In order to mitigate traffic congestions caused by the rapidly increased private car ownership in Shanghai, the transportation agencies implemented several strategies, such as narrowed the lane width to create additional lanes. To investigate the relationship of the lane width to speed, two month of...

Airport screening process takes too long time and people take more attention to this phenomenon and hope it to be solved. In this paper, we propose virtual queuing model in order to minimize the average waiting time, minimum waiting time variance and to ensure the airline's maximum revenue. By establishing...

In this paper, we use the known template to calibrate the parameters of the two-dimensional CT system. The calibration of CT system includes three aspects: the location of the center of the system in the square pallet, the distance between the detector units, and the 180 directions of the X-ray used...

Based on the advanced experience at home and abroad, this paper discusses the bottleneck identification method of airport security inspection process with airport security process as the research object. Firstly, we use MATLAB to establish a simulation model and introduce the number of passenger, the...

In this paper, we construct an evaluation metric of sustainable development called ‘Smart Growth Score’ (SGS) combining with the 3E’s and the ten principles of smart growth. This provides a clearer description of how successful a city develops smartly. We build a scoring model called “Smart Growth Score”...

According to the work characteristics of Nano-satellite constellation, this paper studies the configuration of it and the static routing algorithm of it. Firstly, the coverage rates of different constellation configuration are given and the constellation configuration with the best coverage is confirmed....

Flight safety is important for the development of general aviation; this paper first analyzed the main accident types of general aviation, obtained various factors that cause general aviation flight accidents, regression analysis method was used to analyze factors data, prevention strategies of general...

We herein try to improve the human-machine interaction of military vehicles, which need the evaluation model of designing user interface (UI). Current evaluation of UI depended on the measured data of a large number of users, which were time-consuming as well as lacking quantitative evaluation. And there...

A multiple input multiple output (MIMO) system provides multiple independent transmission channels, thus, under certain conditions, leading to a channel capacity that increases linearly with the number of antennas. Orthogonal frequency division multiplexing (OFDM) is known as an effective technique for...

The concept of bipolar possibility fuzzy soft sets is proposed and some basic operations on them are defined such as complement, extended union, extended intersection, restricted union, restricted intersection, "AND","OR". Then their properties are investigated . An application of bipolar possibility...

Non-rigid 3D shape retrieval and descriptors has become an active and important research topic in content-based 3D object . The aim of this paper is to compare and sythesize the performance of methods for non-rigid 3D shape retrieval and descriptors.This paper reviews the application of non-rigid three-dimensional...

Multi-modal medical image fusion has been emerging as a new and promising research area due to the increasing demands in clinical application. A novel fusion rule for medical brain image fusion is proposed in this paper based on the Nonsubsampled Shearlets Transform (NSST). The functional image is converted...

Aiming at the problem that the sequence data can’t be fused with the interval data in the database directly, the sequence-interval asynchronous data recognition algorithm based on interval association degree was proposed. First of all, reduce the dimension of the sequence data, use the maximum and minimum...

Automatic network topology drawing technology has been studied by many scholars, including straight-line layout and orthogonal layout. There are lots of toolkits to do this task, such as GraphViz and OGDF (The Open Graph Drawing Framework). However, the automatic layout results for some drawings are...

The security robot realizes the detection of the elevator contour and key by the machine vision algorithm, and realizes the control of the elevator door with the manipulator, so as to realize the independent elevator. On the same floor, it achieves the best path and then cruises through path planning,...

In recent years, the breakthrough of deep learning in the field of artificial intelligence algorithms has triggered an academic upsurge which attracted more and more researchers. As a multi-layer perceptron, the key to its success lies in the local link and weight-sharing method. On the one hand, it...

The huge size of network and diversified business characteristics make network traffic difficult to predict and manage. Network measurement is an effective way which can ensure QoS (Quality of Service) and network optimization. However, due to the differences in the implementation rules of equipment...

This paper introduces and inherit the multi-level trusted system model that solves the Trojan virus by encrypting the privacy of user data, and achieve the principle: "not to read the high priority hierarchy, not to write the hierarchy with low priority”. Thus ensuring that the low-priority data privacy...

Accurate forecasting of short term wind speed has been widely applied in the disaster early warning of civil engineering. Considering the characteristics of non-stationary and nonlinear of wind speed, the actual wind speed time series need to be decomposed first and then predicted. In this paper, a set...

For the problems of excessive centralization in information flowing, low performance in business extension, and being difficult to guard against the risk of the bill market in the traditional warehouse receipt trading system, this paper proposes a warehouse receipt trading platform based on block chain...

