Abstract:In recent years, the network security log data shows explosive growth. However, the existing visualization technology is hardly to support the analysis of high dimensional and multi-granularity NetFlow log data. In order to make advantages of the visualization technology, this study proposes a new network security visualization framework to paint the picture, uses the three dimensional histogram which help users to quickly master the abnormal moment of network shown by the Netflow log data, uses information entropy algorithm to process multi-dimensional data, makes use of the matrix chart, bubble diagram, and line chart to synthesize analyzed data in detail. Finally, we carry out an experiment to test the process of DDOS attack, and Port Scanning Attack can be detected easily by proposed system. The study proves that the system which has rich visual graphics and provides simple collaborative interaction can better help network security personnel to analyze the entire network behavior process.

Abstract:Fuzzing is widely used for different kinds of software and systems to detect the vulnerabilities. The effectiveness and efficiency of fuzzing is related to the mutation strategy of the seed files and the code coverage of the seed files for the target program. This study proposes a new method based on deep learning for seed generation. The proposed method analyses and learns the correlation between the seed files and their paths in the target program. Finally, the proposed method generates seed files that more likely explore uncovered paths, thus increases the code coverage of the initial seed files for the target program. Aiming at the PDF reader, we carry out the experiment. The results demonstrates that the seed files generated by proposed method have a good passing rate of the PDF reader, in the meantime, significantly improve the code coverage. The experiment also indicates the applicability of proposed method:the seed files which are generated for specific target program (PDF reader) can also obtain higher code coverage when fuzzing some other kinds of PDF readers.

Abstract:Different core companies have different requirements and standards for the collaborative enterprises associated with the cloud platform, and the collaborative enterprises to be evaluated have different objective features. In order to select the best collaboration companies for the core enterprises of the after-sales automotive service supply chain cloud platform, the weight coefficient of the evaluation index of each cooperative enterprise is determined by the comprehensive weighting method based on the combination of the analytic hierarchy process method and the fuzzy rough set method. The subjective weight is determined by the analytic hierarchy process, and the objective weight is determined by the fuzzy rough set method. The comprehensive weight coefficient is achieved by reintegrating the main and objective weights. Finally, based on the extension discriminant method, the evaluation object is evaluated by the degree of goodness. The result is the ranking of each appraisal object and the order of the advantages and disadvantages. The actual service data of the after-sales service supply chain cloud service platform for the after-sales service is used as an example for comparative analysis. The results demonstrate the effectiveness and feasibility of the method, which are superior to other evaluation methods.

Abstract:To solve the UAV path planning problem, a method based on Fusion of Simplified Sparse A^* algorithm and Simulated Annealing algorithm (FSSA-SA) is proposed. Firstly, after modeling the threat environment, the simulated annealing idea is combined with the solution of the specific route planning problem, and the concrete design and implementation method of the simulated annealing algorithm is given. Secondly, the simplified sparse A^* algorithm is used to search the roundtrip tracks between the start point and the end point, and the better one of the results will be used as the initial solution of the simulated annealing algorithm to realize the fusion of the two algorithms. Then, when annealing proceeds to the low temperature region, the solution quality of the algorithm is further improved by eliminating the redundant track nodes. Finally, in order to verify the superiority of the proposed algorithm, the simulation experiments are carried out with sparse A^* algorithm and simulated annealing algorithm. The experimental results show that the proposed FSSA-SA algorithm has less planning time-consuming than the two algorithms mentioned above; compared with the sparse A^* algorithm, the memory occupied by the FSSA-SA algorithm is two orders of magnitude less when the synthetic cost of the obtained track is not too different; compared with the simulated annealing algorithm, under the same annealing conditions, the integrated cost of the planned track is reduced by about 35% on average.

