Filters








2,984 Hits in 3.2 sec

Time Domain Training Signals Comparison for Computational Fluid Dynamics Based Aerodynamic Identification

Charles R. O'Neill, Andrew S. Arena
2005 Journal of Aircraft  
Physical binary signal excitations are filtered by nature; purely computational binary signals have no nat- ural filter.  ...  Six specific signals are presented: the 3211 multistep and noise in the binary class; the chirp, dc-chirp, and Fresnel in the fre- quency sweep class; and the Schroeder sweep in the multisine class.  ... 
doi:10.2514/1.6424 fatcat:rvekzoemerej7iwc72col3b4fa

Classifier systems that compute action mappings

Pier Luca Lanzi, Daniele Loiacono
2007 Proceedings of the 9th annual conference on Genetic and evolutionary computation - GECCO '07  
In this paper, we introduce a version of XCS with computed actions, briefly XCSCA, that can be applied to problems involving a large number of actions.  ...  The learning in a niche based learning classifier system depends both on the complexity of the problem space and on the number of available actions.  ...  Recently, classifier prediction has also received attention and the idea of computed prediction has been introduced to improve the estimation of classifiers in terms of problem solution [25] .  ... 
doi:10.1145/1276958.1277322 dblp:conf/gecco/LanziL07 fatcat:wpdpjflko5ekhasu3n5wye6bsm

On the Need of New Approaches for the Novel Problem of Long-Term Prediction over Multi-dimensional Data [chapter]

Rui Henriques, Cláudia Antunes
2012 Studies in Computational Intelligence  
For this purpose, firstly, it presents an essential formalization and evaluation method for this novel problem.  ...  This work reviews the problem of long-term classification over multi-dimensional structures to solve planning tasks.  ...  The relevance of understanding evolutionary behavior in planning problems through predictive rules is discussed in [26] [22] .  ... 
doi:10.1007/978-3-642-30454-5_9 fatcat:uo3dzaihsnbtxgm5qig2dzsqg4

Accelerated computation of cyclic steady state for simulated-moving-bed processes

Hong-Mei Yao, Moses O. Tadé, Yu-Chu Tian
2010 Chemical Engineering Science  
However, the SMB unit operation exhibits complex dynamics, leading to challenges in SMB process modelling and model computation.  ...  The QE computation scheme allows larger steps to be taken for predicting the slow change of the starting state within each switching.  ...  used in the computation, the corresponding methods are commonly called Multistep methods; in this case, k-step method (Gear, 1971 ).  ... 
doi:10.1016/j.ces.2009.11.012 fatcat:i7e4r777hfc3bhbnn526vvrzgi

Multistep Electric Vehicle Charging Station Occupancy Prediction using Hybrid LSTM Neural Networks [article]

Tai-Yu Ma, Sébastien Faye
2021 arXiv   pre-print
Public charging station occupancy prediction plays key importance in developing a smart charging strategy to reduce electric vehicle (EV) operator and user inconvenience.  ...  We propose a new mixed long short-term memory neural network incorporating both historical charging state sequences and time-related features for multistep discrete charging occupancy state prediction.  ...  These supervised learning methods (classifiers) model the charging occupancy state at one time step as a binary classification problem based on a feature vector as in Eq.  ... 
arXiv:2106.04986v2 fatcat:tubrnryy45b3bor4ycngi53myu

Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems

Chin-Teng Lin, C.S.G. Lee
1994 IEEE transactions on fuzzy systems  
Computer simulations were conducted to illustrate the performance and applicability of the proposed RNN-FLCS.  ...  Using the temporal difference prediction method, the fuzzy predictor can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the fuzzy controller.  ...  ACKNOWLEDGMENT The authors would like to thank the reviewers for their helpful suggestions in improving the quality of the final manuscript.  ... 
doi:10.1109/91.273126 fatcat:5wkr6rknfjbcfgdmfulc3v7roy

Fast Switch and Spline Function Inversion Algorithm with Multistep Optimization and k-Vector Search for Solving Kepler's Equation in Celestial Mechanics

Daniele Tommasini, David N. Olivieri
2020 Mathematics  
Second, in the case of Kepler's equation, a multistep method for the optimized calculation of the breakpoints of the spline polynomial was designed and implemented in Cython.  ...  In traditional numerical approaches, this problem is reduced to solving the nonlinear equation f(x)−y=0 in each point y of the co-domain.  ...  An exception is the multistep optimization, which is given specifically for Kepler's problem, although the procedure described in this case can be adapted to more general monotonic functions.  ... 
doi:10.3390/math8112017 fatcat:77bbzaqo7rd53ote6nsdcklg5a

Metabolome-scale prediction of intermediate compounds in multistep metabolic pathways with a recursive supervised approach

