Laboratoire d’Informatique Signal et Image de la Côte d’Opale

Industry 4.0 is a revolution in manufacturing by introducing disruptive technologies such as Internet of Things (IoT) and cloud-computing into the heart of the factory. The resulting increased automation and the improved production synergy between stocks, supply chains and customer demands, come along with the threats and attacks from the Internet. Despite extensive literature on the cybersecurity topic, many actors in manufacturing factories are just realizing the impact of cybersecurity in the preservation of their business. This paper introduces step-by-step the concepts and practical aspects of an Industry 4.0 manufacturing factory that are related to cybersecurity. Based on a subdivision of a typical factory into several generic perimeters, we present the vulnerabilities and threats regarding the network and devices usually found in each perimeter. Therefore, it is more efficient to present the recent proposals of the literature regarding cybersecurity guidelines and solutions in Industry 4.0. Instead of spreading a lot of references regarding every aspect of cybersecurity, we focused on a limited number of papers among the recent references. However, for each paper, we provide the details about the purpose of the proposal, the methodology adopted, the technical solution developed and its evaluation by the authors. These solutions range from classical cybersecurity countermeasures to innovative ones, such as those based on honeypots and digital twins. In order to deliver a review also useful to non scientists, we present our guidelines along with those of some organizations involved in cybersecurity harmonization and standardization in the world.

We expose and contrast the impact of landscape characteristics on the performance of search heuristics for black-box multiobjective combinatorial optimization problems. A sound and concise summary of features characterizing the structure of an arbitrary problem instance is identified and related to the expected performance of global and local dominance-based multiobjective optimization algorithms. We provide a critical review of existing features tailored to multiobjective combinatorial optimization problems, and we propose additional ones that do not require any global knowledge from the landscape, making them suitable for large-size problem instances. Their intercorrelation and their association with algorithm performance are also analyzed. This allows us to assess the individual and the joint effect of problem features on algorithm performance, and to highlight the main difficulties encountered by such search heuristics. By providing effective tools for multiobjective landscape analysis, we highlight that multiple features are required to capture problem difficulty, and we provide further insights into the importance of ruggedness and multimodality to characterize multiobjective combinatorial landscapes.

This paper presents the “Multi-Role Project” method (MRP), a broadly applicable project-based learning method, and describes its implementation and evaluation in the context of a Science, Technology, Engineering, and Mathematics (STEM) course. The MRP method is designed around a meta-principle that considers the project learning activity as a role-playing game based on two projects: a learning project and an engineering project. The meta-principle is complemented by five principles that provide a framework to guide the working practices of student teams: distribution of responsibilities; regular interactions and solicitations within the team; anticipation and continuous improvement; positive interdependence and alternating individual/collective work; and open communication and content management. This paper presents the implementation of MRP in a course teaching software engineering, UML language, and project management. The results show that MRP helped the course's students to acquire important professional knowledge and skills, experience near-real-world professional realities, and develop their abilities to work both in teams and autonomously.

Nevergrad is an open source platform for black-box optimization. Join the user group! And if you like Nevergrad, please support us by adding a star on GitHub (https://github.com/facebookresearch/nevergrad).

Recently, Dufrenois and Noyer proposed a one class Fisher's linear discriminant to isolate normal data from outliers. In this paper, a kernelized version of their criterion is presented. Originally on the basis of an iterative optimization process, alternating between subspace selection and clustering, I show here that their criterion has an upper bound making these two problems independent. In particular, the estimation of the label vector is formulated as an unconstrained binary linear problem (UBLP) which can be solved using an iterative perturbation method. Once the label vector is estimated, an optimal projection subspace is obtained by solving a generalized eigenvalue problem. Like many other kernel methods, the performance of the proposed approach depends on the choice of the kernel. Constructed with a Gaussian kernel, I show that the proposed contrast measure is an efficient indicator for selecting an optimal kernel width. This property simplifies the model selection problem which is typically solved by costly (generalized) cross-validation procedures. Initialization, convergence analysis, and computational complexity are also discussed. Lastly, the proposed algorithm is compared with recent novelty detectors on synthetic and real data sets.

