Showing papers presented at "International Conference on Intelligent Computation Technology and Automation in 2010"

Cloud Computing System Based on Trusted Computing Platform

Abstract: Cloud computing provides people a way to share large mount of distributed resources belonging to different organizations. That is a good way to share many kinds of distributed resources, but it also makes security problems more complicate and more important for users than before. In this paper, we analyze some security requirements in cloud computing environment. Since the security problems both in software and hardware, we provided a method to build a trusted computing environment for cloud computing by integrating the trusted computing platform (TCP) into cloud computing system. We propose a new prototype system, in which cloud computing system is combined with Trusted Platform Support Service (TSS) and TSS is based on Trusted Platform Module (TPM). In this design, better effect can be obtained in authentication, role based access and data protection in cloud computing environment.

A Comprehensive Survey of Data Mining-Based Accounting-Fraud Detection Research

Abstract: This survey paper categorizes, compares, and summarizes the data set, algorithm and performance measurement in almost all published technical and review articles in automated accounting fraud detection. Most researches regard fraud companies and non-fraud companies as data subjects, Eigenvalue covers auditor data, company governance data, financial statement data, industries, trading data and other categories. Most data in earlier research were auditor data; Later research establish model by using sharing data and public statement data. Company governance data have been widely used. It is generally believed that ratio data is more effective than accounting data; Seldom research on time Series Data Mining were conducted. The retrieved literature used mining algorithms including statistical test, regression analysis, neural networks, decision tree, Bayesian network, and stack variables etc.. Regression Analysis is widely used on hiding data. Generally the detecting effect and accuracy of NN are superior to regression model. General conclusion is that model detecting is better than auditor detecting rate without assisting. There is a need to introduce other algorithms of no-tag data mining. Owing to the small size of fraud samples, some literature reached conclusion based on training samples and may overestimated the effect of model.

A Semantic Analysis for Internet of Things

Abstract: This paper focuses on the concept itself of Internet of Things, which are related to the literal meaning, the internal property and the external relation. Analyzing the semantic meaning of the word internet of things can help to understand the properties of Internet of Things. Comparing the similarities and differences of the entity Internet of Things and other Internet applications can help to classify the entity. The actual semantics of Internet of Things is Internet of product information, a new type of Internet application. The properties of Internet of Things include the dominance and the attributes. The former means the interconnection of product information in different parts of the world based on Internet, while the latter further explains the three restrictive characters of the product information, namely the electronic tag form, the standardizing restraint, and the ontology supporting. The product information is written in an electronic tag by used the standard words whose semantic meanings are explained in one or more of ontology, so it can be read and understood by a computer. Internet of Things can be seen as a specific application form of Semantic Web.

Digital Watermarking and its Application in Image Copyright Protection

Abstract: Digital watermarking technology is a frontier research field, and it serves an important role in information security. According to the analysis of the definition and basic characteristics of digital watermarking technology, the system model of digital watermarking is given. The system consists of two modules which are watermark embedding module and watermark detection and extraction module. In view of the importance of digital images copyright protection, based on the analysis of the main digital watermarking algorithms, the digital watermarking technology can be applied to the image copyright protection. The two dimension discrete cosine transform is encoded on the Windows platform by using Visual C++ program language. The experiment result shows that the digital watermark is non-perceptible, the watermark information can be extracted even if it has been attacked, and the expected effect can be achieved.

Multi-objective Mobile Robot Path Planning Based on Improved Genetic Algorithm

Abstract: A multi-objective mobile robot path planning algorithm based on improved genetic algorithm is proposed. The algorithm aims to achieve three kinds of optimization objects for planned paths: length, smoothness and security by introducing the chaotic sequence and heuristic method based on environmental knowledge to initialize population so as to improve the individuals’ ergodicity and feasibility in the search space. Meanwhile, according to characteristics of path planning, several genetic operators based on domain-specific knowledge are proposed to improve the algorithm’s efficiency. The computer simulation experiments show that the robot can plan a set of optimized smooth paths which can avoid collision from the start to the target point in environment with many obstacles.

A Palm Vein Recognition System

Abstract: Palm vein pattern recognition is one of the newest bometric techniques researched today. This paper presents a palm vein recognition system that uses blood vessel patterns as personal identifying factor. The vein information is hard to duplicate since veins are internal to the human body. The design details of the palm vein capture device are researched, and preprocessing and feature extraction of palm vein image are also investigated. A small palm vein image database is built by the proposed capture device. Experimental results on the small palm vein database show that the designed system achieves an acceptable level of performance.

