Machine Learning With Data Assimilation and Uncertainty Quantification for Dynamical Systems:A Review

Data assimilation(DA)and uncertainty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics.Typical applications span from computational fluid dynamics(CFD)to geoscience and climate systems.Recently,much effort has been given in combining DA,UQ and machine learning(ML)techniques.These research efforts seek to address some critical challenges in high-dimensional dynamical systems,including but not limited to dynamical system identification,reduced order surrogate modelling,error covariance specification and model error correction.A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains,resulting in the necessity for a comprehensive guide.This paper provides the first overview of state-of-the-art researches in this interdisciplinary field,covering a wide range of applications.This review is aimed at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models,but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems.Therefore,this article has a special focus on how ML methods can overcome the existing limits of DA and UQ,and vice versa.Some exciting perspectives of this rapidly developing research field are also discussed.Index Terms-Data assimilation(DA),deep learning,machine learning(ML),reduced-order-modelling,uncertainty quantification(UQ).

A decision aid for the port placement problem in robot-assisted hysterectomy

Objective:In robot-assisted minimally invasive surgery,proper port positioning ensures that surgical tools have adequate access to the surgical site and avoids mid-surgery collisions of robotic arms.To date,several guidelines have been proposed for more accurate port placement.However,challenges remain due to variations in patient morphology,anatomy,and,in particular,organ displacement due to insuf-flation in certain laparoscopic procedures.The objective of this study was to design and develop a de-cision aid for optimal port placement in robot-assisted hysterectomy that accounts for patient variability and organ displacement due to insufflation.Methods:Three components were constructed:a robot model,a patient-specific model,and an opti-mization algorithm.The three components were integrated,and the system was verified using four different patients who underwent robotic hysterectomy.Once verified,two expert surgeons were asked to evaluate the decision aid for face and construct validity.A usability test was conducted using a torso phantom with target organs located in three different locations.Two expert surgeons performed a simulated hysterectomy task with and without the decision aid to evaluate performance and satisfaction.Results:The optimization algorithm was sensitive to individual differences in anatomy in the four pa-tients.Expert surgeons successfully established face and construct validity.Usability test results showed a 28%-40% reduction in time to task completion with the optimized ports compared to expert-determined port locations without using the decision aid.Conclusions:The decision aid,based on an individualized patient-specific model,robot model,and optimization algorithm,was shown to be effective at addressing the challenges of displaced organs due to insufflation in robot-assisted hysterectomy.The face and construct validity of the decision aid was established by expert surgeons,while efficiency gains in task performance were demonstrated experimentally.

Exploitation of Electromagnetic Models for Sea Wind Speed Estimation from C-Band Sentinel-1 Images

Among the different available wind sources, i.e. in situ measurements, numeric weather models, the retrieval of wind speed from Synthetic Aperture Radar (SAR) data is one of the most widely used methods, since it can give high wind resolution cells. For this purpose, one can find two principal approaches: via electromagnetic (EM) models and empirical (EP) models. In both approaches, the Geophysical Model Functions (GMFs) are used to describe the relation of radar scattering, wind speed, and the geometry of observations. By knowing radar scattering and geometric parameters, it is possible to invert the GMFs to retrieve wind speed. It is very interesting to compare wind speed estimated by the EM models, general descriptions of radar scattering from sea surface, to the one estimated by the EP models, specific descriptions for the inverse problem. Based on the comparisons, some ideas are proposed to improve the performance of the EM models for wind speed retrieval.

Review of Anomaly Detection Systems in Industrial Control Systems Using Deep Feature Learning Approach

Industrial Control Systems (ICS) or SCADA networks are increasingly targeted by cyber-attacks as their architectures shifted from proprietary hardware, software and protocols to standard and open sources ones. Furthermore, these systems which used to be isolated are now interconnected to corporate networks and to the Internet. Among the countermeasures to mitigate the threats, anomaly detection systems play an important role as they can help detect even unknown attacks. Deep learning which has gained a great attention in the last few years due to excellent results in image, video and natural language processing is being used for anomaly detection in information security, particularly in SCADA networks. The salient features of the data from SCADA networks are learnt as hierarchical representation using deep architectures, and those learnt features are used to classify the data into normal or anomalous ones. This article is a review of various architectures such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Stacked Autoencoder (SAE), Long Short Term Memory (LSTM), or a combination of those architectures, for anomaly detection purpose in SCADA networks.

