Search results for "Multilayer"
showing 10 items of 141 documents
Fast and Robust Face Detection on a Parallel Optimized Architecture implemented on FPGA
2009
In this paper, we present a parallel architecture for fast and robust face detection implemented on FPGA hardware. We propose the first implementation that meets both real-time requirements in an embedded context and face detection robustness within complex backgrounds. The chosen face detection method is the Convolutional Face Finder (CFF) algorithm, which consists of a pipeline of convolution and subsampling operations, followed by a multilayer perceptron. We present the design methodology of our face detection processor element (PE). This methodology was followed in order to optimize our implementation in terms of memory usage and parallelization efficiency. We then built a parallel arch…
Anomaly Detection and Classification of Household Electricity Data : A Time Window and Multilayer Hierarchical Network Approach
2022
With the increasing popularity of the smart grid, huge volumes of data are gathered from numerous sensors. How to classify, store, and analyze massive datasets to facilitate the development of the smart grid has recently attracted much attention. In particular, with the popularity of household smart meters and electricity monitoring sensors, a large amount of data can be obtained to analyze household electricity usage so as to better diagnose the leakage and theft behaviors, identify man-made tampering and data fraud, and detect powerline loss. In this paper, the time window method is first proposed to obtain the features and potential periodicity of household electricity data. Combining th…
Multiple Classifiers and Data Fusion for Robust Diagnosis of Gearbox Mixed Faults
2019
Detection and isolation of single and mixed faults in a gearbox are very important to enhance the system reliability, lifetime, and service availability. This paper proposes a hybrid learning algorithm, consisting of multilayer perceptron (MLP)- and convolutional neural network (CNN)-based classifiers, for diagnosis of gearbox mixed faults. Domain knowledge features are required to train the MLP classifier, while the CNN classifier can learn features itself, allowing to reduce the required knowledge features for the counterpart. Vibration data from an experimental setup with gearbox mixed faults is used to validate the effectiveness of the algorithms and compare them with conventional metho…
The role of the disposition of the recycled polymer on the properties of films for greenhouses coverage
2010
Multilayer films, by using postconsumer materials in the central layer, i.e., multilayer composition: virgin polyethylene/postconsumer polymer/virgin polyethylene, allows to get a film for greenhouses coverage with good mechanical properties and photo-oxidation resistance, similar to that of the films made from virgin material and certainly better than the photo-oxidation resistance of the film made melt blending the virgin polyethylene and the postconsumer polymer. Moreover, the disposition of the postconsumer polymer containing oxygenated groups only in the central layer determines a significant slowdown of the photo-oxidation process of the multilayer film although faster than of the pri…
Social network analysis approaches to study crime
2022
Social Network Analysis (SNA) studies groups of individuals and can be applied in a lot of areas such us organizational studies, psychology, economics, information science and criminology. One of the most important results of SNA has been the definition of a set of centrality measures (e.g., degree, closeness, betweenness, or clustering coefficient) which can be used to identify the most influential people with respect to their network of relationships. The main problem with computing centrality metrics on social networks is the typical big size of the data. From the computational point of view, SNA represents social networks as graphs composed of a set of nodes connected by another set of …
Crystal growth and characterization of Zn1-xMgxO advanced micro- and nanostructures
2018
Dentro de la creciente área de investigación de la física de semiconductores, los pertenecientes a la familia II-VI se han convertido en un campo fundamental de la física de materiales debido a que sus propiedades fotofísicas son únicas para crear una nueva generación de dispositivos en el campo de la fotónica y la microelectrónica. Entre ellos, los semiconductores basados en ZnO han ganado un considerable interés en la comunidad científica en parte debido a su alta energía de enlace del excitón (60 meV) la cual es 2.4 veces más alta que la energía térmica a temperatura ambiente. Este hecho puede dar lugar a emisión laser excitónica a temperaturas incluso mayores que la ambiente. Además, gr…
An implicit mesh discontinuous Galerkin formulation for higher-order plate theories
2019
In this work, a discontinuous Galerkin formulation for higher-order plate theories is presented. The starting point of the formulation is the strong form of the governing equations, which are derived in the context of the Generalized Unified Formulation and the Equivalent Single Layer approach from the Principle of Virtual Displacements. To express the problem within the discontinuous Galerkin framework, an auxiliary flux variable is introduced and the governing equations are rewritten as a system of first-order partial differential equations, which are weakly stated over each mesh element. The link among neighboring mesh elements is then retrieved by introducing suitably defined numerical …
Prediction of active peak force using a multilayer perceptron
2017
Both kinematic parameters and ground reaction forces (GRFs) are necessary for understanding the biomechanics of running. Kinematic information of a runner is typically measured by a motion capture system whereas GRF during the support phase of running is measured by force platforms. To analyze both kinematics and kinetics of a runner over several subsequent contacts, an instrumented treadmill or alternatively several force platforms installed over a regulated space are available options, but they are highly immovable, expensive, and sometimes even impractical options. Naturally, it would be highly useful to predict GRFs using a motion capture system only and this way reduce costs and comple…
A Theory for Multilayered Composite Beams
2014
Composite laminates are nowadays widely employed as lightweight components in civil engineering, automotive and aerospace applications due to their excellent mechanical properties, such as, the high strength and stiffness per unit weight, the path loads management capability. Moreover by using composite laminated materials it is possible to manufacture large size structures with less riveted joints, which leads to a reduction of the overall structural complexity and of the manufacturing and inspection times and costs. A drawback of layered composites is represented by the the low values of throughthe-thickness tensile and shear strengths, with respect to the in-plane ones, that affect the o…
Multilayer perceptron training with multiobjective memetic optimization
2016
Machine learning tasks usually come with several mutually conflicting objectives. One example is the simplicity of the learning device contrasted with the accuracy of its performance after learning. Another common example is the trade-off that must often be made between the rate of false positive and false negative predictions in diagnostic applications. For computer programs that learn from data, these objectives are formulated as mathematical functions, each of which describes one facet of the desired learning outcome. Even functions that intend to optimize the same facet may behave in a subtly different and mutually conflicting way, depending on the task and the dataset being examined. Mul…