The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In view of the emotional polarity classification problem, the deep learning has the disadvantages of incomplete information extraction and low precision, a model combining bi-directional gated recurrent unit with multiple convolution neural network is proposed. The unit is used to extract the history and future information of the sentence, then use the multi-convolution neural network for system training,...
An effective and fast face recognition method that is capable of dealing with faces under variable pose and illumination conditions has been proposed in this paper. First, the face is detected and the eyes are located automatically by the two cameras, eyes located in the two cameras are matched and the pose angle of the face is calculated. Then, the frontal face is generated according to the pose...
With the purpose of achieving automated detection of crowd abnormal behavior in public, this paper discusses the category of typical crowd and individual behaviors and their patterns. Popular image features for abnormal behavior detection are also introduced, including global flow based features such as optical flow, and local spatio-temporal based features such as Spatio-temporal Volume (STV). After...
Face detection has been a hotspot either in research and in commercial application. In this paper, Locally Assembled Binary (LAB) feature and Adaboost algorithm are combined to recognize human face in images. On the basis of ensuring the detection speed, the detection accuracy is improved. Integral image technology is also conducted in consideration of detection speed. The proposed method is tested...
In order to overcome the low accuracy defect of the traditional theoretical line losses calculation method in distribution system, an intelligent calculation method based on improved minimum enclosing ball vector machine (MEBVM) is proposed. In this intelligent calculation method, the theoretical line losses calculation is abstracted into multiple regression analysis. All kinds of line losses impact...
Existing intelligent theoretical line losses calculation methods that prevalent on worse line calculation error, are all based on single learning algorithm. In order to overcome this defect, a novel intelligent calculation method based on boosting algorithm is proposed. In this calculation method, the theoretical line losses calculation is abstracted into function fitting problem, in addition, the...
Data-based fault diagnosis technology applied in chemical industry process has attracted great attention, in which the effective methods for visualizing the process variation are still challenging. The self-organizing map (SOM) is an unsupervised learning algorithm of neural network, which is presented to solve the visualization monitoring and fault diagnosis problem. The high-dimensional input space...
The traditional relation extraction methods require the pre-defined relation types and a corpus with human tags. The information extracted by the current open relation extraction (ORE) methods is incomplete, and the relation types are finite. To solve the above problems, we propose ClausORE, which is an n-ary ORE method for Chinese text and extracts the entities and relations between entities from...
Recommender system has become one of the most promising techniques in the era of big data. It aims to help users to quickly find the valuable information from the massive data. Many recommendation approaches have been proposed in recent years. Currently, a majority of researchers still pay attention on designing more effective and efficient methods, and they usually put all the user data into model...
The development of computer science and applications changes with each passing day. The software companies and research institutions put forward higher requirements for computer science majors' professional capacity and creative ability. However, many problems still exist in the current status of teaching computer science majors and directly affect the quality of professional training, so it brings...
In uplink device-to-device (D2D) underlay cellular systems, massive multiple-input multiple-output (MIMO) seems promising as the large antenna array at the base station (BS) can nearly null the D2D-to- cellular interference. But the channel state information from all the users including D2D users to the BS is required to obtain the advantage. For the orthogonal channel training scheme, the pilot overhead...
In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent Fully Connected Neuro-Fuzzy Inference System (F-CONFIS). The F-CONFIS is a new type of neural network that differs from traditional neural networks, which there are the dependent and repeated weights. For these special properties, its learning algorithm should be different from that of the conventional neural networks. Therefore,...
In this paper, based on the transformation from the fuzzy inference system into a fully connected neural network, F-CONFIS, the mixed radix systems in Fully Connected Neural Fuzzy Inference Systems are derived. The functional equivalence between a fuzzy system and a neural network has been proved, however, they are non-constructive. F-CONFIS provides constructive steps to build the equivalence between...
Feature selection is often considered as a key step in text categorization. In this paper, we proposed a new feature selection algorithm, named AD, which comprehensively measures the degree of relevance and distinction of terms occur in document set. We evaluated AD on three benchmark document collections, 20-Newsgroups, Reuters-21578 and WebKB, using two classification algorithms, Naive Bayes and...
The invention of deep belief network (DBN) provides a powerful tool for data modeling. The key advantage of DBN is that it is driven by training data only, which can alleviate researchers from the routine of devising explicit models or features for data with complicated distributions. However, as the dimensionality and quantity of data increase, the computing load of training a DBN increases rapidly...
Based on analysis of plate shape defect pattern in cold rolling, a defect recognition method using RBF-BP combinational neural network model optimized by genetic algorithm is proposed in this paper. The method makes use of genetic algorithm to optimize the weights and thresholds of the input layer, hidden layer and output layer in the RBF-BP network, and a GA-RBF-BP network model is formed. It can...
As one of the dominant techniques for sensing the underwater environments, underwater vision has shown great prospects in ocean investigations and explorations over the last decades. The vision system is usually installed on the platforms of autonomous underwater vehicles (AUVs). Due to the limitation of transmission and storage for underwater signals, it is extremely urgent to explore an efficient...
Aiming at the disadvantages of prediction model of single BP neural network, a prediction model was presented by combining AdaBoost algorithm and BP neural network for improving the forecasting accuracy of single BP neural network. The ensemble BP network based on AdaBoost is used as intelligent algorithm. Overcoming the instability of single BP neural network, the proposed models can give more accurate...
Hydraulic bending roller is a most basic and important method for shape control of strip. The rolled shape quality is decided by the setting value of bending farce in great part. This paper chooses five-stand hot tandem rolling mill in 1810 product line of Tangshan Iron and Steel Company as background, and deals primarily with the study of the bending force prediction model of the rolling unit. To...
In this paper, the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used for the classification of the epileptic electroencephalogram (EEG) signals. The ANFIS combines the adaptation capability of the neural networks and the fuzzy logic-based qualitative approach together. A given input/output data set is deployed to construct a fuzzy inference system, whose membership function parameters are trained...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.