Filters








475 Hits in 7.6 sec

Speed and Accuracy Enhancement of Linear ICA Techniques Using Rational Nonlinear Functions [chapter]

Petr Tichavský, Zbyněk Koldovský, Erkki Oja
Independent Component Analysis and Signal Separation  
Many linear ICA techniques are based on minimizing a nonlinear contrast function and many of them use a hyperbolic tangent (tanh) as their built-in nonlinearity.  ...  As a result, algorithms using the rational functions are typically twice faster than algorithms with tanh.  ...  This work was supported by Ministry of Education, Youth and Sports of the Czech Republic through the project 1M0572 and by Grant Agency of the Czech Republic through the project 102/07/P384.  ... 
doi:10.1007/978-3-540-74494-8_36 dblp:conf/ica/TichavskyKO07 fatcat:u3pob2rzajb7bali3ucjlo53xi

A non-parametric approach for dynamic range estimation of nonlinear systems

Bin Wu, Jianwen Zhu, F.N. Najm
2005 Proceedings. 42nd Design Automation Conference, 2005.  
chaos expansion (PCE), output statistics of interest can be obtained for both linear and nonlinear systems.  ...  In this paper, we propose the first algorithm with the capacity of handling both near-Gaussian and non-Gaussian input signals. Our method is based on the use of independent component analysis (ICA).  ...  is commonly used for contrast enhancing in image and speech recognition; bilinear is a nonlinear filter whose output is linear respect to every single system variable.  ... 
doi:10.1109/dac.2005.193932 fatcat:3722mm767ng67cjvjr34oo6m34

A non-parametric approach for dynamic range estimation of nonlinear systems

Bin Wu, Jianwen Zh, Farid N. Najm
2005 Proceedings of the 42nd annual conference on Design automation - DAC '05  
chaos expansion (PCE), output statistics of interest can be obtained for both linear and nonlinear systems.  ...  In this paper, we propose the first algorithm with the capacity of handling both near-Gaussian and non-Gaussian input signals. Our method is based on the use of independent component analysis (ICA).  ...  is commonly used for contrast enhancing in image and speech recognition; bilinear is a nonlinear filter whose output is linear respect to every single system variable.  ... 
doi:10.1145/1065579.1065800 dblp:conf/dac/WuZN05 fatcat:3bojzpehxfgohogudom27qkmhu

Dynamic-range estimation

Bin Wu, Jianwen Zhu, F.N. Najm
2006 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
of input random processes, but also the propagation of random processes through both linear and nonlinear systems with difficult constructs such as multiplications, divisions, and conditionals.  ...  It is shown that when applied to interesting nonlinear applications such as adaptive filters, polynomial filters, and rational filters, this method can produce complete accurate statistics of each internal  ...  5] and is commonly used for contrast enhancing in image and speech recognition; bilinear is a nonlinear filter whose output is linear with respect to every single system variable.  ... 
doi:10.1109/tcad.2005.859507 fatcat:dft5k42pizbflhtkwsvy46msfq

Peak-Load-Regulation Nuclear Power Unit Fault Diagnosis Using Thermal Sensors Combined with Improved ICA-RF Algorithm

Yifan Wu, Kaiyu Wu, Wei Li, Jianhong Chen, Zitao Yu
2021 Sensors  
A series of stationary physical source functions and a series of non-stationary noise signals are obtained.  ...  The accuracy rate is found to be at the threshold of 99%.  ...  The mathematical calculation of the cost function of traditional ICA is difficult, and the signal separation speed is low.  ... 
doi:10.3390/s21216955 pmid:34770261 pmcid:PMC8588505 fatcat:b3dvp2hn3jdkjfno3monrh2uwi

Short-term Forecasting of Heat Demand of Buildings for Efficient and Optimal Energy Management Based on Integrated Machine Learning Models

Abinet Tesfaye Eseye, Matti Lehtonen
2020 IEEE Transactions on Industrial Informatics  
Moreover, the devised model achieves outperformed forecasting accuracy enhancement, compared to the other nine evaluated models. .  ...  The performance of the proposed EMD-ICA-SVM-based forecasting model is tested using an out-of-sample one-year (2017) hourly dataset of district heat consumption of various building types.  ...  The rational for the effectiveness of the decomposed data in the prediction process is due to the enhanced data decomposition capability of the EMD technique.  ... 
doi:10.1109/tii.2020.2970165 fatcat:mokgyy3iojgorfpvdpz7dnrvoa

Semi-nonnegative joint diagonalization by congruence and semi-nonnegative ICA

Julie Coloigner, Laurent Albera, Amar Kachenoura, Fanny Noury, Lotfi Senhadji
2014 Signal Processing  
The numerical results show the benefit of using a priori information, such as nonnegativity.  ...  All derivatives have been jointly calculated in matrix form using the algebraic basis for matrix calculus and product operator properties.  ...  After developping (12) , the objective function ϕ is a second degree polynomial in µ C . Thus, the optimal stepsize µ it C is a rational function in µ E .  ... 
doi:10.1016/j.sigpro.2014.05.017 fatcat:ytothv6nn5aibbbe6am2nm3o2a

Wind Turbine Bearing Temperature Forecasting Using a New Data-Driven Ensemble Approach

