Construction and Visualization of 3D Landscape

Pingping Liu/ Zhaopan Lu

In order to know the operation condition before working, and reduce the risk of serious accidents of coal production industry. In this paper, by analyzing the characteristics of the environment of underground mine, using virtual reality technology, combined with the 3d Max modeling techniques and VC++ calling the OpenGL graphics interface techniques, the models are well optimized based on progressive mesh LOD algorithm for edge collapse. Using high-tech computer technology to simulate realistic (..)

DOI: 10.1109/iccnea.2017.11

Multi - scale Target Tracking Algorithm with Kalman Filter in Compression Sensing

Yichen Duan/ Xue Li/ Peng Wang/ Dan Xu

Real-time Compressive Tracking (CT) uses the compression sensing theory to provide a new research direction for the target tracking field. The algorithm is simple, efficient and real-time. But there are still shortcomings: tracking results prone to drift phenomenon, cannot adapt to tracking the target scale changes. In order to solve these problems, this paper proposes to use the Kalman filter to generate the distance weights, and then use the weighted Bayesian classifier to correct the tracking(..)

DOI: 10.1109/iccnea.2017.30

Inferring Genome-Wide Gene Regulatory Networks with GPU or CPU Parallel Algorithm

Ming Zheng/ Mugui Zhuo/ Shugong Zhang/ Guixia Liu

Expression of gene block, with the GPU parallel thread structure characteristic calculation, according to the structural characteristics of GPU thread design of double parallel mode, and the use of texture cache memory to achieve high efficiency; on the basis of CPU two level cache capacity of basic blocks further subdivided into sub blocks to improve the cache hit rate, the technology to reduce the number of memory accesses the use of data, reduce the thread migration in the core between the us(..)

DOI: 10.1109/iccnea.2017.84

Association Rule Mining Based on Estimation of Distribution Algorithm for Blood Indices

Xinyu Zhang/ Botu Xue/ Guanghu Sui/ Jianjiang Cui

To come over the limitations of Apriori algorithm and association rule mining algorithm based on Genetic Algorithm (GA), this paper proposed a new association rule mining algorithm based on the population-based incremental algorithm (PBIL), which is a kind of distribution estimation algorithms. The proposed association rule-mining algorithm keeps the advantages of GA mining association rules in coding and the fitness function. Through using probability vector possessing learning properties to up(..)

DOI: 10.1109/iccnea.2017.87

Distributed Computing System Based on Microprocessor Cluster for Wearable Devices

Xin Liu/ Zhiqiang Wei

Wearable equipment in recent years has been rapid development. But the hardware manufacturing complexity and the high cost is a real problem. This paper introduces a microprocessor cluster with both hardware design principle and related distributed software design methods. This cluster has the characteristics of low cost, high reliability, flexible hardware and software system structure, low power consumption, simple equipment manufacturing process and so on, especially suitable for wearable equ(..)

DOI: 10.1109/iccnea.2017.88

Implementing Business-to-Customer, IT Outsourcing and Workflow Management System to Exploit China Education Market for Durham University

Jiacong Zhao/ Chuanlin Huang/ Jingshu Wang/ Chen Qian

DOI: 10.1109/iccnea.2017.89

Novel Model of E-commerce Marketing Based on Big Data Analysis and Processing

Hongsheng Xu/ Ke Li/ Ganglong Fan

The amount of information on the Internet is getting larger and larger, and the energy of the consumer and the ability to deal with information is limited. Electricity supplier enterprises in the development process to do are to use big data for personalized shopping guide. This paper analyzes the situation of the development of e-commerce industry in the background of big data, and puts forward the improvement method. The paper presents novel model of e-commerce marketing based on big data anal(..)

DOI: 10.1109/iccnea.2017.51

Research on Tool Path Planning Method of NURBS Surface Based on CPU - GPU Parallel Computing

Wujia Yu/ Yangqiang Bi/ Zhendong Li

In order to deal with the inefficiency of trational serial tool path algorithms and incompatibility issues on the heterogeneous hardware platforms, this paper suggests a tool path planning method based on CPU-GPU(Central Processing Unit-Graphic Processing Unit) heterogeneous parallel computing. The method contra poses NURBS(Non-Uniform Rational B-Splines) surface which is abstracted as a matrix multiplication on the principle of isoparametric line tool path planning method. Then a parallel algor(..)