Abstract:Faced with the problem of high no-load rate of urban taxi and taxi difficulty of passengers, this study analyzes the passenger hotspots for taxi drivers and taxi hotspots for passengers, and proposes a data processing model based on DBSCAN algorithm. Using this model, the GPS trajectory data of 182 taxis in Beijing are processed, and the data precision is improved. For different audiences, K-means algorithm is used to cluster the data and get the relevant hotspots. Experiments show that the proposed method can not only effectively provide taxi drivers with high probability of passenger hotspots, but also provide a feasible solution to the problem of taxi difficulty of passengers.

Abstract:Automatic parcel sorting system using Automatic Guided Vehicle (AGV) is a research hotspot of intelligent logistics, in which path planning is one of the key issues. In an express sorting system, AGV has the characteristics of high density and large number of vehicles. This situation will cause congestion, making the performance of the whole system decrease. Aiming at this problem, this study proposes a CAA^* (Congestion-Avoidable A^*) algorithm that is able to avoid congestion. Based on A^* algorithm, the proposed algorithm introduces dynamic attribute nodes and establishes dynamic environment model to predict the possible crowding situation of each node, judge whether there are potential congestion nodes in the path planning process and bypass possible congestion nodes. Experimental results show that the proposed CAA^* path planning method can effectively reduce congestion in high-density and large-scale AGV scenarios, thereby improving the density of AGV and system sorting efficiency. Simulation results on practical application sites show that the proposed algorithm improves the AGV density by 28.57% and the sorting efficiency by 24.29% compared with the traditional A^* algorithm.

Abstract:In order to realize the timely diagnosis and treatment of infantile fundus diseases, the developed infant retinal wide-area imaging system can solve the large field of view requirements during imaging. The system includes an illumination portion, an imaging portion, and an image capture device.Designed corneal contact ophthalmoscope, using aspherical design with small aberration and large refractive index to meet the requirements of large field of view. The image acquisition device is designed which is written in C++ for image acquisition, camera calibration, and geometric distortion correction. The experimental results show that the wide-area retinal imaging system for infant can achieve wide-area imaging of 85° field of view; multi-ring fiber optic illumination can obtain clear retinal images; the correction based on camera calibration of image geometric distortion can effectively compensate geometric distortion of the retinal imaging light path. The wide-area retinal imaging system for infant can provide an objective and clear basis for the diagnosis and screening of ophthalmic diseases.

Abstract:In order to solve the issues such that function module of the traditional housing maintenance fund management system is complicated, the process of development and maintenance is tedious, and the new demand is difficult to deal with in time, the system design and development based on the micro service architecture is proposed. This study designs a residential maintenance fund management system based on micro service architecture, and divides the system into several micro service modules. The system uses Spring Cloud to build a micro service architecture, and implements the technology of service registration and discovery, load balancing, routing gateway, and fault tolerance processing, and finally implements various micro service functions. The micro service framework reduces the coupling of the system, speeds up the development cycle of the system, and makes the deployment and maintenance of the system more convenient.

Abstract:The architectural aluminum alloy formwork is widely used due to its good rigidity, long service life, and repeated usage. At present, the sorting and packing of architectural aluminum alloy formwork mainly depends on manual work, which has low sorting efficiency and high classification error rate. In order to improve the sorting efficiency and classification accuracy of aluminium templates, a sorting system for architectural aluminum alloy formwork is designed, which consists of upper management computer, two-dimensional code scanner, MCGS touch screen, and architectural aluminum alloy formwork transmission system. The KingView configuration software which runs on the management computer can complete the station matching according to the delivery list. It updates the sorting database and displays the sorting process in real time. The scanner scans the two-dimensional code of the aluminum alloy formwork label on the conveyor belt to obtain the information of its specifications, types, and engineering location. After processed by KingView configuration software, the information is sent to the corresponding MCGS touch screen. The worker picks up the aluminium alloy formwork on the conveyor belt and carries it to the designated stacking area. MCGS touch screen realizes the function of information exchange between management computer and workers in sorting process. Experiments show that the designed aluminium alloy formwork sorting system has good stability and practicability. It can effectively solve the problem of low efficiency and high classification error rate in manual sorting process.

