Showing papers presented at "International Conference on Intelligent Computation Technology and Automation in 2015"

Study of RBF Neural Network Based on PSO Algorithm in Nonlinear System Identification

Abstract: Development of neural network provided new thought for nonlinear system identification. RBF neural network was widely studied in nonlinear system identification by good approximation ability and fast convergence thereof. In the paper, RBF neural network based on PSO algorithm was proposed, global searching property of PSO algorithm was utilized for remedying RBF local approximation, initial weights of RBF neural network and the base width were globally optimized, insufficiency in RBF neural network random initialization weights and base width was remedied, and identification precision of RBF neural network on nonlinear system was improved aiming at problems of RBF neutral network in nonlinear system identification application, such as local approximation and base width random initialization. The simulation results showed that RBF neural network based on PSO algorithm, proposed in the paper, had prominently better identification precision on nonlinear system than identification of RBF neural network based on GA algorithm and the traditional RBF neural network, and it had great significance on identification of nonlinear systems.

Vegetable Price Prediction Based on PSO-BP Neural Network

Abstract: In order to predict vegetable price accurately, 117 sets of green pepper and related factors price data from 2012 to 2015 in Dan Zhou city were selected as the sample data, of which 100 groups were training data and 17 groups were test data. Based on analyzing fluctuant features of vegetable price, with the global stochastic optimization idea to optimize initial weights and thresholds of back propagation (BP) neural network, the PSO-BP prediction model concerning vegetable retail price was set up by using the particle swarm optimization (PSO) algorithm. The experimental results indicated that compared with the traditional BP method, the PSO-BP method could overcome the over-fitting problem and the local minima problem, effectively reduced training error and increased the predicting precision.

Based on ECDIS and AIS Ship Collision Avoidance Warning System Research

Abstract: The ECDIS (electronic chart display and information system) is a new technology of modern navigation, sailing aims to ensure navigation safety, and improve work efficiency. AIS (automatic identification system) is a kind of can transmit large amount of information, obstacle, weather resistance, with ship shore - ship between information networking ability and close target indication of maritime communication system. And ship collision avoidance system is an important research subject in modern navigation technology, it in the prevention of ship collision accidents, ensure the safety of ship navigation plays a very important role. This paper developed based on ECDIS and AIS ship collision avoidance warning system. The simulation shows that the system is feasible.

The Research on Resource Scheduling Based on Fuzzy Clustering in Cloud Computing

Abstract: In this paper, the assignment performance problem in the process of the allocation resources has not been considered in the present most cloud computing data center, this paper proposes a new cloud computing resources allocation strategy, on the basis of cost model of the parallel task performance, using the improved Fuzzy Clustering Algorithm (CBFCM -- C Cost based Fuzzy Clustering Algorithm) to classify the cloud computing resources set on the service level of user, and the jobs submitted by guest were analyzed using four different scheduling algorithms, and the generated resource scheduling scheme. The experimental results show that job scheduling strategy based on CBFCM resources classification in the cloud computing services have certain advantages. AFCFS job scheduling algorithm in average response time for ART, the average waiting time AWT, average operating cost of ACP performance items, has great advantage than the other three algorithm.

Parallel Performance of an Ant Colony Optimization Algorithm for TSP

Abstract: MAX-MIN ant colony system (MMAS) has been one of the most effective ant colony optimization algorithm for the traveling salesman problem (TSP) up to the present. Despite the intrinsic parallelism, problems such as excessive memory occupation and overlong communication cost arise in the parallel process for large-scale numerical examples. In this paper, for parallel optimization of MMAS, some strategies are proposed: a) by comparing the current solution with the optimal solution, unnecessary ergodic paths and iterations are abandoned, which accelerates the searching process, b) for generating distance matrix and updating pheromone matrix, communications are replaced by calculations, which reduces memory occupation and communication cost enormously. MMAS with the above strategies is implemented on the Sunway Blue Light supercomputer based on MPI. As a result, high feasibility and effectiveness are verified.

Crowd Abnormal Behavior Detection Based on Label Distribution Learning

Abstract: In general, some abnormal crowd behaviors are associated, for example, fight causes tumble or panic and tumble causes stampede. And those abnormal behaviors often happened at the same time. However, most researchers consider those mixed abnormal behaviors as only one behavior and ignore the other behaviors appearing in the video. To analyze those behaviors better, this paper proposes a method using label distribution learning to detect the crowd abnormal behavior such as stampede, fight, panic and tumble. We consider that every behavior sequence associated with some behavior labels, and the behavior label distribution covers a series of behavior labels, representing the describe degree that each behavior labels describe the behavior sequence. Then a label distribution learning algorithm named BFGS can be used to learn the behavior label distribution. Through this way, we not only can obtain which behavior happened, but also all behaviors are taken into account for each behavior sequence. The experimental results show that our approach achieves better performance for crowd abnormal behaviors detection.

