The automatic creation of OLAP cube using an MDA approach

The Model‐Driven Architecture (MDA) is an approach that aligns modeling and automation for software development. By applying such an approach to data warehouse (DW) projects, we can minimize a great deal of time and cost. Furthermore, most of OnLine Analytical Processing (OLAP) platforms seem to be like black boxes that provide wizards only to business intelligence developers to create and manipulate OLAP objects without allowing their sustainability and migration from a platform to another. That is why many works in the literature have proposed using the MDA approach in DW projects. However, most of them have mainly focused on the generation of the DW relational model from the conceptual one, and they overlooked the OLAP model and the cube implementation. To deal with this problem, we propose in this paper an MDA solution to automate the process of getting OLAP cube and its implementation through a set of metamodels and automatic transformations among them. In fact, the proposal generates the OLAP and DW relational models (PSMs) from the conceptual one, using also a PDM model that describes the target business intelligence platform. After that, the source code to create the cube is got from both PSM models. For this aim, we define a set of transformation rules implemented using the Atlas transformation language. Finally, a case study will be provided to validate our approach.     

RBF-NN-based model for prediction of weld bead geometry in Shielded Metal Arc Welding (SMAW)

Welding processes are considered as an essential component in most of industrial manufacturing and for structural applications. Among the most widely used welding processes is the shielded metal arc welding (SMAW) due to its versatility and simplicity. In fact, the welding process is predominant procedure in the maintenance and repair industry, construction of steel structures and also industrial fabrication. The most important physical characteristics of the weldment are the bead geometry which includes bead height and width and the penetration. Different methods and approaches have been developed to achieve the acceptable values of bead geometry parameters. This study presents artificial intelligence techniques (AIT): For example, radial basis function neural network (RBF-NN) and multilayer perceptron neural network (MLP-NN) models were developed to predict the weld bead geometry. A number of 33 plates of mild steel specimens that have undergone SMAW process are analyzed for their weld bead geometry. The input parameters of the SMAW consist of welding current (A), arc length (mm), welding speed (mm/min), diameter of electrode (mm) and welding gap (mm). The outputs of the AIT models include property parameters, namely penetration, bead width and reinforcement. The results showed outstanding level of accuracy utilizing RBF-NN in simulating the weld geometry and very satisfactorily to predict all parameters in comparison with the MLP-NN model.

     

Instances selection algorithm by ensemble margin

Abstract

The main limit of data mining algorithms is their inability to deal with the huge amount of available data in a reasonable processing time. A solution of producing fast and accurate results is instances and features selection. This process eliminates noisy or redundant data in order to reduce the storage and computational cost without performances degradation. In this paper, a new instance selection approach called Ensemble Margin Instance Selection (EMIS) algorithm is proposed. This approach is based on the ensemble margin. To evaluate our approach, we have conducted several experiments on different real-world classification problems from UCI Machine learning repository. The pixel-based image segmentation is a field where the storage requirement and computational cost of applied model become higher. To solve these limitations we conduct a study based on the application of EMIS and other instance selection techniques for the segmentation and automatic recognition of white blood cells WBC (nucleus and cytoplasm) in cytological images.     

Detection of copy-move image forgery based on discrete cosine transform

Since powerful editing software is easily accessible, manipulation on images is expedient and easy without leaving any noticeable evidences. Hence, it turns out to be a challenging chore to authenticate the genuineness of images as it is impossible for human’s naked eye to distinguish between the tampered image and actual image. Among the most common methods extensively used to copy and paste regions within the same image in tampering image is the copy-move method. Discrete Cosine Transform (DCT) has the ability to detect tampered regions accurately. Nevertheless, in terms of precision (FP) and recall (FN), the block size of overlapping block influenced the performance. In this paper, the researchers implemented the copy-move image forgery detection using DCT coefficient. Firstly, by using the standard image conversion technique, RGB image is transformed into grayscale image. Consequently, grayscale image is segregated into overlying blocks of m × m pixels, m = 4.8. 2D DCT coefficients are calculated and reposition into a feature vector using zig-zag scanning in every block. Eventually, lexicographic sort is used to sort the feature vectors. Finally, the duplicated block is located by the Euclidean Distance. In order to gauge the performance of the copy-move detection techniques with various block sizes with respect to accuracy and storage, threshold D_similar = 0.1 and distance threshold (N)_d = 100 are used to implement the 10 input images in order. Consequently, 4 × 4 overlying block size had high false positive thus decreased the accuracy of forged detection in terms of accuracy. However, 8 × 8 overlying block accomplished more accurately for forged detection in terms of precision and recall as compared to 4 × 4 overlying block. In a nutshell, the result of the accuracy performance of different overlying block size are influenced by the diverse size of forged area, distance between two forged areas and threshold value used for the research.