In recent years, frequent traffic accidents, traffic accidents captured countless people's lives, so the road safety problem attracts more and more attention of common people. This paper studies the problem of automatic recognition of road condition, the purpose is to improve the traffic information...

By using block chain technology, bitcoin has realized a real de centralization and point to point digital currency system, which effectively solved the problems of "double payment" and "curbing inflation". Bitcoin has the value and function of money, therefore, in practical application, we need to consider...

ETL is Extract-Transform-Load, which cleans, transforms, and integrates data according to uniform rules. At present, most of the methods for constructing ETL transformation function adopt a graphical representation method and lack precise semantic representation, which cause the computer to not automatically...

This article describes a method for manually calibrating KINECT color and depth cameras using a semi-transparent checkerboard, and at the same time, the two images can be modeled by 3D projection. A detailed comparison of the resulting images and data is given for the specific experimental procedure...

In end to end speech recognition,the linguistic knowledge such as pronunciation 1exicon is not essential??,and therefore the performance of the ASR systems based on CTC is weaker than that of the baseline．Aiming at this problem，a strategy combining the existing linguistic knowledge and the acoustic modeling...

In view of the large number of scattered and unstructured data problems in the process of comprehensive informatization in higher education, the article proposes to build a cloud storage platform to provide users with private cloud storage with high capacity and high reliability, and to exert aggregate...

Fraud detection is one of the biggest challenges facing the telecommunication industry now and in the future，The fight against fraud and anti-fraud has also reached a new stage. Finding a time-sensitive fraud detection method is an important way for operators to solve this problem. In this article, To...

Recommender system is a very important tool to help customers make choices more easily in a large variety of offered products. However, it is difficult to make directly use of the recommender system to provide suggestion for the traditional books in a library because of the shortage of the explicit feedback,...

The on-demand use and the elastic scaling feature of cloud computing make more and more companies deploy web applications on cloud platforms. True elasticity and cost-effectiveness in the pay-per-use cloud business model, however, have not yet been achieved. To address this challenge, we propose an algorithm...

Visual tracking is a hot topic in the field of computer vision, this paper firstly describes the classification and application of visual tracking, and highlights the advantages of object tracking based on infrared image by simple comparison. Combined with the research of this technology, tracking technology...

This paper introduces the basic concept and basic structure of the Reverberation Chamber, as well as its development process. Present situation of the theoretical research and application research on Reverberation Chamber are also introduced. It is emphasized that the Reverberation Chamber has inherent...

Considering the new air combat scenario involving manned/unmanned aerial vehicle cooperative combat formation, a simulation of air-to-air missile launch envelope based on cooperative air combat of manned/unmanned formation is built to resolve the new problem of cooperative air combat. Based on the mechanism...

With the development of electronic periodicals, it is unavoidable that there are some classification management problems. But currently the classification management of papers basically majors in manual classification. Based on Chinese medical literature, this essay compares and analyzes these automatic...

In order to further improve the effectiveness and accuracy of intrusion detection and avoid the security risks brought by network attacks, this paper proposes an intrusion detection strategy based on improved fireworks algorithms??"TFWA-SVM. This algorithm first optimizes the fireworks algorithm, constrains...

In order to improve the efficiency of association rules mining frequent itemsets, some people proposed using hashing techniques to mine association rules, it can greatly improve the time and space efficiency of frequent item sets. the space-time efficiency of the classical Apriori algorithm and the use...

With the rapid development of Synchronous Digital Hierarchy (SDH) technology, it has been more and more widely used in power communication networks. The power communication network has high requirements on the reliability of data transmission, and the self-healing ring has the advantages of automatic...

Influence maximization is an important research focus in our social network. It mainly aims at searching the most influential user node quickly and accurately in the social network. Most studies are based on the quantity of the influenced parties rather than the influence propagation scope in traditional...

Due to the strong mobility of nodes, the possibility and randomness of network holes were increasing in UAV network, and the limited energy-carrying capacity of nodes leads to the limitation of cruising ability. The general geographic assistant routing protocols often failed to satisfy demand in the...

In this work we experimentally demonstrate record 579.5km commercial unrepeatered 2.5G transmission, with the first application of 2.5Gb/s polarization multiplexed quadrature phase shift keyed (PM-QPSK) format combined with a coherent receiver. Such ultra-long haul is enabled by use of Forward Error...

Ceph is a unique unified system that supports object storage, block storage, and file storage with the characteristic of high available, manageable, and free. To build a distributed storage system based on Ceph in a private cloud environment with a high level of data privacy, it can support object storage,...