Masaaki Kotera, Yasuo Tabei, Yoshihiro Yamanishi, Ai Muto, Yuki Moriya, Toshiaki Tokimatsu, Susumu Goto
2014 Computer applications in the biosciences : CABIOS  
Results: In this article, we develop a novel method to predict the multistep reaction sequences for de novo reconstruction of metabolic pathways in the reaction-filling framework.  ...  In the algorithm, we propose a recursive procedure of using step-specific classifiers to predict the intermediate compounds in the multistep reaction sequences, based on chemical substructure fingerprints  ...  ACKNOWLEDGEMENT Computational resources were provided by the Bioinformatics Center and the Supercomputer System, Institute for Chemical Research, Kyoto University. Conflict of Interest: none declared.  ... 
doi:10.1093/bioinformatics/btu265 pmid:24931980 pmcid:PMC4058936 fatcat:wlop7vmxqja6zntxaxivl576qu

Swarm Intelligence in Engineering 2014

Baozhen Yao, Fang Zong, Bin Yu, Rui Mu
2015 Mathematical Problems in Engineering  
Also, the SI is discussed in the area of computer science.  ...  The experimental results indicated that the forecasting model based on COA-SVR outperformed the other two models, especially in the context of jump samplings and multistep prediction.  ...  Acknowledgments These articles present rich and valuable advancements that SI technologies have made for solving problems in engineering.  ... 
doi:10.1155/2015/858901 fatcat:tf3ecrxuffbc5nraz2i7y6deqa

An Accurate Method for Real-Time Aircraft Dynamics Simulation Based on Predictor-Corrector Scheme

Jiaxin Zhao, Hongwei Wang, Heming Zhang
2015 Mathematical Problems in Engineering  
Therefore, a novel real-time multistep method based on Predict-Evaluate-Correct scheme of three-step fourth-order method (RTPEC-34) is proposed and developed in this research to address the gap.  ...  In addition to the development of a highly accurate algorithm based on predictor-corrector, the contribution of this work also includes the analysis of truncation error for real-time problems.  ...  Conclusions In this paper, a novel real-time multistep method based on Predict-Evaluate-Correct scheme of three-step fourth-order (RTPEC-34) method is proposed and developed for the realtime simulation  ... 
doi:10.1155/2015/193179 fatcat:aghyhamkwnbopohsf36bpqi5oa

Stay real!

Nugroho Fredivianus, Kais Kara, Hartmut Schmeck
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion - GECCO Companion '12  
Previously implemented to cope with binaries, the suitability of the newly introduced algorithm is investigated in further tasks.  ...  Several experiments are run and the results are compared to previous work using the real-valued multiplexer problem.  ...  A variant of XCS called XCS-RC, which uses the Rule Combining (RC) technique, has successfully solved some tasks using binary inputs for both single-step and multistep mode [1] .  ... 
doi:10.1145/2330784.2331009 dblp:conf/gecco/FredivianusKS12 fatcat:k42dncyphngo3bmff5dk5av5ei

A numerically stable pipeline net VLSI architecture for the isomorphic Hopfield model

Po-Rong Chang, Bao-Fuh Yeh
1993 IEEE Transactions on Signal Processing  
Comput. Modelling Conf., England, 1990. M. Soucek, Neural and Massively Parallel Computers.  ...  The model used in the experiments was a three layer network with 10 neurons per layer at maximum (this was because of the 1K dual ported memories used).  ...  In a pipeline net, noncompute delay buffers can be inserted at any data path in order to handle the problem of delay matching.  ... 
doi:10.1109/78.215328 fatcat:sple3col35hldlxfhhq4xnnfly

Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning

Manuel Huber, Christoph Kurz, Reiner Leidl
2019 BMC Medical Informatics and Decision Making  
Machine-learning classifiers mostly offer good predictive performance and are increasingly used to support shared decision-making in clinical practice.  ...  Methods: NHS PRO data (130,945 observations) from April 2015 to April 2017 were used to train and test eight classifiers to predict binary postoperative improvement based on minimal important differences  ...  However, there is no free lunch in optimization [19, 20] and thus, no single model works best for all problems.  ... 
doi:10.1186/s12911-018-0731-6 fatcat:qxpbgrqdlzea7hi3pbvc2n6bee

OUP accepted manuscript

2019 Monthly notices of the Royal Astronomical Society  
This provides substantial speedups for problems with large dynamic range.  ...  In one simulation the red giant is set into corotation with the orbital motion and in the other it is non-rotating.  ...  ACKNOWLEDGEMENTS We acknowledge useful conversations with Thomas Quinn and Volker Springel during the development of the multistepping algorithm and refinement on the half time-step prediction.  ... 
doi:10.1093/mnras/stz1219 fatcat:bqy7beeqwrcpfm5gs2r76wl3iy

Goal-directed decision making as probabilistic inference: A computational framework and potential neural correlates

Alec Solway, Matthew M. Botvinick
2012 Psychological review  
The current literature provides a rich body of computational theory addressing habit formation, centering on temporal-difference learning mechanisms.  ...  Less progress has been made toward formalizing the processes involved in goal-directed decision making.  ...  A key feature of multistep decision problems is the need to compute cumulative rewards when rewards are distributed across steps of action.  ... 
doi:10.1037/a0026435 pmid:22229491 pmcid:PMC3767755 fatcat:57a5lns6fzht7bwe4wkjejye2m
« Previous Showing results 1 — 15 out of 2,984 results