On high frequencies (HF, defined to be 3-30 MHz), radio waves can travel long distances by multiple reflections off the ionosphere and off the earth. The focus of this research is to develop an appropriate mathematical model for HF radio waves which a ship travelling across the ocean will use for communications...

In this paper, the food inventory-distribution integrated optimization problem on a two-echelon logistics system composed of a single distribution center and many sales points is studied under the conditions of VMI strategy and determinate demand. Considering both inventory cost and distribution cost...

With the rapid development of public bicycle systems, It has taken only half a century since the development of the first generation of bicycles in the Netherlands to the fourth generation of bicycle sharing systems supported by information technology. By combing relevant literatures on public bicycle...

Based on the application of computer image recognition technology in university campus monitoring, to automatically realize the intelligent management of university by image recognition technology, this scheme could be used in the practical application of campus situation monitoring, face recognition,...

At present, online education is being accepted by every subject in the world. Online education technology is gradually changing the traditional classroom teaching methods. For those, who stop learning, they can use the online learning technology to learn autonomously under any conditions. Today, there...

In order to achieve state-based maintenance of the equipment maintenance support system, this paper proposes to build an equipment maintenance support information system based on networked and knowledgeable technologies. The establishment of equipment maintenance support information system needs to address...

In view of the problems of network time synchronization, transmission delay and large jitter in the smart substation communication system, the multiplexing mode of communication network in smart substation is studied and the WDM network architecture mode is proposed. A new generation of smart substation...

As an important descriptive data mining method, association rules based on apriori algorithm have been widely used in the discovery of the core prescriptions of traditional Chinese medicine, and the correlations between symptoms and syndromes, syndromes and modern examination results, and symptoms and...

For enterprises, restricted by various factors, tacit knowledge cannot be effectively explicit and utilized in enterprises, which is a great waste of knowledge. Therefore, extracting the characteristics of tacit knowledge and constructing corresponding enterprise tacit knowledge database can facilitate...

For non-linear and non-stationary signals, traditional signal processing methods cannot effectively capture their characteristics. For this purpose, time-frequency analysis algorithms are needed to analyze the frequency domain characteristics of the signal at different times. The traditional Empirical...

In this paper, a text fragment splicing method based on K-means and Empire competition algorithm is proposed. First, use K-means clustering to find out a piece of paper that belongs to one line; Then, define the edge distance of the paper, and establish a combined optimization model; using the imperial...

This paper aims to extract traffic rule at intersection from floating car data, traffic rule is the logical connectivity data in road network. Firstly, based on intersection data model, the geometric characteristics of intersection are presented, and the angle of arcs is calculated to get the traffic...

As a new and emerging intelligent algorithm, although young, but the particle swarm algorithm has a very important role in the development of modern society, so we can do nothing without it, its emergence in the academic community caused Depressed big wave. In this article, we try to give its principle,...

The investigation of fake plate vehicles mainly relies on the traffic police verifications and public tip-offs. It is inefficient and produces very little effect. Based on above analysis, a method of recognition for fake plate vehicles is proposed which to investigate the fake plate vehicles effectively,...

The main research content of this topic is the automatic testing framework of lottery games. The research and design of the two test frameworks, data-driven and game-rule-driven, respectively, analyzes and studies the editing, storage and processing of test data. At the same time, the testing framework...

This paper analyzes the content of the cold chain logistics network optimization of fresh agricultural products in large supermarket chain and constructs an optimization model based on double layer programming. The upper model is the total cost optimization model of the cold chain logistics network,...

The main navigation method of Civilian Unmanned Aerial Vehicle (CUAV) is Global Positioning System (GPS) navigation, GPS navigation failure will make CUAV lost control, resulting in heavy losses. How to ensure the reliability and navigation precision of CUAV under the failure of GPS is a hot issue currently...

The deep learning-based speech enhancement has shown considerable success. However, it still suffers performance degradation under mismatch conditions. In this paper, an adaptation method is proposed to improve the performance under noise mismatch conditions. Firstly, we advise a noise aware training...

Malicious phishing stations, which disguise as legitimate devices through MAC address forgery, constitute a lot of Wireless Local Area Network (WLAN) security threats, such as secret information theft, implantation of Trojans and backdoors, etc. In this paper, a passive method based on wireless fingerprinting...

In view of the problem that the slow manual approval of loans and traditional classification algorithms have low recognition rate for a few sample classes, an integrated learning classification model based on PSO optimization support vector machines is proposed. Particle swarm optimization (PSO) is used...

