Shandong Institute of Business and Technology

About: Shandong Institute of Business and Technology is a education organization based out in Yantai, China. It is known for research contribution in the topics: Computer science & Artificial neural network. The organization has 1487 authors who have published 1433 publications receiving 8915 citations.

Construction project risk evaluation based on Rough Sets and Artificial Neural Networks

Abstract: The construction industry is plagued by risk and often suffers poor performance as a result. Therefore, risk management is very important for construction project to achieve its goal. The risk evaluation is the basic work of risk management. There are a number of risk evaluation techniques, but each has its own faults. In this paper, a new model, which integrates Artificial Neural Networks and Rough Sets theory, was proposed to solve the construction project risk evaluation problem. Firstly, select index system for the risk evaluation of the construction projects and collect the data of projects as samples according to the index system. The decision table was formed accordingly. Experts discrete method is used to discrete the values of the attributes. Secondly, Genetic Algorithm was used to reduce the attributes in the decision table. Finally, Artificial Neural Networks model was built according to the index in the reduced attribute set. The testing result of the example indicates that the proposed model is satisfied in risk evaluation reliability, and the studying efficiency has improved compared with the simple Artificial Neural Networks method.

Human concerned object detecting in video

Abstract: The purpose of our work is to detect the target human concerned in video. For security considerations, event detection in video has potential economic and social needs. Human concerned object detecting is very helpful for event detection. In some emergency or special events, people will focus on specific object. We need locate human body and face, detect the sight direction, and determine the object they are looking. Firstly, we divide video into several clips which have same scales, according to weight to segment or merge clips. After video segmentation, we can get some region. What is the concerned object(region) for the people in video? So we need to detect the human and face. We use HOG feature and SVM to classify human with different pose, and detect them out. On this basis, face detection and tracking is performed. We apply yaw and pitch angle to present sight direction, in line with the weight of sight to determine human concerned region. For the complex scenes, we do an articulation judgment and give up the irrelevant background, and highlight the prospects. Experiments show that our method not only applicable to simple scenes, but also complex background scenes, and shows clear and accurate result.

Urban Ecological Assessment: Indicator System and Model Construction

Abstract: The aim of this paper was to facilitate the future development of urban complex, and enhance the sustainability of the civilizing process at the social and national level. On the basis of the primary characteristics of the ecological civilization, this paper discusses the fundamental principles for the evaluation of ecological civilization. We have developed six categories,forty assessment criteria and the corresponding evaluation index model.

Establishment of feature set prediction model based on image processing technology

Abstract: To build a prediction model of color feature set under image processing technology, a color feature extraction method based on image processing technology in two-dimensional images was developed. Taking the grapes as the experimental object, the rapid non-destructive testing method of pH value and soluble solids content (SSC) was put forward. The mean and variance of pixel gray value were extracted from the three color channel images of RGB, HIS, YIQ, YCbCr and HSV color space as color features. Then, a total of 120 color features were obtained. Based on the color feature, the least squares support vector machine was used to establish the grape pH value and the SSC detection model. The results showed that the correlation coefficient of the pH model was 0.870–0.886 and the correlation coefficient of the SSC model was 0.695–0.727 based on the different feature sets. It is concluded that the image color feature extraction can be applied to the grape pH value and SSC value of rapid non-destructive testing.

Integrating Frequent Itemsets Mining with Relational Database

Abstract: Frequent itemsets mining is becoming increasingly important since the size of databases grows even larger. Currently database systems are dominated by relational database. However the performance of SQL based data mining is known to fall behind specialized implementation and expensive mining tools being on sale. In this paper we analyzed a famous frequent itemsets discovery algorithms FP-growth, and propose a new implementation approach called DBFP-Growth to create disk-based FP-tree based on ORACLE PL/SQL, it can execute faster than using SQL directly. Also presents a novel SQL-based method DRRW, which can remove duplicate records from database without temp table generation.