Proceedings of the 4th International Conference on Information Technology and Management Innovation

Session: Artificial Intelligence and Intelligent Information Processing

71 articles
Proceedings Article

Integration Methodology for Smart City Design ——Application of CHORA’s Urban Gallery in the Case of the SSD-Project ,EU.

Zesong Wei, Georg Hubmann, Shicun Sun
Factor 4 improvements represent a critical leap forward in district planning and management in the future. SSD is an innovation project comes from EU,and helds workshop in Technology University of Berlin,Germany. It is an innovation plan helps us achieve Factor 4 improvements in a range of climate change...
Proceedings Article

EMF based Domain Specific Modeling for Distributed Simulation Systems: An Outline

Zhi Zhu, Haibing Li, Yonglin Lei, Yifan Zhu
The design and development of distributed simulation systems are a complex process, and the Domain Specific Modeling (DSM) methodology is progressively gaining popularity as it uses domain knowledge directly to specify systems in a higher level of abstraction. In this research plan an Eclipse Modeling...
Proceedings Article

A Study on Formation of Rural Architectural Space Image Based on the Physical Environment

Changyou Wu, Xiaojun Zhang, Yan Chen
Rural architectural space image presents in the physical environment such as spatial form, characteristics of modeling, material texture, color and functional layout. Combining the examples presented in the physical environment, this paper summarizes the formation modes of rural architectural space image,...
Proceedings Article

A Semantic Mapping Method based on Ontology Structure Graph

Chengzhu Sun, Weibin Chen, Bineng Zhong, Haibo Li
Efficient information sharing and exchanging are becoming increasingly important , but model heterogeneity hinder the communication and collaboration from different enterprises. To solve this problem, a semantic mapping method based on ontology structure graph is put forward in this paper. The requirement...
Proceedings Article

Upper Bound of Primitive Exponent of a Class of Nonnegative Matrix Pairs

Meijin Luo, Xi Li, Sun Tao
There is a one-to-one relationship between nonnegative matrix pairs and two-colored digraph. With the knowledge of graph theory, by studying the associated directed digraph of a class of special nonnegative matrix pairs, that is a class of two-colored digraphs whose uncolored digraph have vertices and...
Proceedings Article

Novel Model of Security Region of Metering Networks and Its Application in Meters’ Status Estimation

Feng Zhou, Yingying Cheng, Huayong Zhou, Ji Xiao
With a large number of smart meters installation and application, the power companies can get a variety of information such as meter metering device via a communication network. Considering the needs of grid state estimation for metering device, we propose a new security domain model network metering...
Proceedings Article

Research of FFT Improved Asynchronous Sample Arithmetic in Harmonic Component Detection

Xiaoling Yan, Liming Wang
Along with the diversification and complication development of electric equipment in warship, the harmonic pollution in power system is more and more seriously, and the harmonic detection technology increasingly turns into a very important subject. FFT arithmetic is an usual method to detect harmonic...
Proceedings Article

Application scope of prediction model for interval grey number based on GM (1, 1)

Lianming Zhao
Prediction models have some modeling conditions and application scope, we can use them to simulate or predict only when the models are satisfies those conditions. In this paper, we study the application scope of prediction model for interval grey number based on GM (1, 1) through the mathematical derivation....
Proceedings Article

Scheduling Model and Algorithm for Collaborative Product Design Based on MD

Xiaolei Wang, Meiliang He, Quan Xu
In order to improve the efficiency of collaborative product design, project task and team should be allocated and scheduled reasonably. Firstly, the matching degree between task and team was defined. Then, trading-off project duration and cost, multi-objective scheduling model of collaborative product...
Proceedings Article

Output Adjust Assignment Algorithms about Electric Power Unit Transmission Congestion

Huaren Zhou, Lili Wang
output, transmission power and direction of each line about a network with a plurality of generating units and a number of main lines depends on the power grid structure and each generation unit. we get the approximate expressions of the output of each generator. When the transmission congestion appear,...
Proceedings Article