Guangxi Yan, Chengqing Yu, Yu Bai
2021 Machines  
Finally, the imperialist competitive algorithm (ICA) optimizes the weights for subseries and combines them to achieve the final forecasting results.  ...  algorithms with predictors; (2) the experiment results proved that the proposed model outperformed other selective models, with higher accuracies in all datasets, including three state-of-the-art models  ...  Acknowledgments: This study is fully supported by the National Natural Science Foundation of China (Grant No. 61902108) and the Natural Science Foundation of Hebei Province (Grant No. F2019208305).  ... 
doi:10.3390/machines9110248 fatcat:5rh64hsi2ndf5kqriokgmmpyky

AI-Enabled Intelligent Visible Light Communications: Challenges, Progress, and Future

Jianyang Shi, Wenqing Niu, Yinaer Ha, Zengyi Xu, Ziwei Li, Shaohua Yu, Nan Chi
2022 Photonics  
We first depict a full model of the visible light channel and discuss its main challenges. The advantages and disadvantages of machine learning in VLC are discussed and analyzed by simulation.  ...  However, the extra electro-optical and photoelectric conversions in VLC systems usually introduce exceeding complexity to communication channels, in particular severe nonlinearities.  ...  L are the tap numbers of linearity and nonlinearity.  ... 
doi:10.3390/photonics9080529 fatcat:f23jdnvqjngnbnsw72hhasdmni

Adaptive optics based on machine learning: a review

Youming Guo, The Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China, Libo Zhong, Lei Min, Jiaying Wang, Yu Wu, Kele Chen, Kai Wei, Changhui Rao, The Laboratory on Adaptive Optics, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China, University of Chinese Academy of Sciences, Beijing 100049, China
2022 Opto-Electronic Advances  
Although this technique has already been used in various applications, the basic setup and methods have not changed over the past 40 years.  ...  Adaptive optics techniques have been developed over the past half century and routinely used in large ground-based telescopes for more than 30 years.  ...  Besides of improving accuracy and speed of traditional narrow field-of-view WFS, deep learning can also be used to improve the performance of tomography WFS.  ... 
doi:10.29026/oea.2022.200082 fatcat:fkuhbsrwpvcxnca35tz54hx2lm

Predicting Primary Energy Consumption Using Hybrid ARIMA and GA-SVR Based on EEMD Decomposition

Yu-Sheng Kao, Kazumitsu Nawata, Chi-Yo Huang
2020 Mathematics  
Forecasting energy consumption is not easy because of the nonlinear nature of the time series for energy consumptions, which cannot be accurately predicted by traditional forecasting methods.  ...  An empirical study case based on the Taiwanese consumption of energy will be used to verify the feasibility of the proposed forecast framework.  ...  Conflicts of Interest: The authors declare no conflicts of interests.  ... 
doi:10.3390/math8101722 fatcat:cvemvs5jufhh5hodedb5rzsimm

Various epileptic seizure detection techniques using biomedical signals: a review

Yash Paul
2018 Brain Informatics  
In this paper, seizure detection techniques are classified as time, frequency, wavelet (time-frequency), empirical mode decomposition and rational function techniques.  ...  The aim of this review paper is to present state-of-the-art methods and ideas that will lead to valid future research direction in the field of seizure detection. which permits unrestricted use, distribution  ...  Another attempt to classify seizure detection as linear and nonlinear techniques is made in [7] [8] [9] . Tzallas et al.  ... 
doi:10.1186/s40708-018-0084-z pmid:29987692 fatcat:7xuxlw73q5bqphxae6p3v2ajgq

Artifacts Removal in EEG Signal Using a NARX Model Based CS Learning Algorithm

2018 Multimedia Research  
Here, the performance of the proposed model is analysed using signal to noise ratio (SNR) and root mean square error (RMSE) value.  ...  In order to remove the artifacts signal such as EOG, EMG and ECG, we have proposed, a new nonlinear autoregressive with exogenous input (NARX) filter in this paper.  ...  The results of RMSE value is used to measure the accuracy of the resultant signal. ( ) ∑ N t o p E E N RMSE 1 = 2 1 = Where, N is the total number of iteration time and the predicted value error is defined  ... 
doi:10.46253/j.mr.v1i1.a1 fatcat:sx4n4izzrfhbjmvo5x6gwujcxu

Applications of Machine Learning to Wind Engineering

Teng Wu, Reda Snaiki
2022 Frontiers in Built Environment  
This contribution examines the state of research and practice of ML for its applications to wind engineering.  ...  Advances of the analytical, numerical, experimental and field-measurement approaches in wind engineering offers unprecedented volume of data that, together with rapidly evolving learning algorithms and  ...  The principal component analysis (PCA) is a commonly used linear technique that can be regarded as a two-layer neural network with a linear activation function.  ... 
doi:10.3389/fbuil.2022.811460 fatcat:4wch33eqgvgx3cbw3agonxfkeq

A Hybrid Kernel-Based Change Detection Method for Remotely Sensed Data in a Similarity Space

Reza Shah-Hosseini, Saeid Homayouni, Abdolreza Safari
2015 Remote Sensing  
Also, a low degree of automation is not optimal for real-time CD applications and also one-dimensional representations of classical CD methods hide the useful information in multi-temporal images.  ...  and (e) initial value of the kernel parameter was estimated by a statistical method based on the L2-norm distance.  ...  Acknowledgements The authors sincerely appreciate the assistance and cooperation of ENVI EXCELIS and PCI Geomatics Companies for making available the multi-temporal Quickbird images of earthquake tsunami  ... 
doi:10.3390/rs71012829 fatcat:neut3zgasnbf3i57omqdkna3o4
« Previous Showing results 1 — 15 out of 475 results