The Experts below are selected from a list of 184368 Experts worldwide ranked by ideXlab platform
Lindsay G Cowell - One of the best experts on this subject based on the ideXlab platform.
-
machine learning on sequential data using a recurrent weighted average
Neurocomputing, 2019Co-Authors: Jared Ostmeyer, Lindsay G CowellAbstract:Abstract Recurrent Neural Networks (RNN) are a type of statistical model designed to handle sequential data. The model reads a sequence one symbol at a time. Each symbol is processed based on information collected from the previous symbols. With existing RNN architectures, each symbol is processed using only information from the previous Processing Step. To overcome this limitation, we propose a new kind of RNN model that computes a recurrent weighted average (RWA) over every past Processing Step. Because the RWA can be computed as a running average, the computational overhead scales like that of any other RNN architecture. The approach essentially reformulates the attention mechanism into a stand-alone model. The performance of the RWA model is assessed on the variable copy problem, the adding problem, classification of artificial grammar, classification of sequences by length, and classification of the MNIST images (where the pixels are read sequentially one at a time). On almost every task, the RWA model is found to fit the data significantly faster than a standard LSTM model.
Jared Ostmeyer - One of the best experts on this subject based on the ideXlab platform.
-
machine learning on sequential data using a recurrent weighted average
Neurocomputing, 2019Co-Authors: Jared Ostmeyer, Lindsay G CowellAbstract:Abstract Recurrent Neural Networks (RNN) are a type of statistical model designed to handle sequential data. The model reads a sequence one symbol at a time. Each symbol is processed based on information collected from the previous symbols. With existing RNN architectures, each symbol is processed using only information from the previous Processing Step. To overcome this limitation, we propose a new kind of RNN model that computes a recurrent weighted average (RWA) over every past Processing Step. Because the RWA can be computed as a running average, the computational overhead scales like that of any other RNN architecture. The approach essentially reformulates the attention mechanism into a stand-alone model. The performance of the RWA model is assessed on the variable copy problem, the adding problem, classification of artificial grammar, classification of sequences by length, and classification of the MNIST images (where the pixels are read sequentially one at a time). On almost every task, the RWA model is found to fit the data significantly faster than a standard LSTM model.
Xi Zheng - One of the best experts on this subject based on the ideXlab platform.
-
Hyperspectral image classification based on joint spectrum of spatial space and spectral space
Springer New York LLC, 2018Co-Authors: Zhang Xiaorong, Pan Zhibin, Lu Xiaoqiang, Hu Bingliang, Xi ZhengAbstract:This paper presents a novel feature extraction model that incorporates local histogram in spatial space and pixel spectrum in spectral space, with the goal of hyperspectral image classification. We named this joint spectrum as 3D spectrum. Moreover, as a pre-Processing Step, an iterative procedure, which exploits spectral information in such a way that it considers corrupted bands existing in the data cube, is applied to original hyperspectral image. Further, Affine transform is applied to the bands chosen by the aforementioned procedure. The final feature is extracted by affine transform and 3D spectrum model, and as an input of widely used classifier of Support Vector Machine. As a post-Processing Step, multiple iterative results are fused in the level of probability. Our experimental results indicate that the proposed methodology leads to state-of-the-art classification results when combined with probabilistic classifiers for several widely used hyperspectral data sets, even when very only limited training samples are available. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.
-
hyperspectral image classification based on joint spectrum of spatial space and spectral space
Multimedia Tools and Applications, 2018Co-Authors: Zhibin Pan, Xiaorong Zhang, Xi ZhengAbstract:This paper presents a novel feature extraction model that incorporates local histogram in spatial space and pixel spectrum in spectral space, with the goal of hyperspectral image classification. We named this joint spectrum as 3D spectrum. Moreover, as a pre-Processing Step, an iterative procedure, which exploits spectral information in such a way that it considers corrupted bands existing in the data cube, is applied to original hyperspectral image. Further, Affine transform is applied to the bands chosen by the aforementioned procedure. The final feature is extracted by affine transform and 3D spectrum model, and as an input of widely used classifier of Support Vector Machine. As a post-Processing Step, multiple iterative results are fused in the level of probability. Our experimental results indicate that the proposed methodology leads to state-of-the-art classification results when combined with probabilistic classifiers for several widely used hyperspectral data sets, even when very only limited training samples are available.
Peter Goos - One of the best experts on this subject based on the ideXlab platform.
-
d optimal design of split split plot experiments
Biometrika, 2009Co-Authors: Bradley Jones, Peter GoosAbstract:In industrial experimentation, there is growing interest in studies that span more than one Processing Step. Convenience often dictates restrictions in randomization in passing from one Processing Step to another. When the study encompasses three Processing Steps, this leads to split-split-plot designs. We provide an algorithm for computing D-optimal split-split-plot designs and several illustrative examples.
-
d optimal design of split split plot experiments
2007Co-Authors: Jones Bradley, Peter GoosAbstract:In industrial experimentation there is growing interest in studies that span more than one Processing Step. Convenience often dictates restrictions in randomization in passing from one Processing Step to another. When the study encompasses three Processing Steps, this leads to split-split-plot designs. We provide an algorithm for computing D-optimal split-split-plot designs and provide many illustrative examples. We then apply our methods to construct D-optimal alternatives to a previously run split-split-plot design for cheese production.
Leonardo Barbini - One of the best experts on this subject based on the ideXlab platform.
-
phase editing as a signal pre Processing Step for automated bearing fault detection
Mechanical Systems and Signal Processing, 2017Co-Authors: Leonardo Barbini, Agusmian Partogi Ompusunggu, A J Hillis, J L Du Bois, A BarticAbstract:Abstract Scheduled maintenance and inspection of bearing elements in industrial machinery contributes significantly to the operating costs. Savings can be made through automatic vibration-based damage detection and prognostics, to permit condition-based maintenance. However automation of the detection process is difficult due to the complexity of vibration signals in realistic operating environments. The sensitivity of existing methods to the choice of parameters imposes a requirement for oversight from a skilled operator. This paper presents a novel approach to the removal of unwanted vibrational components from the signal: phase editing. The approach uses a computationally-efficient full-band demodulation and requires very little oversight. Its effectiveness is tested on experimental data sets from three different test-rigs, and comparisons are made with two state-of-the-art Processing techniques: spectral kurtosis and cepstral pre- whitening. The results from the phase editing technique show a 10% improvement in damage detection rates compared to the state-of-the-art while simultaneously improving on the degree of automation. This outcome represents a significant contribution in the pursuit of fully automatic fault detection.