A Simple Additive Weighting Vertical Handoff Algorithm Based on SINR and AHP for Heterogeneous Wireless Networks

Abstract: The architecture for the Beyond 3rd Generation or 4th Generation wireless networks aims at integrating various heterogeneous wireless access networks over an IP backbone. To provide seamless mobility, one of the design issues is the vertical handoff support. In this paper, we propose a SINR(Signal to Interference plus Noise Ratio) and AHP(Analytic Hierarchy Process) based SAW(Simple Additive Weighting)(SASAW) vertical handoff algorithm which uses the combined effects of SINR, user required bandwidth, user traffic cost and available bandwidth of the participating access networks to make handoff decisions for multi-attribute QoS consideration according to the features of the traffic. The results show that our proposed scheme can achieve excellent performance according to the characteristics of the traffic by considering the relations of multiple attributions synthetically.

UAV Path Planning Based on Bidirectional Sparse A* Search Algorithm

Abstract: Nowadays, unmanned aerial vehicle (UAV) as an effective platform has been widely applied to military and civil fields. This paper focuses on UAV path planning problem. Sparse A* Search algorithm (SAS) proposed by R.J.SZCZERBA for route planning is introduced firstly. Then the Bidirectional Sparse A* Search algorithm (BSAS) is presented after the discussion of the deficiency of the application of SAS algorithm in UAV path planning. BSAS algorithm expands the start point and goal point respectively for searching path and calculates whether there is a Line of Sight (LOS) between every two different expansion nodes produced by the two expansion processes to get UAV path. The results show that the BSAS algorithm has stronger robustness and obtains better planning path than the SAS algorithm.

Comparison of High Capacity SVC and STATCOM in Real Power Grid

Abstract: Both SVC (Static Var Compensator) and STATCOM (Static Synchronous Compensator) are important equipment of reactive compensation, which are compared in voltage supporting, improving the transient stability and transmission limit, and damping low frequency oscillation. Simulation results are presented as high capacity static var system for SVC or STATCOM is placed on transmission path of power system. Firstly, single SVC and STATCOM are limited in voltage supporting after fault occurrence, but STATCOM is little better than SVC. Secondly, STATCOM is much better than SVC in improving the transient stability and transmission limit. Thirdly, on the damping low frequency oscillation, STATCOM is much better than SVC as SVC and STATCOM have the same capacity, and performs similarly with SVC as the two have the same controllable capacity. Lastly, the results also indicate that dynamical response speed effects the control result little though STATCOM responses much faster than SVC.

Very Short-Term Load Forecasting Based on Neural Network and Rough Set

Abstract: The short-term load forecasting model based on neural network has been applied widely in energy management systems (EMS) because of its high forecasting accuracy and self-learning ability. But the forecasting errors of the load curve near peaks are large, especially at the large slope difference on both side of a peak. So the load forecasting based on rough set and neural network is proposed. The load in the current time interval, load in the previous time interval, load deviation between the current time interval and the previous time interval and current time is regarded as an input of a neural network respectively. The forecasting load at following time interval is the output of the neural network. The trained neural network is the load forecasting model based on neural network. Then, the forecasting load at following time interval obtained by the neural network based load forecasting model is compensated by rough set to increase the forecasting accuracy. The simulation experiments show that the presented load forecasting based on rough set and neural network can improve the forecasting accuracy significantly.

Modern Logistics Monitoring Platform Based on the Internet of Things

Abstract: In this paper, a modern logistics monitoring platform based on the Internet of Things was studied and its system architecture and functions were particularly designed. The platform was designed based on the following technologies. In aspect of goods identification, a global unified electronic product code EPC was adopted and each goods was given a unique code that was according with international standards. Reading and writing EPC data was by taking use of RFID technology, which read data from electronic tags via a wireless non-contact method. In aspect of goods code management, new concepts of dynamic EPC and static EPC were proposed for goods in transport and movement. Through introduction of dynamic EPC and static EPC, data flow significantly was reduced, the management process was simplified and management efficiency was improved. In aspect of network transmission, both wired network and wireless network were taken for transmission task. Wired networks were available based on Internet and LAN. For mobile sites, wireless network GRPS was used for communication. In aspect of positioning goods, global positioning system GPS was used for location and tracking of goods. In aspect of platform function design, the system’s function requirements were analyzed and designed, and a series of its functions were proposed, such as real-time data acquisition, automatic alarm, remote control, data control and processing, historical information record and product quality safety tracing, market analysis and intelligent projections etc.. Modern logistics monitoring platform based on the Internet of Things, because of its advanced technologies, excellent performances and integrated functions, would play an important role in the development of modern logistics.