This paper proposed to develop an auxiliary software system for recognizing the medical data of hepatic pathological changes based on the deep learning of medical data identification technology.Built under the idea of personal demands and self-service platform, the system is supported by artificial intelligence,...

Social tag recommendation system provides the information sharing platform for users, allowing users to "tag" for the browsing of the items marked information. Tags both describe the semantics of the item and reflect the user's preferences. However, existing tag recommendation systems face the problem...

VCPS (Vehicular Cyber Physical System) effectively improves road safety and improves driver's driving environment. However, due to the large scale of the VANET network, the predictability of the trajectory, and the open nature of the wireless channel, it is more vulnerable to privacy and security threats....

This paper studies a new distributed multi-agent rendezvous problem based on state backtracking. It uses the historical state information of the agent as a reference for the current time to achieve the purpose of preserving topology connectivity and accelerating the rendezvous speed. The agent uses different...

In industry 4.0, CPS will play a huge role in the industrial production and supply management [1-3]. CPS makes the industrial system more intelligent, making the subsequent salesbusinesses more data-oriented and intelligent. However, the industry environment produces large of data during the production...

Because the system under test contains multiple subsystem interactions, the correctness and consistency of the interface return between the subsystems plays an important role in the entire process. It is very important to ensure the quality of the interface testing. However, there are many types of interfaces...

Weibo emotion recognition is one of the main tasks of the study of social public opinion. BI-LSTM, as a derivative model of RNN,has been widely used in the task of text emotion analysis. However,existing models do not make good use of prior information sun as emotion words and emoji, and we always capture...

This paper proposes an image super-resolution algorithm based on the condition of Wasserstein distance generation against network, aiming at improving the quality of reconstructed images and improving the condition against the stability of neural network in image super-resolution research. Wasserstein...

Flight management system is an important part of avionics system. Traditionally, the schedulability analysis of this system was carried out after the design of the system was completed and in the stage of implementation and verification, this made the system unable to accurately analyze the hardware...

The CPS system senses and recognizes the physical world through numerous node devices and processes the collected data accordingly, then it can achieve the interconnection of the physical world and the virtual network world. However, under the existing conditions, the CPS system has not yet realized...

Reinforcement learning algorithm for solving robotic locomotion control problem has achieved great progress. Use a Gaussian distribution to represent the locomotion policy of the robot is a general way. A locomotion policy means the distribution of action output. However, in real-world control problems,...

Collaborative filtering recommendation algorithm based on KNN neighbor selection does not consider the blind follower of neighbors when selecting neighbors, which causes some neighbor users to play a minor role in predicting the target user's scoring of unknown items. In response to this problem, a contribution...

A distinctive data hiding method based on Jigsaw Sudoku is proposed in this paper. Different from other methods, the proposed method is based on Jigsaw Sudoku which is a kind of irregularly shaped Sudoku. Due to the novelty of Jigsaw Sudoku, the proposed method can provide a safer scheme for data hiding...

Using WSNs (Wireless Sensor Networks) and Internet to realize the unification addressing, collection of big data era need huge amounts of information and establish a wider range of universality to reduce differences design complexity is the IoT (Internet of Things) development of new ideas in recent...

Recently, model-free reinforcement learning algorithms such as TRPO for solving locomotion control tasks has achieved great success. But for difficult locomotion problem with high dimensional visual observation, these algorithms are not sample efficient. This paper proposes an OU process sampling strategy...

To reduce the cost of crowd density monitoring in indoor space, facilitate supervisors to monitor crowd density in indoor space at any time. The article uses the characteristics of indoor temperature and humidity changes with the number of changes and combines WeChat Public Platform and design this indoor...

With the development of global satellite navigation systems, the design of multi-mode navigation receivers based on software radio has become a research hotspot in the entire navigation system. The design of a Beidou/GPS dual-mode receiver based on the MAX2769B is introduced. The architecture of the...

Deep learning is emerging as a multilayer neural network dimensionality reduction algorithm, the neural network model with multiple deep hidden layer through the formation of the high dimensional data of input layer feature extraction, to find a low dimensional nested data structure, the formation of...

Aiming at the problem of Q value update is slow and easy to produce dimension disaster for Q learning algorithm in complex unknown environment, A path planning algorithm for opposite Q learning robot based on virtual sub targets in unknown environment is proposed .The algorithm is according to the state...

In this paper, our proposed scheme using two steganography images. Unlike other data hiding schemes, this scheme studies the characteristics of the Tangram puzzle model and the secret message bytes that make up the eight binary bits that are hidden into the two graphs. Key matrix M *, horizontal and...