Comparative analysis of carbon emissions quota calculation and allocation method for coal-fired power plant in China

Libao Yin, Xinxin Meng, Zhengyang Gao, Shuo Ji
With the rapid development of economic globalization and the improvement of people's living standards, and the impact of global warming gradually strengthened. The emissions and trading scheme of carbon dioxide has been widespread concern at home and abroad. The establishment of carbon emissions system...
Proceedings Article

Investment Risk Evaluation for Demand Side Management: Improved Bayesian Model

Changxin Yin, Ming Zeng, Xuefeng Ma, Lu Yin, Yang Lv, Bin Shu, Chunxue Li
The vigorous promotion of DSM is of great significance in improving energy conservation and power system reliability. At present, DSM technology of China has been developed, meanwhile, related projects will be carried out extensively. Therefore, investment risk evaluation for DSM projects of power enterprises...
Proceedings Article

Determination of bisphenol A in beer by immunoaffinity column tandem high-performance liquid chromatography

K.H. Li, L.X. Zhu, R.R. Liu, W. Meng
A rapid and sensitive method using immuno-affinity columns (IACs) as sample purification procedure and high-performance liquid chromatography (HPLC) tandem fluorescence detector (FLD) for detection has been developed for the determination of bisphenol A (BPA) in beer. The limit of detection (LOD) is...
Proceedings Article

Research of combination of electricity GM (1,1) and seasonal time series forecasting model

Yuping Wang, Fangpeng Zheng, Kelei He, Chunxue Li
Load forecasting is one of the important content of power system. Gray GM (1,1) model with seasonal time series was proposed by analyzing the development of the electricity load forecasting. This paper made an empirical analysis of the model with data specifically related to electricity in Guizhou region...
Proceedings Article

High Reliability Electricity Pricing Method Research

H.L. Wang, W. Long, R. Liu
How to effectively coordinate the reliability and economy in the market environment is becoming a hot spot of today's power market research. Explore viable mechanism of supply and demand based on reliability under market conditions, establish a reasonable reliability service trade mode, the reliability...
Proceedings Article

Multi-layer Partition Method Combined with Multi-target Genetic Optimization for Urban Power Grid Structure Planning

Z.Q. Yao, C.W. Zhao, Y.C. Zong, F.J. Chi, J. Zhang, L.Y. Liu
The planning and designing of the power grid structure is most important in the planning and construction of power grid. With the development of urbanization and widespread insertion of distributed generations, the traditional planning method for urban power grid structure is facing new challenges and...
Proceedings Article

Traffic Safety Evaluation of Urban Road Intersection Based on Grey Clustering

Jingfei Yu, Li Wang
For problems on impacting urban road traffic in view of traffic safety conditions of the urban road intersections, the paper evaluated the intersection safety levels by the traffic conflict technique and grey cluster analysis method. The result of the case analysis shows that the evaluation results are...
Proceedings Article

An improved compatible clustering algorithm

Renxia Wan, Duoqian Miao, Caixia Li
In this paper, we discuss the problem of compatible clustering, we propose a new compatible clustering algorithm based on pNCompClu[9]. The new algorithm adopts spherical space approximation technique to replace the point neighborhood mechanism of pNCompClu. Experiments show that the proposed algorithm...
Proceedings Article

The application of DTM method in the earthwork calculation by partition

Yijie Wang, Hao Zhang
no matter which method chosen to calculate earthwork, it always needs to consider about describing the design surface as accurate as possible. However, in fact, each project has different construction from each other. And each construction has its different design elevation. Meanwhile, for a complete...
Proceedings Article

The optimal path optimization choice and simulation based on the labeling algorithm

Di Liang, Bin Wang
This paper uses a university traffic path optimization choice as the research object to analysis the traffic situation. It use the labeling algorithm and the Dijkstra algorithm. The Matlab is used to programme and operate the results. It is mainly solved the problem of optimal route choices and several...
Proceedings Article