Abstract:In the "Internet Plus" environment, the ecological service mode for industrial-academic-research cooperation has emerged with the goal of expanding the cooperation scope and improving the outcomes of industrial-academic-research cooperation. This service mode designates to be user's value-oriented, the core is to speed up the technology transfer for both supply and demand and to fulfill every need, thus to help further solve the asymmetric information by industrial chain integration and strengthened horizontal user relations circle expansion. Based on this cooperative ecological service mode of research and development, the construction of ecological service model, which is applied to practice, constructs " Internet Plus Industrial-Academic-Research Cooperation Intelligent Service Platform", provides diversified content, social and docking ecosystem services, and has achieved remarkable results.

Abstract:The purpose of this study is to solve the problems of current Web display technology, i.e., a single user can only work collaboratively with a single remote user through remote video conferencing and desktop mirroring, which does not meet the requirements of multi-user massive information sharing display, and does not support the high-resolution display of massive images, and so on. This work studies the technology of ultra-high resolution display on the splicing display screen of users of large-scale images based on Web clusters, according to the characteristics of multi-user massive information sharing display and the difficulty of display. The experimental results show that the proposed Web cluster parallel splicing massive image display technology is effective, and it can provide a feasible solution for the high-resolution display of massive images of multiple remote users on the splicing display.

Abstract:This study takes ironmaking production parameters of iron and steel enterprises as research materials and realizes diversified display of blast furnace ironmaking burdening optimization, ironmaking data, and 3D model. This work mainly studies the cross-platform intelligent ironmaking burdening system designed and developed under Qt platform, adopts linear programming methods to build a mathematical model of ironmaking burdening, solves the simplex algorithm to achieve cost optimization, makes use of FFmpeg library to realize playing of mathematical model animation of blast furnace, and takes advantage of OpenGL to realize dynamic display of 3D model of blast furnace. This article firstly introduces some relevant techniques used in the system; then analyzes data extraction, updating, and optimization algorithm designs of the system; and finally introduces realization and tests of burdening optimization, 2D data display, and dynamic display of 3D model.

Abstract:At the age of big data, faced the explosive growth of massive heterogeneous big data, the real-time supply capacity of enterprise index data needs to be improved comprehensively. The real-time computing method of big data index based on stream processing is composed of logs collection, message management, coordination management, real-time processing, and other parts. Not only open source software such as Hadoop, Zookeeper, Storm, Kafka, and Redis are used, but also the techniques of database log analysis, stream processing, and memory calculation are applied. This paper presents the discussion of the technical framework, implementation method and path of the real-time computing method of big data index based on Storm, and provides the algorithm verification process and result analysis.

Abstract:Aiming at the problems of tedious steps, low efficiency, and long working cycle of traditional field geological data acquisition and digitization, a geological data field acquisition system based on World Wind mobile terminal is developed, which integrates World Wind map technology, network communication technology, multi-thread technology, and data storage technology. The realization methods of positioning module, data input module, solid projection module, and three-dimensional display module are mainly expounded. The research and development of this system realizes the information collection, browsing and display of field geological work, provides convenient data entry mode for geological workers, promoting the digitalization, informatization, and modernization of geological and mining work.

Abstract:Aiming at the increasingly heavy work of transmission line patrol and the problem of difficult patrol, high risk and low automation of Unmanned Aerial Vehicle (UAV) for transmission, a kind of intelligent patrol system and method for automatic driving of transmission line multi-rotor UAV is proposed. Combining artificial intelligence image recognition technology, the system realizes the intelligent processing of the patrol data, so that a new automatic intelligent patrol operation mode for transmission lines is established. This study focuses on the structure, function, and key technologies of the inspection system. Through the application of transmission line inspection in Foshan area, the system greatly improves the efficiency of power grid inspection, and proves its effectiveness and rationality.