The study of music recommendation research was conducted and the corresponding research hotspots were proposed. The literature analysis method was used to briefly introduce the recommendation strategy from the perspective of the recommendation algorithm. It further proposes a method of using rough set...

The method of fundamental solution (MFS) has been known as an effective and simple boundary meshless algorithm. However, the MFS generates dense coefficient matrix and thus requires a lot of computation time for solving large-scale problems by using direct solvers in a personal computer. The generalized...

Nowadays, through the online health care community platform, users can raise health related questions and doctors would provide corresponding answers. However, some answers could be low-quality and repeated. In this paper, we aim to evaluate and predict the quality of the answers in online health care...

In the past ten years, convolutional neural networks have achieved a series of breakthrough developments in the areas of classification detection, pattern recognition, and semantic segmentation. Convolutional neural network learning have led to a wide range of applications and research for its capabilities...

The Cyber Physical System, as an emerging product of embedded systems, sensor networks, and wireless networks, has received extensive attention from domestic and foreign scholars. Lots of Cyber Physical System have emerged, such as medical CPS and energy CPS. And so on, VCPS is one of the applications....

To Propose a recognition algorithm combines the feature of cascade of HOG/HOF with the multi-layer classifier. By extracting the foreground region of the video sequence and extracting the HOG feature and the HOF feature to makes up the HOG/HOF cascade feature. Then making all the HOG/HOF cascade features...

For terahertz image with low signal-to-noise ratio, serious blur and poor resolution, this paper uses the mean filter to denoise the terahertz image, and then uses Faster RCNN algorithm to detect and identify the dangerous goods in the terahertz image. Different from traditional algorithms, Faster RCNN...

The Modern industrial devices are becoming more and more complicated and the data generated by industrial processes are increasing. It has become increasingly difficult to establish accurate mathematical models for fault diagnosis. In view of this situation, data-driven fault diagnosis methods have attracted...

The study of video-based emotion recognition is still a difficult and hot research issue in the area of computer vision and human-computer interaction. How to effectively extract key frames from videos, construct spatiotemporal feature space of videos, and build model based on the mapping relationship...

Nowadays, distributed Stream calculating is a leading technology for analyzing and managing massive streaming data. When distributed Stream calculating system working, because of data volume and distribution in the input streams often change over time, the system may be overloaded. While overload can...

With the development of the blockchain technology, and applications of blockchain technologies more and more widely, we can apply the Blockchains to Industrial Control System(ICS) for network security. The key technology of blockchain include: distributed ledge, asymmetric cryptography, consensus algorithm...

In the ROS environment, study the D H modeling, trajectory planning algorithm and simulation of Youbot mechanical arm. In the ROS environment, with MoveIt!Tools, mechanical arm Yobot model based on D H parameter model, the calculation of the mechanical arm homogeneous transformation matrix, through simulation...

Various methods have been proposed in previous works to achieve effective printed Chinese character recognition. Feature extraction and production of large scale multi-font Chinese character remains a major challenge owing to the wide variety in the shape,layout,and grey-level distribution of single...

The emerging Cyber Physical Systems (CPSs) are a kind of novel intelligent complex systems that tightly integrated different scales of computation and physical components and interacted under the future network. A cloud computing environment offers a simplified, centralized platform or resources for...

In view of the cost of traditional design of new fonts, a method of combining deep learning for font style conversion is proposed. By using a U-Net type network structure combining the training method of generative adversarial network, supervised learning part of fonts, the font style conversion ability...

Mobile payment is a very important service in this age of the Internet, but threats from a safety perspective are very serious. Based on the uniqueness of the mobile payment, establishes a hierarchy appraisal target system by improving the AHP method. To better determine the weight that affects the safety...

Accurate fetal heart rate detection is the main task for fetal heart rate monitoring. To improve accuracy of fetal heart rate estimation, filtering processing would be taken for the collected fetal heart sound signals and then processed fetal heart sound signals would undergo time-frequency analysis...

This paper brings forward an experiment design for IPv6 routing&forwarding which based on the special IETF ForCES technology, with the goal of more flexible using of IP routing&switch theory, better acquainted about inner architecture of network device, more familiar with the new technology of network...

This paper studies a distributed multi-agent rendezvous problem that preserves topology connectivity. Based on the constraint function, the agent's own and its neighbor's current time and last time's condition are used as conditions to judge the agent's movement trend and connectivity quality in the...

Ant Colony Optimization(ACO) is an intelligence-optimized algorithm Which can solve a large-scale task scheduling problem in cloud computing. However, the basic ant colony algorithm used in large scale task scheduling will easily lead to low distribution efficiency. To solve this problem, this paper...

