Abstract:Real-time operating systems lay claim to multitasking resource accessing control. Resources competition not only results in priority inversion and tasks blocking, but also prolongs timing delay caused by acquiring resources regularly. Although conventional resources accessing protocol works out priority inversion issues, there are still some defects such as frequent context switch, scheduling efficiency etc. With a research on the implement of MiniCore OS and SRP, this paper analyses the detailed criteria of scheduling and demonstrates the causation of low scheduling efficiency under SRP. To solve these issues above, we proposed and implemented a ready queue based on winner tree and a job selection mechanism with low timing overhead. Theoretical analyses and experiment results justify the better performance on large scale tasks scheduling under SRP protocol.

Abstract:Rely on the technique of full life cycle computer aided animation generation, in the 3D animation auto-generation system of short message, short message from the sender is translated to an animation and presented to the recipient, with the aid of computer. Camera is the key way to show the content of 3D animation and the effectiveness of the camera directly affects the expression of the content of the animation. In this paper, combining with the characteristics of mobile phone animation system, we design the scheme of camera shooting through qualitative planning and quantitative planning. Firstly, we describe the camera attributes and shooting schemes by ontology. With the method of logical reasoning, we get main targets from scenes of different topics and take different shooting styles and combinations of camera lens. Then, the qualitative descriptions of cameras are converted into graph data for quantitative calculation and parameter assignment. And finally we achieve the auto-generation of camera planning.

Abstract:According to the threats of link attack and background knowledge attack in redistribution of data of multi sensitive attributes, this paper firstly puts forward the concept of update set of sensitive attribute and the same equivalence of the sensitive group. Then, for some common situations of data redistribution, it puts forward some new strategies of data redistribution based on DMSA algorithm. Finally, it is proved by experiments that it has low occult rate and loss degree of additional information. The result also indicates data has high availability and good privacy after released with this new strategy.

Abstract:With the popularity of mobile applications, and the features of police work, the traditional model of law enforcement is already unable to meet the practical needs. The system uses advanced and widely used mobile technology, android operating system, analyzing and achieving the system for traffic law enforcement according to the police's demand.With the realization of the system, the traffic police can make full use of existing information resources anytime, anywhere, providing technical support for improving work efficiency, increasing the efficiency in the course of law enforcement inspection, raising the of process in suspicion of illegal vehicles on the scene of the inspection, grasping the latest law enforcement inspection, so as to strengthen the supervision of law enforcement road checks.

Abstract:The sudden water pollution incidents occur frequently, so it has become a trend to do simulated research on sudden water pollution incident utilizing GIS platform, remote sensing technology and water quality model. Aiming at solving the problem that mass, heterogeneous and dynamic remote sensing data could not be disposed rapidly and stored efficiently; the storage system of remote sense tile data used in the sudden water pollution incidents was designed and implemented based on HBase. The system is supported by the digital earth platform and integrated with remote sensing tile pyramid model and MapReduce framework. The linear quad tree coding index of the remote sensing tile data was improved in this system according to the frequent load character of remote sensing tile data caused by event situation with real-time and dynamic observation and stored into HBase together with water pollution data. The access efficiency of the remote sensing tile data was increased through adding cache area. Applying this system to Weihe River sudden water pollution in Shanxi, the results showed that the improved index could extract the remote sensing data of the water pollution area within 22 milliseconds and the introduction of the caching mechanism saved almost 2/3 loading time on the remote sensing data in water pollution area. Therefore, the storage system could be accessed efficiently and it could satisfy the quick emergent simulation demand of the sudden water pollution incidents.

Abstract:To improve the informatization level of high-speed railway infrastructure safety monitoring and realize the real-time warning of overproof monitoring data, this paper studies and realizes high-speed railway infrastructure safety monitoring management system. This paper completes image vectorization and attribute data input by using ArcScan. System database of Oracle 11g is used and spatial database based on ArcSDE is constructed within it, then map service is published via ArcGIS Server. Based on B/S architecture, system in this paper realizes the real-time communication between the server and browser, and the functions of GIS module by calling of the ArcGIS API for JavaScript, realizing the real-time warning of overproof monitoring data. Application shows that the system improves the imformatization level of high-speed railway infrastructure safety monitoring, and its practicality is high.

