100 Hits in 2.6 sec

Mixed-State Models for Nonstationary Multiobject Activities

Naresh P Cuntoor, Rama Chellappa
2006 EURASIP Journal on Advances in Signal Processing  
We present a mixed-state space approach for modeling and segmenting human activities.  ...  The discrete-valued component of the mixed state represents higher-level behavior while the continuous state models the dynamics within behavioral segments.  ...  Mixed-state models Mixed-state models have been used for several applications including activity modeling, air traffic management, smart highway system, and so forth (see [17] [18] [19] [20] ).  ... 
doi:10.1155/2007/65989 fatcat:hhakf2lbzbcq7p34bou6mb6m5q

Mathematical Modeling for Resources and Environmental Systems

Y. P. Li, G. H. Huang, S. L. Nie, B. Chen, X. S. Qin
2013 Mathematical Problems in Engineering  
Chen et al. proposed a multiobjective optimization model for siting and sizing distributed generation plants in distribution systems.  ...  Moreover, a variety of processes and activities are interrelated to each other, resulting in complicated systems with interactive, dynamic, nonlinear, multiobjective, multistage, multilayer, and uncertain  ...  Chen et al. proposed a multiobjective optimization model for siting and sizing distributed generation plants in distribution systems.  ... 
doi:10.1155/2013/674316 fatcat:n2bzvudydba7rfivnk6fr4hvb4

Signal Processing Technologies for Ambient Intelligence in Home-Care Applications

Francesco G. B. De Natale, Aggelos K. Katsaggelos, Oscar Mayora, Ying Wu
2007 EURASIP Journal on Advances in Signal Processing  
Chellappa further emphasize the behavioral analysis problem in their paper "Mixed-state models for nonstationary, multiobject activities."  ...  The discrete-valued component of the mixed state represents higher-level behavior, while the continuous-state models the dynamics within behavioral segments.  ... 
doi:10.1155/2007/91730 fatcat:ad25ejmfevcyfmet4etakwxl6u

A hybrid vibration signal prediction model using Autocorrelation Local Characteristic-scale Decomposition and improved Long Short Term Memory

Huixin Tian, Daixu Ren, Kun Li
2019 IEEE Access  
However, it is difficult to predict using a simple model for its nonlinear and nonstationary characteristics.  ...  Accurate state monitoring and the fault prediction model is very important for the smooth running of a reciprocating compressor.  ...  However, it does not work well for nonstationary vibration signals.  ... 
doi:10.1109/access.2019.2916000 fatcat:h6v7xsazjvbepkajsxxu2bokqy

2014 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 25

2014 IEEE Transactions on Neural Networks and Learning Systems  
Xu, C., +, TNNLS Apr. 2014 728-737 Feature Learning for Image Classification Via Multiobjective Genetic Programming.  ...  ., +, TNNLS May 2014 1013-1020 Local Stability Analysis of Discrete-Time, Continuous-State, Complex-Valued Recurrent Neural Networks With Inner State Feedback.  ... 
doi:10.1109/tnnls.2015.2396731 fatcat:ztnfcozrejhhfdwg7t2f5xlype

Research on GDP Forecast Analysis Combining BP Neural Network and ARIMA Model

Shaobo Lu, Huihua Chen
2021 Computational Intelligence and Neuroscience  
of the ARIMA model of 2%.  ...  Based on the BP neural network and the ARIMA model, this paper predicts the nonlinear residual of GDP and adds the predicted values of the two models to obtain the final predicted value of the model.  ...  of the ARIMA-BP mixed model is 5 × 6 × 1, and the structure in the sample 2 construction of the ARIMA-BP mixed model is 5 × 11 × 1. e model is trained to predict the daily closing price of the total GDP  ... 
doi:10.1155/2021/1026978 pmid:34804136 pmcid:PMC8604606 fatcat:swtdxb4grbbxbexuq22vcmyy4y

Data-based mechanistic modeling, forecasting, and control

2001 IEEE Control Systems  
Daniel Berckmans and his staff in the Laboratory for Agricultural Buildings Research at the Katholieke Universiteit Leuven, Belgium.  ...  Acknowledgments The authors are grateful to the United Kingdom Biotechnology and Biological Sciences Research Council for its support, through Research Grants 89/E06813 and 89/MMI09731, together with the  ...  , and smoothing of nonstationary time series; and nonminimal state space (NMSS) methods of control system design.  ... 
doi:10.1109/37.954517 fatcat:cckvehpmkbbiph6dhuob7bulle

Scanning the Issue

Azim Eskandarian
2020 IEEE transactions on intelligent transportation systems (Print)  
Based on these findings and the current state-of-the-art solutions for interaction between autonomous vehicles (AVs) and pedestrians, a road map for future research is proposed regarding what methods and  ...  This work excogitates a DCNN model for video foreground/background segmentation. Initially, a Conv-LSTM2D image to image encoder-decoder (EnDec) model is designed.  ...  Here, each dynamic is modeled as a mixed-logical-dynamical system.  ... 
doi:10.1109/tits.2020.2972652 fatcat:ppev3ra7hbeopio2yqbbf32gbu

Stream water age distributions controlled by storage dynamics and nonlinear hydrologic connectivity: Modeling with high-resolution isotope data

