We would like to extend our warmest welcome to all of you to Shenzhen city, China's first Special Economic Zone, to attend 2018 International Conference on Big Data and Computing (ICBDC 2018), from 28 April to 30 April, 2018.
Proceeding Downloads
Application research of big data experimental teaching platform based on OpenStack
In view of the traditional cloud computing and big data experimental teaching platform in Colleges and universities can not meet the requirements of practical teaching, based on open source OpenStack, we designed and implemented an experimental teaching ...
Meta Learning for Imbalanced Big Data Analysis by using Generative Adversarial Networks
Imbalanced big data means big data where the ratio of a certain class is relatively small compared to other classes. When the machine learning model is trained by using imbalanced big data, the problem with performance drops for the minority class ...
Demand-oriented Energy Big Data Services using Hadoop-based Large-scale Distributed System Platform for District Heating
In the energy industry, a variety of Big Data services have been developed and provided for both producers and consumers. These services bring more convenience, reliability stability and a higher operational efficiency in energy control and management. ...
A Unified SQL Middleware for NoSQL Databases
With the popularity of smart mobile devices and the development of big data, NoSQL databases came into being. Compared to the traditional relational databases, NoSQL databases have the advantages of unstructured storage, high availability and high ...
SAT-based Important Data Reliability Enhancement Model for Big Data Storage
Disk reliability is a serious problem in the big data foundation environment. Although the reliability of disk drives has greatly improved over the past few years, they are still the most vulnerable core components in the server. If they fail, the ...
Network Traffic Monitoring System Based on Big Data Technology
With the rapid growth of network traffic and the increasing rich methods of network attacks, traditional network traffic monitoring system cannot meet the requirements of data storage and query in real time. Therefore, how to monitor the large scale ...
Neural Network Based Movie Rating Prediction
Movie rating is a numerical comprehensive evaluation of movie viewers. It represents an objective basis for general audience and advertisers to choose high quality movie, and is a crucial factor affecting row piece and estimate final box office ...
Multi: Source Data Inconsistency Detection and Repair Based on CRC Algorithm
Most existing systems suffer from data quality problems. Data quality has been affected by many factors such as manual operation, software problems and hardware problems, especially data inconsistencies. As an important carrier of data, database system ...
Cooperating with high available write cache and local read only buffer to reduces the latency of small read and write
Distributed file system is the basic platform for big data analysis. For VM, database, log generation and other file processing, the traditional distributed file system for big data analysis cannot meet the IOPS requirements. Flash storage is becoming ...
Data Driven Topsis Method and Its Application in E-commerce APP
With the rapid development of the Internet economy, the survival and development of e-commerce APP is more and more reflected in the differences in competitiveness. With the advent of the era of big data, data has been growing explosively. Massive data ...
The Improvement of HDFS Authentication Model Based on Token Push Mechanism
In order to solve the problems of single point overload, repeated authentication, replay attack and time synchronization in the security authentication of HDFS, an improved Kerberos protocol based on token push mechanism is proposed. First of all, ...
Dynamic Privacy Pricing Based on Reinforcement Learning
In recent years, with the fast development of big data, the value of personal data has attracted great attention. How to balance the conflict between the exploitation of personal data and the protection of personal privacy is now one of the most ...
Automatic Feature Learning for MOOC Forum Thread Classification
Discussion thread classification plays an important role for Massive Open Online Courses (MOOCs) forum. Most existing methods in this filed focus on extracting text features (e.g. key words) from the content of discussions using NLP methods. However, ...
Climate Event Detection Algorithm Based on Climate Category Word Embedding
Detecting climate events efficiently and accurately is important in traffic warning, disaster warning, and disease prevention. Given that ordinary event detection algorithms are ignored in climate domain's knowledge, the results of climate domain's ...
Efficient Methods to Select Top-K propagators based on Distance and Radius Neighbor
The problem of influence maximization aims to select Top-K propagators according to the available budget in which when these propagators are selected the influence coverage is maximized. While most existing approaches aim to increase the influence, ...
Musical Notes Estimation Based on Greatest Common Devisor and Likelihood
In this paper, based on the relationship between fundamental frequency and harmonics, a musical note estimation algorithm using the greatest common divisor of peaks is proposed. By applying the algorithm to multi-notes estimation program that measures ...
The properties of stochastic restricted two-parameter ridge type estimator in linear regression model
Zhou and Wu [1] proposed a stochastic restricted two-parameter ridge type estimator in linear regression model. In this paper we discuss the superiority of stochastic restricted two-parameter ridge type estimator with ridge estimator, two-parameter ...
Fast random pair divisive construction of kNN graph using generic distance measures
We introduce a fast hierarchical method algorithm to construct an approximate kNN-graph. The method is simple to implement and generic, as it works with any type of data for which a symmetric distance function can be provided. We tested the method with ...
Research on the Hypertension Syndrome Elements Differentiation of TCM Based on Multi-label Learning and Ensemble Learning
Hypertension is one of the important causes of cardiovascular diseases. In China, the prevalence of hypertension is showing an upward trend. Syndrome elements differentiation has been given great attention in the field of Traditional Chinese Medicine (...
Medical Question Similarity Calculation Based On Weighted Domain Dictionary
In the calculation of question similarity in the mobile medical question answering system, not all the importance of the words are the same. To solve the problem, we proposed a improved similarity calculation method based on the vector space model and ...
Combining wAMAN and Matrix Factorization to Optimize One-Class Collaborative Filtering and Its Application in an Emotion-Aware Movie Recommendation System
With the development of modern science, the exponential explosion of information makes it difficult for people to find useful information from such a huge information set. As a consequence, different algorithms emerge to help people build an intelligent ...
A Performance Comparison of HTTP Servers in a 10G/40G Network
The performance of server-side applications is crucial for big data analytics. As HTTP web servers are widely used as back ends to run Web Services which are universally supported by big data technologies, and the emergence of high capacity networks ...
Cloud Computing Security and Privacy
Cloud computing is an emerging technology that can provide organizations, enterprises and governments with cheaper, more convenient and larger scale computing resources. However, cloud computing will bring potential risks and threats, especially on ...
3D Modeling Method Based on Deep Belief Networks (DBNs) and Interactive Evolutionary Algorithm (IEA)
3D modeling usually refers to be the use of 3D software to build production through the virtual 3D space model with 3D data. At present, most 3D modeling software such as 3dmax, FLAC3D and Midas all need adjust models to get a satisfactory model or by ...
Software Reliability Prediction Based on Optimized Support Vector Regression
Modeling software reliability, through improving the accuracy of reliability prediction, it plays an important role in improving the reliability of military equipment software. Firstly, Support Vector Regression algorithm and the related parameter types ...
Trajectory Privacy Preserving for LBS in P2P Environment
This paper presents a trajectory similarity measurement method based on user's local anonymous area. This method can protect the location privacy among users between each other in an anonymous group. Based on the trajectory similarity and real user's ...
3-D Route Intelligent Planning for Underwater Platform with Multi-Constraint Based on Ant Colony
In order to satisfy all kinds of constraint factors and performance indexes, improve the effectiveness and applicability of path planning algorithm, 3-D route intelligent planning for underwater platform with multi-Constraint based on ant colony is ...
Computational Model and Its Precision Evaluation for TWSTFT
Time synchronization is one of the pivotal technologies in the design of satellite navigation and positioning system. According to the principle of time comparison by two-way satellite common-view, its computational model in the earth-centered inertial ...