Non-circular Gear Modal Analysis Based on ABAQUS

Abstract: In this paper, the design of non-circular section of the curve profile of gear method in Pro / E drawing a non-circular gear teeth, and draw out the mirror and drawing commands through a three-dimensional model of the first-order and third-order elliptical gears. And oval gear created virtual assembly, a complete model of oval gear deputy. According to the theory of elasticity and modal finite element analysis software ABAQUS, non-circular gear designed to create a finite element analysis model of vice, so that various modal analysis oval gear, get the oval gear each mode of mode shapes and natural frequencies, the analysis is verified by comparing the dynamic characteristics of the oval gear (non-circular gears).

A Complete Evaluation of the Chinese IP Geolocation Databases

Abstract: Direct query to IP geolocation databases is a convenient and widespread way for determining geographic location where a host with corresponding IP address is. However, many databases available on the Internet may not provide accuracy data as they claim. In this paper, we focus on analyzing IP addresses of mainland China recorded in popular China-based IP geolocation databases. First, distributions and characteristics of IP addresses and blocks of mainland China at different geographic granularities are analyzed. Second, entries consistency comparisons among databases are implemented and those with better performances are recommended, we also use small amount of ground truth data to verify the recommended databases. Finally, clustering and classification analyses are conducted for IP blocks with different locations and preliminary conclusions are drawn.

Economy Benefit Comparison of CCHP System and Conventional Separate Supply System

Abstract: As the energy shortage and environmental problems gradually deepened, the Combined Cooling, Heating and Power (CCHP) system has gained attention for its high efficiency and low emission. In this paper, we compare the CCHP system with the conventional separate supply system, and considered the cost saving as the objective function of the multi-objective optimization. In order to show the energy conservation and environmental protection advantages of CCHP, we set the Green House Gases emission reductions and energy savings as constraint conditions. At last, we determined the optimal economic effect of CCHP and conventional separate supply system by case study. It is indicated that the emission reduction of CCHP system is better than the conventional separate supply system in the study, and when the electric price is higher than 0.11 times of gas price, the cost of CCHP system is smaller.

Influential Factors of Vending Machine Interface to Enhance the Interaction Performance

Abstract: time-consuming purchases and operation failures could often occur in the utilization of Vending Machines (VMs) due to the violations between human purchase behavior and design interfaces. An unhindered, clear and concise selfservice shopping mood needs to be discovered under the study of human purchase behavior and characteristics of Human- Machine Interaction (HMI) process in order to solve these problems. In this paper, each step of human's habitual purchase behaviors on VMs were analyzed so that the features of operations were extracted. Thenkey points of psychological load and mistake operation were located by investigating the operation on the screen of VMs and being combined with the found features of purchase behavior so that the HMI process can be optimized. Lastly, experiments were conducted so that a conclusion can be drawn that the improved screen operation procedures did reduce the time of purchase and times of operation failure. This study and the validating framework could not only provide a model to solve the HMI of VM problems, but also lay a foundation for future research on the new way of machine-based sales system.

A Method for Rolling Bearing Fault Diagnosis Based on Sensitive Feature Selection and Nonlinear Feature Fusion

Abstract: To solve the problem that there were non-sensitive features and over-high dimensions in the feature set of fault diagnosis, a new feature extraction method based on sensitive feature selection and nonlinear feature fusion for rolling element bearing fault diagnosis was proposed. CDET was utilized to choose features sensitive to fault severity from the high dimensional feature set, and weighted the selected sensitive features by their sensitive degree. The weighted sensitive feature subset was compressed with LPP to reduce its dimensions and get the compressed more sensitive feature subset, which can enhance the discrimination between all classes by improving the between-class scatter and within-class scatter for fault classification. Compared with the classification result of the original high dimensional feature set based on direct LPP without feature selection, the classification result of the proposed method has the advantages of higher compactness and higher computational efficiency.