Beamlet Transform Based Pavement Image Crack Detection

Abstract: The complex nature of road images and weak signal make the detection of pavement cracks particularly difficult. An algorithm for pavement cracks detection based on Beamlet Transform is proposed. Beamlet transform is a new tool for high dimensional singularity analysis. First, the pavement surface image was segmented into unit image and transformed to binary image. Then beamlet transform was performed. Experimental results show the proposed method is effective in detecting line features with any orientation, location and length in pavement images. Compared with traditional edge detectors, the proposed method has the ability of anti-noise and linear connection.

Research on Clustering Routing Algorithms in Wireless Sensor Networks

Abstract: compared with the traditional wireless networks, wireless sensor networks have energy constraints, low-data-rate of high redundant and data flow of high-to-one, and so on. Energy effectiveness is the key performance indicators of wireless sensor networks. Based on the analysis of energy management strategy in the wireless sensor networks, the main factors affecting energy consumption are: perceptual data, data processing and radio communications, the radio communication is the main part of energy consumption. In the wireless sensor networks, the realization of energy-efficiency could be improved while in the different layers of communication protocol stack. However, as the basis of the limitations of the physical layer, the improvement is focus on design and implementation of network-layer protocol. The researchers agreed that the clustering of nodes in wireless sensor networks is an effective program of energy conservation. This article dedicated to research the clustering routing algorithm in wireless sensor networks.

Basic Concepts on AUTOSAR Development

Abstract: AUTOSAR(AUTomotiveOpen System ARchitecture) is an open and standardized automotive software architecture, jointly developed by automobile manufacturers, suppliers and tool developers. The AUTOSAR standard will serve as a platform upon which future vehicle applications will be implemented and will also serve to minimize the current barriers between functional domains. To improve cost-efficiency and reusability, AUTOSAR separates application software from the associated hardware. This stage, AUTOSAR is still in the promotion phase, and many countries are committed to its applications, including Japan and South Korea. It will widespread in automotive industry. This paper showed the basic concepts of AUTOSAR and comparisons of some confusing concepts for future in-depth study.

An Improved Differential Evolution Algorithm for TSP Problem

Abstract: TSP (Traveling Salesman Problem) is a kind of typical NP problems, mostly settled by genetic algorithm (GA). Differential Evolution Algorithm (DE) is a kind of new Evolution Algorithm which has many similarities with GA. We proposed to solve TSP problem by improved differential evolution algorithm. Added an auxiliary operator for regulating integer sequence to mutation process, and replaced the original crossover operator by Liuhai crossover operator. Experimental results show that this method can effectively improve the convergence speed and optimal quality, show good characteristic in the solution of TSP problem.

Research on SVM Classification Performance in Rolling Bearing Diagnosis

Abstract: SVM are introduced into rolling bearings intelligent fault diagnosis due to the fact that it is hard to obtain enough fault samples in practice and the perfect performance of SVM. The two-class classifier performance of SVM is discussed under the different conditions with the combination of wavelet packet denoising, decomposition and SVM. The performance comparison of SVM and RBF neural networks is presented. The multi-class classification performance of SVM is researched with a novel method of PCA and SVM, and feature extracting is discussed. The experiment and analysis results show that SVM have perfect classified performance in only limited training samples and the diagnosis precision is less dependent on the kernel function and the parameter, which is suitable in the engineering applications. SVM also has better performance than RBF networks both in training speed and recognition rate. PCA method can effectively reduce the calculating complexity of the fault classifier and keep high diagnosis precision. The fault diagnosis method based on PCA and SVM can extract rolling bearing fault features effectively and recognize the fault pattern accurately.

SVM-Based Automatic Classification of Musical Instruments

Abstract: Instrumental music is often classified or retrieved in terms of instruments played in it. With a large database consists of Chinese traditional music and western classical music, this paper extracted several features to automatically classify Chinese and western instruments by SVM classifier, and analyzed the classification results.