DOI: 10.1109/iccnea.2017.52

Discussion on the Factors of Stability for Benchmark Example with a Spherical Failure Surface in Clay

Jinhui Liu/ Wantao Ding

A three-dimensional slope stability problem involving a spherical failure surface in clay is often used in the literature as a benchmark example against which numerical models are validated. In the existing research literature, the analytical expression has been obtained for the factors of safety by assuming plane-strain mechanisms during slope failure. And the hypothesis does not comply with the actual project due to the size effect of slope and surrounding constraints placed on the slope. This(..)

DOI: 10.1109/iccnea.2017.53

Intrusion Detection Based on Self-adaptive Differential Evolutionary Extreme Learning Machine

Junhua Ku/ Bing Zheng/ Dawei Yun

Nowadays with the rapid development of network-based services and users of the internet in everyday life, intrusion detection becomes a promising area of research in the domain of security. Intrusion detection system (IDS) can detect the intrusions of someone who is not authorized to the present computer system automatically, so intrusion detection system has emerged as an essential component and an important technique for network security. Extreme learning machine (ELM) is an interested area of(..)

DOI: 10.1109/iccnea.2017.57

Job to Major (J2M): an Open Source Based Application

Haitao Liu/ Dongzhao Zhou/ Jiacong Zhao/ Shuang Gao

This paper presents Job to Major (J2M), an open-source tool design to link job requirements with University of Southampton's major information. J2M currently provides two functions: suggesting the most suitable majors to potential students of the university based on the job requirements, find jobs that are closely link to what students acquire from their major. The development of J2M is according to Garrett's model which divides the application development mainly into three stages business goals(..)

DOI: 10.1109/iccnea.2017.58

The Mining Algorithm of Frequent Itemsets based on Mapreduce and FP-tree

Bo He/ Jianhui Pei/ Hongyuan Zhang

The date mining based on big data was a very important field. In order to improve the mining efficiency, the mining algorithm of frequent itemsets based on mapreduce and FP-tree was proposed, namely, MAFIM algorithm. Firstly, the data were distributed by mapreduce. Secondly, local frequent itemsets were computed by FP-tree. Thirdly, the mining results were combined by the center node. Finally, global frequent itemsets were got by mapreduce and the search strategy. Theoretical analysis and experi(..)

DOI: 10.1109/iccnea.2017.59

Self-adaptive Differential Evolutionary Extreme Learning Machine and Its Application in Facial Age Estimation

Junhua Ku/ Kongduo Xing

In this paper, Self-adaptive Differential Evolutionary Extreme Learning Machine (SaDE-ELM) was proposed as a new class of learning algorithm for single-hidden layer feed forward neural network (SLFN). In order to achieve good generalization performance, SaDE-ELM calculates the error on a subset of testing data for parameter optimization. Since SaDE-ELM employs extra data for validation to avoid the over fitting problem, more samples are needed for model training. In this paper, the cross-validat(..)

DOI: 10.1109/iccnea.2017.31

GrandStore: Towards Large-Scale Free Personal Cloud Storage

Li Zhang/ Bing Tang

Personal cloud storage services are gaining popularity, such as SkyDrive, iCloud, Dropbox, etc. All of them provide a certain amount of free storage space for individual users, while the free space is quite limit, and you should upgrade to a paid account to get extra space. Therefore, a new approach is proposed in this paper, that many free personal cloud storage accounts are integrated in order to realize large-scale free personal cloud storage. A prototype system called GrandStore is designed (..)

DOI: 10.1109/iccnea.2017.110

Adaptive Correcting Strokes Extracted From Chinese Characters in Digital Ink of Non-Native Writers Based on Comprehensive Visualization

Hao Bai/ Xiwen Zhang

The correcting process for strokes extracted from Chinese characters is the necessary step to extract the errors of writing errors automatically. Visualization of extracted strokes is the prerequisite for manual correction. Therefore, visualization and adaptive correction methods are proposed. To reduce the cognitive burden of correcting, color, brightness, saturation and order number is comprehensively used to visualize extracted strokes. And tag list is applied for correcting different types o(..)

DOI: 10.1109/iccnea.2017.33

Research on the application of dynamic fuzzy logic in intelligent knowledge base system

Wang Tao

With the Big data under the background of artificial intelligence --AI is increasingly popular, the core role of knowledge base system experts in the increasingly emerge, but whether the automatic driving or artificial recognition need to deal with a lot of expert knowledge data AI, and the expert knowledge not only is fuzzy, and has dynamic. This paper from a new perspective, a comprehensive interpretation of the dynamic fuzzy system theory, and the theory of dynamic fuzzy dynamic fuzzy on the (..)