With the improvement of living standard, riding comfort has become an important indicator of choosing a car, but the noise in the car is the key factor affecting the ride comfort. The traditional passive noise reduction technology has a good inhibitory effect on high frequency noise, but the effect of...

This article focuses on the application of AP algorithms in active noise control systems. The active noise control system is a real-time tracking noise signal, which is then cancelled with an opposite signal to achieve noise reduction. Therefore, the active noise control system requires high real-time...

In order to achieve a good noise reduction effect in a closed space, an active noise control system was built. Hybrid control systems have faster convergence and better stability than feedforward control systems and feedback control systems. We will study feedforward, feedback and hybrid control systems....

This paper studies the classification of gastrointestinal stromal tumor (GIST) with machine learning and radiomics methods. The highlight of the paper is that combining features extracted from computed tomography (CT) images by radiomics and convolutional neural networks (CNNs) are used in classification...

This paper proposes a non-equal width multi-channel loudness compensation algorithm for digital hearing aids. This method achieves a non-equal width multi-channel loudness compensation scheme based on the sensitivity of the human ear to the frequency and the perception of sound intensity. First, the...

Based on the security threats faced by mobile intelligent terminals in the Internet of Things, this paper proposes a trusted enhancement framework for Android mobile intelligent terminals based on the SD card trusted module. A trustworthy computing environment including Trusted Security Management Center...

In this paper, we propose a reconfigurable architecture that supports various convolutional neural networks (CNNs) such as GoogLeNet and AlexNet. The proposed architecture mainly includes 24 parallel PEs (processing engines) for image data convolution processing, each engine containing 9x4 MAC (multiplier-accumulator)...

With the development of society, people's living standards improve, on the side of entertainment have become increasingly demanding, musical fountain as a highly ornamental recreational facilities, increasing the public's favorite subject. According to the current development of musical fountain, this...

Different from common texts, microblog texts have large amount of emotions and net-words. Its words and sentences expression are more colloquial and network popular, so traditional sentiment dictionary does not suit for the context of modern microblog short texts. This article puts forward an approach...

In the process of fuzzy soft set multi-attribute decision making, and It is difficult to determine the weight of the attribute parameters which results in low efficiency of decision making. Therefore, a new method of determining the entropy weight which is calculated by the notion of the importance degree...

In the global navigation satellite system (GNSS), communication between ground monitoring stations and master control stations can be easily disturbed by the multi-access interference (MAI). This paper proposes a Kalan filtering multiuser detector method to anti MAI that can improve receiver bit error...

To improve registration performance of machine vision under complex environment, an improved RANSAC rapid point cloud registration algorithm is presented upon the principle of cross ratio invariability for internal feature points of a registered target. By analyzing the model of a registered target,...

In order to adapt to the huge impact and influence brought by the mobile networks as well as the Internet to the university newspaper, it is imperative to implement an intelligent, digitalized school newspaper management system. Based on mobile devices, the hierarchical structure of the program was designed...

According to the increasingly serious network security problems, a complete set of internal network penetration testing method is proposed for the Windows operating system, and the key resources of the intranet are taken as the center, and a concrete solution to the protection is put forward. Finally,...

In this paper, a model is established to research the energy profile in the four states. The mainly work is the analysis on energy profile. After deleting the redundant data in the given table and supplying the missing data, we divide energy into several categories. Then, we take the sustainable energy...

To improve the accuracy and robustness of human action recognition, a kind of human action recognition algorithm based on the weighing bad-of-word model was put forward. The features extracted from video sequences through existing algorithms contained HOG feature, HOF feature, and MBH feature, and relevant...

Nowadays, there is a huge amount of webpage information on the Internet, which quality is uneven, and the Internet is full of all kinds of information that is hard to distinguish. In order to solve the credibility problem of agricultural web information, this paper proposes a model to establish the relationship...

The growth of urban intelligence relies on the deep integration of economic prosperity, environmental sustainability and social equity, so the establishment of a rational urban intelligence evaluation model has far-reaching impact on the development of a city. This paper evaluates the development of...

In this paper, we propose a method based on Bidirectional LSTM-CRF for article title summarization. And for the summary generated by the model is not compliant with the grammar rules problem, we use POS (Part of Speech) to revise the generated summary. In order to verity our method, we conducted an experiment...

Since Geoffrey Hinton first proposed the concept of deep learning in 2006, which in Reducing the dimensionality of data with neural networks, deep learning has been the continuous concern of the researchers. Deep learning uses a multi-layer neural network to simulate the multi-layer abstract learning...

