2018 International Conference on Big Data and Artificial Intelligence (BDAI)

22-24 June 2018

Filter Results

Displaying Results 1 - 25 of 30
  • [Front cover]

    Publication Year: 2018, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (60424 KB)
    Freely Available from IEEE
  • [Front cover]

    Publication Year: 2018, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (34 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2018, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (23 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2018, Page(s):iii - iv
    Request permission for commercial reuse | PDF file iconPDF (88 KB)
    Freely Available from IEEE
  • [Front cover]

    Publication Year: 2018, Page(s):c1 - c3
    Request permission for commercial reuse | PDF file iconPDF (36 KB)
    Freely Available from IEEE
  • A Cluster Analysis of Mutual Funds Data

    Publication Year: 2018, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (129 KB) | HTML iconHTML

    The factors of clustering mutual fund (such as Net Asset Value (NAV)) do not direct to both return and risk of mutual funds which they are important factors for investors. This research helps an investor can estimate profit and loss rate of the mutual fund in his/her portfolio by using the net asset value change ratios (NAVCR). Then, both the NAVCR and value of each mutual fund will be used for cl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of Cloud Data Storage and Processing System

    Publication Year: 2018, Page(s):6 - 9
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (108 KB) | HTML iconHTML

    The data storage and processing system based on cloud computing can take cloud server as the core, make use of sensor technology synthetically, and provide data storage and computing function for client. Combining GPRS/WiFi technology with Ali cloud server, this paper realizes cloud storage and cloud computing processing of remote important environment information and dynamic display of real-time ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Big Data Technology Applied to Learning Behavior Evaluation System

    Publication Year: 2018, Page(s):10 - 17
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (208 KB) | HTML iconHTML

    Teaching and Learning process is one of the criteria set and a vital element for an educational institution. Learning behavior analytics based on big data is relatively new. Aiming at the problem of the lack of system architecture and practical application of big data technology in the educational field, this paper sets its focus on big data application architecture framework in the educational fi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on the Optimization of Military Supplies under Big Data Background

    Publication Year: 2018, Page(s):18 - 23
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (98 KB) | HTML iconHTML

    On the basis of analyzing the characteristics of big data technology and combining the actual demand of military demand industry in our army, this paper constructs a comprehensive analysis environment of big data for military demand, and on this basis, analyses the data of the collection and allocation of voucher accounts, military clothing archives data, the living standard of troops and the actu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization of Column-oriented Storage Compression Strategy Based on Hbase

    Publication Year: 2018, Page(s):24 - 28
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (246 KB) | HTML iconHTML

    In order to solve the problem of high learning cost and low compression efficiency caused by large data dispersion, this paper presents a sorted-based compression strategy selection method for HBase. Firstly, a method to sort the data in each column is designed according to the characteristics of HBase to strengthen the data compaction. Secondly, according to the characteristics of the data, a col... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Ensemble Strategy Combining Gradient Boosted Decision Trees and Factorization Machine Based Neural Network for Clicks Prediction

    Publication Year: 2018, Page(s):29 - 33
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB) | HTML iconHTML

    Click-through rate (CTR) prediction is generally formulated as a supervised classification problem. One challenge in CTR prediction, especially the features with high-sparsity, is to exploit the potential generalization ability under the given samples. In this paper, we first present a novel Factorization Machine (FM) based Neural Network (FNN), which helps capture the nonlinear interactions betwe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research of Load Balancing and High Availability of VoLTE Core Network in Cloud Environment

    Publication Year: 2018, Page(s):34 - 37
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (101 KB) | HTML iconHTML

    This paper aims to study the feasibility, reliability, load balancing ability and high availability of VoLTE core network in cloud computing environment. By utilizing the mindset of SaaS (software as a service), and based on the general standard of cloud servers, storage and network equipment, along with the use of IT virtualization to deploy telecommunications equipment in the cloud computing env... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of Internet Traffic Identification on Machine Learning Methods

    Publication Year: 2018, Page(s):38 - 41
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (131 KB) | HTML iconHTML

    Traffic classification is the essential part in computer network. It can identify the traffic application so as to better manage the network, filter the insecure network flows and provide better network services. However, traditional traffic identification methods cannot work well when encounter opaque packets or more complex flows. Machine learning methods become the most efficient way to solve t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Path Planning for Mobile Robot's Continuous Action Space Based on Deep Reinforcement Learning

    Publication Year: 2018, Page(s):42 - 46
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (219 KB) | HTML iconHTML

    In this paper, a path planning method based on deep reinforcement learning in the unknown environment of mobile robots is proposed, in order to meet the path planning of the kinematic model and constraint conditions of the mobile robot under continuous action space. The path planning method plans a path from the starting point to the target point to avoid obstacles, but these planned paths do not ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tibetan-Chinese Cross-language Topic Extraction and Alignment

    Publication Year: 2018, Page(s):67 - 71
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (229 KB) | HTML iconHTML