Shared Resource Quality Monitoring and Dynamic Trust Management in a Community Cloud

The collaboration tools offered by Cloud Computing have increased the need to share data and services within companies or between autonomous organizations. This has led to the deployment of community cloud infrastructures. However, several challenges will arise from this grouping of heterogeneous organizations. One of the main challenges is the management of trust between the actors of the community. Trust issues arise from the uncertainty about the quality of the resources and entities involved. The quality of a resource can be examined from a security or functional perspective. Therefore, ensuring security and monitoring the quality of resources is to ensure a high level of trust. Therefore, we propose in this paper a technique for dynamic trust management and quality monitoring of resources shared between organizations. Our approach consists, on the one hand, in evaluating the quality of resources based on quality of service measurement attributes and, on the other hand, in updating the trust values according to the information deduced from these measurements. The proposed framework is evaluated in terms of resource sharing success rate and execution time. Experimental results and comparison with TNA-SL and InterTrust models show that the framework can identify and track the behavior of malicious organizations with relatively low execution time.

Human Skeleton Detection, Modeling and Gesture Imitation Learning for a Social Purpose

Gesture recognition is topical in computer science and aims at interpreting human gestures via mathematical algorithms. Among the numerous applications are physical rehabilitation and imitation games. In this work, we suggest performing human gesture recognition within the context of a serious imitation game, which would aim at improving social interactions with teenagers with autism spectrum disorders. We use an artificial intelligence algorithm to detect the skeleton of the participant, then model the human pose space and describe an imitation learning method using a Gaussian Mixture Model in the Riemannian manifold.

The Gaussian Beam Summation and the Gaussian Launching Methods in Scattering Problem

This paper is mainly devoted to application of the Gaussian beam summation technique in electromagnetic simulations problem. Gaussian beams are asymptotic solutions of the Helmholtz equation within the paraxial approximation. Since they are insensitive to ray transition region, several techniques based on Gaussian beam are used to evaluate high frequency EM wave equation, which overcome partially or fully the difficulties of singular regions (caustics, zero field in shadow zones). This paper concentrates on the explicit formulation of the electromagnetic field scattered from radar target. In this approach, when the incident field illuminates the target, the scattering is accounted in a complex weighing function. The wave field at a receiver is evaluated as superposition of Gaussian beams concentrated close to rays emerging from the target, passing through the neighbor of the receiver.

Trust Assessment Model Based on a Zero Trust Strategy in a Community Cloud Environment

The adoption of Cloud Computing services in everyday business life has grown rapidly in recent years due to the many benefits of this paradigm. The various collaboration tools offered by Cloud Computing have eliminated or reduced the notion of distance between entities of the same company or between different organizations. This has led to an increase in the need to share resources (data and services). Community Cloud environments have thus emerged to facilitate interactions between organizations with identical needs and with specific and high security requirements. However, establishing trust and secure resource sharing relationships is a major challenge in this type of complex and heterogeneous environment. This paper proposes a trust assessment model (SeComTrust) based on the Zero Trust cybersecurity strategy. First, the paper introduces a community cloud architecture subdivided into different security domains. Second, it presents a process for selecting a trusted organization for an exchange based on direct or recommended trust value and reputation. Finally, a system for promoting or relegating organizations in the different security domains is applied. Experimental results show that our model guarantees the scalability of a community cloud with a high success rate of secure and quality resource sharing.

An Hybrid Model for Rectal Tumour Response Prediction during Radiotherapy

A hybrid model is proposed in this study to predict rectal tumour response during radiotherapy treatment. As the oxygen partial pressure distribution (pO2) is a data which is naturally represented at the microscopic scale, we firstly estimate the optimal pO2 distribution using both a diffusion equation and a discrete multi-scale model (that we proposed in a previous study). The aim is to use the effectiveness in algorithmic complexity of the discrete model and its multi-scale aspect in this work to estimate biological information at cellular scale and then construct them at macroscopic scale. Secondly, the obtained pO2 distribution results are used as an input of a biomechanical model in order to simulate tumour volume evolution during radiotherapy. FDG PET images of 21 rectal cancer patients undergoing radiotherapy are used to simulate the tumour evolution during the treatment. The simulated results using the proposed hybride model, allow the interpretation of tumour aggressiveness.