Abstract:Seismic data in the field of oil and gas exploration is a typical kind of big data. The I/O storage system has become a major performance bottleneck of the whole system when pre-stack migration imaging is processed for seismic data using large scale parallel processing application software. Adopting the key technologies of the storage host cluster, dynamic storage multipath and parallel file system, this paper puts forward a storage framework model, analyzes the superiority, and does its deployment. The function and performance of this system is tested in typical application scenarios and the results verify the advantages of the system.

Abstract:With the development of enterprise informationization, the enterprise business system continually increases. The added business systems often use different technologies and security policies, and maintain separate authentication and authorization system, thus it is easy to form "islands of information". Unified authentication based single sign on technique emerges at the right moment for eliminating such isolating access control. However, there are some disadvantages on the security, scalability and maintainability of existing single sign-on models. In this paper, based on the Security Assertion Markup Language(SAML), a unified authentication single sign-on framework with high security, interoperability, and loosely coupling is designed and implemented, which includes the identity providers filter(SSO-IDP) and service providers filter(SSO-SP) modules, single sign-on interaction protocol and security mechanisms.

Abstract:This paper proposes an improved power grid panoramic information model for a comprehensive description of end customer interruption events, which solves the problem that traditional model can not describe low voltage interruption precisely. We implement a power supply reliability of end customer service system based on this model. The system implements integration and modeling of different source data, and indices calculation and visualization with no dependency on automatic devices.

Abstract:This paper puts forward the realization of collaborative virtual environment assist in skills training system against on the CBT(computer based training) systems, which contains the problems of single-user, lack of immersion and no collaborative learning is assisted. The system designs system framework and workflows base on stratified structure idea. It proposes a rapid-modeling strategy based on model complexity to build collaborative virtual training scenarios. It uses mult-communication server technology to build the multi-user collaborative work environment. It reduces the burden of server in collaborative perception process by timing acquisition and sending data methods and meets the needs of teachers' real-time commentary and multi-user discussions by vector electronic drawing board and text messaging mechanism. It verifies the feasibility and superiority between the new system and traditional CBT by application examples.

Abstract:Focused on the bottleneck of the web page distribution performance caused by the sharp increasing of website quantity carried by CAS website group platform, we have deeply analyzed the network structure of the platform. We optimize and remould the platform by adopting several methods such as using NFS Share mode to replace FTP Synchronous mode, setting up intermedia data server, replacing with virtualization platform, etc. We successfully improve the handling capacity of the release module of the platform, and effectively resolve the problem of the platform distribution performance.

Abstract:This paper presents the design and implementation of Android application for Internet of things for building equipment. There are two key points in the development of Android application for Internet of things for building equipment. One of the key points is that the forms of software interface and the data source are different between the subsystems, the other is the heterogeneous data in subsystems. To reduce the coupling of system architectures and improve the reusability of code, an approach for implementing event-driven is adopted. To access the remote database by Android terminals, WebService is proposed. Users can monitor the remote devices' status and modify the configuration information anytime they want by using Android terminal. The user interface is very succinct and beautiful. This Android application has already been used in the lab of Shandong Jianzhu University.

Abstract:In this paper, the optical communication networks applied in Power States are introduced. The present methods for EPON fiber cables monitoring are analyzed and evaluated. A new method which is composed of OTDR(Optical Time Domain Reflectometer), light switch, and optical multiplexer reflector(final filter) is proposed for fiber optic online monitoring. The on-line monitoring system can monitor the real-time transmission of fiber-optic cables, detect hidden obstacles and quickly position the fiber obstacle. Implementation of the parallel monitoring system will improve the time of barriers clearing, and lower the fault probability of Optic fiber communications in Power States.

Abstract:This paper introduces the concept, application scenarios and implementation requirements of the programmable function in protection and monitoring device and proposes the design scheme of programmable function applicable to different hardware and software platform. Based on the analysis of data interface and definition between programmable function and standard or universal function, the design of programming language and the realization of compiling user programs to intermediate code and target code are elaborated. Finally, this paper demonstrates the method of executing user programs efficiently by constructing a logical stack in the virtual machine and proposes an approach of supporting software of graphical programming. The design scheme can provide flexible application programming interface for secondary development of protection and monitoring device.