C. Soulsby, C. Birkel, J. Geris, J. Dick, C. Tunaley, D. Tetzlaff
2015 Water Resources Research  
This approach is well suited for constraining process-based modeling in a range of northern temperate and boreal environments.  ...  This, in turn, determines the spatial distribution of flow paths and the integration of their contrasting nonstationary ages.  ...  also greater potential for mixing (satMV).  ... 
doi:10.1002/2015wr017888 pmid:27478255 pmcid:PMC4949550 fatcat:6g6dfeuo6bgstnttteuxncms6m

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert–Huang Transform and Deep Learning

Tong Gao, Wei Sheng, Mingliang Zhou, Bin Fang, Futing Luo, Jiajun Li
2020 Sensors  
state-of-the-art algorithms.  ...  First, the method for fault diagnosis of inertial sensors is formulated into an HHT-based deep learning problem.  ...  In the future, an improved feature coding method that contains the state of the EEMD and frequency shifting can be studied for integrating the additional operation into the BLSTM-based regression model  ... 
doi:10.3390/s20195633 pmid:33019773 pmcid:PMC7583962 fatcat:3ilthvjqxrgtriivybo6xcwpyu

A Decomposition-Ensemble Approach with Denoising Strategy for PM2.5 Concentration Forecasting

Guangyuan Xing, Er-long Zhao, Chengyuan Zhang, Jing Wu, Giancarlo Consolo
2021 Discrete Dynamics in Nature and Society  
This novel approach is an improved approach under the effective "denoising, decomposition, and ensemble" framework, especially for nonlinear and nonstationary features of PM2.5 concentration data.  ...  Then, variational mode decomposition (VMD) is implemented to decompose the denoised data for producing the components.  ...  In addition, considering the limitations of a single model, some scholars proposed the mixed models to make a better forecasting accuracy, which combined the advantages of different models to obtain more  ... 
doi:10.1155/2021/5577041 fatcat:nx5weibjvjetfoccgjtisjgtr4

2020 Index IEEE Transactions on Industrial Informatics Vol. 16

2020 IEEE Transactions on Industrial Informatics  
Forests-Based Model for Ultra-Short-Term Prediction of PV Characteristics; TII Jan. 2020 202-214 Imran, A., see Hussain, B., TII Aug. 2020 4986-4996 Imran, M., see Fu, S., TII Sept. 2020 6013-6022  ...  Cai, H., TII Jan. 2020 587-594 Jiang, L., see Xia, Z., TII Jan. 2020 629-638 Jiang, Q., Yan, S., Yan, X., Yi, H., and Gao, F., Data-Driven Two-Dimensional Deep Correlated Representation Learning for  ...  Crowdsourcing Model for Energy Efficiency Retrofit and Mixed-Integer Equilibrium Analysis.  ... 
doi:10.1109/tii.2021.3053362 fatcat:blfvdtsc3fdstnk6qoaazskd3i

Multiclass Motor Imagery Recognition of Single Joint in Upper Limb Based on NSGA- II OVO TWSVM

Shan Guan, Kai Zhao, Fuwang Wang
2018 Computational Intelligence and Neuroscience  
, AF-CSP to extract motor imagery (MI) features, and to improve classification performance, the second generation nondominated sorting evolutionary algorithm (NSGA-II) is used to tune hyperparameters for  ...  This model is compared with least squares support vector machine (LS-SVM), back propagation (BP), extreme learning machine (ELM), particle swarm optimization support vector machine (PSO-SVM), and grid  ...  Then calculate the mixed space covariance matrix of the two types motor imagery , as follows: = + (4) Eigenvalue decomposition for covariance of mixed space is as follows: = (5) where is the eigenvector  ... 
doi:10.1155/2018/6265108 pmid:30050566 pmcid:PMC6046167 fatcat:hdtbezrbdrbrvdnd7ydlcjaqim

An Advanced Hybrid Forecasting System for Wind Speed Point Forecasting and Interval Forecasting

Haipeng Zhang, Hua Luo, Danilo Comminiello
2020 Complexity  
However, as wind is irregular, nonlinear, and nonstationary, to accurately predict wind speed is a difficult task.  ...  To test the effectiveness of the forecasting system, the 10-min and one-hour wind speed sequences from the Sotavento wind farm in Spain were applied for conducting comparison experiments.  ...  C t is the cell state, Y t is the output of the cell at time t, o t is the activation of the output gate, and g(x), σ(x), and h(x) are activation functions.  ... 
doi:10.1155/2020/7854286 fatcat:x5cri5mdtnbenjsolgahjbrmaa

AI in Finance: Challenges, Techniques and Opportunities [article]

Longbing Cao
2021 arXiv   pre-print
The comparison, criticism and discussion of classic vs. modern AI techniques for finance are followed.  ...  This area has been lasting for decades with both classic and modern AI techniques applied to increasingly broader areas of finance, economy and society.  ...  Time-series and signal analysis State space modeling, time-series analysis, spectral analysis, long-memory timeseries analysis, nonstationary analysis, etc.  ... 
arXiv:2107.09051v1 fatcat:g62cz4dqt5dcrbckn4lbveat3u
« Previous Showing results 1 — 15 out of 100 results