Research on Co-simulation Using ADAMS and MATLAB for Active Vibration Isolation System

Abstract: This paper presents an approach to research the active vibration isolation system under LQG control strategy through the method of co-simulation using ADAMS and MATLAB. Create System's dynamics simulation prototype in ADAMS, and return the acceleration of vibration isolation platform, the system dynamic deflection and the base's dynamic displacement as performance parameters, then establish the LQG controller of active vibration isolation system in MATLAB, and then import the prototype into MATLAB for control. The results indicate that the LQG controller can effectively improve the isolation effect of vibration isolation system, meanwhile the method of co-simulation using ADAMS and MATLAB, which can simplify the process of simulation, make the simulation results more accurate and increase the design reliability, provides a new way for dynamics studies of active vibration isolation system, or even more complex systems.

The System of Wireless Smart House Based on GSM and ZigBee

Abstract: GSM is combined with the new generation wireless network communication technology ZigBee, which established a wireless smart house system based on the GSM and ZigBee. The system refer to DSP chips to achieve controlling and monitoring the home applications, achieving to remote control and monitoring. This designment has reflected the characteristic of low cost, low power dissipation, great practical and good scalability.

Real-Time Hand Gesture Recognition for Service Robot

Abstract: A real-time facial expressions recognition system is developed for human-robot interaction of service robot. The proposed system is mainly composed of two subsystems: one for Active shape model(ASM) motion extraction, and one for the classification of the estimated motion. The system first uses a cascade classifier to locate the potential face regions from video frame. Then, ASM is automatically initialized in the candidate regions. Based on the statistical property of deformable ASM, some facial features are extracted by using real-time pyramidASM fitting method. The geometrical displacement between the estimated ASM feature node coordinates and mean shape of ASM is fed into the recognition subsystem in which, a Support Vector Machines (SVMs) is proposed to classify the calculated landmarks’ relative motion. Experimental results show the potential performance of our facial expressions recognition system.

Study of Vehicle Weight-in-Motion System Based on Fiber-Optic Microbend Sensor

Abstract: In order to resolve the problem of electromagnetic interference and low precision in weight-in-motion (WIM) system, a WIM system based on the fiber-optic microbend sensor is proposed. The working principle of micro-bend fiber-optic sensor is discussed. The pressure on the sensor cause optical fiber deformed, which lead to the loss of output light, so the vehicle weight can be obtained through measuring the variation of light intensity in optical fiber. Photoelectric conversion and sampling circuits are designed, and wavelet transform is adopted to denoise the sampled signal. Static response experiment shows that the fiber-optic microbend WIM system has fine linear character to the pressure in the scope of 0-3000Kg. and its sensitivity is 3.8mV/Kg. Dynamic response experiments indicate that its measurement error is less than 5% when the vehicle velocity is under 15Km/h, which meet the requirement of weight in motion system very well.

Research on a Novel Digital Photovoltaic Array Simulator

Abstract: In order to make the design and optimization of solar energy systems convenient, it is very essential to choose the suitable engineering mathematic model of solar cells A convenient and practicable engineering mathematic model of silicon solar cell is offered in this paper, which is based on photovoltaic array output I-U characteristic curve Piecewise curve fitting method is also presented to simulate the photovoltaic array characteristic curves A new digital photovoltaic array simulator with Buck converter is designed in detail The designed simulator uses dual-loop control with PI regulator, which greatly enhances the system's dynamic performance and steady-state accuracy The feasibility and rationality of the design are verified by the results of simulation and experiment It can be used in replacement of actual photovoltaic arrays to provide a controllable environment for research and design of photovoltaic inverters and control systems

A Hybrid PSO for Optimizing Locations of Booster Chlorination Stations in Water Distribution Systems

Abstract: Free chlorine residual needs to be maintained in the specified range (between minimum and maximum) in water distribution systems to avoid deterioration of the microbial quality of water, control taste and/or odor problems, and hinder formation of carcinogenic disinfection by-product. Booster chlorination is the addition of chlorine at locations distributed in water networks to maintain the chlorine residuals within a specified range throughout the distribution system. A notion of partial coverage is introduced for locating optimal booster chlorination stations in water distribution systems. It assumes that the water quality at a particular upstream node could be partially inferred by the water sampled at some downstream nodes if it delivers the proportions of water to the sampled nodes that are between the minimum coverage criteria and maximum coverage criteria. An optimization model is formulated in the presence of partial coverage based on the maximum covering location problem. A hybrid PSO, combined with GA algorithms, is proposed to get the solution. The new methodology is then applied to a hypothetical network. The results show that the hybrid PSO has substantial effect on the solution of the location of booster chlorination in water distribution systems.