    Getting information about Tibetan topics in other languages is the basis and the most critical module of cross-language topic detection and tracking. This paper firstly extracts Tibetan-Chinese topics using LDA model, and then proposes a voting method based on cosine distance, Euclidean distance, Hellinger distance and KL distance to realize Tibetan-Chinese cross-language topic alignment. Finally,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ECG Signal Classification with Deep Learning for Heart Disease Identification

    Publication Year: 2018, Page(s):47 - 51
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (164 KB) | HTML iconHTML

    Electrocardiogram (ECG) signal is widely used in medical diagnosis of heart diseases. Automatic extraction of relevant and reliable information from ECG signals has not been an easy task for computerized system. This study proposes to use 12-layer 1-d CNN to classify 1 lead individual heartbeat signal into five classes of heart diseases. The proposed method was tested on MIT/BIH arrhythmia databas... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Security Enhanced Cloud Storage Access Control System Based on Attribute Based Encryption

    Publication Year: 2018, Page(s):52 - 57
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (363 KB) | HTML iconHTML

    With the rapid development of Internet cloud computing technology, services such as cloud storage and cloud disk become a user data storage and backup tool. But at the same time, security of user data has also been great threatened. In this condition, a security enhanced cloud storage access control system based on attributes has been designed and implemented. The system generates the access polic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on Music Emotion Classification Based on the Feature Model of Emotion Category Contribution

    Publication Year: 2018, Page(s):58 - 61
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (119 KB) | HTML iconHTML

    There are problems in the text vector space model: the high dimension causes the sparsity of the vector space, the classification contribution is lower, and the classification accuracy, etc.The characteristic model for the contribution of special words to the emotion category is presented, An improved classification dimension decision fusion method based on the combination of audio features and ly... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on ARIA of Affective Recommendation Index Algorithm Based on Topic Selection of Publications

    Publication Year: 2018, Page(s):62 - 66
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (102 KB) | HTML iconHTML

    At present, the publishing organization’s publication selection planning method lags behind, making China’s publishing industry economic benefits greatly reduced. This paper presents a new affective analysis method—Affective Recommendation index (ARIA) based on the method of fine-grained affective analysis, which combines conditional random field model (CRF) and affective weighting method to analy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rule-Extraction from Soft Decision Trees

    Publication Year: 2018, Page(s):72 - 77
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (175 KB) | HTML iconHTML

    Soft Decision Trees have been proven to have better performance in terms of accuracy and complexity compared to conventional Decision Trees. Nevertheless, they do not possess inherent explanation capability to interpret the learning process of which the conventional Decision Trees are capable because a Soft Decision Tree redirects instances to all its children nodes with probabilities given by a “... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Text Keyword Extraction Based on Meta-Learning Strategy

    Publication Year: 2018, Page(s):78 - 81
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (129 KB) | HTML iconHTML

    Keyword extraction is an important content in many fields and it is a key step to achieve document retrieval, information retrieval, scientific and technological literature indexing, news reading, text clustering and classification, Machine Translation and so on. In order to improved the accuracy of keyword extraction for text, we put forward a framework of keyword extraction based on meta-learnin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • English Education Text Recommendation Technology Based on Word Embedding

    Publication Year: 2018, Page(s):82 - 86
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (112 KB) | HTML iconHTML

    Text is a common way for learners to obtain information. But the resources for English teaching texts on the Internet are very large. Because of language barriers, learners cannot select them well in a short time. In order to solve this problem, this paper uses word embedding technology to generate word vectors for each word in the text through the model. Text vectors are expressed in two ways: on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Branching Strategy Based on the Length of Learnt Clause

    Publication Year: 2018, Page(s):87 - 91
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (133 KB) | HTML iconHTML

    Decision strategy is as a great part in the CDCL algorithm, so the efficient branching strategy is one of the key features of the SAT problem solver. Originally some basic knowledge and concepts are brought in, then there are some concrete steps of the branching variable heuristic algorithm-VSIDS algorithm, finally based on the relationship between the learnt clause length and the decision level, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study on Tariff Risk Early Warning of Electric Power Users Based on PSO-SVM Algorithm

    Publication Year: 2018, Page(s):92 - 96
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (135 KB) | HTML iconHTML

    Tariff recovery risks of electricity power users are always major problems for electric power supply company, and data mining technology can realize early warning of tariff recovery risks by analyzing users’ power consumption, payment and arrears data. Firstly, based on basic information, payment behavior, and default behavior of electric power users, this paper establishes a risk warning model fo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Two-Phase Model for Sleep Staging Using Single Channel EEG

    Publication Year: 2018, Page(s):123 - 127
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (725 KB) | HTML iconHTML

    Sleep staging is the basis for assessing sleep quality and diagnosing sleep disorder. In this paper, we propose a two phase model, based on deep neural networks and support vector machine for automatic sleep staging using raw single channel EEG signals. Instead of hand-engineering features, the first phase of model apply the combination of convolutional neural networks (extract time-invariant feat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.