The Research of Hybrid Genetic Algorithm Based on the Shortest Machine-processing time

Li-Jun Zhong, Le Wang
A hybrid genetic algorithm is proposed based on the shortest machine-processing time. The searching direction is guided by the both global and local to improve the efficiency of the algorithm. It is applied to solve the engineering problems in a military enterprise, and the results are satisfied.
Proceedings Article

Research on the Methods of Holding Control Strategy for Bus

Tingting Hu, Xiucheng Guo, Zhenping Xi, Jiabin Li
Research on the holding control methods for bus can improve the reliability of bus transfer and reduce travel delays of passengers effectively. What’s more, it can help to improve the quality and attractiveness of public transport service and promote the priority development of urban public transport....
Proceedings Article

Numerical simulation of particle motion in the rotary flow in binoculars

Z.W. Wu, X.N. Zhang, Y.Y. Li
Using DPM model to simulate the particle with different size motion in the rotary flow in binoculars continuous, the sliding mesh used the concentric binoculars spiral flow simulation, and take the numerical simulation of the different particle motion in the flow to explore the motion characteristics...
Proceedings Article

Study on Parameters Setting of Chan and Vese Model to Iris Segmentation

Ying Chen, Fengyu Yang
Iris recognition plays an important role in personal identification. The first and critical step in the process of an iris recognition system is iris segmentation. In this study, several aspects are done. Firstly, the fundamental of Chan-Vese level set is described. Secondly, the process of related parameters...
Proceedings Article

Risk Assessment of Plan Schedule by Monte Carlo Simulation

Zhaoni Kong, Jianping Zhang, Chao Li, Xiaoying Zheng, Qingqing Guan
With an increasingly complex and rapidly changing construction circumstance, owners and their contractors are confronting challenges from risk management while maintaining control and improving performance. With great capabilities for project management solution, Monte Carlo simulation was used to forecast...
Proceedings Article

Comprehensive Measurement Model for the Line Network Scale of Modern Trams in New Urban Districts

Junhong Hu, Haijun Zhang, Xiucheng Guo
This paper presents the measurement index system of tram-line network on the basis of the defining of its scale of modern trams. The author makes a comprehensive measurement for the line network scale of modern trams in new urban districts by using measurement theory. Based on the uncertainty mathematic...
Proceedings Article

Solving of the Transcendental Equations in Layered Media

Neng-Zhong Lei, Ie-Lung Chung
In this paper, we use an efficient method to solve the wave numbers of transient wave propagation in layered media. To solve those problems, the analytic solution for the interior domain is combined both a homogeneous solution and a particular solution, the exterior domain is described by a homogeneous...
Proceedings Article

Digital Image Watermarking Based on Normalization and Visual Feature

Chen Chen, Huimin Guo
In this paper, a Discrete Cosine Transform (DCT) domain robust digital watermarking algorithm based on image normalization of invariant moment and the sense of visual feature of person is proposed. In order to boost up the safety and the solidity of the watermark, the watermark is scrambled and chaotically...
Proceedings Article

About the Component’s Offcenter in ISSS

Jin Duan, Xiao-Ming Chen, Hu Qi, Yun-Gui Li
In this paper, the problem of component’s offcenter, such as shear wall offcenter, beam offcenter, etc., would be discussed in detailbased on the ISSS which is developed by the authors [1-4] to satisfy the engineering requirement for high performance simulation (HPS). The computing results would be presented...
Proceedings Article

Determination to the Confidence Level of PSD Estimation with Given D.O.F. Based on WELCH Algorithm

Xue-Wang Zhu, Si-Jian Zhang, Qing-Lin Liu
Approach is proposed for determining the confidence level of the power spectral density (PSD) estimation with give Degree-of-freedom (D.O.F.) based on WELCH algorithm, a modified periodogram estimator for estimating PSD. A relationship between the random error, defined as a ratio of variance and mean...
Proceedings Article

