Special Issue "Big Data Analytics"
A special issue of Information (ISSN 2078-2489).
Deadline for manuscript submissions: closed (30 September 2015)
Dr. Joseph K. Liu
Faculty of Information Technology, Monash University, Australia
Interests: applied cryptography; computer system security; lightweight security
Nowadays, big data has become a new, hot research topic among academics and the industry community. It refers to a collection of data sets that are too large or too complex for efficient processing and analysis using traditional database management tools. The development of big data will enhance decision making, insight discovery, and process optimization. However, there are still numerous technical challenges and issues that need to be improved and broadly explored. This Special Issue aims to provide the last and most innovative research on all theoretical and practical aspects in all areas of big data processing, analysis, and mining.
Topics of interest include, but are not limited to:
- Privacy-preservation for big data
- Traditional and emerging methods for big data
- Machine learning for big data
- Intelligent and unconventional methods for big data
- Search and optimization for big data
- Parallel, accelerated, and distributed big data analysis
- High performance computing for big data
- Novel hardware and software architectures for big data
- Real-world applications and success stories of big data analysis
- Mining of unstructured, spatio-temporal, streaming, and multimedia data
Dr. Joseph K. Liu
Professor Dr. Xiaofeng Chen
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access quarterly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 350 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- big data
- cloud computing
- information system security
- data processing and analysis
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Title: Data Analytics of Unstructured Healthcare Big Data Collected from Streams or Crawled from the Web: The Promise and a Practical Solution
Authors: Sabah Mohammed 1, Jinan Fiaidhi 1, Jens Weber 2 Osama Mohammed 2 and Simon Fong 3
Affiliation: 1 Department of Computer Science, Lakehead University, Thunder Bay, Ontario P7B 5E1, Canada; E-Mails: email@example.com (S.M.); firstname.lastname@example.org (J.F.)
2 Department of Computer, University of Victoria, Victoria, BC, V8W 2Y2, Canada;
E-Mails: email@example.com (J.W.); firstname.lastname@example.org (O.M.)
3 Department of Computer and Information Science University of Macau, Avenida da Universidade, Taipa, Macau; E-Mail: email@example.com
Abstract: One of the vital challenges to leveraging Big Data in healthcare are the development of proper analytics tools applicable to unstructured healthcare data (e.g. stream data collected from wearable vital signs sensors, health related blogs, online medical publications, pharmacovigilance, textual discharge summaries for referral purposes) which can reach massive proportions over time. These tools need to be architected for healthcare researchers to enable them to see far past what traditional data analytics solutions provide. Most of the current data analytics tools and techniques used in healthcare are borrowed from eCommerce with a plethora of metrics for uncertain complex workflows that often confuse healthcare researchers and clinicians making their use almost impossible. This article addresses this challenge and identifies a solution that prove to work for the healthcare researchers using clear visual compositions of the analysis process especially for unstructured data that requires comprehensive sequence of processes including crawling, preprocessing, filtering, categorization, mining and forecasting. The article also provides practical experiments as a proof of concept for the visual composition for some common analytics problems based on R and RapidMiner analytics platform where healthcare researchers can use it to categorize medical notes and to analyze stream of ECG Data for detecting arrhythmia.
Keywords: Unstructured Data, Stream Data Analytics, NLP, R, RapidMiner, Visual Workflow Composition