigates the end-users' angle, being a crucial parameter in the success of robotics solutions operating within a healthcare environment. In this direction, the results of a survey designed to capture the nursing professionals' perspective toward more informed robotics design and development are presented.

BACKGROUND: Several missing value imputation methods for gene expression data have been proposed in the literature. In the past few years, researchers have been putting a great deal of effort into presenting systematic evaluations of the different imputation algorithms. Initially, most algorithms were assessed with an emphasis on the accuracy of the imputation, using metrics such as the root mean squared error. However, it has become clear that the success of the estimation of the expression value should be evaluated in more practical terms as well. One can consider, for example, the ability of the method to preserve the significant genes in the dataset, or its discriminative/predictive power for classification/clustering purposes. RESULTS AND CONCLUSIONS: We performed a broad analysis of the impact of five well-known missing value imputation methods on three clustering and four classification methods, in the context of 12 cancer gene expression datasets. We employed a statistical framework, for the first time in this field, to assess whether different imputation methods improve the performance of the clustering/classification methods. Our results suggest that the imputation methods evaluated have a minor impact on the classification and downstream clustering analyses. Simple methods such as replacing the missing values by mean or the median values performed as well as more complex strategies. The datasets analyzed in this study are available at http://costalab.org/Imputation/ .

This paper aims at designing a nonasymptotic and robust pseudo-state estimator for a class of fractional order linear systems which can be transformed into the Brunovsky's observable canonical form of pseudo-state space representation with unknown initial conditions. First, this form is expressed by a fractional order linear differential equation involving the initial values of the fractional sequential derivatives of the output, based on which the modulating functions method is applied. Then, the former initial values and the fractional derivatives of the output are exactly given by algebraic integral formulae using a recursive way, which are used to nonasymptotically estimate the pseudo-state of the system in noisy environment. Second, the pseudo-state estimator is studied in discrete noisy case, which contains the numerical error due to a used numerical integration method, and the noise error contribution due to a class of stochastic processes. Then, the noise error contribution is analyzed, where an error bound useful for the selection of design parameter is provided. Finally, numerical examples illustrate the efficiency of the proposed pseudo-state estimator, where some comparisons with the fractional order Luenberger-like observer and a new fractional order H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> -like observer are given.

Abstract The field of small‐scale robotics is undergoing a paradigm shift toward the use of soft smart materials. The integration of soft smart components in micro‐ and nanorobotic platforms not only allows for more sophisticated locomotion mechanisms, but also more closely mimicks the functioning of biological systems. A soft hybrid nanorobot that mimics an electric eel, a knifefish with an elongated cylindrical body that is able to generate electricity during its motion, is presented here. These nanoeels consist of a flexible piezoelectric tail composed of a polyvinylidene fluoride–based copolymer, linked to a polypyrrole nanowire, which is decorated with nickel rings for magnetic actuation. Upon the application of rotating magnetic fields, the piezoelectric soft tail is deformed causing changes in its electric polarization. Capitalizing on this magnetically coupled piezoelectric effect, electrostatically enhanced on‐demand release of therapeutic cargo loaded on the surface of the piezoelectric tail is demonstrated. It is also shown that this approach allows for a pulsatile release of payloads. Interestingly, the driving magnetic parameters can be selected to provide the nanoeel with translational motion or to control the discharge kinetics of the drug.

Fused Filament Fabrication (FFF) technology is increasingly applied in automotive, aerospace and medical applications. FFF is one of the most widely used additive manufacturing techniques to manufacture thermoplastics or their composites. FFF enables improvement in both cycle time and total cost of product development. Such improvements are achieved through the quick manufacture of functional prototypes enable real-world product development and testing. While the benefits of FFF are undeniable, its use in demanding applications is hindered by materials properties. The used commodity and standard polymers actually exhibit low to medium thermal and mechanical properties. To overcome this limitation, the aerospace industry looks for high-performance thermoplastics to obtain plastic parts strong enough to be used as a replacement for metal. Recent developments in FFF equipment now enable engineering polymers, such as Polyether ether ketone (PEEK) and Polyether imide (PEI), to be utilized for parts with increased mechanical and thermal properties. Thus, this article reviews and discusses the properties and the printing parameters of PEEK and PEI produced by FFF.