On Parallel Honeynet Log Mining Algorithm using P-Apriori in Cloud Environment

Jun Luo, Jing Liu, Song Han
The current analysis on honeynet log mining was facing malpractice of horizontal partitioning and insufficient data problems. By which we use Apriori algorithm with parallel processing to decrease the frequency of database scan operation and set up an improved algorithm S-Apriori, and then P-Apriori...
Proceedings Article

Study on Electric Power Enterprise Operation Risk Measurement Based on Blind Number Theory

Fusen Zhong, Shenyou Zhang
This study adopts questionnaire survey to analyze and comb operational risk of the electric power enterprise, and construct the index system of operational risk of electric power enterprise. Then adopt the factor analysis method and blind number theory to screen and quantify the key indicators of operational...
Proceedings Article

The Method of Applying Support Vector Machine to Engineering Data Regression

Jin Tian
Based on machine learning concepts, this paper has put forward two key problems of the application of support vector regression and has given a solution to these problems. It is that the different characteristics of the sample data are decisive factors of the schemes of the selection, and the procedure...
Proceedings Article

Some properties and applicatons of (inverse)Ln-1-matrices

Chuansheng Yang, Chao Wang
In this paper we study some combinatorial properties and inequalities of some classes of Z-matrices. These matrices arise in many problems in the mathematical and physical sciences. We show that all (inverse) Ln-1-matrices are irreducible and some eigenvalue inequalities of (inverse) Ln-1-matrices
Proceedings Article

Study of Query Interface Matching Based on Singular Value Decomposition

Heping Gou, Yongxia Jing, Yuan Zhao
Deep Web query interface matching is one of the key technologies to realize rapid Deep Web data query. On the study of query interface representation, feature extraction and weight calculation, the method based on singular value decomposition is presented. It transforms the query interface set into a...
Proceedings Article

Massive data processing techniques and model in Internet of things

Yuebin Wang, Quanfeng Yan, Liqiang Liu
with the further development of Internet,rapid scales. Technology the expansion of Internet use is growing due to such rapid growth in this industry, the amount of data dealt by Internet of things becomes the feature of massive amount. The key problems that should be considered with, is how to efficiently...
Proceedings Article

Design of Marine Geological Survey Monitoring Model and Its Realization

Hong-Wen Chen, Chang-Gao Shao
The marine geological survey project is an important method of marine data acquisition,which relates to the national marine rights and interests and security. To strengthen monitoring and dispatching of survey ships and supervision on offshore projects, a marine geological survey monitoring model, based...
Proceedings Article

Improvement of the Vehicle License Plate Recognition System in the Environment of Rain and Fog

Zhun Wang, Zhenyu Liu
License Plate Recognition (LPR) is one of the key technologies of the intelligence of communication management. A certain amount of difficulties to license plate recognition are caused by the environment of rain and fog. License plate recognition system for this kind of environment is studied in this...
Proceedings Article

Application of Support Vector Machines Arithmetic in Body Posture Detection

Bo Du, Lu Yin, Zhuo Zhang
It is very critical to detect elder people's falling down in time for it will be harmed to them even to death if they can't be found early. Body posture detection system is based on STM32F103C8T6 as controller which can detect falling down in time from the two parts of host and slave. Data transferred...
Proceedings Article

Design and development of All-in-one computer for distributed file system

Lin Qian, Yan Chen, Jun Yu, Guangxin Zhu, Hengmao Pang, Xigao Li
Application requirements and the business volume increased significantly, considering the performance bottleneck and single point failure and other problems, distributed file system gradually will replace centralized storage. This paper discussed the independent designation and development of all in...
Proceedings Article

Research on large scale data processing technology based on cloud computing

Qiuhua Wen
To improve the single problem in large data processing system based on cloud computing technology, the research focuses on the impact of network data processing model based on hybrid architecture, fusion processing, and decentralized processing. This research can be used in the next generation of cloud...
Proceedings Article

