Search results for "Robustne"
showing 10 items of 515 documents
Learning the relevant image features with multiple kernels
2009
This paper proposes to learn the relevant features of remote sensing images for automatic spatio-spectral classification with the automatic optimization of multiple kernels. The method consists of building dedicated kernels for different sets of bands, contextual or textural features. The optimal linear combination of kernels is optimized through gradient descent on the support vector machine (SVM) objective function. Since a na¨ive implementation is computationally demanding, we propose an efficient model selection procedure based on kernel alignment. The result is a weight — learned from the data — for each kernel where both relevant and meaningless image features emerge after training. E…
PO-CALC: A novel tool to correct common inconsistencies in the measurement of phenoloxidase activity
2015
Abstract A broad range of physiological and evolutionarily studies requires standard and robust methods to assess the strength and activity of an individual’s immune defense. In insects, this goal is generally reached by spectrophotometrically measuring (pro-) phenoloxidase activity, an enzymatic and non-specific process activated after wounding and parasite infections. However, the literature surprisingly lacks a standard method to calculate these values from spectrophotometer data and thus to be able to compare results across studies. In this study, we demonstrated that nine methods commonly used to extract phenoloxidase activities (1) provide inconsistent results when tested on the same …
Macroelement Model for the Progressive-Collapse Analysis of Infilled Frames
2021
A new multistrut macromodel for the analysis of the progressive-collapse response of infilled reinforced concrete (RC) frames is presented in this paper. The model consists of three struts: two outer infinitely rigid and resistant struts and one inner fiber-section strut. The inclination of the struts as well as the stress-strain response are modulated by two parameters that are obtained by means of analytical correlations provided in the paper. The latter link the geometric and mechanical properties of an infilled frame to the geometric configuration and mechanical response of the equivalent strut model. This confers the model the capability to adapt to consider different collapse configur…
Selection From Bibliographic Resources of an Analytical Method for Cosmetic Products
2018
Abstract This chapter is focussed on a general strategy to select an appropriate method from the scientific literature to solve an analytical problem in cosmetic analysis using useful and flexible web tools. A short introduction on the use of ScienceDirect (Elsevier), Scopus (Elsevier), SciFinder Scholar (American Chemical Society), Web of Science (Thomson Reuters) and the freely available Google Scholar is given. The main analytical features to be considered in the selection of the method, such as limit of detection, limit of quantification, linearity, precision (repeatability, intermediate precision and reproducibility), selectivity, robustness and accuracy, are briefly described. Additio…
Stabilization of polyiodide networks with Cu(ii) complexes of small methylated polyazacyclophanes: shifting directional control from H-bonds to I⋯I i…
2020
Ordered polyiodide networks have recently gathered considerable attention as electronic materials, a topic historically dominated by metals. Could we incorporate metal cations into polyiodide frameworks in a controlled manner to simultaneously boost electronic properties and robustness of these materials? Herein we present a first principles study featuring three analogous polyazacyclophanes (L, L-Me, L-Me3), differing only in the extent of N-methylation. We demonstrate (potentiometry, ITC) how they all form the same CuL2+ (L = L, L-Me, L-Me3) complex as prevalent species in solution, so that a level playing field exists where only N-methylation distinguishes them. Then we use them as count…
A non-parametric Scale-based Corner Detector
2008
This paper introduces a new Harris-affine corner detector algorithm, that does not need parameters to locate corners in images, given an observation scale. Standard detectors require to fine tune the values of parameters which strictly depend on the particular input image. A quantitative comparison between our implementation and a standard Harris-affine implementation provides good results, showing that the proposed methodology is robust and accurate. The benchmark consists of public images used in literature for feature detection.
An Efficient, Robust, and Scalable Trust Management Scheme for Unattended Wireless Sensor Networks
2012
Unattended Wireless Sensor Networks (UWSNs) are characterized by long periods of disconnected operation and fixed or irregular intervals between visits by the sink. The absence of an online trusted third party, i.e., an on-site sink, makes existing trust management schemes used in legacy wireless sensor networks not applicable to UWSNs directly. In this paper, we propose a trust management scheme for UWSNs to provide efficient, robust and scalable trust data storage. For trust data storage, we employ geographic hash table to efficiently identify data storage nodes and to significantly reduce storage cost. We demonstrate, through detailed analyses and extensive simulations, that the proposed…
Extending the sGLOH descriptor
2015
This paper proposes an extension of the sGLOH keypoint descriptor [3] which improves its robustness and discriminability. The sGLOH descriptor can handle discrete rotations by a cyclic shift of its elements thanks to its circular structure, but its performance can decrease when the keypoint relative rotation is in between two sGLOH discrete rotations. The proposed extension couples together two sGLOH descriptors for the same patch with different rotations in order to cope with this issue and it can be also applied straightly to the sCOr and sGOr matching strategies of sGLOH. Experimental results show a consistent improvement of the descriptor discriminability, while different setups can be …
Explainable Reinforcement Learning with the Tsetlin Machine
2021
The Tsetlin Machine is a recent supervised machine learning algorithm that has obtained competitive results in several benchmarks, both in terms of accuracy and resource usage. It has been used for convolution, classification, and regression, producing interpretable rules. In this paper, we introduce the first framework for reinforcement learning based on the Tsetlin Machine. We combined the value iteration algorithm with the regression Tsetlin Machine, as the value function approximator, to investigate the feasibility of training the Tsetlin Machine through bootstrapping. Moreover, we document robustness and accuracy of learning on several instances of the grid-world problem.
Semi-Supervised Classification Method for Hyperspectral Remote Sensing Images
2004
A new approach to the classification of hyperspectral images is proposed. The main problem with supervised methods is that the learning process heavily depends on the quality of the training data set. In remote sensing, the training set is useful only for simultaneous images or for images with the same classes taken under the same conditions; and, even worse, the training set is frequently not available. On the other hand, unsupervised methods are not sensitive to the number of labelled samples since they work on the whole image. Nevertheless, relationship between clusters and classes is not ensured. In this context, we propose a combined strategy of supervised and unsupervised learning met…