Abstract:As the increasing number of applications in Office Mobile, it's hard for the traditional IT network infrastructure to carry out the remote management and maintenance. Citrix-based Cloud Desktop is proposed in this paper, which can manage and maintain users' terminal equipment, reduce the operation and maintenance costs and fulfill the enterprise's centralized management. Meanwhile, Cloud Desktop provides users with a personalized desktop and a variety of access methods, which improve service levels and business continuity needs. Compared with the traditional IT infrastructure, the Cloud Desktop provides users with faster & higher predictability, higher cost performance and richer applications. Moreover, it is particularly prominent in energy conservation and cost savings.

Abstract:Neutral beam injection(NBI) is recognized as one of the most effective means of plasma heating. In order to meet the demand of NBI system itself and the complexity of the working environment, a set of new methods for NBI system management are proposed. In this paper, the architecture and implementation of NBI management software are presented. NBI management software is developed based on the Client/Server(C/S) model, multithreading, socket communication technologies and heartbeat wave mechanism. It provides universal service interfaces and a uniform management terminal for different types of software and hardware. The implement of NBI management software enhances the stability of NBI system and provides safeguards for its steady-state operation.

Abstract:Through the analysis of the functional characteristics of the electronic seal and the pertro transportation vehicles related requirements in the process of transportation task, we designed a pertro transport vehicle monitoring system based on electronic seal. This system can change the present situation of oil transportation enterprises with the poor performance of system regulation and traces effects, hard preventing to steal oil and poor universality. This system has implemented the safety of quality and quantity according to pertro transport, thus improving the vehicle management level of the pertro industry and also promoting the healthy and rapid development of industry.

Abstract:The structure of safety monitoring system for petroleum hazardous chemicals based on GIS, GPS, GPRS and wireless sensor network technology is presented in this paper, as well as the system's software architecture and function design. The system conducts real-time pipeline inspections on oil and gas pipelines by using wireless sensor network technology, GPS and GPRS technology. It accomplishes the query, comprehensive analysis and dynamic management on petroleum hazardous chemicals by using geographic information system, so as to provide scientific basis for the safety monitoring of petroleum hazardous chemicals. It has important practical significance for reducing the occurrence of accidents or loss of casualties.

Abstract:The neighborhood weight function built in image segmentation using the improved fuzzy c-means clustering algorithm fails to simultaneously consider space structure and grayscale range information, which results in the problem of noise sensitivity and rough dealing with edge texture information. To this problem, in this paper, a FCM algorithm combined with wavelet transform and improved neighborhood weights is proposed. First, the algorithm deals with the original gray image by using the adapt threshold denoising method, which is based on wavelet used for multi-resolution analysis. Second, it constructs an improved neighborhood weight function based on the local spatial neighborhood information and grayscale range information of the image patches by combining with the thought of bilateral filtering in the reconstructed image. The experiment results show that the proposed algorithm has a higher accuracy of segmentation than the traditional FCM algorithm and improved FCM algorithm and is more robustness to the strong noise with more smooth image edges.

Abstract:In practical applications, when the object itself contains some inherent color or texture features, these features can be used as a priori information, which can greatly improve the accuracy of the segmentation. Therefore, this paper proposes an improved level set method which is based on prior information. Firstly, we use the thought of the energy structure of C-V model to construct an energy function that contains of color information to segment color image. Then, we put the color component into the traditional structure tensor for the texture image segmentation. Finally, we get the new level set model from the traditional C-V model with the new energy structure and the penalty term of Li model. In view of the color and the texture information of strawberry fruit, the improved level set method has been applied to the segmentation of fruit image in agriculture. By experiment on laboratory and nature, the result shows that the improved can not only segment out strawberry, but also segment texture on the surface of strawberry. Comparing with the OTSU algorithm, the traditional C-V model and improved C-V model, the experimental results show that the proposed method has better segmentation result.

Abstract:Non-sufficient training samples cannot comprehensively convey the possible changes such as illumination, expression and gesture, so it is hard to improve the accuracy of face recognition. To overcome the problem, Yong proposed a method that exploits the symmetry of the face to generate new samples and perform face recognition. The new training samples really reflect some possible appearance of the face. However, it usually gets bad symmetrical face samples based mirror image with the changes of facial poses, which may affect the accuracy of recognition. The SVD has advantages of stability and shift in-variance, which can ensure the rate of recognition in the case of small changes of face images. To ease the shortage of the above method, the authors improved it by generating‘symmetrical face’training samples based SVD and mirror image, respectively. The experimental results in ORL, PEFET and UMIST databases show that the improved method outperforms the effect of Yong's method.