Research and Design of Energy Data Acquisition System in Cement Enterprise

Xiangsong Li, Xiaohong Wang, Shaohong Jing
n the growing demand for energy, while energy supply is becoming increasingly tense, prices continue to rise. This makes the energy consumption cost plays a more and more proportion in the enterprise cost calculation. To improve the energy utilization rate, cement enterprises take various optimization...
Proceedings Article

Fine-grained AR-UCON Model Based on Time Constraints under Cloud Computing Environment

Yuejiang Sun, Chunxia Qi
Traditional access control technologies are not well adapted to cloud computing environments. Usage Control (UCON) model is featured with attribute variability and decision-making continuity, which means advantageous in the new environment. But UCON model is highly abstract and difficult to apply. For...
Proceedings Article

An Improved Genetic Algorithm Based On Stages Hybridization For Evolvable Hardware Design

Huicong Wu, Jinze Wang
Facing the complexity and variability of electronic circuit design, evolvable hardware has gradually become one of the effective methods to design hardware. Algorithm influences the direction and progress of evolution. In order to improve algorithm and solve the current problem that the evolutionary...
Proceedings Article

Customer segmentation model based on two-step optimization in big data era

Wei Gao, Huiting Jia, Ruzhen Yan
With the advent of the era of big datasets, real-time data is becoming increasingly important in assisting the decision making process for commercial banks. In this paper, we develop a two-step optimization model (FSGA-FCEN) based on genetic algorithm (GA) and cluster ensemble (CE) for customer segmentation....
Proceedings Article

The Application of Natural Computation for Solving the Traveling Salesman Problems

Huowen Jiang, Huanliang Xiong, Huiyun Zhang
Traveling Salesman Problems is a classical kind of combined optimization problems. Solving TSP effectively can produce very important theoretical value in computable theory, and also has very high applied value in practice. Solving travel salesman problems by using some traditional algorithms is limited,...
Proceedings Article

FACIAL EXPRESSION RECOGNITION BASED ON IMPROVED LBP OPERATOR AND K-MEANS CLUSTERING

Yunfei Wang, Hui Ding, Yi Liu, Yanyan Pan
For facial expression features extraction and automatic clustering, a method is proposed. This method integrates improved LBP operator and K-means clustering. Firstly, facial features are located by integral and variance projection. Improved LBP operator with changed threshold is figured out. Secondly,...
Proceedings Article

Design of An Extensible Anti-Virus Framework

Zhoue He
Anti-Virus engine depends too much upon the signature database and each detection module couples tightly. To solve this problem, an extensible framework is presented. The function module and data module are decoupled by using the intelligent signature and decomposing composite modules. Inversion control...
Proceedings Article

Parallel strategy for Optimal Power Efficiency

Zhoue He
Large-scale data streams processing is import to data processing application. So we need to investigate the parallel strategy for the Large-scale data streams processing. Here we propose two parallel strategies to handle data streams in real time, and consider the power efficiency as an important factor...
Proceedings Article

A Hybrid Genetic Algorithm for the Distributed Permutation Flowshop Scheduling Problem

Yan Li, Zhigang Chen
For solving the distributed permutation flowshop scheduling problem (DPFSP) with the objective of minimizing makespan we design a hybrid genetic algorithm. This algorithm combines a simple genetic algorithm, a local search algorithm and a plant allocation rule with the aim of minimizing the makespan....
Proceedings Article

A Low-Complexity DOA Estimation Algorithm for 2D Massive MIMO System

Xiaoyu Li, Wei Wu, Xiaofei Zhang
Massive multiple-input multiple-output (MIMO) system has become a crucial technology meeting the ever-increasing data consumption demand, for it has more channel capacity, higher frequency spectrum efficiency and reliability. The direction of arrival (DOA) estimation on the base station has a marked...
Proceedings Article