International audience

Cooperative machine learning has many applications, such as data annotation, where an initial model trained with partially labeled data is used to predict labels for unseen data continuously. Predicted labels with a low confidence value are manually revised to allow the model to be retrained with the predicted and revised data. In this paper, we propose an alternative to this approach: an initial training process called Deep Unsupervised Active Learning. Using the proposed training scheme, a classification model can incrementally acquire new knowledge during the testing phase without manual guidance or correction of decision making. The training process consists of two stages: the first stage of supervised training using a classification model, and an unsupervised active learning stage during the test phase. The labels predicted during the test phase, with high confidence, are continuously used to extend the knowledge base of the model. To optimize the proposed method, the model must have a high initial recognition rate. To this end, we exploited the Visual Geometric Group (VGG16) pre-trained model applied to three datasets: Mathematical Image Analysis (AMI), University of Science and Technology Beijing (USTB2), and Annotated Web Ears (AWE). This approach achieved impressive performance that shows a significant improvement in the recognition rate of the USTB2 dataset by coloring its images using a Generative Adversarial Network (GAN). The obtained performances are interesting compared to the current methods: the recognition rates are 100.00%, 98.33%, and 51.25% for the USTB2, AMI, and AWE datasets, respectively.

When a living tissue is subjected to cyclic stretching, the stress-strain curves show a shift down with the increase in the number of cycles until stabilization. This phenomenon is referred to in the literature as a preconditioning and is performed to obtain repeatable and predictable measurements. Preconditioning has been routinely performed in skin tissue tests; however, its effects on the mechanical properties of the material such as viscoelastic response, tangent modulus, sensitivity to strain rate, the stress relaxation rate, etc….remain unclear. In addition, various physical interpretations of this phenomenon have been proposed and there is no general agreement on its origin at the microscopic or mesoscopic scales. The purpose of this study was to investigate the effect of the cyclical stretching and the stress-relaxation tests on the mechanical properties of the porcine skin. Cyclic uniaxial tensile tests at large and constant strain were performed on different skin samples. The change in the reaction force, and skin's tangent modulus as a function of the number of cycles, as well as the strain rate effect on the mechanical behavior of skin samples after cycling were investigated. Stress-relaxation tests were also performed on skin samples. The change in the reaction force as a function of relaxation time and the strain rate effect on the mechanical behavior of skin samples after the stress-relaxation were investigated. The mechanical behavior of a skin sample under stress-relaxation test was modeled using a combination of hyperelasticity and viscoelasticity. Overall, the results showed that the mechanical behavior of the skin was strongly influenced by cycling and stress relaxation tests. Indeed, it was observed that the skin's resistance decreased by about half for two hours of cycling; the tangent modulus degraded by nearly 30% and skin samples became insensitive to the strain rates and accumulated progressively an inelastic deformation over time during cycling. Finally, the hysteresis loops became very narrow at the end of cycling and after relaxation process.

The integer order differentiation by integration method based on the Jacobi orthogonal polynomials for noisy signals was originally introduced by Mboup, Join and Fliess. We propose to extend this method from the integer order to the fractional order to estimate the fractional order derivatives of noisy signals. Firstly, two fractional order differentiators are deduced from the Jacobi orthogonal polynomial filter, using the Riemann-Liouville and the Caputo fractional order derivative definitions respectively. Exact and simple formulae for these differentiators are given by integral expressions. Hence, they can be used for both continuous-time and discrete-time models in on-line or off-line applications. Secondly, some error bounds are provided for the corresponding estimation errors. These bounds allow to study the design parameters' influence. The noise error contribution due to a large class of stochastic processes is studied in discrete case. The latter shows that the differentiator based on the Caputo fractional order derivative can cope with a class of noises, whose mean value and variance functions are polynomial time-varying. Thanks to the design parameters analysis, the proposed fractional order differentiators are significantly improved by admitting a time-delay. Thirdly, in order to reduce the calculation time for on-line applications, a recursive algorithm is proposed. Finally, the proposed differentiator based on the Riemann-Liouville fractional order derivative is used to estimate the state of a fractional order system and numerical simulations illustrate the accuracy and the robustness with respect to corrupting noises.