Abstract:Under the condition of insufficiency of the training sets, Bayesian will easily make the classification of the new incremental and unlabeled training texts incorrectly. If these incorrectly labeled texts are added to the Bayesian classifier early, it will reduce the performance of Bayesian classifier. In addition, incremental learning with fixed confidence level parameter will cause low learning efficiency and instable generalization ability. In order to solve the above problems, this paper proposes an incremental learning method of dynamic confidence level and sequence selectable. Firstly, the new incremental training subsets are made up of these texts which are classified by current Bayesian classifier correctly. Secondly, it uses confidence level to dynamically monitor the performance of classifier, and then chooses texts from the new incremental training subsets. Finally, strengthen the positive impact of the more mature data, weaken the negative impact of the noise data, and complete the text classification of the test sets by choosing reasonable learning sequence. The experimental results show that the classification efficiency and precision are both advanced by using the method this paper proposes.

Abstract:In recent years, there is an exponential growth of the number of web services in the real world. In the web service research area, the most of concerning problem is how to discover the potential web services to meet users' needs fast and accurately. Nowadays, a lot of discovery methods based on semantic are employing the ontologies of concepts among the parameters of web services interface. With content of concept, when the semantic matching is fail, they take other methods such as keyword-based matching and structure-based analysis to make up for the defect. These methods improve the precision and efficiency in the web service discovery in a certain degree. However, all of these methods dismiss the semantic similarity of Information Content. In this paper, we propose a method which employs a combination of methods based on semantic web service discovery technology and the concept of semantic similarity of the IC. It uses owls-tc 2.0 as a test set. The experiments show that our method is effective to improve the precision of web service discovery.

Abstract:The traditional statistical analysis methods ignore the relations between variables. Transfer entropy could express relations between variables effectively. So this paper proposes an MPCA online monitoring method based on entropy transfer for batch process. The transfer entropy is adopted to describe the complex relations between process variables. The non-parametric kernel density estimation method which does not depend on the prior distribution of data is utilized to calculate transfer entropy to deal with the non-Gauss distribution of the process data. By constructing the transfer entropy matrix combined with the sliding window to achieve the expression of dynamic information transfer between process variables, the MPCA model is then established based on these matrices for detecting faults of batch process. The simulation results show that, compared with the traditional MSPC method, the proposed method can timely identify the faults with better accuracy.

Abstract:In view of the existing algorithms are of long searching time and easily to prematurely converge to the optimal solution, this paper proposes a method for solving circle permutation problem using particle swarm optimization algorithm. First of all, based on the analyzing of relationship between circular permutation problem and the traveling salesman problem, circular permutation problem is translated into traveling salesman problem and accordingly, a corresponding combinatorial optimization problem is obtained. Then, the problem is solved by particle swarm optimization algorithm. Thirdly, in order to further improve the precision of the algorithm, this paper proposes a scheme based on a hybrid particle swarm optimization algorithm. Finally, in the simulation experiments, compared with the existing algorithm, the simulation results show that the proposed method is effective.

Abstract:At present, in the market, more than 85% of the electronic sphygmomanometers adopt oscillometric method to measure blood pressure. The key step of oscillometric method is to extract the pure oscillation pulse wave from the original signals, which is used for the measurement of blood pressure. This paper will use the self-made device based on the flation of blood pressure data acquisition to collect data. In the view of the high frequency noise and baseline drifting caused by the motor oscillation, respiration and body movement, electronic component temperature changes and so on, method of combination of moving average filter and mathematical morphology is proposed. The experimental result shows that this method can effectively eliminate the high frequency noise and drift signal in the oscillation pulse wave. The signal spectrum analysis shows that it clearly reduces the amplitude of high frequency signal, makes the SNR get a good improvement, and improves the accuracy of blood pressure measurement.