Abstract:The characteristics of test data in construction machinery industry are many formats, large data volume, and high business complexity. Traditional website construction has many defects in terms of website friendliness and aesthetics. In addition, slow loading and unstable running of web pages are easy to occur when processing large amounts of data concurrently. The operating efficiency of enterprise test business is seriously affected, resulting in the increase of enterprise cost. Single-page application technology (referred to as SPA) is a brand new website construction mode, which is the mainstream of current web development technology. It applies modular programming method to provide users with better website experience. Its construction mechanism solves the problems largely brought by traditional website construction methods. This paper mainly discusses the use of SPA website architecture to build a test business management system applicable to large enterprises, to solve the problems faced by enterprise test data management, to improve the digitalization ability of test business, and to improve the efficiency of enterprise test operation finally.

Abstract:Aiming at the problems of high power consumption, poor global coverage and low efficiency of intelligent cold chain transportation system in the whole world, taking intelligent refrigerated container as the research object, this paper introduces an intelligent cold chain transportation terminal system based on LEO satellite and NB-IoT communication technology, and gives the system design, hardware design, software design, low power consumption design and test results of the intelligent cold chain transportation terminal system. The transport terminal system uses STM32 as the main controller and integrates temperature, humidity and location information sensors. It is compatible with LEO satellite and NB-IoT communication modes. The system can globally monitor the position, status and safety of refrigerated containers equipped with the intelligent terminal. Practical operation shows that the scheme is reliable and has certain popularization and application value.

Abstract:With the rapid development of network technology, the amount of data generated by real-time system is increasing exponentially. Business applications are putting forward more and more high demand on the management and real-time requirement. As the traditional stand-alone RTDB technology has met the needs with difficulty, the distributed thinking is introduced into the RTDB field. It mainly studies from the Data distribution mode, data redundancy backup, data consistency, and other aspects, proposes a design of data distributed storage in real-time data system. This design can provide technical support for current RTDB scalability and reliability.

Abstract:Multi-Instance Multi-Label (MIML) learning is new machine learning framework where an example is described by multiple instances and associated with multiple classes of labels. A method of designing MIML algorithm is to identify its equivalence in the traditional supervised learning framework, using multi-instance learning or multi-label learning as the bridge, then using an algorithm for training and modeling. But in the degradation process, there will be the loss of information, then affecting the classification accuracy. This study improves the MIMLSVM algorithm by using a multi-label algorithm GLOCAL that considers both global and local correlations. The experimental results show that the improved algorithm has achieved sound classification results.

Abstract:Short texts clustering is a popular topic in the field of information extraction. There is a "long tail phenomenon" when the scale of data is large, which causes high dimensions of features and information loss of small class. To solve these problems, this study proposes a Frequent Itemsets collaborative Pruning iteration Clustering framework (FIPC). This framework combines the iterative clustering framework with the K-mediods algorithm, using the collaborative pruning strategy to cluster text of small class. The result of experiments shows that the FIPC framework can achieve text clustering of small class with high accuracy, and avoid the problem of overlapping clusters.

Abstract:In the Fourier frequency domain, the restored image is still very fuzzy because the inverse filter is particularly sensitive to additive noise. In view of this problem, we propose a dynamic fuzzy image processing method based on Wiener filter and Generative Adversarial Networks (GAN). Firstly, the Wiener filter is used to blur the algorithm, and the noise is minimized by mean variance minimization. But expected result is not achieved because it is impossible to judge the moving range of the shooting device. Then, we consider to use a free unpredetermined distribution of GAN model, define a class generator G(y) and a class discriminant D(x), with machine learning approach to learn and feedback repeatedly, until the generated model cannot distinguish the data sample S(y) and real data samples r(x), the image is approximately restored successfully. At the same time, the concept of "fuzzy kernel" is introduced to simulate the fuzzy trajectory of the image and to make precise restoration. Finally, it is difficult to make quantitative judgment on the restoration degree of the image. Therefore, three evaluation indexes are used to objectively evaluate these images-Peak Signal-to-Noise Ratio (PSNR), fuzzy coefficient KBlur, and quality factor Q. The experimental results show that the three evaluation indexes of the image under this method are improved to some extent, so as to obtain a more successful conclusion of image restoration.

