Search

Abstract The manufacturing processes of composite materials modify the internal structure and therefore the mechanical properties of cured composite parts. In particular, draping of woven prepregs leads to angle changes between warp and weft yarns when the geometry of the part is double curved. We here propose to take the fiber reorientation caused by forming into account in the structural analysis of a cured composite. For this purpose, the simulation for the forming of prepregs was based on a rate constitutive equation. Then, a simple orthotropic elastic model of the cured composite was developed to take into account the angle change created by the forming. An experimental validation of this approach was performed in the case of traction on a cured test specimen after a bias extension test. Structural analyses of 3D composite parts obtained by draping also showed that it was necessary to take into account the reorientation of the fibers. [ABSTRACT FROM AUTHOR]

With the increasing size and complexity of available databases, existing machine learning and data mining algorithms are facing a scalability challenge. In many applications, the number of features describing the data could be extremely high. This hinders or even could make any further exploration infeasible. In fact, many of these features are redundant or simply irrelevant. Hence, feature selection plays a key role in helping to overcome the problem of information overload especially in big data applications. Since many complex datasets could be modeled by graphs of interconnected labeled elements, in this work, we are particularly interested in feature selection for subgraph patterns. In this paper, we propose MR-SimLab , a MapReduce -based approach for subgraph selection from large input subgraph sets. In many applications, it is easy to compute pairwise similarities between labels of the graph nodes. Our approach leverages such rich information to measure an approximate subgraph matching by aggregating the elementary label similarities between the matched nodes. Based on the aggregated similarity scores, our approach selects a small subset of informative representative subgraphs. We provide a distributed implementation of our algorithm on top of the MapReduce framework that optimizes the computational efficiency of our approach for big data applications. We experimentally evaluate MR-SimLab on real datasets. The obtained results show that our approach is scalable and that the selected subgraphs are informative. [ABSTRACT FROM AUTHOR]

The cloud computing allows to use virtually infinite resources, and seems to be a new promising opportunity to solve scientific computing problems. The MapReduce parallel programming model is a new framework favoring the design of algorithms for cloud computing. Such framework favors processing of problems across huge datasets using a large number of heterogeneous computers over the web. In this paper, we are interested in evaluating how the MapReduce framework can create an innovative way for solving operational research problems. We proposed a MapReduce-based approach for the shortest path problem in large-scale real-road networks. Such a problem is the cornerstone of any real-world routing problem including the dial-a-ride problem (DARP), the pickup and delivery problem (PDP) and its dynamic variants. Most of efficient methods dedicated to these routing problems have to use the shortest path algorithms to construct the distance matrix between each pair of nodes and it could be a time-consuming task on a large-scale network due to its size. We focus on the design of an efficient MapReduce-based approach since a classical shortest path algorithm is not suitable to accomplish efficiently such task. Our objective is not to guarantee the optimality but to provide high quality solutions in acceptable computational time. The proposed approach consists in partitioning the original graph into a set of subgraphs, then solving the shortest path on each subgraph in a parallel way to obtain a solution for the original graph. An iterative improvement procedure is introduced to improve the solution. It is benchmarked on a graph modeling French road networks extracted from OpenStreetMap. The results of the experiment show that such approach achieves significant gain of computational time. [ABSTRACT FROM AUTHOR]

Recently, graph mining approaches have become very popular, especially in certain domains such as bioinformatics, chemoinformatics and social networks. One of the most challenging tasks is frequent subgraph discovery. This task has been highly motivated by the tremendously increasing size of existing graph databases. Due to this fact, there is an urgent need of efficient and scaling approaches for frequent subgraph discovery. In this paper, we propose a novel approach for large-scale subgraph mining by means of a density-based partitioning technique, using the MapReduce framework. Our partitioning aims to balance computational load on a collection of machines. We experimentally show that our approach decreases significantly the execution time and scales the subgraph discovery process to large graph databases. [ABSTRACT FROM AUTHOR]

Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities. [ABSTRACT FROM AUTHOR]

Tectonic inversion in the Bouhedma-Boudouaou Mountains was investigated through recent field work and seismic lines interpretation calibrated with petroleum well data. Located to the Central-Southern Atlas of Tunisia, this area signed shortened intra-continental fold-and-thrust belts. Two dissymmetric anticlines characterize Bouhedma – Boudouaou major fold. These structures show a strong virgation respectively from E-W to NNE-SSW as a response to the interference between both tectonic inversion and tectonic inheritance. This complex geometry is driven by Mesozoic rifting, which marked an extensional inherited regime. A set of late Triassic-Early Jurassic E-W and NW-SE normal faults dipping respectively to the North and to the East seems to widely affect the overall geodynamic evolution of this domain. They result in major thickness changes across the hanging wall and the footwall blocks in response with the rifting activity. Tectonic inversion is inferred from convergence between African and European plates since late Cretaceous. During Serravalian - Tortonian event, NW-SE trending paroxysm led to: 1) folding of pre-inversion and syn-inversion strata, 2) reactivation of pre-existing normal faults to reverse ones and 3) orogeny of the main structures with NE-SW and E-W trending. The compressional feature still remains active during Quaternary event (Post-Villafranchian) with N-S trending compression. Contraction during inversion generates folding and internal deformation as well as Fault-Propagation-Fold and folding related strike. [ABSTRACT FROM AUTHOR]

