IEEE Transactions on Big Data
From the July-September 2016 issue
Visual Analytics in Urban Computing: An Overview
By Yixian Zheng, Wenchao Wu, Yuanzhe Chen, Huamin Qu, and Lionel M. Ni
Nowadays, various data collected in urban context provide unprecedented opportunities for building a smarter city through urban computing. However, due to heterogeneity, high complexity and large volumes of these urban data, analyzing them is not an easy task, which often requires integrating human perception in analytical process, triggering a broad use of visualization. In this survey, we first summarize frequently used data types in urban visual analytics, and then elaborate on existing visualization techniques for time, locations and other properties of urban data. Furthermore, we discuss how visualization can be combined with automated analytical approaches. Existing work on urban visual analytics is categorized into two classes based on different outputs of such combinations: 1) For data exploration and pattern interpretation, we describe representative visual analytics tools designed for better insights of different types of urban data. 2) For visual learning, we discuss how visualization can help in three major steps of automated analytical approaches (i.e., cohort construction; feature selection & model construction; result evaluation & tuning) for a more effective machine learning or data mining process, leading to sort of artificial intelligence, such as a classifier, a predictor or a regression model. Finally, we outlook the future of urban visual analytics, and conclude the survey with potential research directions.
Editorials and Announcements
- We're pleased to announce that Qiang Yang, head of the Huawei Noah's Ark Research Lab and a professor at the Hong Kong University of Science and Technology, has accepted the position of inaugural Editor-in-Chief beginning 1 Jan. 2015. Read more.
- Welcome to the IEEE Transactions on Big Data (Jan-March 2015)
- Introduction to the IEEE Transactions on Big Data (Jan-March 2015)
- Big Data Analytics and the Web (July-Sept 2016)
- Big Scholar Data Discovery and Collaboration (Continued) (April-June 2016)
- Big Scholar Data Discovery and Collaboration (Jan-March 2016)
- Big Data Analytics and the Web (Oct-Dec 2015)
- Big Media Data: Understanding, Search, and Mining (Part 2) (Oct-Dec 2015)
- Big Media Data: Understanding, Search, and Mining (July-Sept 2015)
Call for Papers
Special Issue on Big Data Systems on Emerging Architectures
Extended Submission deadline: October 31, 2016. View PDF.
The continued evolution of computing hardware and infrastructure imposes new challenges and bottlenecks to big data management. Over the last few years there has been a renewed interest in the area of (big) data systems on emerging hardware. The opportunities and challenges from emerging computing systems have been raised different scales, from a single machine to thousands of machines. The need for effectively utilizing computing resources creates new technologies and research directions: from conventional ones (e.g., cluster computing, in-memory computing), to more recent ones (e.g., GPGPU, many-core processors, and NVRAM). In addition to performance, many other system features are important for big data applications, like energy consumption and total ownership costs. For a specific application domain such as graph processing and deep learning, the design and development of novel systems on emerging hardware will create the insight into new solution approaches of the application domain and even further. Thus, there is a need to fundamentally address all the above-mentioned issues in big data systems. IEEE Transaction on Big Data (TBD) seeks original manuscripts for a Special Issue on the theme - Big Data Systems on Emerging Architectures scheduled to appear in an issue of 2017.
Special Issue on Theoretical Foundations for Big Data Security and Privacy
Submission deadline: December 1, 2016. View PDF.
Big data is one of the hottest research topics in science and technology communities, and it possesses a great application potential in every sector of human society. However, security and privacy, especially theoretical foundations of them, are critical barriers for extensive applications of big data. We have seen the vulnerability of the available privacy preserving data publishing methods against the dramatic development of mining techniques. We also meet the challenges to apply strict privacy protection frameworks (e.g., differential privacy) in practice. In terms of cryptography, we are experiencing the extraordinary efficiency problem given the volume and scale of big data. Moreover, we have to handle the existing and emerging attack methods in the big data environment. In summary, it is time for us to face the challenges. We have to improve or adjust the existing security and privacy techniques, even invent new tools and techniques, to accommodate the new problems and challenges in the age of big data.
Special Issue on Trustworthiness in Big Data and Cloud Computing Systems
Submission deadline: January 15, 2017. View PDF.
The rapid advancement of digital sensors, computers, networks, and smart devices with their extensive use is leading to the integration of a significant amount of diversified data that results in emerging research on Big Data. Cloud computing means storing, computing, and accessing data and programs over the Internet. The growth of cloud computing and cloud data stores have been a precursor and facilitator to the emergence of Big Data. Thus, Big Data and Cloud systems are considered complimentary to each other.
Since Big Data are often in unstructured or semi-structured forms that are being generated from various sources, trustworthiness in data collection, integration, computing, decision-making, and data management becomes a great concern. For example, can we trust current Big Data storage and protection systems or can the use of Big Data analytic enhance security and privacy of the whole system? On the other hand, trustworthiness is also one of the most concerning issues in Cloud Computing environments in terms of fault tolerance, data loss recovery, data privacy/security/safety, and data protection, due to its open environment with very limited end user-side controls. Currently, many new applications are being developed explicitly for cloud system deployment, while many traditional applications will eventually evolve to cloud. The end user-side wants these cloud-based services to be at least as trustworthy and available as traditional offerings. To meet these expectations, cloud service providers and cloud consumers need to gain a solid understanding of the unique challenges of cloud computing and learn how to mitigate risks.
While information society, commercial and scientific companies, and industries share the need for massive throughput, trustworthiness of services will become a big concern. However, trustworthiness in both Big Data and Cloud Computing systems has received less attention from researchers and practitioners. The aim of this special issue is to solicit both original research that discusses the trustworthiness issues, trustworthy platforms, trustworthy frameworks, and design methodologies for Big Data and Cloud Computing systems.
Special Issue on Biomedical Big Data: Understanding, Learning and Applications
Submission deadline: March 1, 2017. View PDF.
Biomedical imaging is an essential component in various fields of biomedical research and clinical practice. Biologists quantitatively study cell behavior and generate high-throughput microscopy data sets. Neuroscientists detect regional metabolic brain activity from positron emission tomography (PET), functional magnetic resonance imaging (MRI), and magnetic resonance spectrum imaging (MRSI) scans. Virologists generate 3D reconstructions of viruses from micrographs, and radiologists identify and quantify tumors from MRI and computed tomography (CT) scans. Advanced imaging equipment and diverse applications have driven the generation of biomedical big data. The main challenge and bottleneck for the related research is the conversion of “biomedical big data” into interpretable information and hence discoveries. Computer vision theory has a huge potential in many aspects for automated understanding of biomedical data and has been used successfully to speed up and improve applications such as large-scale cell image analysis (image preconditioning, cell segmentation and detection, cell tracking, and cell behavior identification), image reconstruction and registration, organ segmentation and disease classification. Moreover, when it comes to the new era of machine learning, deep learning has revolutionized multiple fields of computer vision, significantly pushing the state of arts of computer vision systems in a broad array of high-level tasks.
This special issue serves as a forum to bring together active researchers all over the world to share their recent advances in this exciting area. We solicit original contributions in three-fold: (1) present state-of-the-art theories and novel application scenarios related to biomedical big data analytics; (2) survey the recent progress in this area; and (3) build benchmark datasets.
General Call for Papers
Access Recently Published TBD Articles
Sign up for the Transactions Connection Newsletter.
TBD is financially cosponsored by:
TBD is technically cosponsored by: