Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)

Session: Machine Learning, Models and Algorithm

33 articles
Proceedings Article

Key Research of Pre-processing on Mongolian-Chinese Neural Machine Translation

Jian Du, Hongxu Hou, Jing Wu, Zhipeng Shen, Jinting Li, Hongbin Wang
Neural machine translation has recently achieved promising results with the big scale corpus. But there is little research on the small scale corpus, such as Mongolian. Mongolian belongs to the agglutinative language while Chinese is a pictograph. It is necessary to do some pre-processing for both Mongolian...
Proceedings Article

The Research of Grade Prediction Model Based on Improved K-means Algorithm

Yongguang Zhang, Hua Wang, Hongyang Li
Grades reflect how well you learnt in courses. This paper introduce a model to predict student grade-data with a refined K-means clustering algorithm. K-means clustering algorithm based on the normal distribution is proposed to overcome the flaws that caused by using Euclidean distance algorithm to measure...
Proceedings Article

The Modified Model of Q-learning Search Strategy Based on LDA-DBN

Shihao Zhu, Guangfeng Zhang, Dongfan Zhao
The network in web has the characteristic of information roughness. Focused crawling is able to grab the information selectively when topic relate to web page. In this paper, utilizing the characteristics of Gibbs using in DBN and LDA, in the sliding window containing the URL link to semantic recognition,...
Proceedings Article

A General Conceptual Model of Recommendation Based on Multi-Agent Approach

Xunhui Zhang, Tao Wang, Gang Yin, Xinjun Mao, Huaimin Wang
In recent years, recommendation is becoming more and more popular in many fields. However, there are still some problems, such as single point failure, lack of ability to support different devices and etc. To solve these problems, researches have been carried out using multi-agent approach but some new...
Proceedings Article

Robust Model for Multimodal Location of the Hazmat under Uncertainty

Liping Liu, Zipeng Yi
In reality, the demand of O-D pair can be affected by various factors and then lead to uncertain demand. Finally, it will impactthe location of transfer yards. A bi-objective nonlinear robust model is established for locating multimodal transfer yards with hazardous materials in this paper. To solve...
Proceedings Article

The Correlation Analysis of Clean Energy Output Based on Nonparametric Kernel Density Estimation Probability Models

Xiaolin Qin, Yonggang Li, Chao Shen, Zengqiang Zhang, Xuyao Zeng
There often exists correlation among adjacent photovoltaic power stations and wind farms. This paper provides a method based on the nonparametric kernel density estimation theory and Spearman rank correlation to analysis the correlation of clean energy outputs. Firstly, a variable bandwidth kernel density...
Proceedings Article

Penalty-PSO Algorithm for Sequencing Mixed Model Assembly Line

Chenglong Lu, Bo Zhu, Beibei Liu, Yuwei Wan
A mathematical model of sequencing problem which takes the minimum overload time as the optimization objective is estab-lished to solve mixed model assembly line sequencing problem in semi-closed station. A new penalty strategy that can eliminate the influence of the viscous effect which caused by the...
Proceedings Article

A Comparative Analysis toward Two Famous Smart-Tourism by Integrated Dynamic-Programming & Project Appraisal Model

Tianhang Huang, Nan Zhang
The purpose of this study is aimed to construct a comprehensive theoretical framework for explaining the characteristics of different Smart Tourism Projects' Designing and Developing, and finding the best practice model in this booming area. Based on the three stages of R&D project pipeline of dynamic-programming...
Proceedings Article

A Probability PPV Model for Social Network Influence Maximization Problem

Yunjia Ge, Dong Wang
For Influence Maximization(IM) problem based on social network, effective and personalized probability learning method was still not theoretical guaranteed. In this paper, we proposed a PPV probability model based on IM problem, which effectively learnt influence probabilities and personal-ized influence...
Proceedings Article

Technology of Exploratory OLAP Based on the Integral Analytical Model

Anna Korobko
The paper presents the original approach to the exploratory OLAP of the heterogeneous resources based on the integral analytical model. Applying the multidimensional data model as a technological fundament allows to analyze the structure of the joining sources according to unified notation, allows to...
Proceedings Article

Development of a Unified Model of Data Representation for Cross-System Interaction

Tatiana Penkova, Anna Korobko, Artem Belorusov
The paper presents an unconventional approach to formation of unified models for representation of cross-system interaction. The authors highlight the necessity of system integration method development that would bring in a standardised way to data exchange between heterogeneous resources with an opportunity...
Proceedings Article

Adaptive Model of Data Exchange for Cross-System Interaction

Tatiana Penkova, Anna Korobko, Artem Belorusov
The article approaches the problem of adaptive data exchange model making for cross-system data interaction. The authors demonstrated the need in development of system integration methods that would facilitate the standardised data exchange across heterogeneous sources with an opportunity to adapt flexibly...
Proceedings Article

Study on the Distribution Model of Supermarket Chain Based on AHP

Caixia Chen, Chun Shi
In the past few years, With the constant expansion of supermarket chains, logistic distribution has been a Bottleneck of the development of supermarket chains. It is an important reason that distribution model is not well chose. This article based on the analysis of the limitation of traditional selective...
Proceedings Article

Validation of Dynamic Simulation Models on Uncertainty

Xiaojun Guo, Shaojing Su
Autonomous underwater vehicles (AUV) play an important role in human activities. They are different from of the vehicles other areas (such as air, ground). Movement, communication, target detection all involve complex hydrology and climatic condition. For special application fields it's even more complex....
Proceedings Article

The Classification Model of Customer Groups Based on Grader

Tao Xi, Lijing Wang
The customer demands were divided into dominant and implicit requirements. Classified by professional ability and social background of customer groups, classified indexes of customer groups were established to accurately obtain implicit requirements. In general, natural language expression of customers...
Proceedings Article

Simulation-based Prediction Model of the Auto-body Multi-Stage Forming Process

Dong-Guk Han, Dong-Won Jung
Usually auto body need several forming stages in the real manufacturing. Every forming parameter within the process has a significant influece on the forming quality. A reasonable desgin of the stamping process is needed. According to statistics, stamping process cover auto parts account for a large...
Proceedings Article

An Improved K-means Clustering Algorithm Based on Meliorated Initial Centre

Xiang Li, Zhenwei Wei, Lingling Li
The initial clustering center of traditional K-means clustering algorithm is selected at random that different initial clustering center will get different clustering results, which have great randomicity and poor stability. To improve the K-means clustering algorithm optimized by adopting local outlier...
Proceedings Article

Design of Sliding Rope Protection Algorithm for Mine Hoist in Iron Mine

Jinyang Xia, Yanping Wang, Linlin Shao
Rope protection is the protection function of large mineral lifting equipment. At present, most of the iron ore hoist sliding rope protection is the speed difference detection algorithm, and it is able to determine whether or not the hoisting machine system has a sliding rope fault, which can give the...
Proceedings Article

An Improved Possibilistic Fuzzy Entropy Clustering Based on Artificial Bee Colony Algorithm

Baofeng Guo, Mingyan Jiang
In this paper, a possibilistic fuzzy entropy clustering algorithm (PFECM) based on unsupervised possibilistic clustering (UPC) algorithm and partition entropy (PE) has been proposed. Meanwhile, an efficient global optimization method-artificial bee colony (ABC) algorithm is introduced to optimize the...
Proceedings Article

A Transmission Probability Control Algorithm Based on Competing Node Estimation in MANET

Shentao Wang, Xiaoli Liu, Jingwen Sui, Shengze Qiang, Rui Li, Junqiang He
Most of Transmission Probability Control Algorithms in Mobile Ad hoc Network (MANET) research are based on the assumption that the number of competing nodes is known by every node. With an increasing number of wireless devices or appliances, the number of competing node in network is changed dynamically,...
Proceedings Article

A Dynamic Slot Allocation Algorithm in High-Band Radio Networks

Shentao Wang, Xiaoli Liu, Bin Liu, Shibiao He, Shengze Qiang, Rui Li, Junqiang He
The High Band Radio network has extensive value in the military application. A Dynamic Slot Allocation Algorithm (DSA) based on the High Band Radio network TDMA protocol is proposed in this paper, DSA algorithm allocates slots dynamically according to the difference of network traffics. The simulation...
Proceedings Article

Parallel Algorithm for Identifying Overlapping Communities from Local Extension

Hua Long, Baoan Li
The overlapping communities identification in complex networks was studied with the parallel algorithm from local extension. The algorithm thought originated from clustering of modularity. Firstly, based on the Map/Reduce framework, the core node was selected according to the distribution and aggregation...
Proceedings Article

The Method of Structural Damage Identification by ACO Algorithm and Wavelet Theory

Deqing Guan, Jun Tang, Tao He
In order to effectively identify the location and extent of structural damage, a two-stage damage identification method, ACO algorithm and wavelet theory were presented. First, the curvature mode of structure with damage was obtained with finite element analysis. The curvature modes were analyzed using...
Proceedings Article

Damage Identification of Frame Structure by Wavelet-Genetic Algorithm

Deqing Guan, Tao He, Jun Tang
This article takes the frame structure as the research object, and combines wavelet analysis with genetic algorithm for structural damage identification. Firstly, wavelet analysis is used to identify the structural damage location and the number of damaged units, then the genetic algorithm is used to...
Proceedings Article

Detection of Application-Layer DDoS by Clustering Algorithm

Chuyu She, Wushao Wen, Zaihua Lin, Kesong Zheng
Affinity Propagation (AP) algorithm is a relatively new clustering algorithm that can handle large datasets to obtain more satisfactory results. This paper introduces a detection mechanism for application-layer DDoS attack by using AP algorithm. In this detection strategy, we first extract some features...
Proceedings Article

A Fast Depth Intra Mode Selection Algorithm

Jieling Fan, Qiang Li, Jianlin Song
For the purpose of reducing the complexity of depth intra coding, a fast intra prediction mode decision algorithm is proposed. First, the fast decision of depth modeling modes (DMMs) is obtained by using Laplace Operator detection method. Second by using the correlation between the wedgelet pattern and...
Proceedings Article

A Definition of Structure Hole and Algorithms

Tianji Zhao
In this paper we only use graph's structural information to generate other information in order to get the structural hole. Our work firstly delivers a formula well defines the structural hole, gives an iterative algorithm and a descending algorithm to find solution. The definition combines the advantages...
Proceedings Article

Optimized TF-IDF Algorithm with the Adaptive Weight of Position of Word

Jie Chen, Cai Chen, Yi Liang
The classical TF-IDF algorithm only considers the weight of the term frequency and the inverse document frequency, without considering the weights of other feature of word. After the author analyzing summary of Chinese expression habits, an adaptive weight of position of word algorithm based on TF-IDF...
Proceedings Article

Research of Reactive Power Planning Optimization Based on Improved Adaptive Genetic Algorithm for Wind Power Plant

Shijie Liu
Contrapose the randomness of wind speed and the wind power, use the method of multi-scenario based on probability analysis to study reactive power planning of wind power system and make the multi-scenario expectation model. On this basis, use improved adaptive genetic algorithm with subsection self-adaption...
Proceedings Article

Research on Optimization of Generator Grid-Related Parameters Based on Double-Stranded Quantum Genetic Algorithm

Yan Xu, Lixin Fan, Yunqian Li, Zhong Chen
With the expansion of grid scale and the development of UHV technology, grid partitioning mode is more and more widely applied. While the grid is closely connected with the large power grid, there is still the risk of separation and isolation mode operation. Under this background, this paper carries...
Proceedings Article

An Efficient Character Segmentation Algorithm for Offline Handwritten Uighur Scripts Based on Grapheme Analysis

Yamei Xu, Panpan Du
Cursive offline handwritten Uighur scripts contain a lot of small and random writing strokes, which makes the character segmentation is more complicated. In view of this, a new efficient character segmentation algorithm based on grapheme (part of a character) analysis is proposed in this paper. Firstly,...
Proceedings Article

Research on Vehicle Detection and Tracking Algorithm Based on the Methods of Frame Difference and Adaptive Background Subtraction Difference

Yiqin Cao, Xiao Yun, Tao Zhong, Xiaosheng Huang
This paper proposed methods of vehicle detection and tracking algorithm in real-time traffic. In the detection of real-time moving vehicle, vehicle areas would be determined through road line detection. Then, the main color information of moving and non-moving area would be obtained through frame difference....
Proceedings Article

Balanced COD-CLARANS: A Constrained Clustering Algorithm to Optimize Logistics Distribution Network

Tong Zhang, Dong Wang, Haonan Chen
In this paper, we focus on the problem of the siting of distribution stations, which is of key importance during designing a logistics distribution network. This problem includes dealing with physical obstacles in real world, making the orders as close as possible to their respective stations and making...