A New Express Management System Based on Encrypted QR Code

Abstract: Recently, the express service develops rapidly. However, traditional express service suffers from several noteworthy drawbacks, e.g., Low level of informatization, high risk of information leak and low efficiency of freight. In this paper, we propose a new express management system based on encrypted QR code to overcome above problem. Firstly, the system adopts an encrypted QR code to store all information of goods. Secondly, after courier scan the encrypted QR code by using our designed APP for smart phones, the real-time logistics information of goods in the database is automatically updated through GPRS (General Packet Radio Service) or Wi-Fi. In the meantime, the server sends the real-time logistics information of goods to consignee. Thirdly, the APP provides an optimal delivery route for courier by employing the improved genetic algorithm. Lastly, at the delivery point, after the courier scans the encrypted QR code, the APP automatically sends a message to consignee to receive goods. Our benchmark research shows that the new express management system can effectively protect the privacy of clients, improve efficiency of express service1.

Loitering Detection Based on Trajectory Analysis

Abstract: Some potential danger, such as robbery, steal, and drug-dealing activity, can be avoided effectively by detecting loitering behavior in advance. In this paper, we propose a loitering detection algorithm by analyzing the trajectory of pedestrian. Firstly, we propose a trajectory extraction method combined with motion estimation and object detection to adapt to the tracking under a static camera scene. Then we judge the loitering behavior by analyzing the trajectory of object through the duration time and angles variation between the initial point and remaining points on the trajectory. The experiments were performed using several surveillance cameras. And experimental results show that the proposed method provides superior performance in terms of accuracy, robustness, and speed.

Applications of Wireless Sensor Network in the Field of Production and Distribution

Abstract: Currently, wireless sensor networks with its unique performance also have a wide range of applications in agriculture, industry, aquaculture etc., especially in the production of these industries, wireless sensor networks play an important role. The paper presents the applications of wireless sensor network in the field of production and distribution, and the applications in the marketing chain. It can be unfortunately that with the enrichment of content that sensors can monitor, WSN will occupy more and more important role in social production.

The Multi-join Query Optimization for Smart Grid Data

Abstract: As the worldwide smart grid development, the high volume of data is generated by the smart grid devices. Database system, which stores large amounts of smart grid data is facing the growing amount of data storage and query requirements of increasingly complex. Meanwhile, smart grid has high requirements for data processing speed which makes traditional query strategies show many deficiencies. A new hybrid intelligent algorithm is proposed to optimize the multijoin query problem for smart grid data. The algorithm based on the Genetic Algorithm (GA), involves Guo Tao (GT) algorithm in crossover to maintain population diversity, and prevents premature convergence of the GA, and the mutation operator involves the Particle Swarm Optimization (PSO) to improve convergence speed and solution accuracy. The suggested algorithm ensures rapid processing of data and simulation result shows the query cost of the designed algorithm is lower than the GA, and it meets the smart grid data query requirement.

Research on the Finite Element Analysis and Failure Strengthening Test of Electric Bus Quick-Change Battery Box

Abstract: Since new-energy vehicles, electric buses have many advantages, they are more and more popular now. As the core component of the electric bus, power battery pack safety and reliability are highly demanding. Working in the complicated vehicular environment, as the carrier of the battery pack and the vehicle body, the structural design rationality and reliability of battery box are very important. Mechanical analysis, constraint modal analysis and frequency response analysis with finite element model simulation, and vibration test research in different conditions for the battery box were studied in this paper. Through the study of theory and test, distribution of weak spots, failure modes of the battery box and failure strengthening test condition were achieved. The research results provide basic and reference for the structural design improvement of the battery box.

The Research of Cost Control about the Third Party Logistics Enterprise Based on Activity-Based Costing Model

Abstract: With the application of activity-based cost simulation model widely, cost simulation model can provide a better perspective to understand their motivation for the enterprise implementation of activities, and the number of resource consumption during the campaign execution. Therefore, the basic model of logistics cost and activity-based cost and activity-based cost management methods are combined, in order to make it more adapt to the field of logistics. This paper starts from ABC, ABC in the interpretation of the application of the third party logistics enterprise, proved effective on the control of logistics cost to ABC, adapt to the modern logistics enterprise management way, and accurately calculate the logistics cost, provide a more effective basis and support for the decision-making of logistics enterprises.

Stepper Motor Control Based on AT89S51 Microcontroller

Abstract: Along with the application of computer and microelectronic technology in industrial production, the use of computer technology and microelectronic technology to control the stepping motor has gradually become a new technology. Stepper motor control system is designed based on AT89S51, including the hardware circuit design and software design. Keyboard input signal is used to control the stepper motor rotation direction and speed. The rotation direction is displayed by LED. The design has high reliability and strong stability, which can be applied to the field of disk drive, robots and automation instrument.