     

CRPD: a novel clustering routing protocol for dynamic wireless sensor networks

A wireless sensor network (WSN) consists of a large number of static or mobile, low-cost, and low-power sensor nodes. And energy is one of the most important factors that should be considered. In this paper, we propose clustering-based routing protocol for dynamic networks (CRPD) to reduce energy consumption and improve energy efficiency through clustering and routing algorithms. The basic idea is to periodically update the network topology and select the node with larger degree and high residual energy as the cluster head to be responsible for data aggregation and transmission. With the nodes moving, joining, and choosing the optimal clustering radius, the energy load of the whole network can be evenly distributed to each sensor node, which can significantly prolong the network lifetime. Extensive simulations show that CRPD is more energy-efficient than the existing protocols.     

Deep Learning for Tomato Diseases: Classification and Symptoms Visualization

Several studies have invested in machine learning classifiers to protect plants from diseases by processing leaf images. Most of the proposed classifiers are trained and evaluated with small datasets, focusing on the extraction of hand-crafted features from image to classify the leaves. In this study, we have used a large dataset compared to the state-of-the art. Here, the dataset contains 14,828 images of tomato leaves infected with nine diseases. To train our classifier, we have introduced the Convolutional Neural Network (CNN) as a learning algorithm. One of the biggest advantages of CNN is the automatic extraction of features by processing directly the raw images. To analyze the proposed deep model, we have used visualization methods to understand symptoms and to localize disease regions in leaf. The obtained results are encouraging, reaching 99.18% of accuracy, which ourperforms dramatically shallow models, and they can be used as a practical tool for farmers to protect tomato against disease.     

Impact of spare parts remanufacturing on the operation and maintenance performance of offshore wind turbines: a multi-agent approach

Offshore wind farms are a growing source of energy, which aims to ensure a clean energy with a low environmental impact. In this context, this paper investigates opportunities of the turbine gearbox end of life-cycle to improve the operation and maintenance strategies. We determine the impact of spare part policy based on the remanufacturing of gearboxes recovered after each replacement. The remanufacturing implementation allows the extension of the gearbox life-cycle and involves a perfect organization and coordination between maintenance, monitoring, operation and spare part supply chain to determine the best way to use each gearbox of each wind turbine. In this paper, we present a multi-agent based approach to analyze the impact of the spare parts remanufacturing strategy on the performance of an offshore wind farm in term of total cost and carbon footprint.     

Corrosion investigation of zinc−aluminum alloy matrix (ZA-27) reinforced with alumina (Al2O3) and fly ash

In this study, zinc?aluminum alloy (ZA-27) matrix composites reinforced by different weight fractions of fly ash or alumina (Al₂O₃) were produced using the traditional stir casting technique. The corrosion behaviors of both unreinforced alloy and reinforced composites were examined using direct current polarization (DCP) test in a simulated sea solution (3.5 wt.% NaCl). Scanning electron microscopy (SEM) and energy dispersive x-ray (EDX) were used to examine the morphology of the composites’ surface before and after corrosion tests. The results of corrosion revealed that reinforcing ZA-27 alloy by fly ash or Al₂O₃ particles decreases its tendency to uniform corrosion due to the formation of weak microgalvanic couple between matrix and reinforcement particles. The fly ash and alumina (Al₂O₃) particles have protected the matrix material from pits formation at early stage of polarization. However, once these pits are formed, they grow faster. Positive hysteresis of the polarization curves implies that the salt layer breakdown and matrix dissolution overshadow surface passivation during the reverse scan. The electrochemical results are consistent with the pits’ morphology of the corroded composite. Composites with fly ash reinforcements have autocatalytic pits, whereas composites with alumina (Al₂O₃) reinforcements have shallow pits.