Abstract:The data sparsity and cold start problem of collaborative filtering recommendation algorithm affects and constrains the quality of recommendation. Trust calculation based on user-project bipartite graph can effectively utilize the hidden connection between users. The algorithm model proposed in this study includes the calculation of improved user-project adaptive trust, incorporates an improved enhanced trust mechanism based on user preferences, linear weighted JMSD correlation coefficient. Experiments under the two sets of data set show that the improved algorithm model has a lower Mean Absolute Error (MAE) and higher recall rate (Recall) than the three benchmark algorithms, both models have their own focus, which improves the quality of recommendations.

Abstract:Hubs have a significant negative impact on high-dimensional data analysis. The current research uses five kinds of Hubness strategies to improve the classification effect, but each strategy has a limited scope of application. In order to solve this problem, PM-MD-based integration is proposed for the Hubness-based classifiers. The PM-MD integration determines a decision profile of the classification object through KNN and determines a class support vector of the classification object through the classifier. Finally, the competitiveness of the classifier integration is evaluated by comparing the similarity between the decision profile and the class support vector. When PM-MD dealing with high-dimensional data sets, because the Gaussian potential function tends to reduce the distance which leads to a lack of discrimination, it is proposed to use Euclidean distance to directly calculate the decision profile to improve the classification accuracy. The experimental results on 12 UCI datasets show that PM-MD obtains sound and stable classification results, and the improved PM-MD further improves the classification accuracy.

Abstract:Along with the deep research on neural network, the object detection precision and speed are improved. But, computational cost is higher and higher with the deepening of network layer and increasing model volume, it cannot meet the needs that the neural network realizes fast forward reasoning directly in the embedded devices. In order to solve this problem, we study deep learning object detection optimization algorithm for embedded devices in this study. First, we choose the appropriate object detection algorithm and neural network frame structure. Then, the training and model pruning are carried out for the images collected under the specific detection scenario. Finally, the assembly instruction is optimized for the pruned object detection model transplanted to the embedded device. Compared with the original network model, the proposed model volume is reduced by 9.96% and the speed is accelerated by 8.82 times after comprehensive optimization.

Abstract:At the present stage, the environmental testing equipment failures occur frequently and it is necessary to automatically judge whether the equipment fails. Although the equipment does not trigger alarm equipment in the equipment room, the monitoring data is beyond the normal working range. In order to solve this kind of equipment fault problem, a method of target detection and recognition based on Faster R-CNN is proposed. By training the convolutional feature map for the manually marked image data, the detection and recognition model of switch, indicator and digital instrument in this scenario is obtained. Experiments show that the Faster R-CNN algorithm can detect the faults of the three kinds of equipment with different shooting angles, occlusion, and different illumination conditions, and can achieve ideal results and basically achieve the efficiency of real-time monitoring.

Abstract:As a key step in binocular 3D reconstruction, the binocular stereo matching algorithm completes the transformation from planar vision to stereo vision. But how to balance the running speed and accuracy of the binocular stereo matching algorithm is still a difficult problem. In this study, focused on that existing local stereo matching algorithm has low matching accuracy in specific regions such as weak texture and depth discontinuity, while considered the real-time performance of the algorithm at the same time, an improved stereo matching algorithm based on cross-scale guided filtering is proposed. Firstly, the two cost calculation methods of SAD and Census transform are combined, and then the cost aggregation is performed by using cross-scale guided filtering. When calculating the disparity calculation, a judgment criterion is used to judge the reliance of the disparity value corresponding to the minimum aggregation cost of each pixel in the image. When it is judged that the corresponding disparity value is unreliable, an adaptive window based on gradient similarity is constructed for the pixel, and the disparity value corresponding to the pixel is corrected based on the adaptive window. Finally, the final disparity map is obtained by parallax refinement. Experimental results on standard stereo image pairs on the Middlebury test platform show higher accuracy than traditional guided filter based stereo matching algorithms.