Abstract Advanced analytics are fundamental to transform large manufacturing data into resourceful knowledge for various purposes. In its very nature, such “industrial big data” can relay its usefulness to reach further utilitarian applications. In this context, Machine Learning (ML) is among the major predictive modeling approaches that can enable manufacturing researchers and practitioners to improve the product quality and achieve resource efficiency by exploiting large amounts of data (which is collected during manufacturing process). However, disposing ML algorithms is a challenging task for manufacturing industrial actors due to the prior specification of one or more algorithms hyperparameters (HPs) and their values. Moreover, manufacturing industrial actors often lack the technical expertise to apply advanced analytics. Consequently, it necessitates frequent consultations with data scientists; but such collaborations tends to cost the delays, which can generate the risks such as human-resource bottlenecks. As the complexity of these tasks increases, so does the demand for support solutions. In response, the field of automated ML (AutoML) is a data mining-based formalism that aims to reduce human effort and speedup the development cycle through automation. In this regard, existing approaches include evolutionary algorithms, Bayesian optimization, and reinforcement learning. These approaches mainly focus on providing the user assistance by automating the partial or entire data analysis process, but they provide very limited details concerning their impact on the analysis. The major goal of these conventional approaches has been generally focused on the performance factors, while the other important and even crucial aspects such as computational complexity are rather omitted. Therefore, in this paper, we present a novel meta-learning based approach to automate ML predictive models built over the industrial big data. The approach is leveraged with development of, AMLBID, an Automated ML tool for Big Industrial Data analyses. It attempts to support the manufacturing engineers and researchers who presumably have meager skills to carry out the advanced analytics. The empirical results show that AMLBID surpasses the state-of-the-art approaches and could retrieve the usefulness of large manufacturing data to prosper the research in manufacturing domain and improve the use of predictive models instead of precluding their outcomes.

This paper presents a method for joint detection and tracking of vehicles with a scanning laser rangefinder. The lidar measurements of an object have the particularity to be spatially distributed, which generally leads to a detection step before any tracking. Differently, the proposed method relies on the raw measurement processing without any detection step, which improves the overall performance in multiobject tracking while providing good estimation accuracies. The solution uses the sequential Monte Carlo methods by incorporating the geometric invariant of the objects of interest (vehicles). This approach also offers an efficient solution to the problem of multitarget tracking by integrating naturally the track management in the filtering process.

To provide an accurate positioning, the land vehicle navigation applications are based on global positioning system (GPS). The addition of a digital road map allows locating the vehicle continuously and helps the driver to get the best path. These systems are usually enhanced with dead reckoning sensors due to GPS outages in urban areas in particular. For instance, the odometer sensors can be used to correct the vehicle location in this case. We present here a global estimation method of solving the fusion problem of the GPS, odometer, and digital road map measurements in the presence of GPS outages. It relies on a hybrid filter that takes advantage of the combination of a Kalman filter, which computes the linear part of the state equations and a particle filter to provide an optimal resolution scheme. When GPS fails, the filter fuses all available pseudorange measures to improve the vehicle positioning. In the case of an urban transport scenario, the results show that the number of particles is significantly reduced to achieve the same performance of a single particle filter in terms of accuracy. Moreover, software solutions can be developed for real-time applications.

ITST 2017 - 15th International Conference on ITS Telecommunications, Warsaw, POLOGNE, 29-/05/2017 - 31/05/2017

The emergence of BPMN as a standard notation to express the business processes is based on its simplicity of notations and its exhaustive expressiveness. Nevertheless the lack of formal semantics in the BPMN can cause syntactic and structural errors. The former requires less effort to be checked, while the later usually requires attention to prove some properties, like deadlock-freedom and livelock-freedom. In this paper, we address the issue of detecting the structural errors with an approach based on model checking. It verifies the soundness of business process model and helps the business modelers to avoid the deadlocks, livelocks, and multiple terminations errors.

The Machine Learning (ML) based solutions in manufacturing industrial contexts often require skilled resources. More practical non-expert software solutions are then desired to enhance the usability of ML algorithms. The algorithm selection and configuration is one of the most difficult tasks for users like manufacturing specialists. The identification of the most appropriate algorithm in an automatic manner is among the major research challenges to achieve optimal performance of ML tools. In this paper, we present an auto-explained Automated Machine Learning tool for Big Industrial Data (AMLBID) to better cope with the prominent challenges posed by the evolution of Big Industrial Data. It is a meta-learning based decision support system for the automated selection and tuning of implied hyperparameters for ML algorithms. Moreover, the framework is equipped with an explainer module that makes the outcomes transparent and interpretable for well-performing ML systems.

Moving foreground detection is a very important step for many applications such as human behavior analysis for visual surveillance, model-based action recognition, road traffic monitoring, etc. Background subtraction is a very popular approach, but it is difficult to apply given that it must overcome many obstacles, such as dynamic background changes, lighting variations, occlusions, and so on. In the presented work, we focus on this problem (foreground/background segmentation), using a type-2 fuzzy modeling to manage the uncertainty of the video process and of the data. The proposed method models the state of each pixel using an imprecise and adjustable Gaussian mixture model, which is exploited by several fuzzy classifiers to ultimately estimate the pixel class for each frame. More precisely, this decision not only takes into account the history of its evolution, but also its spatial neighborhood and its possible displacements in the previous frames. Then we compare the proposed method with other close methods, including methods based on a Gaussian mixture model or on fuzzy sets. This comparison will allow us to assess our method’s performance, and to propose some perspectives to this work.