DOI: 10.1109/iccnea.2017.35

Speaker-dependent Isolated-Word Speech Recognition System Based on Vector Quantization

Yinyin Zhao/ Lei Zhu

Speaker-dependent speech recognition system requires the system should not only recognize speech, but also recognize the speaker of the segment. In this paper, two indicators are selected—short-time average zero-crossing rate and dual-threshold endpoint to test the signal endpoint through the study of speaker-dependent isolated-word speech characteristics, and MFCC parameters are taken as the characteristic parameters; based on vector quantization, template matching algorithms are designed, and (..)

DOI: 10.1109/iccnea.2017.103

Research on Fault Diagnosis Technology of CNC Machine Tool Based on Machining Surface Roughness

Zhou Guang-wen/ Mao Chun-yu/ Tian Mei/ Sun Yan-hong

This paper studied the relationship between the spindle fault and the roughness characteristics， by surface roughness of machining. Spindle common fault is divided into the spindle system is not balanced, the spindle system is not right, the spindle system has a transverse crack and the spindle system rolling bearing failure. The characteristic amount of the machining surface is extracted by CCD laser speckle surface roughness measurement technique. Machine fault information and rough surface re(..)

DOI: 10.1109/iccnea.2017.66

Application Research of Virtual 3D Animation Technology in the Design of Human Computer Interface

Zhou Xiaocheng

As everyone knows, the time of virtual reality has come, how to control and correct use of VR has become a significant topic. "In the era of virtual reality better human-computer interaction", "virtual reality interactive context and traditional context where is the difference in space", "touch interactive virtual reality experience what? Through the man-machine interface design, the use of virtual 3D animation technology, implementation of new methods and new ways of product design.

DOI: 10.1109/iccnea.2017.68

The Study of Following Behavior to Bi-direction Pedestrian Flow with the Dynamic Preconscious Effect

Xin Tang/ Xueyu Zhao/ Lin Pan/ Jiying Wang/ Yi Yang

In view of the preconscious behavior of pedestrian and walking speed differences, a lattice gas model of bi-direction pedestrian flow is established in this paper. According to the characteristics of pedestrian following behavior and preconscious dynamic change in different walking conditions, bi-direction pedestrian behavior model based on dynamic preconsciousness is constructed to study the bias decision-making behavior of pedestrian movement. Through numerical simulation, the influence of reg(..)

DOI: 10.1109/iccnea.2017.69

The Application of Improved PSO Algorithm in the Geometric Constraint Solving

Tian Wei/ Zhu Xiaogang

Geometric constraint solving is a hot topic in the constraint design research field. Particle swarm optimization (PSO) is a method to solve the optimization problem from the biological population’s behavior characteristics. PSO is easy to diverge and fall into the local optimum. There are various kinds of improvements. In addition to improving some performance, the corresponding cost is paid. In this paper, a particle swarm optimization algorithm based on the geese is adopted to solve the geomet(..)

DOI: 10.1109/iccnea.2017.70

The Application of Human-Computer Interaction Idea in Computer Aided Industrial Design

Zhang Liang/ Zhao Jian/ Zheng Li-nan/ Li Nan

The interactive, experiential, real-time, efficient and comprehensive features of human-computer interactive technology in virtual display make it possible to virtualize products with panoramic, instantaneous and experiential features. The computer aided design based on human-computer interactive technology, through the design and present from shape, color and structure of products, enables designers to pre-design in advance to avoid the mode of production then design in before, which can be a g(..)

DOI: 10.1109/iccnea.2017.71

Research on Low Voltage Power Line Carrier Communication Simulation Software

Ye Jun/ Li songnong/ Sun Hongliang/ Hou Xingzhe

The use of semi-physical simulation platform for school laboratory and classroom building scene a lot of field measurements, analysis of power line channel transmission characteristics of the different environments, and features a three-dimensional graphic display of variable power line channel under different scenarios. At the same time in order to improve the efficiency of the data analysis, the use of MATLAB simulation software design based on off-line data analysis software GUI interface. It(..)

DOI: 10.1109/iccnea.2017.78

Visualization Analysis of NoSQL Research Field Based on SCI by CiteSpace Ⅴ

Ming He/ Ying Zhang/ Pixian Zhao/ Yongjun Wu/ Jianning Zhang/ Yingxin She/ Qike Jiang

NoSQL is one of the technical trends that rises in this context in the Web 2.0 Era. With the aim to explore the research status and development trends related to NoSQL technology, articles between 1998 and 2016 were collected from Thomson ISI’s SCI. After the analysis by using CiteSpace Ⅴ, the pivotal documents related to NoSQL, as well as institutions, co-citation patterns, research hotspots and frontiers, etc., were visualized and identified.

