This paper proposes a new text classification method named document matrix convolutional neural networks (DM-CNN). Unlike the original ways of converting texts into 1-dimensional vectors and processing each word as a pixel, this model is based on the n-dimensional word embeddings obtained in advance,...

Zero pronoun resolution is very important in natural language processing. Identification of zero pronoun is the fundamental task of its resolution. Existing feature engineering based identification approaches are unsuitable for big data applications due to labor-intensive work. Furthermore, as extracted...

This paper will improve the spectral amplitude coding is used for OCDMA wavelength division multiplexing passive optical network system. Improved the system bit error rate of less than 10-10, multiple access interference suppressed to some extent, the performance of the transmission network stable and...

The underwater target classification is a challenging task due to the complexity of marine environment and the diversity of underwater target features. Most of the-state-of-the-art target recognition systems depend on feature extraction schemes based on expert knowledge in order to effectively represent...

In this paper, the sentiment analysis based on the deep learning model was studied. By comparing the effects of the shallow learning model SVM and the deep learning model LSTM on the classification of Weibo comments, we found that the classification result of the LSTM model is better than that of the...

Unconstrained face verification has been actively studied for decades in computer vision. Recent algorithms rely on Convolution Neural Network to further improve the accuracy. However, such algorithms tend to be time-consuming and computationally complex, which cannot meet the real-time requirements....

Traditional method commonly used in bulk sampling and sieve analyses is inevitablely involved the bed surface excavation and destroy the original bed size distribution. In this work, an automatic surface size distribution observation method based on digital image analysis without involving the bed surface...

Infrared sequence image processing is widely used in engineering, but the research of infrared phase processing is rare. In this paper, a method of generating thermal wave phase image based on infrared phase locked-in, phase difference processing and its application in coatings defect detection and recognition...

Sheet metal stamping is an important method of plastic processing, which is one of the basic means of modern manufacturing industry. With the increasing demands of stamping quality, the production quality of stamping process optimization requirements are also rising. In this paper, finite element theory,...

This paper proposes a novel approach for accurate and robust face recognition by using Local Quantized Patterns computed from gabor-filtered images(GLQP) and Deep Belief Network ensembled dynamic random forests(DBN-DRF). GLQP is a kind of local pattern feature extractor based on gabor filters applying,...

Real-time detection of learner's sitting posture not only helps prevent myopia in time but also promotes the improvement of learning efficiency. However, most of the current sitting detection methods have the shortcomings of low detection variety and recognition rate, et al. Based on this, a sitting...

With the ability to measure and simulate more processes at finer scales, the number of data dimensions and data objects has grown significantly in today's datasets. Much existing research has focused on different visualizations for different data exploration tasks. In this paper, based on the financial...

Since Dense SIFT causes a long time spending during clustering due to an excessive order of magnitude, and its feature descriptors reserve excessive insignificant features, we present a new method that using SLIC to select descriptors to address this problem. Furthermore, when VLAD aggregates, the partial...

This paper presents vibration control of a flexible manipulator by an adaptive direct strain gain tuning feedback control. Adaptive feedback gain tuning is applied on the measured strain. These experiments compared the control performance of fixed and adaptive feedback gain control. Results show that...

In view of the problem that the X-ray flat panel detector products are slow from receiving X-Ray tube's exposure to generating the X-Ray medical image, it can not meet the time requirement of post-processing customers. It uses pre-offset calibration to reconstruct dark-field template based on the ck1417...

Image segmentation is a key problem in several fields of science and technology, for E.g. medicine, robotics, and industrial development. The importance of perceptual grouping and organization in vision possess numerous significant factors, such as similarity, proximity, and good continuation, which...