Abstract:Train settlement is an important reason for affecting the speed and safe operation of train, meanwhile the changing of train axle box acceleration caused by track irregularities can reflect the status information of track irregularity. Extracting the steady target characteristics of pathway can provide the matching point of orbit for subsequent SLAM algorithm. Through the analysis of components of the pathway, the steady target characteristic of pathway parts could be extracted. Image equalization, enhancing and filling in with hole is to be used to complete the rail and fasteners outline at the beginning of the recognition. Binary expansion and generating linear structure of 0 or 90 degree, horizontal and vertical closing-opening operation, generating elements in pairs is to be used to complete the rail and fasteners initial contour extraction. According to the experiments it will prove that the improved RHT on linear feature extraction can increase the speed of PC and reduce the memory space, which can reduce the Flash on the subsequent DSP hardware development. It has great theoretical significance in supporting for the whole project.

Abstract:Traveling salesman problem(TSP) is a classical combinatorial optimization problem. Moreover, it is also a predigested form of various complex problems. Consequently, it is a research hotspot that an effective algorithm is found to solve this problem. The stochastic relaxation method is a kind of heuristic random search algorithm based on Metropolis iteration method. In order to solve the problem of plunging into local optimum of the algorithm when solving TSP, this paper puts forward three kinds of different improved methods. Namely, during the process of producing new solutions in solution transformation, firstly, three cities are randomly selected. Then, three different processing methods are given, respectively. Finally, in simulation, compared with the existing method, the results show that the proposed three methods have shorter paths and better results.

Abstract:According to the threats of general leakage, cross leakage, similar leakage and multidimensional independent leakage in redistribution of data of multi sensitive attributes, this paper puts forward the concept of sensitive attribute sensitivity level and sensitivity level of sensitive attribute values. Then, it separates each dimension of sensitive attributes based on l-diversity model. It also puts forward the lq-diversity model of differentiated multi sensitive property. Experiments prove that it is safe for the distribution of data of multiple sensitive attributes. Finally, according to lq-diversity model, the paper puts forward a corresponding DMSA algorithm, which is proved to be correct and feasible, and has low occult rate and loss degree of additional information. The result indicates data has high availability and good privacy after released with this method.

Abstract:In the traditional virtual machine scheduling, we only focus on the current load, without fully considering the historical data in the virtual machine. As a result, we will suffer from load imbalance when scheduling the cloud computing resource. In order to solve that problem, this paper puts forward the algorithm of resource scheduling based on heuristic genetic algorithm, which can schedule the cloud computing resource while meeting the multi-objective planning. This algorithm fully considers various overheads and factors of virtual machine while providing service to users, so as to make the server, which provides cloud computing resource, achieve load balancing. By analyzing, researching and calculating current load and historical data, the writer induces the best scheduling scheme of cloud computer resource, which can meet the data constrains for the load variation and minimum dynamic migration overhead. Finally, by verifying the algorithm in a simulation experiment, the writer compares and measures the load of virtual machine by bringing in load change rate and two performance parameters of the average load distance. The experimental data shows that the proposed algorithm has very good global convergence and utilization rate of resources. It can solve the load imbalance and the large overheads of dynamic migration in the process of resource scheduling. Therefore, the algorithm is feasible and effective.

Abstract:For relational database of oil-gas well engineering domain, this paper presented a method of SPARQL-SQL query transformation based semantic views. In this method, a specific ontology is used to describe schema of relational database and tables are defined as semantic query views based on domain ontology. Through semantic mapping provided by semantic views, SPARQL query is parsed and rewrited to SQL statements on relational data sources. A virtual data center system is implemented with which feasibility and validity of methods provided in this paper are tested, and we achieved a good application effect.

Abstract:With the study of existing dimming methods and the consideration of the current research situation about AEC algorithm, an original feedback auto dimming algorithm based on image strategy which use the information of histogram of license plate has been proposed in this paper. The algorithm which has been presented uses distribution of histogram of license plate to judge the exposure information, and then takes advantage of the judgement information by adjusting brightness base under brightness mode to achieve automatic exposure control at the circumstance of complex lighting conditions, which overcomes the drawbacks of existing dimming methods. Meanwhile, the procedures of how above dimming algorithm works has been introduced in detail and then the algorithm has been effectively tested in practice. Finally, the algorithm is a field test conducted field tests based on the existing dimming method of "Smart Zhitong Eye". The experimental results show that the proposed algorithm can effectively improve the recognition rate compared with the traditional dimming algorithm of license plate recognition, and can be directly applied in the front-end embedded video acquisition and recognition of license plate capture equipment.

