Abstractive Arabic Text Summarization Using Hyperparameter Tuned Denoising Deep Neural Network

ive Arabic Text Summarization using Hyperparameter Tuned Denoising Deep Neural Network(AATS-HTDDNN)technique.The presented AATS-HTDDNN technique aims to generate summaries of Arabic text.In the presented AATS-HTDDNN technique,the DDNN model is utilized to generate the summary.This study exploits the Chameleon Swarm Optimization(CSO)algorithm to fine-tune the hyperparameters relevant to the DDNN model since it considerably affects the summarization efficiency.This phase shows the novelty of the current study.To validate the enhanced summarization performance of the proposed AATS-HTDDNN model,a comprehensive experimental analysis was conducted.The comparison study outcomes confirmed the better performance of the AATS-HTDDNN model over other approaches.

A defect recognition model for cross-section profile of hot-rolled strip based on deep learning

The cross-section profile is a key signal for evaluating hot-rolled strip quality,and ignoring its defects can easily lead to a final failure.The characteristics of complex curve,significant irregular fluctuation and imperfect sample data make it a challenge of recognizing cross-section defects,and current industrial judgment methods rely excessively on human decision making.A novel stacked denoising autoencoders(SDAE)model optimized with support vector machine(SVM)theory was proposed for the recognition of cross-section defects.Firstly,interpolation filtering and principal component analysis were employed to linearly reduce the data dimensionality of the profile curve.Secondly,the deep learning algorithm SDAE was used layer by layer for greedy unsupervised feature learning,and its final layer of back-propagation neural network was replaced by SVM for supervised learning of the final features,and the final model SDAE_SVM was obtained by further optimizing the entire network parameters via error back-propagation.Finally,the curve mirroring and combination stitching methods were used as data augmentation for the training set,which dealt with the problem of sample imbalance in the original data set,and the accuracy of cross-section defect prediction was further improved.The approach was applied in a 1780-mm hot rolling line of a steel mill to achieve the automatic diagnosis and classification of defects in cross-section profile of hot-rolled strip,which helps to reduce flatness quality concerns in downstream processes.

Adaptive sampling and reconstruction for gradient-domain rendering

Gradient-domain rendering estimates finite difference gradients of image intensities and reconstructs the final result by solving a screened Poisson problem,which shows improvements over merely sampling pixel intensities.Adaptive sampling is another orthogonal research area that focuses on distributing samples adaptively in the primal domain.However,adaptive sampling in the gradient domain with low sampling budget has been less explored.Our idea is based on the observation that signals in the gradient domain are sparse,which provides more flexibility for adaptive sampling.We propose a deep-learning-based end-to-end sampling and reconstruction framework in gradient-domain rendering,enabling adaptive sampling gradient and the primal maps simultaneously.We conducted extensive experiments for evaluation and showed that our method produces better reconstruction quality than other methods in the test dataset.

Micro-Earthquake Seismicity and Tectonic Significance of the 2012 Ms 4.9 Baoying Earthquake,Jiangsu,China

On July 20,2012,the Ms 4.9 Baoying Earthquake occurred near the junction of Baoying County and Gaoyou City in Jiangsu Province,eastern China.Due to no obvious surface rupture and limited observation of earthquake sequence,the seismogenic structure of the Ms 4.9 Baoying Earthquake is still unclear.In this study,80 earthquakes provided by China Earthquake Network Center(CENC)are first relocated;and then the relocated 75 events with high signal-to-noise ratios as templates are utilized to scan through continuous waveform data(July 11 to August 31,2012)using graphics processing unit-based match and locate(GPU-M&L)technique.Then the Deep Denoiser,a deeplearning-based noise reduction technique,is used to further confirm some newly detected events;and the double-difference relocation(Hypo DD)algorithm is used to relocate the earthquakes.We detect and relocate more than twice as many events as the CENC routine catalog,which includes 15 foreshocks and 230 aftershocks.The results show that the foreshocks are mainly distributed in the NW direction along the extended SE section of the blind Xiagonghe fault(XF),which is orthogonal to the strike of the seismogenic fault of the Ms 4.9 Baoying Earthquake(Yangchacang-Sangshutou fault,named YSF).Most of the aftershocks are generally distributed along the NNE-trending YSF and illuminate a steeply dipping plane.This study reveals detailed spatiotemporal evolution of the earthquake sequence and suggests that the buried XF extends southeastward and cuts through the NNE-trending seismogenic YSF.