Zobrazeno 1 - 10
of 87
pro vyhledávání: '"Martin T. Hagan"'
Autor:
Joseph Kelley, Martin T. Hagan
Publikováno v:
IEEE/ASME Transactions on Mechatronics. 25:1499-1509
This article presents a new online approach for predicting component degradation in hydraulic systems using a few distributed sensors. The procedure uses neural network nonlinear autoregressive exogenous (NARX) models to model a healthy hydraulic sys
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9173305e86abe0b029296a599f4e3d0d
https://doi.org/10.1109/tmech.2020.2977857
https://doi.org/10.1109/tmech.2020.2977857
Autor:
Martin T. Hagan, Carl D. Latino
Publikováno v:
1996 Annual Conference Proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb3cee993c8609f287fc10683e5b8aef
https://doi.org/10.18260/1-2--6361
https://doi.org/10.18260/1-2--6361
Autor:
Amir Jafari, Martin T. Hagan
Publikováno v:
Engineering Applications of Artificial Intelligence. 74:312-321
In this paper, we introduce new, more efficient, methods for training recurrent neural networks (RNNs) for system identification and Model Reference Control (MRC). These methods are based on a new understanding of the error surfaces of RNNs that has
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::222754022cd5e9beffcf813b42dd30f3
https://doi.org/10.1016/j.engappai.2018.07.005
https://doi.org/10.1016/j.engappai.2018.07.005
Autor:
Daniel M. Hagan, Martin T. Hagan
Publikováno v:
Journal of Artificial Intelligence and Soft Computing Research. 8:173-189
In this paper, we describe how several soft computing tools can be used to assist in high throughput screening of potential drug candidates. Individual small molecules (ligands) are assessed for their potential to bind to specific proteins (receptors
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56d047250d85fa8f6b8189002342db2f
https://doi.org/10.1515/jaiscr-2018-0012
https://doi.org/10.1515/jaiscr-2018-0012
Publikováno v:
2017 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI).
Committees of multilayer neural networks were used to estimate the appropriate surface area and thickness of RF absorbing material needed to achieve a desired quality factor (Q) inside a reverberation chamber. The networks were trained with Bayesian
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f8c213a7d1856f1f835c72b13ef67d3
https://doi.org/10.1109/isemc.2017.8077843
https://doi.org/10.1109/isemc.2017.8077843
Publikováno v:
IEEE Transactions on Automatic Control. 59:2496-2501
This technical note addresses the stability analysis of nonlinear dynamic systems. Three main contributions are made. First, we show that the standard assumption of a continuous Lyapunov function can be (and in some cases must be) relaxed. We introdu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::787a1161cb78b7d96200a0b9c9cbbe33
https://doi.org/10.1109/tac.2014.2304174
https://doi.org/10.1109/tac.2014.2304174
Autor:
Martin T. Hagan, Manh Cong Phan
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 24:1709-1721
We found in previous work that the error surfaces of recurrent networks have spurious valleys that can cause significant difficulties in training these networks. Our earlier work focused on single-layer networks. In this paper, we extend the previous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ddfbf7c71701c744ae848725f6e8765
https://doi.org/10.1109/tnnls.2013.2258470
https://doi.org/10.1109/tnnls.2013.2258470
Autor:
Martin T. Hagan, Daniel M. Hagan
Publikováno v:
IJCNN
In this paper, we describe how neural networks can be used for high throughput screening of potential drug candidates. Individual small molecules (ligands) are assessed for their potential to bind to specific proteins (receptors). Committees of multi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d4ec6e93e8ab03ddf00e60daf1802a9
https://doi.org/10.1109/ijcnn.2016.7727252
https://doi.org/10.1109/ijcnn.2016.7727252
Publikováno v:
Journal of Medical Devices. 10
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a2dfe189c26a963a872ef5138b97a6f
https://doi.org/10.1115/1.4033220
https://doi.org/10.1115/1.4033220
Autor:
Enrique Alba, Martin T. Hagan, Guillermo Leguizamón, Marco A. Moreno-Armendáriz, José de Jesús Rubio, Carlos A. Cruz-Villar
Publikováno v:
Computational Intelligence and Neuroscience, Vol 2016 (2016)
Computational Intelligence and Neuroscience
Computational Intelligence and Neuroscience
Among the many hot lines of modern research, hybridization stands out. Analyzing basic building blocks (ideas, algorithms, and procedures) and then building a new artifact (algorithm, machine, and tool) are in the core of Science. In this journal iss
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e20687b9e7ba15895738080a87a8bec
https://doaj.org/article/a7fac1d5b5a74583a2e31822c0a98b47
https://doaj.org/article/a7fac1d5b5a74583a2e31822c0a98b47