Search

Your search keyword '"CHE Wen-gang"' showing total 25 results
Start Over Author "CHE Wen-gang"
25 results on '"CHE Wen-gang"'

1. A Study on the Motif Pattern of Dark-Cloud Cover in the Securities

Author

Long Jing, Che Wen-Gang, Yu Ren, and Zhou Zhi-Yuan

Subjects
Engineering (General). Civil engineering (General), TA1-2040
Abstract

Morphological analysis is the analysis and mining of the graphics formed of the securities price changes. Investors need to forecast the trend of future before buying and selling points, which can avoid great loss. Therefore, the analysis of motif pattern of K-line in the form of futures investment technology analysis is very significant. Based on the thoughts of short-term trend clustering, this paper proposes a method of detecting the motif pattern of Dark-Cloud Cover in stock time series by analysing stock historic data and K-line shape, in order to predict the stock market trends. And we prove the effectiveness and practicality of the method by a series of experimental analysis.

Published
2017
Full Text
View/download PDF

2. A multi-stage feature distillation-weighted lightweight image super-resolution network.

Author

YANG Sheng-rong, CHE Wen-gang, GAO Sheng-xiang, and ZHAO Yun-lai

Abstract

To address the issues of insufficient receptive fields for extracting low-level features and the lack of reinforcement for local key features in lightweight networks, this paper proposed a multistage feature distillation-weighted lightweight image super-resolution network LMSWN. Firstly, a pyramid- like module is employed to expand the receptive field during shallow feature extraction, integrate feature information of different scales, and enrich the information flow of the network. Secondly, a multi-stage residual distillation-weighted module is designed to enhance the ability of square convolution to extract local key features, recover more detailed information, and improve reconstruction performance. At the same time, the combination of channel separation and 1x1 convolution realizes gradual distillation of features, reducing the number of network parameters. Finally, two adaptive parameters are introduced to jointly learn the features of the two branches of the multi-stage residual distillationweighted module, enhancing the attention to different levels of feature information and further enhancing the representation ability of the network. Experimental results show that the proposed network is fully validated on five benchmark datasets: Set 5, Set 14, BSDS 100, Urban 100, and Manga 109, and its performance exceeds the current mainstream lightweight network [ABSTRACT FROM AUTHOR]

Published
2024

5. Prediction Model of River Water Level Based on LS-SVM

Author

Ding Haijiao and Che Wen-gang

Subjects
Support vector machine, Hydrology, Flow (psychology), Environmental science, Data mining, computer.software_genre, River water, computer, Data modeling, Water level
Abstract

In order to predict the changes of water level of natural river, this paper applied the method of LS-SVM, combining with sichuan zigong hydrologic measured water level data and flow data builded a double input single output (water level and flow-water level) river water level prediction model. Through the analysis of the prediction results, can draw the conclusion: The accuracy of the prediction model, which was established by LS-SVM is very high, can meet the needs of the river water level prediction.

Published
2015

6. Notice of Retraction: A Novel Forecasting Model of Fuzzy Time Series Based on K-means Clustering

Author

Fu Fang-Ping, Che Wen-gang, and Chi Kai

Subjects
Computer science, Fuzzy set, k-means clustering, Domain of discourse, Data mining, Time series, computer.software_genre, Cluster analysis, computer, Fuzzy logic, Technology forecasting, Economic forecasting
Abstract

Fuzzy time series (FTS) is an effective method in forecasting problems due to its salient capabilities of tracking uncertainty and vagueness in observation data. However, in FTS forecasting, it is required about 5-7 intervals in the universe of discourse, as a result, the method of partition intervals become a major consideration. Recently, some studies have demonstrated that the method using length-variant intervals is able to improve the forecasting accuracy at a large scale. In this paper, a K-means clustering technique is used while selecting the length of each interval, and then a novel model of FTS is introduced accordingly. The empirical results show that this model provides a more general platform for partitioning universe of discourse, and gets higher forecasting accuracy rates than those of the existing methods.

Published
2010

7. Question Classification Based on Incremental Modified Bayes

Author

Mao Cunli, Meng Xiang-yan, Li Ying-wei, Yu Zhengtao, and Che Wen-gang

Subjects
Computer science, business.industry, Information processing, Pattern recognition, Percentage point, Bayes classifier, Machine learning, computer.software_genre, Support vector machine, Bayes' theorem, ComputingMethodologies_PATTERNRECOGNITION, Incremental learning, Bayes error rate, Artificial intelligence, business, computer, Statistic
Abstract

How to use the incremental training corpus to improve the question classification accuracy rate in the process of question classification based on statistic learning. A question classification method based on the incremental modified Bayes was presented in this paper. The method used the modified Bayes and combined the incremental learning to correct the parameter by the incremental training set stage by stage, and established the question classification model based on the incremental modified Bayes. A question classification experiment was done in the domain of Yunnan tourism, the experimental results showed that the presented method evidently excelled than the modified Bayes method in the accuracy rate and the training time, the average accuracy rate was improved 3.3 percentage points than the accuracy rate of the modified Bayes method; the average training time was improved 39.1 percentage points than the training time efficiency of the modified Bayes method.

Published
2008

Catalog

Books, media, physical & digital resources
See catalog results