DOI: 10.1109/iccnea.2017.39

Study on Static Task Scheduling Based on Heterogeneous Multi-Core Processor

Shen Yang/ Qi Deyu

Aiming at the situation of priority scheduling algorithm of chaos, later redundant processing in the task scheduling on current multi-core heterogeneous processors, this paper proposes a task scheduling algorithm with weighted priority algorithm-- WPTS. It is related to three attribute values of the main reference tasks, which can be obtained by weighted comparison that can overcome the confusion and redundancy of task selection to a certain extent. And it can maintain the priority processing of(..)

DOI: 10.1109/iccnea.2017.38

New Method of Image Smoothing and Edge Detection Based on Nonlinear Ambiguity Function

Yanhong Jin

With the continuous development of the national economy and science and technology, the scope of the application of images is constantly expanding. The image has many uncertainties, and the improvement of this feature is often blurred and can not be accurately calibrated, which results in complex and diverse processing techniques. Image smoothing and edge detection are very important feature technologies in image processing, and they also the research focus in the field of image processing. This(..)

DOI: 10.1109/iccnea.2017.47

Research and Application of an Intelligent Decision Support System

Xiaoqing Zhou/ Zhiyong Zhou/ Jianqiong Xiao/ Jiaxiu Sun

This paper discusses a new decision-support system that integrates data warehouse, knowledge warehouse and model warehouse. Contrast to the fixed model of the old decision-support system and its limited application, the new system can overcome the shortcoming of the old system efficiently, and also it can simplify model-obtaining and coding. So the new system strengthens the effectiveness, intelligence and efficiency of the decision.

DOI: 10.1109/iccnea.2017.95

Learning Better Classification-based Reordering Model for Phrase-based Translation

Li Fuxue/ Xiao Tong/ Zhu Jingbo

Reordering is of a challenging issue in phrase-based statistical machine translation systems. This paper proposed three techniques to optimize classification-based reordering models for phrase-based translation under the bracket transduction grammar framework. First, a forced decoding technique is adopted to learn reordering samples for maximum entropy model training. Secondly, additional features are learned from the context of two consecutive phrases to enhance the prediction ability of the re(..)

DOI: 10.1109/iccnea.2017.82

Optimal Pricing for Service Provision in IaaS Cloud Markets

Gang Fang/ Zhengce Cai/ Xianwei Li

Pricing plays an important role for service provision in cloud computing. In this paper, we investigate price based resource access control in two Monopoly IaaS cloud market, respectively. The two IaaS cloud market is formed by one public cloud service providers (CSPs) and cloud broker (CB), provisioning cloud services to delay-sensitive cloud users (CUs). In the first monopoly cloud market, we treat the public CSP as an M/M/1 queueing system and study this CSP’s pricing effect on the equilibriu(..)

DOI: 10.1109/iccnea.2017.18

Lidar Image Classification based on Convolutional Neural Networks

Yang Wenhui/ Yu Fan

This paper presents a new method of recognition of lidar cloud point images based on convolutional neural network. This experiment uses 3D CAD ModelNet, and generates 3D point cloud data by simulating the scanning process of lidar. The data is divided into cells, and the distance is represented by gray values. Finally, the data is stored as grayscale images. Changing the number of cells dividing point cloud results in different experimental results. Experiments show that the proposed method has (..)

DOI: 10.1109/iccnea.2017.37

Design and Development of Intelligent Logistics System Based on Semantic Web and Data Mining Technology

Yi Wang/ Xue Bai/ Haoyuan Ou

The intelligent logistics distribution of e-commerce is the computer technology and modern hardware equipment, software system and advanced management tools used by the logistics distribution enterprise. Data mining technology is the process of finding the probability distribution of random variables from a large number of source data. Automation of intelligent logistics system can improve labor productivity and reduce the error of logistics operation. This paper proposes design and development (..)

DOI: 10.1109/iccnea.2017.92

Design of Routing Protocol and Node Structure in Wireless Sensor Network based on Improved Ant Colony Optimization Algorithm

Yan Song/ Xiaomei Yao

Wireless sensor network is composed of many wireless sensor nodes with the same or different functions. A typical sensor node consists of four parts: sensor unit, information processing unit, wireless communication unit and energy supply unit. In this paper, the existing ant colony algorithm is analyzed, and an improved ant colony optimization algorithm is proposed. The paper presents design of routing protocol and node structure in wireless sensor network based on improved ant colony optimizati(..)