Abstract:In order to solve the correctness issues of computer system design, a formal method which is complete on the test space is studied a general method of formal verification of hardware system in HOL4 is discussed in this paper. The method includes how to use the higher-order logic to describe the implementation and specification of hardware system and the general process of proving goals in HOL4. Meanwhile, taking multiplier as example, a functional decomposition method for modeling the design of circuit logically is proposed. Relevant properties of the circuit are ratiocinated and verified using the theorem prover HOL4, which proves that the model of the circuit design satisfies the properties.

Abstract:Target classification is a key link in the field of computer vision and pattern recognition. SVM(support vector machine) is a new machine learning method put forward based on statistical learning theory. In this paper, an offline image target classification algorithm based on gradient histogram feature of support vector machine is proposed. First, the training set is preprocessed, and then the image is extracted by histogram feature extraction. Finally, the classifier can be detected by training. The test images are tested by using the classifier. The test results show that the target classification test has good effect.

Abstract:Lock alias analysis can obtain the precise lock pointer information. Efficient lock alias analysis can make a good contribution to data races analysis and deadlock analysis. However, existing lock alias analyses often use a conservative approach, which impacts the accuracy of analysis. This paper proposes a lock alias analysis method. This method firstly gains SSA-form intermediate code by a GCC plugin. Then it preprocesses the intermediate code to obtain the statements related to function pointer and lock operation. Based on this we present the flow-sensitive and context-sensitive function pointer and lock analysis algorithm(referred as FP_LOCK algorithm). Experimental results show that this method has well precision and advances 9.95 times on average compared with the original algorithm.

Abstract:Regarding an intelligent vehicle competition navigation algorithm based on mobile robot, the article describes a method that sensor node can be placed by a new structure, which differs from the traditional one. Under the structure, rules of navigation for recognizing the set path are defined. In order to verify the above algorithm, mobile robot navigation system based on MCF52259 MCU was designed and put into practice. The algorithm has obtained good effect on recognizing complicate path.

Abstract:The CTC system is the core of information system of railway transportation, so the reliability of data protection is very important. Manually regular database backup and manually recovery in the event of failure cannot guarantee uninterrupted operation of the railway transportation system. We design a solution based on Oracle Data Guard technology to implement real-time data backup and the restore process is completely transparent to the user, which does not affect the normal use of the dispatcher and the station attendant. We can execute the backup process under the condition of minimum resource available. We implement the solution and achieve excellent effect in the application scenario.

Abstract:With the rapid development of photovoltaic industry, photovoltaic power generation has become a new force of renewable energy. However, the influence of power photovoltaic system subjects to different weather conditions and has the characteristics of uncertainty and periodicity. For accurate prediction of photovoltaic power to ensure the stability of power system, this paper uses GA-BP algorithm for prediction and analysis of power generation of photovoltaic system. Results show that the model and method presented in this paper can predict the power output of photovoltaic system and are of more accuracy and certain practical value.

Abstract:As a new mode of service, cloud computing receives the favour of various enterprises in recent years. Though there are three kinds of deployment models to be chosen, enterprises also worry about the storage and transmission security of data. A method of Attribute Based Access Control(ABAC) was used to ensure that only authorized users had access to the data in the cloud. In addition, the method of rough set attribute reduction method was used to reduce the redundant attributes, retain authority conflicts and speed up the access time.

Abstract:In face of problems such as low query speed and difficult maintenance caused by data volumes increasing in real-time state table of boundary load switch monitoring system database, this paper proposes data table partition optimization method, expounds the implementation process in detail, and removes obsolete data by sliding partitioned window. Through a large number of test data, the query efficiency of a same table before and after partitioning are compared. Results indicate that using the technology of table partition can shorten data query time dramatically and improve the stability of the database.

Abstract:In this paper, we present the architecture and technology of a new performance testing platform of the stream data processing for the power grid. This testing platform provides a browser-based test script and test scenario design service. It also supports the full life cycle management and high availability guarantee for the execution of test task. Meanwhile, this platform uses Linux container to build a virtualized testing resource pool, which can achieve the lightweight, flexible management of testing resources for large-scale load testing.