This paper puts forward to the image super-resolution algorithm based on the resent. The algorithm makes use of the depth residual network to reconstruct the low rate image, and the super-resolution images obtained by the cycle are, judged by the convolution neural network. The residual learning is introduced...

The emerging Cyber Physical Systems (CPSs) are complex, muliti-disciplinary next generation engineered systems that integrate embedded computing technology into the physical phenomena by using transformation research approaches. A cloud computing environment offers a simplified, centralized platform...

This paper deals with the Unmanned Aerial Vehicle (UAV) Routing and Scheduling problem applied in logistics, with the implementation of Dynamic Mixed Integer Linear Programming (MILP) to tackle the problem. The MILP accounts for multiply constraints and objectives based on the demand of practicality...

With the rise of a new generation of information technology represented by cloud computing, big data, and artificial intelligence, the competition in global information technology field has become increasingly keen. In this new wave of technology, we have the opportunity to catch up from behind. The...

In this paper, a digitally controlled full-bridge LLC resonant converter based on DSP is designed. The frequency conversion control method is adopted to keep the output voltage constant and achieve the soft-switching of the switches. In this paper, the modes of operation of the full-bridge LLC resonant...

This paper presents a high gain wideband omnidirectional COCO antenna array. The antenna array operates at 1500MHz-2000MHz and can be used for mobile communication. The planar micro-strip array antenna is composed of seventeen trapezoidal micro-strip patch antennas with different sizes. By loading a...

Aiming at the problem of non-smooth contours (contour noises, scratches and jitters), it is easy to generate redundant branches. Based on EPTA algorithm, an improved parallel thinning algorithm is proposed. Through an iteration that eliminates the restrictions and proportional iterations, the pixels...

In this paper, the basic concept of the algorithm is introduced first. Then four basic design strategies commonly used in algorithm design are discussed. The divide-and-conquer strategy is the most commonly used strategy for designing effective algorithms. The dynamic programming algorithm is a method...

The main content of this paper is to implement a human action recognition method based on depth image and dense trajectories. Firstly, the binocular RGB camera is used to collect images, and then the depth image is obtained through stereo matching algorithm. We use depth images to extract human action...

In the rapid development of the Internet, the abuse of Over Loading has become increasingly prominent in the production and life. Facing these challenges, recommender systems emerge as the times require. This paper first introduces the classic collaborative filtering recommendation algorithm and introduces...

According to the demand of optimization design of UAV communication system, this article proposes a method of calculating the link loss of UAV data chain by studying the channel characteristics of UAV data link; establishes the path loss of UAV channel of UAV Model; analyzes the influence of frequency,...

As the communication would be interrupted by the airframe when the aircraft platform communicates with VHF over-the-horizon, the paper adopts the modeling method of computing geometry to conduct reducing-dimension modeling through coordinate transformation and rotation. Through simplifying the complicated...

Coastal radar tracking refers to the process of processing measured values from a target, maintaining the current state of the target, and associating them with the current and subsequent states of the target and performing smooth updating. With quick development of coastal and port vessel surveillance,...

In order to solve the problem of inflexible parameter settings in traditional dynamic channelization structure, a weighted overlap-add (WOLA) filter bank is proposed to implement dynamic channelization structure. The filter bank is deduced and emulated through MATLAB. The simulation results show that...

Particle swarm optimization has attracted the attention of researchers because of its outstanding performance in optimization problems. The Beetle Antennae search algorithm(BAS) is a newly proposed simple and efficient search algorithm. This paper combines it with the particle swarm optimization algorithm,...

This paper expounds the concept and status of data structure from how the computer solves the practical problems through program design, based on the analysis of the connection and difference between data structure and algorithm, the general principles followed by data structure are given, and further...

This paper describes the application of minimum spanning tree algorithm in process of stereo matching and optimization of depth map. A stereo matching method for the real-time application scene of binocular vision is proposed, which the stereo matching is completed under the sample of the image and reduced...

As an important application in the field of aviation, the flight Cyber-Physical System (CPS) can play a significant role in the safety and efficiency of the aviation industry. This article focuses on the six characteristics of CPS. Then the dynamic equation of the aircraft in the physical world is established...

The propulsion technology of high speed linear motor is a hot spot in the field of motor field in recent years. This technology has a wide application prospect. In this paper, based on the working principle of permanent magnet synchronous linear motor, a driver of permanent magnet synchronous linear...

Convolutional neural network (CNN) was a widely used algorithm for image classification in the field of computer vision. At present, in terms of identification of illegal web pages, the main application methods rely on manpower too much, which is a costly and time-consuming method. This paper will apply...