DOI: 10.1109/iccnea.2017.54

Forecasting CSI 300 index using a Hybrid Functional Link Artificial Neural Network and Particle Swarm Optimization with Improved Wavelet Mutation

Tian Lu/ Zhongyan Li

Financial market dynamics forecasting has long been a focus of economic research. A hybridizing functional link artificial neural network (FLANN) and improved particle warm optimization (PSO) based on wavelet mutation (WM), named as IWM-PSO-FLANN, for forecasting the CSI 300 index is proposed in this paper. In the training model, it expands a wider mutation range while apply wavelet theory to the PSO, in order to exploring the solution space more effectively for better parameter solution. In the(..)

DOI: 10.1109/iccnea.2017.55

Equivalence on Quadratic Lyapunov Function Based Algorithms in Stochastic Networks

Li Hu/ Gao Lu/ Liu Jiaqi/ Wang Shangyue

Quadratic Lyapunov function based Algorithms (QLAs) for stochastic network optimization problems, which are cross-layer scheduling algorithms designed by Lyapunov optimization technique, have been widely used and studied. In this paper, we investigate the performance of using Lyapunov drift and perturbation in QLAs. By analyzing attraction points and utility performance of four variants of OQLA (Original QLA), we examine the rationality of OQLA for using the first-order part of an upper bound of(..)

DOI: 10.1109/iccnea.2017.56

A Remote-Attestation-Based Extended Hash Algorithm for Privacy Protection

Yongxiong Zhang/ Liangming Wang/ Yucong You/ Luxia Yi

Compared to other remote attestation methods, the binary-based approach is the most direct and complete one, but privacy protection has become an important problem. In this paper, we presented an Extended Hash Algorithm (EHA) for privacy protection based on remote attestation method. Based on the traditional Merkle Hash Tree, EHA altered the algorithm of node connection. The new algorithm could ensure the same result in any measure order. The security key is added when the node connection calcul(..)

DOI: 10.1109/iccnea.2017.60

Key Point Detection in Images Based on Triangle Distribution of Directed Complex Network

Qingyu Zou/ Jianwen Guan/ Jing Bai/ Weiliang Sun

Key point detection is still a challenging issue in pattern recognition. With the recent developments on complex network theory, pattern recognition techniques based on graphs have improved considerably. Key point detection can be approached by community identification in directed complex network because image is related with network model. This paper presents a complex network approach for key point detection in video monitoring image, which is both accurate and fast. We evaluate our method for(..)

DOI: 10.1109/iccnea.2017.62

Research on Combination Forecasting Model of Mine Gas Emission

Liang Rong/ Chang Xintan/ Jia Pengtao/ Dong Dingwen

This paper focuses on the effective analysis of the mine gas emission monitoring data, so as to realize the accurate and reliable mine gas emission prediction. Firstly, a weighted multiple computing models based on parametric t– norm is constructed. And a new mine gas emission combination forecasting method is proposed. The BP neural network model and the support vector machine were used as the single prediction models. Finally, genetic algorithm and least square method were used to determine th(..)

DOI: 10.1109/iccnea.2017.32

WLAN Based Wireless Self-organization Link: Research and Realization

Yunhai Guo/ Zhengxiang Li

Communication is one of essential elements of our life. In some cases, we need wireless links to support data transmission such as television relay. But the existing GPRS and other network often need the support of power transmission line. And in the remote areas, the transmission rate of traditional network is very slow. In this paper, the development and realization of wireless self-organization link based on the wireless router and WLAN, managed by OpenWrt open source system is presented. It (..)

DOI: 10.1109/iccnea.2017.99

Egwra: Qos Routing Algorithm In Wireless Mesh Networks Based On Evolutionary Game Theory

Yan Weiguang/ Pan Xianmin

This paper applies the theory of Evolutionary Game to QoS routing algorithm for wireless mesh networks which can not only improve the performance of traditional QoS routing protocols but also be able to reduce the cost of the routing algorithm.

DOI: 10.1109/iccnea.2017.100

Design of a WSN Node for Rice Field based on Hybrid Antenna

Huaqiang Chen/ Weixing Wang/ Baoxia Sun/ Jiangpeng Weng/ Fenglian Tie

Aim at the problems existing in the information monitoring of the farmland environment such as the limited energy, low system stability and large monitoring area, a WSN node for rice field based on hybrid antenna is designed to realize the real-time on-line monitoring for the environmental parameters of rice fields in the network. As for the hardware, the node uses a STM32F103VET6 as a processing core, and a WLK01L39 RF chip is used in wireless communication module, while the sensor module is co(..)

DOI: 10.1109/iccnea.2017.101