DOA Tracking Algorithm for Acoustic Vector-Sensor Array via Adaptive PARAFAC-RLST

Weiyang Chen, Wei Wu, Xiaoyu Li, Xiaofei Zhang
In this paper, we consider a direction of arrival (DOA) tracking algorithm via adaptive parallel factor via recursive least squares tracking (PARAFAC-RLST) for acoustic vector-sensor array. The adaptive algorithm can efficiently track multiple targets by recursively updated the loading matrices at time...
Proceedings Article

Research on Correlation analysis of industry electricity quantity

Yongjun Wang, Gang Yao, Yanying He
Power sale quantity of Power grid enterprise is affected by many factors. First, this paper introduces the correlation analysis method, including the Pearson correlation coefficient, partial correlation coefficient and the multiple correlation coefficient; Then analyzing the external influence factor,...
Proceedings Article

A Research on Machine Learning Methods for Big Data Processing

Junfei Qiu, Youming Sun
Machine learning has found widespread implementations and applications in many different domains in our life. However, as the big data era is coming, some traditional machine learning techniques cannot satisfy the requirements of real-time processing for large volumes of data. In response, machine learning...
Proceedings Article

Breadth-First Maximum-Likelihood Sequence Detection of Ring Convolutional Coded Continuous Phase Modulation

Lei Zhang, Huaping Lu, Aimin Zhu, Jiuqiang Cui
This paper shows a breadth-first maximum-likelihood sequence detection method for ring convolutional coded continuous phase modulation (CPM) over additive white Gaussian noise (AWGN) channel. By reserving the states which are closest to the received signal in the normalized squared Euclidean distance...
Proceedings Article

Gradient-based Neural Network for Online Solution of Lyapunov Matrix Equation with Li Activation Function

Shiheng Wang, Shidong Dai, Ke Wang
A new type of activation function, named Li activation function, is used in gradient-based neural network (GNN) to solve Lyapunov matrix equation. With this activation function, theoretical analysis shows that GNN can converge in finite time, while it can converge only in infinite time with two conventional...
Proceedings Article

Research on Wavelet Transform Blind Equalizer Based on Different Place

Yingge Han, Baokun Li, Lin Zhang
In order to improve the convergence speed of adaptive equalizer, orthogonal wavelet transform has been introduced into adaptive equalizer. The orthogonal wavelet transform are placed in the front of the equalizer (forward filter) in the existing literature, which will reduce the performance of equalizer....
Proceedings Article

A Generalized Stability Theorem for Discrete Chaos Systems with Application in Avalanche Image Encryption

Xue Wang, Lequan Min, E Chen
This study first proposes a concept of generalized stability (GST) for discrete chaos system, which is the generalization of chaos generalized synchronization (CGS). Then this study sets up a constructive theorem of GST for discrete chaos system, which provides a general representation of GST in discrete...
Proceedings Article

Research on the Correlation Model of Network Load Index in Mobile Packet Domain under the Background of Network Integration

Xidong Zhang, Guojun Lai, Heng Zhang, Hao Chen, Yang Zhao
According to the network data of mobile packet domain in backbone network, this article analyzes the correlation model of network load index in mobile packet domain. Based on the mobile service and analysis model of user behaviors, in this paper we proposed a correlation model and curve model on total...
Proceedings Article

Short-term load forecasting based on correlation coefficient and weighted support vector regression machine

Limei Liu
Accurate load forecasting can keep the safety of power grid operation stability and guarantee the normal production and life of society. Support vector regression machine is suitable to load forecasting. Its nature of learning method is to give a good forecasting ability according to a small amount of...
Proceedings Article

The feasibility parameters quantification FMECA algorithm based on fuzzy theory

Yanmei Lv, Hongtao Zhen, Dong Zhang
According to the optimization problem in a variety of corrective and improvement actions that exist in the FMECA method, this paper introduces the fuzzy theory of FMECA analysis, study quantitative method of the degree of severity S , occurrence probability O and detestability D of RPN algorithm, and...
Proceedings Article