Hardware Design of Fall Detection System Based on ADXL345 Sensor

Abstract: In order to meet the demand for nursing care of the elderly, this paper introduces fall detection principle, overall composition, design scheme, main control circuit and the control program of a fall detection system based on ADXL345 sensor. The system selects MSP430F149 as the microprocessor to complete the signal analysis and processing functions, and judge whether the individual falls through the fall detection algorithm. The attitude angle which is related to the acceleration of the output of the ADXL345 sensor is considered as the judgment standard. According to the electrical signals change, the system can make accurate judgments, send out the alarm and start up the protective device. It has the characteristics of compact structure, simple and reasonable design, flexible control.

Dynamic Economic Dispatch of MicroGrid Using Improved Imperialist Competitive Algorithm

Abstract: In grid mode, aiming at the influence of the uncertainty of photovoltaic power generation, wind power generation and load in micro grid, on the premise of each constraint of the system, we set up a mathematical model of micro grid dynamic economic dispatch based on chance constrained programming. Aiming at micro grid total operation costs minimum, we consider the controllable units fuel costs, the costs of emitting carbon dioxide of the controllable units, unit maintenance costs, active power buying costs and spinning reserve buying costs from distribution network, etc. We use probability constraints to depict the reliability of the micro grid operation, and consider output constraints and climbing constraints of the controllable units. Considering imperialist competitive algorithm is easy fallen to local minimum and converge slowly, by introducing the chaos theory, an improved imperialist competitive algorithm is proposed to solve the mathematical model we propose. Finally, with an micro grid system as an example, we analysis the influence to micro grid economy and the dispatch results in different reliability probability level, and we compare the convergence properties of the algorithm we propose with the conventional algorithms to verify the effectiveness of the algorithm we propose.

Research on Speed Control System of Brushless DC Motor Based on Neural Network

Abstract: Considering the shortcomings of low precision, response lag and control instability of conventional PID controller in brushless dc motor speed control system, an intelligent controller is designed, which is combines RBFneural network with PID controller. This paper analyzed operating principle of the brushless dc motor, and deduced transfer function model of the controller. The control programs and control model of the designed controller were also provided. At last, the designed controller was validated through Mat lab software in the simulation. In the process of simulation, three parameters of PID were adjusted obviously by RBF-Neural Network. The results of simulation show that the designed controller is more effectively in improving the control performance and faster in response than conventional PID controller.

The Sources Apportionment of Heavy Metal Pollution Base on Tree Ring in Jinan

Abstract: Heavy metal pollution is becoming a growing global problem in Jinan, tree is a useful bio indicators which record annual impressions of the pollution environment With the economic development in 80s to 90s, higher value of Pb, Cd, Mn and Cr contamination in tree rings are close relate to pollution emissions of a large number of serious pollution small and medium-sized enterprise, last century, higher value of Pb contamination of JQ sample point, near the outer ring road, is closely related to rapidly increased traffic capacity, At the beginning of this century, As nutrient element of plant, Mn, Ca are higher in juvenile stage and no obvious fluctuation in other stage because of young-age effect of trees, After correlation analysis and principal component analysis, found that coal, iron and steel smelting, cement production and motor vehicle exhaust emission are main contributor of heavy metal pollution both in SZ point and JQ point

Analysis about Seismic Constrained System of Single Tower Cable-Stayed Bridge

Abstract: Taking Shihezi single tower cable-stayed bridge as the engineering background to establish finite element seismic model, using the nonlinear dynamic time history to get seismic analysis of the bridge under strong earthquake. In order to study the effect of damping constrained system on single tower cable-stayed bridge's seismic performance, this paper makes a contrastive analysis about the longitudinal, lateral different constrained system. In the longitudinal direction, we make a seismic calculation under the rare earthquake action while the single tower cable-stayed bridge respectively use different constrained system, such as rigid system, floating system, vertical supporting system, vertical support and elastic cable system, vertical support and viscous damper (FVD), etc, drawing the following conclusion: When using the movable support as the vertical bearing, friction resistance of the bearing can greatly improved the seismic performance of the structure, so its influence should be considered while calculating, the system that includes vertical support and the FVD is the optimal longitudinal seismic constrained system correspondingly. In the lateral direction, we respectively make a seismic calculation under the rare earthquake action while the pylons respectively use rigid system, floating system, transverse hinged, transverse free, vertical support and elastic cable, vertical support and viscous dampers (FVD) etc different constrained forms, transition pier respectively use transverse hinged, transverse free, lead rubber bearing, vertical support and viscous dampers (FVD) etc different constrained forms, drawing the following conclusions: If the force of transition pier stress has no conclusive effect on the design, the main tower with vertical support and viscous dampers while the transition pier with transverse hinged is the relatively optimal constrained system, If the force of transition pier stress has conclusive effect on the design, the main tower with vertical support and elastic cable while the transition pier with lead rubber bearings is the relatively optimal constrained system.