The deep reinforcement learning algorithm based on visual perception and intelligent decision combines the perception ability of convolutional neural network with the decision control ability of reinforcement learning via end-to-end learning style and realizes the process from raw visual input to decision...

In this paper, a hybrid constellation of both quadrature amplitude modulation/phase shift keying (QAM/PSK) and pulse amplitude modulation (PAM) aided index spatial modulation (ISM), which called ISM-Q/P scheme, is presented to exploit the potential spatial gain from both spatial domain of transmit antennas...

With the development of embedded technology, the application of embedded products is dazzling. Whether the system project can guarantee the completion of quality has become a problem to be solved at present. Due to the uncertainty and uniqueness of the embedded development process, how to assess the...

support vector machine (SVM) is developed based on statistical learning theory new method, its training algorithm is essentially a problem of solving the quadratic programming. This paper summarizes the basic principle of SVM, and then use SVM to stock prediction research status at home and abroad were...

This article reviews the discourse-based machine translation evaluation metrics. According to different methods of using, machine translation evaluation based on discourse is divided into two categories: evaluation based on discourse structure and evaluation based on discourse features. For these two...

Aiming at the problem that large-scale terrain loading in unity has large memory usage and the scene operation is not smooth enough, a terrain dynamic loading method suitable for Unity is designed. The ray collision detection method is used to detect the terrain block of the current viewpoint in real...

With the continuous development of China's economy and the rise of the Internet of Things technology, today's rising living standards, flower cultivation is increasingly favored by people. However, due to the acceleration of the pace of life, people are often dying because of their busy life and frequent...

Particles aggregation technology is a kind of effective method to strengthen the collection and removal of ultrafine particles. The flow field of the turbulence coalescence device was simulated by FLUENT, and the results showed that diaphragms in the turbulence coalescence device could produce vortices,...

Deep learning has made breakthrough progress in image recognition, target detection and tracking in recent years. It is proved too good at classification tasks. In this paper, we have compared use of Convolutional neural network(CNN), VGG16, Long Short-Term Memory (LSTM), and Bidirectional LSTM to perform...

As one of the key candidate technologies for 5G, the NOMA (Non-orthogonal Multiple Access Technology) employs the way of power domain reuse, which has improved the system throughput and frequency utilization effectively. Among the existing discussions about the NOMA system, it is mostly acknowledged...

One of the most important features of medium-and-low speed maglev train is the ability to turn the small curve. When the train is in the small curve, as each levitation electromagnet module is a rigid structure, which cannot bend and deform, the electromagnet module and the F-shaped rail dislocate from...

Since the reform and opening up, with the continuous development of the market economy and the advancement of science and technology, people have gradually strengthened the pursuit of the spiritual level while satisfying the material needs, and digital media have entered people's lives. The popularization...

In recent years, the issues of efficiency for civil aviation industry and how to increase the efficiency for civil aviation industry in china are very important. In macro aspect, this paper analyzes the empirical data of civil aviation industry in china from 2000 to 2016 based on DEA model; in micro...

In order to reconstruct low-resolution images into high-resolution images and compensate for the loss of information between high-resolution images and low-resolution images, this paper presents an effective super-resolution reconstruction optimization method, which analyzes the advantages and disadvantages...

The design of broadband beamformers can be formulated as a minimax problem such that the maximum error between the actual response function and a given desired response function in a specified domain is minimized. There is a transition region between the passband region and the stopband region, and the...

With the development of economic globalization, the rapid development of industries in various fields, big data technology has attracted more and more attention. Network data is constantly being generated at an unprecedented rate, and it is necessary to intelligently process huge data, and then to make...

There are many unsafe factors in the construction of coal mine, so it belongs to the high-risk industry. Therefore, it is necessary to refine the safety management of coal mine construction, and create a safe and stable production environment to reduce the occurrence of personal injury incidents. Safety...

Due to the rapid development of society and information technology, the traditional POI data collection methods can no longer meet the new requirements from users. Specifically, the data collection methods are costly, the data update speed is slow, and the attributes are not complete. Based on the geographic...

This paper, an improved recurrent neural network, long and short time memory model (LSTM) is used to estimate the SOC estimation of vehicle lithium ion battery, and the SOC estimation model of the battery based on LSTM network is established. Based on the electrochemical reaction of lithium ion batteries...

When the deep reinforcement learning algorithm based on visual perception is applied to the issue of robot’s dynamic obstacle avoidance, the perception ability of convolutional neural network is combined with the decision control ability of reinforcement learning, and the process from raw visual input...