Deep convolutional neural networks (CNNs) have contributed to the significant progress of the single image super resolution (SISR) field. However, most of existing CNN-based SR models require high computing power, which is not conducive to daily use. In addition, these algorithms need to use a large number of CNN to obtain global features. Therefore, this paper proposes an image super-resolution framework based on adaptive residual neural network, using the adaptive framework to switch between global and local reasoning for internal features in a flexible way, it can extract a large number of global features without neglecting key information, which is conducive to the comprehensiveness of residual images. After the adaptive block, SENet is added to conduct channel modeling for the extracted features, and the importance of each feature channel is automatically acquired by learning method. Then, according to this importance, useful features are promoted and those that are not useful for the current task are suppressed. In this way, with more nonlinearity, the complex correlation between channels can be better fitted, and the number of parameters and computation can be reduced, which can improve the performance of super resolution to a certain extent.
Steam reheating system is emerging as a multivariable system with steam-steam exchanger, the
strong coupling and time delay characteristics. The traditional approach for the predictive control in
power plant requires modeling based on accurate mathematical model, and some multivariate
statistical algorithm cannot avoid falling into the over-fitting, therefore these approaches is not
suitable for prediction of the reheating temperature in power plants. In this paper, we used the least
squares support vector machine (LS-SVM) regression algorithm to predict the temperature of the
steam reheating in the power plant combined with the data set of the steam reheating in a 120MW
power plant. Comparing with the existing algorithms, the result shows that the LS-SVM is a robust
and reliable tool for prediction in engineering application field.
Discrete wavelet transform (DWT) is an important tool in digital signal processing. In this paper, a new algorithm to
compute DWT is proposed: first, based on the previous work of performing discrete Fourier transform (DFT) via linear
sums of discrete moments, we introduce a multiplierless DFT by performing appropriate bit operations and shift
operations in binary system; then by convolution theorem, the computation is transformed to the computation of DFT. In
addition, a efficient systolic array is designed to implement the DWT which is a demonstration of the locality of dataflow
in the algorithms. The approach is also applicable to multi-dimensional DWT.
Proc. SPIE. 6789, MIPPR 2007: Medical Imaging, Parallel Processing of Images, and Optimization Techniques
KEYWORDS: Fourier transforms, Binary data, Digital signal processing, Evolutionary algorithms, Bridges, Medical imaging, Real-time computing, Data processing, Information technology, Pattern recognition
Discrete Fourier transform (DFT) is an important tool in digital signal processing. We have proposed an approach to
performing DFT via linear sums of discrete moments. In this paper, based on the previous work, we present a new
method of performing fast Fourier transform without multiplications by performing appropriate bit operations and shift
operations in binary system, which can be implemented by integer additions of fixed points. The systolic implementation
is a demonstration of the locality of dataflow in the algorithms and hence it implies an easy and potential hardware/VLSI
realization. The approach is also applicable to DFT inverses.
Proceedings Volume Editor (1)
This will count as one of your downloads.
You will have access to both the presentation and article (if available).