Abstract:In the process of moving target detection, the traditional algorithm is based on modeling a single feature background, and the background description is not accurate enough. To solve this problem, this study proposes an algorithm based on Vibe background modeling that incorporates color and edge features. The proposed algorithm solves the problem of noise, breakpoints, and internal pores in the moving target detection result of the three-frame difference algorithm, and compensates the image processing results based on the morphological processing algorithm. In order to ensure the accuracy of moving target detection and speed up the elimination of the "ghosting" phenomenon in the first frame of Vibe algorithm, this study combines Vibe algorithm and improved three-frame difference algorithm to realize real-time detection of moving targets. Through research analysis and computational derivation, the detection results of moving targets in the experiment show that the improved three-frame difference algorithm based on Vibe background modeling is better than the three-frame difference algorithm.

Abstract:According to the order and dependencies of data initialization for Java EE application, a data initialization method based on design pattern is proposed. First, the data to be initialized is regarded as a complex object, and it is represented by the product role of the builder mode, using the abstract builder role to define the order of data initialization, and using Hibernate framework to save every part of the data to the database. Then, it defines the initialization algorithm in the application development stage and the formal operation stage through the strategy pattern. Finally, it uses singleton pattern to encapsulate the general steps of JDBC and Hibernate operation. Taking the data initialization operation of target assessment management system in colleges and universities for example, through reading the initial data stored in the Excel file by JXL as the implementation logic of the concrete builder's role, the concrete realization process of the method is described in detail. The test and practice show that the data initialization method can meet the application requirements of the system, it has high reusability and can improve the expansibility and maintainability of data initialization operation.

Abstract:Aiming at the shortcomings of the existing association classification algorithm, such as large resource consumption, difficult rule pruning, and complex classification model, an improved classification scheme ACCP based on classification and pruning is proposed. The algorithm mines the fore items of classification rules respectively according to the different classification attribute values, and improves the frequent item set mining process and rule pruning, which effectively improves the classification accuracy and algorithm operation efficiency. The experimental results show that the improved algorithm has higher classification accuracy than traditional CBA algorithm and C4.5 decision tree algorithm, and has achieved satisfied application results.

Abstract:Turbulence image restoration is a hot topic in the field of meteorology, but there are few studies on the classification of turbulent disturbance intensity images. Aerial images of different scenarios are processed for atmospheric turbulence. 2000 corresponding turbulent interference images are generated by adjusting the intensity of turbulence degradation value, and then they are sent into the convolutional neural network after the image preprocessing in turbulent degradation intensity classification, finally by optimizing the structures, convolutional neural network model of the activation function and the adjustment of vector for further improving classification accuracy. Experiments show that the classification accuracy of turbulent degradation images which have different interference intensities by convolutional neural network is about 80%, which demonstrates that this method is of guiding significance for the restoration of atmospheric turbulent degradation images.

Abstract:As the cost decrease of hardware and software with proven technologies, the traditional way to analyze and manage data has obvious shortages to meet the needs of business development. Because the monitoring and evaluation data of environmental protection matches the characteristics of big data, it is possible to build a new data management platform using big data technology. In this study, we design the three-layer architecture and physical implementation proposal of big data management platform for environmental evaluation, with the research of elastic expansion, stream processing, data lake, massive parallel processing, machine learning, and other technologies. We try to resolve the data processing issues of high speed, deep insight, and intelligence so that to provide high efficient support to business management.

Abstract:With the rapid development of mobile devices, the requirement of wireless network speed and quality for industrial applications is getting higher and higher. However, the development of wireless network is slow and far from meeting the actual needs. Therefore, in view of the bottleneck problem of wireless network transmission speed and quality, this study proposes a parallel gateway using multi-channel wireless transmission. The system uses a pair of parallel gateways to establish a multi-channel wireless connection to realize the parallel transmission of Ethernet frame data, so as to improve the transmission speed of wireless networks. Moreover, UDT transmission protocol is used for data transmission between parallel gateways to improve the quality of data transmission.

