scholarly journals Support or Risk? Software Project Risk Assessment Model Based on Rough Set Theory and Backpropagation Neural Network

2019 ◽  
Vol 11 (17) ◽  
pp. 4513 ◽  
Author(s):  
Xiaoqing Li ◽  
Qingquan Jiang ◽  
Maxwell K. Hsu ◽  
Qinglan Chen
Keyword(s):  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Attribute Reduction ◽  
Assessment Model ◽  
Software Project ◽  
Risk Assessment Model ◽  
Backpropagation Neural Network ◽  
Model Based ◽  
Sample Data

Software supports continuous economic growth but has risks of uncertainty. In order to improve the risk-assessing accuracy of software project development, this paper proposes an assessment model based on the combination of backpropagation neural network (BPNN) and rough set theory (RST). First, a risk list with 35 risk factors were grouped into six risk categories via the brainstorming method and the original sample data set was constructed according to the initial risk list. Subsequently, an attribute reduction algorithm of the rough set was used to eliminate the redundancy attributes from the original sample dataset. The input factors of the software project risk assessment model could be reduced from thirty-five to twelve by the attribute reduction. Finally, the refined sample data subset was used to train the BPNN and the test sample data subset was used to verify the trained BPNN. The test results showed that the proposed joint model could achieve a better assessment than the model based only on the BPNN.

Influence of factors on collapse risk of loess tunnel: a multi-index assessment model

2018 ◽  
Vol 16 (5) ◽  
pp. 734-749
Author(s):  
Xueliang Zhang ◽  
Meixia Wang ◽  
Binghua Zhou ◽  
Xintong Wang
Keyword(s):  
Risk Assessment ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Surrounding Rock ◽  
Assessment Model ◽  
Burial Depth ◽  
Risk Assessment Model ◽  
Content Type ◽  
Close Time

Purpose Because of the properties of loess, the occurrence of collapse following deformation of a large settlement is a common problem during the excavation of tunnels on loess ground. Hence, risk management for safer loess tunnel construction is of great significance. The purpose of this paper is to explore the influence of factors on collapse risk of loess tunnels and establish a risk assessment model using rough set theory and extension theory. Design/methodology/approach The surrounding rock level, groundwater conditions, burial depth, excavation method and support close time were selected as the factors and settlement deformation was the verification index for risk assessment. First, using rough set theory, the influence of risk factors on the collapse risk of loess tunnels was calculated by researching engineering data of excavated sections. Then, a collapse risk assessment model was developed based on extension theory. As the final step, the model was applied to practical engineering in the Loess Plateau of China. Findings The weights of surrounding rock level, groundwater conditions, burial depth, excavation method and support close time obtained using rough set theory were respectively 10.811 per cent, 18.919 per cent, 24.324 per cent, 40.541 per cent and 5.406 per cent. The assessment results obtained using the model were in good agreement with field observations. Originality/value This study highlights key points in collapse risk management of loess tunnels, which could be very useful for future construction methods. The model, using easily obtained parameters, helps in predicting the collapse risk level of loess tunnels excavated under different geological conditions and by different construction organizations and provides a reference for future studies.

scholarly journals Attribute Reduction Based on Consistent Covering Rough Set and Its Application

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Jianchuan Bai ◽  
Kewen Xia ◽  
Yongliang Lin ◽  
Panpan Wu
Keyword(s):  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Attribute Reduction ◽  
Relevance Vector Machine ◽  
Support Vector ◽  
Processing Step ◽  
Important Processing ◽  
Continuous Attribute ◽  
Covering Rough Set

As an important processing step for rough set theory, attribute reduction aims at eliminating data redundancy and drawing useful information. Covering rough set, as a generalization of classical rough set theory, has attracted wide attention on both theory and application. By using the covering rough set, the process of continuous attribute discretization can be avoided. Firstly, this paper focuses on consistent covering rough set and reviews some basic concepts in consistent covering rough set theory. Then, we establish the model of attribute reduction and elaborate the steps of attribute reduction based on consistent covering rough set. Finally, we apply the studied method to actual lagging data. It can be proved that our method is feasible and the reduction results are recognized by Least Squares Support Vector Machine (LS-SVM) and Relevance Vector Machine (RVM). Furthermore, the recognition results are consistent with the actual test results of a gas well, which verifies the effectiveness and efficiency of the presented method.

The Incremental Knowledge Acquisition Based on Hash Algorithm

2016 ◽  
Vol 24 (03) ◽  
pp. 347-366 ◽  
Author(s):  
Qing-Hua Zhang ◽  
Long-Yang Yao ◽  
Guan-Sheng Zhang ◽  
Yu-Ke Xin
Keyword(s):  
Knowledge Acquisition ◽  
Set Theory ◽  
Rough Set ◽  
Granular Computing ◽  
Rough Set Theory ◽  
Attribute Reduction ◽  
Algorithm Analysis ◽  
Data Sets ◽  
Hash Algorithm ◽  
Acquisition Method

In this paper, a new incremental knowledge acquisition method is proposed based on rough set theory, decision tree and granular computing. In order to effectively process dynamic data, describing the data by rough set theory, computing equivalence classes and calculating positive region with hash algorithm are analyzed respectively at first. Then, attribute reduction, value reduction and the extraction of rule set by hash algorithm are completed efficiently. Finally, for each new additional data, the incremental knowledge acquisition method is proposed and used to update the original rules. Both algorithm analysis and experiments show that for processing the dynamic information systems, compared with the traditional algorithms and the incremental knowledge acquisition algorithms based on granular computing, the time complexity of the proposed algorithm is lower due to the efficiency of hash algorithm and also this algorithm is more effective when it is used to deal with the huge data sets.

Sign in / Sign up

Export Citation Format

Share Document