Abstract:Clustered file system is a key component of cloud computing. It can be divided into two major groups, which are shared-disk file system and distributed file system, in which the latter is the hot spot of academic research in recent years. This paper mainly focuses on IOPS, which is an important performance indicator for VM(virtual machine). We employ fio as the testing tool and experimental results show that,(1) when a VM runs on sharing-disk file system and distributed cluster file system both with 3 storage nodes, the write IOPS of the former is higher than the latter about 40%, but the read IOPS of latter is 1.5 times as much as the former;(2) when multiple VMs run simultaneously on sharing-disk file system and distributed cluster file system both with less than 16 storage nodes, the write IOPS of VMs for both clusters are almost the same; otherwise, the write IOPS performance of the latter is better than the former.

Abstract:Software-based hash function has been popularly applied to current networking searching area, but it is difficult to meet the demand of high-speed real-time applications in backbone network and services with mass data. In the general design of hardware-based hash function, there are still some drawbacks such as complex logic circuit memory inefficiency, and incremental updates for dataset needed to be solved. This paper proposed a design of hardware perfect hash function on FPGA based on bit-extraction algorithm, using simple bit-selection and bit logic operation. The achievable load factor can be up to 1, and the amortized memory cost of the hash function is about 2.8-5.6 bits/key for 32-bit keys, and the system clock frequency is about 300MHz(Throughput more than 14Gbps). The proposed method can be applied to real-time applications that require high-speed table lookup, e.g. IP address lookup, packet classification, string matching and intrusion detection systems.

Abstract:With the wide application of real-time systems in time-critical and safety-critical areas, the timing property of a program is getting more and more attention. Henzinger has come up with LET(Logical Execution Time) programming model, which introduces semantic to deal with timing in an explicit way, assuring the timing predictability of a system. However, traditional RTOS is based on exactly different abstractions and can hardly support LET programming model in a good way. Minicore is a novel operating system model, in which a program is composed of a set of services without internal synchronization point. Minicore is based on a similar abstraction with LET model and minicore program is more time-predictable and controllable. Combining the control model of LET and execution model of Minicore, we can get a novel time-determinable programming framework. This paper mainly describes the design and implementation of the memory management of this framework. An implementation of intelligent car system is presented as a case study to prove the feasibility of this system.

Abstract:With the human living standards improving, small cars gradually become the first choice of travel. However, the attendant traffic problems are increasingly restricting the development of human society. This design based on STM32 and Android mobile phones, achieves mutual communication in the cars, mobile phones and servers through bluetooth and 3G networks, and then implements real-time monitoring of the car running status and online diagnosis.

Abstract:Target tracking is not only an important operation mode of fire-control radar, but also the primary task of the fire-control system. Extensible and repeatable signal-level target tracking simulation system of fire-control radar based on HLA is developed in this paper. Then according to the features of closed loop, continuous tracking, automatic measuring, starting from the signal-level simulation, combining antenna module, receiver and signal processing module, control system module in tracking system of fire-control radar, dynamic target tracking simulation is completed. The simulation result indicates that the dynamical process of target tracking is carried out through the simulation system distinctly and effectively, which is of some reference value for the research on training simulation system design of fire-control radar and electronic warfare system evaluation.

Abstract:ZigBee technology is a hot topic, which has the characteristics of low complexity, low power, low data rate, low cost, etc. and has varies of applications. In this paper, firstly, ZigBee topology and ZigBee protocol are introduced. Then ZigBee Application technology and various communication modes' characterizes are analyzed. The current ZigBee technology's key problems are summarized and the design example are put forward. Finally, the direction of future research is summarized.

Abstract:The design is the upgrading of the existing elevator monitoring system, which has realized the recording and data acquisition of the elevator working state. And it has also realized the dynamic showing on local display and real-time processing on remote monitoring platform. The whole system includes two main components, which are data collecting from lower machine and monitoring software on the server. The lower computer gathers the parameters of PLC and inverter of the spot elevator and the parameters are sent to the specified port of the server through H7710(GPRS module). The data is received with Apache MINA framework and stored in oracle database. PC monitoring software adopts B/S mode. According to the granted permissions, users can deal with the operation of remote monitoring, information querying and alarm processing to the equipments of their companies. Practical applications prove that the monitor system is stable in performance and the design method is reasonable. It can be widely used in the field of elevator monitoring.