• Decision trees construction outputs suffer from over-fitting and complexity problems. • Attribute selection and data sampling combination aims to overcome construction problems. • This paper presents a PSO approach to select an optimal attribute and sample combination. • The optimal selected solution helps in avoiding over-fitting and complexity problems. • The empirical results clearly show that the proposed approach shows good solutions. Decision trees are efficient means for building classification models due to the compressibility, simplicity and ease of interpretation of their results. However, during the construction phase of decision trees, the outputs are often large trees that are affected by many uncertainties in the data (particularity, noise and residual variation). Combining attribute selection and data sampling presents one of the most promising research directions to overcome decision tree construction problems. However, the search space composed of all possible combinations of subsets of training samples and attributes is extremely large. In this paper, a novel approach is presented that allows generating an optimized decision tree by selecting an optimal couple of training samples and attributes subsets for training. As the search space of candidate couples of training samples and attributes subsets is extremely large, we use particle swarm optimization to make the search of an " optimal " solution tractable. The selected optimized solution helps in avoiding over-fitting and complexity problems suffered in the construction phase of decision trees. We conducted an extensive experimental evaluation on 22 datasets from the UCI Machine Learning Repository. The obtained results show that the proposed approach outperforms state-of-the-art classical as well as evolutionary decision tree construction methods in terms of simplicity, accuracy, and F-measure. We further evaluate our approach on a real-world engineering application for condition monitoring of rotating machinery under severe non-stationary conditions. The obtained results showed that the proposed approach allowed to optimize the use of instantaneous angular speed to diagnose gears defects. [ABSTRACT FROM AUTHOR]

The primary task of a memory-based collaborative filtering (CF) recommendation system is to select a group of nearest (similar) user neighbors for an active user. Traditional memory-based CF schemes tend to only focus on improving as much as possible the accuracy by recommending familiar items ( i.e ., popular items over the group). Yet, this may reduce the number of items that could be recommended and consequently weakens the chances of recommending novel items. To address this problem, it is desirable to consider recommendation coverage when selecting the appropriate group. This could help in simultaneously making both accurate and diverse recommendations. In this paper, we propose to focus mainly on the growing of the large search space of users’ profiles and to use an evolutionary multi-objective optimization-based recommendation system to pull up a group of profiles that maximizes both similarity with the active user and diversity between its members. In such manner, the recommendation system will provide high performances in terms of both accuracy and diversity. The experimental results on the Movielens benchmark and on a real-world insurance dataset show the efficiency of our approach in terms of accuracy and diversity compared to state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Random Forest is an ensemble classification approach. It aims to design a discrete finite group of decision trees constructed based on bootstrap samples and random attribute selection. Random Forests have strong generalization capacities due to the variance in the training and attribute couple subsets used for constructing different decision trees in the forest. However, to construct a robust and effective random forest, two main issues need to be taken into account namely: (1) increasing the accuracy and diversity of decision trees; (2) decreasing the number of decision trees. In this paper, a genetic algorithm-based approach to tackle the aforementioned challenges related to random forest construction is proposed. Three objectives are taken into consideration. First, strengthening the classification accuracy of individual decision trees as well as that of the forest. Second, making use of diversity measures among the decision trees to improve the generalization of the constructed model. Third, minimizing the number of trees in the forest and finding an optimal subset of the random forest. An experimental evaluation on several datasets from the UCI Machine Learning Repository is conducted. The obtained results show that the proposed approach outperforms state-of-the-art classical as well as evolutionary random forest construction methods. Finally, the proposed approach is used to build a reliable random forest model for detecting Botnet traffic in Internet of Things environment. • We propose a genetic algorithm to construct an improved random forest. • We design a theoretic solution allowing a smart convergence to the best solutions. • We propose a Powerset system to optimize the encoding of the forests in chromosomes. • Our objective function optimizes the accuracy and diversity of the trees of models. • Application to the detection of Botnet traffic in Internet of Things networks. [ABSTRACT FROM AUTHOR]

In the North African Atlas, Triassic sedimentary rocks exhibit a variety of deformation styles that are caused by the interaction between halokinesis, tectonics and sedimentation. This paper aims to present an integrated study documenting the occurrence of salt-tectonic processes in the Maknassy-Mezzouna orogenic system. The interpretation of both, field mapping and seismic data suggests the existence of a complex tectonic evolution of these Triassic evaporites, with the occurrence of Mesozoic extensional/transtensional and Tertiary compressional/transpressional tectonic regime accompanied by sedimentary loading. This evolution took place along three major events of either lateral or vertical migration of Triassic evaporites. The first one is tectonic-driven and is related to the extensional/transtensional tectonic regime, which occurred during the break-up of Pangea and rifting of Neotethyan Ocean in the Early Jurassic. The second remobilization of salt Triassic rock developed during the Cretaceous. The initial mobilization of the Triassic salt was probably induced by sedimentary loading with a limited contribution of tectonic forces. During its third stage of evolution, salt Triassic rocks evolve into salt sheets due to the shortening deformation occurred during Tertiary and Quaternary in relationship with the closure of the Neotethyan realm. Salt migration controls subsidence, generates depocenter shifts and causes thickness variation of the entire post-Triassic sedimentary sequence. The signature of salt Triassic syn-sedimentary control is confirmed by thickness reduction and abrupt variation of structural dip that affects all the sedimentary pile in the flanks of salt sheets. In seismic sections the syn-sedimentary salt tectonic control is observed by geometries like pinching out, thickness reduction, onlap termination geometry as well as unconformities identified along the flanks of the salt sheets. • Salt tectonism is driven by regional deformation in the first stage, during Mesozoic extension. • In the second stage, Triassic salt migration shows sedimentary loading effect with minor contribution of tectonic forces. • Tertiary and Quaternary shortening is responsible for engendering Triassic salt sheets. • Established cross sections and interpretation of seismic sections reveal syn-sedimentary salt tectonic control. [ABSTRACT FROM AUTHOR]