Routing protocols for vehicular ad hoc networks resort to clustering in order to optimize network performance. Concerning the optimized link state routing protocol and the plethora of its derivatives, the multipoint relaying (MPR) technique has proven its efficiency as an accurate clustering scheme over the last two decades. However, it has been emphasized recently that the MPR technique, which was originally designed for open areas, does not benefit from the particular configuration of road sections, which are intrinsically spatially constrained. A clustering scheme exploiting this particularity, namely chain-branch-leaf (CBL), has been introduced in order to enhance the flooding of broadcast traffic, including that related to routing operations. In this paper, both MPR and CBL are evaluated through MATLAB simulation over several scenarios based on realistic road configurations and traffic generated with SUMO simulator. The results show that CBL actually reduces the number of nodes acting as relays (cluster-heads) in the network, thus decreasing the routing traffic related to creation and retransmission of topology control messages. Also, they show that, with CBL, the nodes chosen as relays remain longer in this role, thus favoring the overall network stability, and that most of the nodes remain attached longer to the same relay than with the MPR technique.

Phytoplankton is an important indicator of water quality assessment. To understand phytoplankton dynamics, many fixed buoys and ferry boxes were implemented, resulting in the generation of substantial data signals. Collected data are used as inputs of an effective monitoring system. The system, based on unsupervised hidden Markov model (HMM), is designed not only to detect phytoplancton blooms but also to understand their dynamics. HMM parameters are usually estimated by an iterative expectation-maximization (EM) approach. We propose to estimate HMM parameters by using spectral clustering algorithm. The monitoring system is assessed based on database signals from MAREL-Carnot station, Boulogne-sur-Mer, France. Experimental results show that the proposed system is efficient to detect environmental states such as phytoplankton productive and nonproductive periods without a priori knowledge. Furthermore, discovered states are consistent with biological interpretation.

This paper presents a new Remote Hyperspectral Imaging System (RHIS) embedded on an Unmanned Aquatic Drone (UAD) for plastic detection and identification in coastal and freshwater environments. This original system, namely the Remotely Operated Vehicle of the University of Littoral Côte d’Opale (ROV-ULCO), works in a near-field of view, where the distance between the hyperspectral camera and the water surface is about 45 cm. In this paper, the new ROV-ULCO system with all its components is firstly presented. Then, a hyperspectral image database of plastic litter acquired with this system is described. This database contains hyperspectral data cubes of different plastic types and polymers corresponding to the most-common plastic litter items found in aquatic environments. An in situ spectral analysis was conducted from this benchmark database to characterize the hyperspectral reflectance of these items in order to identify the absorption feature wavelengths for each type of plastic. Finally, the ability of our original system RHIS to automatically recognize different types of plastic litter was assessed by applying different supervised machine learning methods on a set of representative image patches of marine litter. The obtained results highlighted the plastic litter classification capability with an overall accuracy close to 90%. This paper showed that the newly presented RHIS coupled with the UAD is a promising approach to identify plastic waste in aquatic environments.

In this paper, we consider the problem of blindly calibrating a mobile sensor network-i.e., determining the gain and the offset of each sensor-from heterogeneous observations on a defined spatial area over time. For that purpose, we propose to revisit blind sensor calibration as an informed nonnegative matrix factorization (NMF) problem with missing entries. In the considered framework, one matrix factor contains the calibration structure of the sensors-and especially the values of the sensed phenomenon- while the other one contains the calibration parameters of the whole sensor network. The available information is taken into account by using a specific parameterization of the NMF problem. Moreover, we also consider additional NMF constraints which can be independently taken into account, i.e., an approximate constraint over the mean calibration parameters and a sparse approximation of the sensed phenomenon over a known dictionary. The enhancement of our proposed approaches is investigated through more than 5000 simulations and is shown to be accurate for the considered application and to outperform a multihop micro-calibration technique as well as a method based on low-rank matrix completion and nonnegative least squares.

This study concerns the implementation of an underwater positioning system in shallow water environment. Shallow water localization of the beacon is done by using the propagation of acoustic signals in water. The experiment is based on the use of a boat equipped with two hydrophones and an emitting beacon. The signal received on each sensors are processed to compute the difference in time arrival between them (TDOA) and to derive the boat location. In this paper a close loop architecture is proposed to process the signal. This architecture based on a Kalman filter allows to track the peaks of correlation in a delay Doppler map. Underwater tests are done to validate the method. They lead to a precision of about one meter.

In this paper, we consider the problem of blindly calibrating a mobile sensor network-i.e., determining the gain and the offset of each sensor-from heterogeneous observations on a defined spatial area over time. For that purpose, we previously proposed a blind sensor calibration method based on Weighted Informed Nonnegative Matrix Factorization with missing entries. It required a minimum number of rendezvous-i.e., data sensed by different sensors at almost the same time and place-which might be difficult to satisfy in practice. In this paper we relax the rendezvous requirement by using a sparse decomposition of the signal of interest with respect to a known dictionary. The calibration can thus be performed if sensors share some common support in the dictionary, and provides a consistent performance even if no sensors are in exact rendezvous.

status: Published online

International audience