The Future Development of Smart Grid in China

Abstract: Smart grid becomes the hot topic concerning future power grid development trend home and abroad in recent years. Three modes and features of the development of smart grid in the world, the positioning of smart grid construction, three stages of smart grid development plan and technical innovation of smart grid in China are described and analyzed. Some suggestions of technical route of smart grid in China are presented.

Prediction of Stock Trading Signal Based on Support Vector Machine

Abstract: The prediction of stock trading signal is studied in this paper. Considering the excellent performance of Support Vector Machine (SVM) in pattern recognition, we apply SVM to construct a prediction model to find the stock trading signal. In addition, Piecewise linear representation (PLR) is good at extracting valuable information from a time sequence. PLR is used for checking of turning points in this study. The experiments on some real stocks show that SVM obtains a better result in prediction accuracy and profitability than traditional Back Propagation neural network does.

An Adaptive Data Management Model for Smart Grid

Abstract: Application of big data techniques in power system will contribute to the sustainable development of power industry companies and the establishment of strong smart grid. There are significant challenges for big data analytics because of heterogeneous data and scalability, system complexity, reliability, and real time requirements for smart grid. In this paper, a data management model is proposed based on knowledge cube, which is an intelligent and adaptive database. The knowledge cube is established based on Topical, Association, Spatial and Temporal. The proposed data management model could handle data that is only relevant to its semantics. And the cube could be combined adaptively with the necessary information about other relevant knowledge cubes by the association component. The proposed knowledge cubes can support the capture and tracking of dynamic data. The proposed model provides a powerful and extensible framework that is particularly well suited to analyzing big variety data in smart grid.

Design and Verification of Star-Map Simulation Software Based on CCD Star Tracker

Abstract: Reliable simulating star map is the important data source for ground test and performance test of star tracker In order to provide star maps for test conveniently, a star map simulation software was developed in this paper The imaging position of observing stars on the CCD plane can be calculated by constructing an ideal model of star sensor By using the Gaussian gray diffusion model to simulate imaging of star and adding some noise signal to make the simulation of real sky better The validity of simulating star map is verified by using angle-distance of two stars, calculation result shows that the mean value of optional angle-distance is 0017613 degree The result shows that the simulation software design method is reliable, high precision and easy to implement

The Prediction on Residential Real Estate Price Based on BPNN

Abstract: The paper brings up a mixed optimizing model based on IPSO-BPNN. The model has used IPSO to optimize the definition of original weights and threshold value. We take the real estate market in Changsha as an example. This algorithm can be applied in the price prediction of residential property.

A Random Pulse Generator for Simulating Nuclear Radiation Signals

Abstract: According to the statistical properties of the nuclear signal pulse on the amplitude and time, a random pulse generator for simulating nuclear radiation signals is designed in this paper. The noise of the ADC acquisition circuit is used to obtain two-way seeds of random number. The obtained seeds of random number are processed by linear feedback shift register (LFSR) to generate high-speed and uniformly distributed random number continuously, then random numbers of Gaussian distribution are produced based on lookup table method and random numbers of exponential distribution are produced by setting the threshold value. Random numbers of Gaussian distribution are sent to the D/A converter to convert digital signal to analog signal, and random numbers of exponential distribution are sent to control time interval between two pulse signals. Eventually the random pulse that follows the gauss distribution on the amplitude and the exponential distribution on the time interval between two adjacent pulse signals is shaped by pulse shaped circuit. The practical test results show that the random pulse follows the gauss distribution on the amplitude and the exponential distribution on the time interval between two adjacent pulse signals, meeting statistical regularity of nuclear signal.

Study on Parking Guidance and Information System Based on Intelligent Mobile Phone Terminal

Abstract: With problem of urban parking becoming more and more serious, parking guidance has become a key point of breakthrough in modern intelligent transportation urgently. This paper describes Parking Guidance and Information System (PGIS) based on intelligent mobile phone terminal. First, the structure of PGIS is established. Secondly, the strategy of PGIS is described in detail. Thirdly, the key technology of PGIS is discussed. At last, the overall framework of mobile phone client preliminary is designed. Based on the optimized guidance strategy, the PGIS presented in this paper can overcome the limitations of traditional systems of information date distribution and provide the drivers with real-time parking guidance information.