In this paper, a filter of order five with enhanced stopband performance using mixed mode resonators is designed. Using different resonating mode resonators is to obtain different harmonic frequencies so that harmonics of the designed filter could be suppressed while keeping the same dominant frequency...

Recently, distributed stream computing has emerged as a popular model for real-time data stream analytics. This paper focuses on computing resources scheduling of distributed stream processing. To adapt to the fluctuation of data stream, distributed stream processing system must elastically provision...

In this paper, we present a method to extract features of dynamic gestures and use the Hierarchical Extreme Learning Machine (H-ELM) for gesture recognition. We use a Kinect sensor to record the motion of the three joint points of palm, wrist and elbow. The relation among the three trajectories is extracted...

Short text comprehension summary generation is currently a hot issue. In this paper, we improve the attention mechanism under the framework of encoder-decoder and proposes a comprehensible short text abstract generation model that integrates the global and local semantic information. The model consists...

This paper proposes a fast deformation part model (DPM) with neural network (FDPDPM) for face detection. It can make fully use of the advantage of high level feature and classifier with spatial location information. In fact, this paper uses a truncated the variant of VVGNET and a pyramid of multi-scale...

Short text information is less, and short text comprehension abstract generation is currently a hot and difficult issue. We proposed an understanding-based short text summary generation model that combines multi-level semantic information. We improved the structure of encoder in the framework of encoder-decoder...

For the image inpainting using incomplete Chinese characters proposed a new method for Chinese characters repair, the first use of U-Net type network structure combining the training method of generating against network design a style Chinese characters converter, and then repair the missing content...

In this paper we consider the image deploring problem with space invariant PSFs under anti-reflecting boundary conditions. Under the assumption that PSFs are strongly symmetric and boundary values of image are homogeneous, the image deploring problem is transformed to the circular DE convolution problem...

With the development of semantic Internet of Things, there are many smart applications and services springing up in different domains. However, the gap between semantic representations and various sensor data formats used in IoT devices raises doubts and challenges for us. This paper aims to convert...

Hashing have has been successfully applied to different methods regarding a wide range of problems. It is fairly very effective for large-scale image retrieval in reducing the processing time. Although a number of hashing methods have been developed in recent years. Most of them the methods are based...

In order to ensure the stability in financial markets and the position in international financial market game of China, this paper uses the method of artificial intelligence to research and forecast the interbank interest rates of banking industry, which is from the time dimension of the day wave. According...

Universal Serial Bus (USB) is a personal computer interconnection protocol, developed to make the connection of peripheral devices to a computer easier and more efficient. USB has become the dominant standard for plug-and-play connections between personal computers and peripherals. USB connectivity has...

Due to the lack of readers’ rating data, university library recommender system is facing the problem of sparsity of data. This study proposes a general logarithmic transformation model which can convert the reader’s implicit feedback data to the rating, thus alleviating the sparsity to a certain extent....

Image segmentation is one of the classic methods of image signal processing. It is widely used in the scientific research, biomedical engineering, military guidance and so on. Based on the region extraction, this paper introduces three typical image segmentation methods: region growth algorithm, watershed...

To improve the efficiency of classroom attendance check, a college attendance platform based on Bluetooth technology and Android platform is put forward to quickly check the attendance at classroom by scanning the Bluetooth address of students’ mobile phones. The teacher may check the attendance manually...

According to the characteristics of equipment support activities, this paper puts forward the idea of equipment support data requirements modeling, which is "activity-oriented and process-oriented". Firstly, the relationship between equipment support tasks, functions and activities is analyzed. Based...

In the real scene, the target itself and the background will be unpredictable changes, such as the occlusion and other factors will bring greater challenges to the object tracking. In this paper, we proposed a method that handle the occlusion based on Kernel Correlation Filters (KCFFR, KCF with forward...

With the continuous development of machine vision, intelligent detection of bottom spray glue has gradually become a reality. In this paper, we proposed an algorithm of detection the glue spray on bottom of vehicle based on machine vision. By sampling and detecting the spray interest area, the algorithm...

In solving the problem of feature weight calculation for automatic text classification, we use the most widely used TF-IDF algorithm. Although the algorithm is widely used, there is a problem that the feature categories have different weights when calculating the weights. This paper proposes an improved...

In this paper, the vehicle audio encryption system based on scrambling thought and applied to vehicle-mounted media is proposed. The pseudo random number is generated each time it is encrypted, and it is substituted into the Fibonacci transform to generate a key with variable length. The audio data is...