Abstract:Myocardial infarction is a vascular necrosis of myocardial cells. Because of the different degrees of necrosis, the performance on the electrocardiogram is different. Because the characteristics of atypical myocardial infarction are not obvious, the current method has low detection accuracy. In this study, a method combining BP neural network and convolutional neural network is proposed according to the type of disease to improve the accuracy of detecting atypical myocardial infarction and reduce the time complexity of typical myocardial infarction. First, the original ECG signal is filtered, smoothed, de-baselined, etc., and the relevant feature values are extracted. The BP neural network is used to train the classification. For the features that are not obvious, the convolutional neural network is used for training after intercepting at a fixed length. In order to further improve the accuracy, the 12-lead data was combined for analysis. The experimental results show that this method improves the detection of myocardial infarction by 2% compared with other methods, especially in the detection of atypical myocardial infarction.

Abstract:The scheduling problem of the production plan is one of the main factors that affect the production efficiency of the workshop. A reasonable scheduling plan can efficiently use the existing production resources of the workshop, increase the production capacity of the workshop, and reduce production costs. Firstly, the production and operation status of the brake pad are analyzed in this study. The production scheduling mathematical model for the multi-types and variable batch production mode of hot-pressing workshop is established. Secondly, a Combined Mean-Genetic algorithm is designed to solve the scheduling mathematical model of hot-pressing workshop. Finally, the algorithm is verified by experimental simulation. The experimental results show that the Combined Mean-Genetic algorithm can well solve the scheduling problem of the current brake pad production plan.

Abstract:Collaborative Virtual Reality (VR) technology has a wide application background. An omni-directional wheelchair was used as an application object to discuss the technology of VR and so on. The kinematic relationship of the wheelchair was analyzed with combining the motion principle and arrangement of Mecanum wheel, alternate wheel, and conical wheel. The Virtual Reality Modeling Language (VRML) was used to make real-time customization and motion simulation based on the wheelchair 3D Pre/E model. The change of part color and the replacement of wheelchair components can be realized through the operation custom console. By using this method, the omni-directional movements such as longitudinal, lateral, and rotary motion can be emulated via the simulation panel. In this way, clients can participate in the design and get a wheelchair according to their individual requirements, which will give them a deeper and more impressive feeling about the wheelchair's special motion functions.

Abstract:In order to realize the dynamic remote monitoring of the environmental system, a Zigbee-based wireless sensor network monitoring system is designed. The Zigbee wireless data transmission terminal module realizes the interface protocol of different sensors through the built-in single-chip microcomputer system, and reads, encodes, and transmits the sensor data in real-time; the coordinator in the system realizes receiving, decoding, and verifying the data packet. The correct data is forwarded to the server; the ZStack protocol is introduced in the wireless sensor network, thereby realizing the dynamic addition and deletion of the wireless terminal and the coordinator node; the monitoring terminal is divided into a desktop and a mobile terminal, and the remote real-time monitoring of the environment system is realized by visiting the data stored in the server through the wireless network.

Abstract:Existing software quality assessment models mainly focus on the basic quality characteristics of software systems, and ignore characteristics of customer value and developer organization. Therefore, these models can not evaluate the quality of software systems comprehensively and scientifically. This study characterizes the complex dependence relationships among generalized quality variables by Bayesian network, and constructs a more targeted quantitative model for software quality evaluation. The application shows that the model can comprehensively assess the generalized quality characteristics, make a reasonable evaluation of software quality, and find out the key factors affecting software quality based on the reverse reasoning function of Bayesian network.

Abstract:Aiming at the problem of quantitative decoding performance of high-density parity-check codes, this study proposes a quantitative min-sum decoding approach based on deep learning, referenced as QMSND. In order to improve the decoding performance and efficiency, the proposed decoder can adjust the weight parameters of a Tanner graph dynamically, and quantize the input vector and the message of nodes at every iteration in nonuniform fashion via deep neural network. Computer simulation results show that the performance of proposed QMSND decoding with 8-bits presentation is very close to that of the float neural min-sum decoding without quantization. Therefore, the proposed decoding approach is easy to implement by hardware and has some practicability.