Application of Fractional-order Model Reference Adaptive Control on Industry Boiler Burning System

Abstract: Fractional order model reference adaptive control was applied to control the temperature of boiler burning system, and simulation was made by Matlab/Smiulink. The simulation result shows that it can still achieve good control effect even if control objects changed but control parameters not changed. It provides basis for using fractional order model reference adaptive control in the field of industry.

Traffic Incident Duration Prediction Based on Artificial Neural Network

Abstract: The prediction of traffic incident duration is an important foundation of advanced incident management system and driver information system. In this paper, actual traffic incident data was used to study the prediction problem of traffic incident duration by the method of neural network. 660 sets of actual traffic incident data from a freeway management center were used to train a neural network model, and 170 sets of incident data in the same data collection, which are different from training data, were used to test the prediction effect of the model. The test result shows that the correlation of the prediction values and the actual values is 0.8535, which indicates that the prediction result of the neural network model can basically represent actual incident duration.

Sliding Mode Direct Torque Control for Induction Motor with Robust Stator Flux Observer

Abstract: A sliding mode controller for induction motor (IM) is investigated in this paper. It features in very low flux and torque ripple. In order to guarantee electromagnetic torque and stator flux to track its reference signal strictly, the electromagnetic torque sliding mode variable and stator flux sliding mode variable were selected separately. Furthermore, a robust stator flux observer is designed for sliding mode direct torque controlled induction motor system. The design of state observer is based on regional pole assignment theory. The observer gain matrix is obtained by solving linear matrix inequality (LMI) using LMI Toolbox in MATLAB. Finally, the effectiveness and validity of the proposed control approach is verified by computer simulation results.

The Study on an Intelligent General-Purpose Automated Software Testing Suite

Abstract: To make the labor intensive manual software testing automated, we present the design and implementation of an intelligent general-purpose automated software testing suite. With the two main tools in the suite: an automated software testing scheduler, Harness, and a log file error analyzer, Logscanner, the summary report can be sent to the testing engineer immediately after the test is over via email, even when the testing engineer is away from the testing site. The functionality and features of the general purpose automated software testing suite help to increase the testing efficiency, reduce the labor intensity of software testing, which in turn, leads to the decrease in testing cost.

Remote Monitoring Intelligent System Based on Fingerprint Door Lock

Abstract: Fingerprint identification with a unique, reliable, in the security field has been widely used. This paper introduces design of remote monitoring intelligent system based on fingerprint lock. The system can accurately identify lively fingerprint, and sent unlock ID information, the illegal burglary information to the owner by the GSM network or to the monitoring center of property management office by the PSTN.

The Research on the WebGIS Application Based on the J2EE Framework and ArcGIS Server

Abstract: WebGIS is the integration product of GIS and Internet technologies, it is a best solution to achieve the interoperability of GIS. In this paper, from analyzing the functional characteristics of different version of ArcGIS server, it takes ArcGIS server9.2 as the GIS server software, and then ArcGIS Server Java ADF and JSF as the main technologies of the WebGIS application are analyzed, the process of the construction of WebGIS for Forestry Bureau in China is proposed, at last a WebGIS application with the function of display, querying, analysis is developed, which the WebGIS application is based on the J2EE framework and ArcGIS Server in B/S environment.

Insect Sound Recognition Based on SBC and HMM

Abstract: In order to help general technicians to recognize insects conveniently in pests management, this paper proposed a viable scheme to identify insect sounds automatically by using Sub-band based cepstral(SBC) and Hidden Markov Model(HMM). The acoustic signal is preprocessed, segmented into a series of sound samples. SBC is extracted from the sound sample as the feature, and HMMs are trained with given features. The matching for a test sample is completed by finding the best matcher in all HMMs. The method is tested in a database with acoustic samples of 50 different insect sounds. The recognition rate was above 90%. The test results proved the efficiency of the proposed method.