Task Decision Support System Research and design of Space Maritime TT&C

Huifen Duan, Junlei Bao, Dehua Zhang
In order to improve the efficiency of the command of the maritime aerospace measurement and control tasks, the timely discovery and analyzing and solving the abnormal situation in the process of the task, research and design the assistant decision system which be appropriate for the task of the maritime...
Proceedings Article

An MCMC-BASED PARTICLE FILTER TBD ALGORITHM FOR MULTI-TARGET DETECTION AND TRACKING

Ling Fan
This paper presents an MCMC-based particle filter TBD algorithm for multi-target detection and tracking in low SNR environment. In this algorithm, a set of unweighted samples is used to represent the posterior distribution of the joint multi-target state. Then, a MH algorithm is adopted to recursively...
Proceedings Article

Instantaneous frequency estimation of non-stationary signal

Xiaoxuan Qi, Tingting Guo
In signal processing, the estimation of instantaneous frequency is a kind of very important issue for non-stationary multi-component signal. Firstly, this paper adopts EMD decomposition to decompose non-stationary multi-component signal and convert into a series of single component signal. Then using...
Proceedings Article

Application of multi-feature based on LMD in fault Feature extraction of bearing Type

Xiaoxuan Qi, Changyuan Xu
This paper presents a application of kurtosis and approximate entropy in rolling bearing fault diagnosis.First use the method of LMD adaptive decomposed he rolling bearing vibration signal into different time scales of PF component , then filtered to get PF component, and rebuilt a new weighted optimization...
Proceedings Article

Off-line Signature Verification Using Linear Regression Classifier

Bo Xu, Daozhi Lin, Hongyang Chao, Weifeng Li, Qingmin Liao
In this paper we propose a novel classification method based on Linear Regression Classification (LRC) for offline signature verification. The class-specific models can be simply established by using the registered samples (examples), and a test signature can be linearly represented by these registered...
Proceedings Article

An algorithm of Handwritten Digital Recognition Based on BP-Bagging

Zuojun Liu, Lihong Li, Mi Yu
The handwritten number recognition algorithm based on BP-bagging generates the basic classification by BP network and generates multiple classifiers by bagging. The algorithm treats a handwritten character as an image. By scanning the images, 25 dimension features are extracted, and then compresses the...
Proceedings Article

Speech Dereverberation Based on Sparse Matrix Decomposition

Miao Fan, Liyang Liu, Weifeng Li
Because of the increasingly demands of high quality audio signal, speech dereverberation,as the preliminary processing of speaker recognition and automatic speech recognition(ASR), becomes more and more important. The speech obtained from microphones is always distorted by reverberation. Conventional...
Proceedings Article

A new threshold segmentation algorithm for segmenting micro-focus X-ray BGA solder joint image

Hui Wang, Dan Liu
Grid Array Ball (BGA) has been used in the production of electronic devices and components because of its small size, high I / O port density and so on. However, BGA solder joint defects will reduce the performance of the motherboard. Because micro-focus X-ray BGA solder joint image has a large number...
Proceedings Article

An Traffic Subarea Partition Algorithm based on State recognition

Liangzhi Zhang, Peide Li
Traffic State subarea partition problem has been a hot topic. A sub-area partition algorithm is proposed in this paper based on state connectivity matrix with flow variance in intersections within the road network. The principle of subarea partition is posed in the paper, and a dynamic algorithm is designed...
Proceedings Article

A Survey on Thangka Image Inpainting Method Based on Structure-borne

Xiaojing Liu
The ancient Tangka image with reflecting Tibet art has been broken by the nature and human with different degrees The part-shed Tangka image is researched as a type of special breaking. After discussing digital image inpainting, the digital image restoration based on the structure, and Thangka image...