A Decision Support Framework for the Choice of Languages and Methods for the Design of Real Time Embedded Systems

The choice of methods or design languages is a crucial phase in the development of systems and software, also for real time and embedded systems. An open question that remains in the design of these types of systems is to build a method, or to choose one among those existing, capable to cover the life cycle of a project, and particularly the development phases. This article contributes to answer the question, by proposing an approach based on a multi-criteria comparative study, of few languages and methods dedicated to the design of real time and embedded systems. The underlying objective of this work is to present to designers a wide range of approaches, and elements that can guide their choices. In order to reach this goal, we propose different comparison criteria. Each criterion is divided into sub-criteria, so that the designers can refine their choices according to the qualities they prefer and wish to have in the method or language. We also define a rating scale which is used to assess the retained languages and methods. The scores obtained from this assessment are presented in tables, one table per criterion, followed by a summary table giving the overall scores. Graphics built from these tables are provided and intend to facilitate the judgement and thus the choice of the designers.

Numerical Modeling of Electromagnetic Scattering from Sea Surface Covered by Oil

The aim of this work is to study the impacts of the oil spills on the electromagnetic scattering of the ocean surfaces in bistatic and monostatic configurations. Therefore, in this paper, we will study the influence of the pollutants (oil spills) on the physical and geometrical properties of sea surface. In recent literature, the study of the electromagnetic scattering from contaminated sea surface (sea surface covered by oil spill) was limited in monostatic case. In this paper, we will study this effect in bistatic configuration, which is interested in presence of pollution in sea surface. Indeed, we will start the numerical analysis of the bistatic scattering coefficients of a clean sea surface. Then, we will study the electromagnetic signature from sea surface covered by oil spills in bistatic case using the numerical Forward-Backward Method (FBM). The obtained numerical simulation of bistatic scattering coefficients of clean and contaminated sea surface is studied as a function of various parameters (frequency, incident angle, sea state, type of pollutant…). And the obtained results are also compared with those published in the literature, including those using asymptotic methods.

Habits on Social Networks at Workplace: A Survey of Motivations and Behaviour

This article explores the use of social networks by workers in Abidjan, Côte d’Ivoire, with particular emphasis on a descriptive or quantitative analysis aimed at understanding motivations and methods of use. More than five hundred and fifty questionnaires were distributed, highlighting workers’ preferred digital channels and platforms. The results indicate that the majority use social media through their mobile phones, with WhatsApp being the most popular app, followed by Facebook and LinkedIn. The study reveals that workers use social media for entertainment purposes and to develop professional and social relationships, with 55% unable to live without social media at work for recreational activities. In addition, 35% spend on average 1 to 2 hours on social networks, mainly between 12 p.m. and 2 p.m. It also appears that 46% believe that social networks moderately improve their productivity. These findings can guide marketing strategies, training, technology development and government policies related to the use of social media in the workplace.

40 Gb/s NRZ-DQPSK data wavelength conversion with amplitude regeneration using four-wave mixing in a quantum dash semiconductor optical amplifier

Differential quadrature phase shift keying （DQPSK） modulation is attractive in high-speed optical communications because of its resistance to fiber non-linearities and more efficient use of fiber bandwidth compared to conventional intensity modulation schemes. Because of its wavelength conversion ability and phase preservation, semiconductor optical amplifier （SOA） four- wave mixing （FWM） has attracted much attention. We experimentally study wavelength conversion of 40 Gbit/s （20 Gbaud） non-return-to-zero （NRZ）-DQPSK data using FWM in a quantum dash SOA with 20 dB gain and 5 dBm output saturation power. Q factor improvement and eye diagram reshaping is shown for up to 3 nm pump-probe detuning and is superior to that reported for a higher gain bulk SOA.