A de-nosing approach is needed to eliminate the maternal heart sound and internal noise in the acquired fetal heart sound signal, but blind separation algorithm, as a conventional approach, does not perform well in the de-noising of fetal heart sound. Hence, a new fetal heart sound de-noising approach...

Reviewing the shortcomings of plant classification methods in recent years. The advantages of convolutional neural networks in image classification are briefly described. In order to classify plants simply and efficiently, a plant recognition method based on convolutional neural network was proposed....

The traditional image retrieval adopts a text-based method, which requires a lot of manual annotation of the images in the image library and matches according to the keywords when searching. Already not suitable for the modern image network retrieval, this paper proposes a network model based on the...

Merkle tree has been widely applied in the field of P2P transmission. In this paper, an efficient authentication scheme is proposed in the integrity check module for vehicle live video streaming system by optimizing the construction and verification of the Merkle tree. It can create and check nodes at...

The aim of this study is to improve the imbalance pricing problems of Self-service package platform based on mobile Internet. The primary emphasis in this paper is on improving the completion of the to-do task. Based on the pricing established by factor analysis and regression equation, the author adopts...

For the realization of the real-time collection, upload, visualization and intelligent management of air quality data, mobile management system of gas sampling was designed based on the technologies including Web GIS, ZigBee wireless sensor network, the 4G (4th generation) communication system and so...

With the continuous development of Internet technology, how to deal with and analyze a large number of data has become a hot spot. The mail system generates a large number of logs every day, and the traditional technology is not efficient in handling huge log data and is unable to make use of the information...

Embedded systems often use a number of multitasking operations and controls, these systems must have a mechanism to ensure the implementation of the current task, so that it has no effect on other tasks, that is, to prevent the system's resources and tasks are accessed illegally. There are usually two...

In this paper, we derive one of Shannon's theorems, the maximum capacity theorem of noisy channels :. The derivation of noisy continuous channel capacity is based on the derivation of discrete channels and most of the conclusions are a limit discretization of the corresponding theorems of discrete channels....

Aiming at the low accuracy of vehicle image retrieval algorithm based on deep learning, an improved vehicle image classification retrieval model based on convolutional neural network is proposed. According to the complexity of the car image, using convolution neural network to extract the image features...

This paper presents a method for the identification and classification of medical data of hepatic pathological changes by using SVM FNN and KNN. The liver lesion classifier is a neural network model trained by experts’ hand-divided samples and cross-validated to optimize the results. It can achieve better...

With the progress of science, the traditional image retrieval technology no longer applies in terms of accuracy and retrieval speed. The emergence of big data and GPU has laid a solid foundation for the development of deep learning. However, the emergence of big data also means that the data is noisy...

This paper mainly proposed to identify and classify the medical data of cervical cancer using neural network models such as SVM, FNN, KNN and so on. The computer recognition algorithm can overcome the deficiency that artificial identification tends to be affected by cognitive ability, subjective experience...

Based on the introduction of the traditional feature weighting algorithm TF-IDF, based on the phenomenon that the eigenvalue extraction is not effective when the text to be classified is not uniform, an improved TF-IDF algorithm is proposed in this paper, which considers the uneven text distribution...

Aiming at the application of a class of image encryption algorithm based on chaotic system, a chaotic image encryption algorithm based on Kent mapping and AES (Advanced Encryption Standard) encryption algorithm is proposed. Firstly, an initial condition is defined and a parameter related to plaintext...

High frequency (HF) propagation can achieve long distance, low cost communications and it is one of the most important communication methods. The focus of this research is to develop an appropriate mathematical model for HF radio waves to communicate efficiently over various surface of the earth. First...

This paper based on agricultural information with timeliness, regional and other complex factors, proposed a method based on the features of agricultural webpage information to classify the credibility of agricultural webpage information. By constructing the model of the relationship between the features...

This article briefly introduced the origin and development of distributed database, HBase in detail the load balancing problem and the original load balancing algorithm. The original load balancing algorithm considers only the space usage load of each node in the cluster, does not consider the hot spot...

In recent years, the world has witnessed massive growth in the field of information technology and intelligent device, giving rise to exponentially expansion of internet websites in terms of quantity as well as complexity. Meanwhile, the public has also enlarged demand for characteristic analysis of...

By analyzing the current image encryption algorithm based on a class of artificial neural network in recent years, this paper proposes a new hyperchaotic image encryption algorithm based on 4D of Hopfield-type neural network and AES(Advanced Encryption Standard) encryption algorithm, First, defines four...