Tactical big data analytics: challenges, use cases, and solutions

@article{Savas2014TacticalBD,
  title={Tactical big data analytics: challenges, use cases, and solutions},
  author={Onur Savas and Yalin Evren Sagduyu and Julia Deng and Jason H. Li},
  journal={SIGMETRICS Perform. Evaluation Rev.},
  year={2014},
  volume={41},
  pages={86-89}
}
We discuss tactical challenges of the Big Data analytics regarding the underlying data, application space, and com- puting environment, and present a comprehensive solution framework motivated by the relevant tactical use cases. First, we summarize the unique characteristics of the Big Data problem in the Department of Defense (DoD) context and underline the main differences from the commercial Big Data problems. Then, we introduce two use cases, (i) Big Data analytics with multi-intelligence… 

Figures from this paper

Predictive Analytics On Big Data - An Overview

This paper categorizes the major technical challenges of predictive analytics on big data under six headings and concludes with the identification of open issues and future directions to work on for researchers in this field.

An Analysis for Big Data and its Technologies

The meaning, characteristics, models, technologies, life cycle and many other aspects of big data are provided.

Efficient Analysis of Big Data Using Map Reduce Framework

Various methods for catering to the problems in hand through MapReduce framework over HDFS are suggested, which is needed for implementing Big Data analysis using HDFS.

Ample Data Exploration and Map Reduce Indoctrination Decisive Factor

During this analysis paper the authors recommend numerous ways for line of work to the issues in hand through MapReduce framework over HDFS, which is required for implementing huge information analysis victimization HDFS.

Military Simulation Big Data: Background, State of the Art, and Challenges

Several large-scale military simulations producing big data (MS big data) for a variety of usages are reviewed and the main characteristics of result data are summarized and a framework is proposed as a basis for future work.

Big Data technologies to process spatial and attribute data when designing and operating mine-engineering systems

Various methods applied to collect and analyse ‘big data’ to do a feasibility study and design mine and engineering systems are covered.

An Improved Version of Big Data Classification and Clustering using Graph Search Technique

Map Reduce is a technique which makes use of file indexing with mapping, sorting, shuffling, reducing etc. which is mainly used for classification and clustering of Big Data.

Big data implementation and visualization

  • Deepa GuptaSameera Siddiqui
  • Computer Science
    2014 International Conference on Advances in Engineering & Technology Research (ICAETR - 2014)
  • 2014
This work presents pseudo code to compute and query a nanocube, and shows how it can be used to generate well-known visual encodings such as heat maps, histograms, and parallel coordinate plots.

Categorizing Requirements for Enterprise Architecture Management in Big Data Literature

Based on a systematic literature identification, conceptual categories of requirements for EA management are elicited utilizing an inductive category formation and constitute a category system that facilitates a new perspective on EA management and fosters the innovation-driven evolution of the EA management discipline.

Forensic Data Analysis Challenges in Large Scale Systems

There is significant scope to apply big-data techniques to the challenges of monitoring and forensic data analysis in large-scale systems, but it is key that, where big- data techniques are applied, accepted standards for eDiscovery are adhered to, so that the results of any forensic analysis stand the best chance of being accepted as evidence.

References

SHOWING 1-8 OF 8 REFERENCES

GraphLab: A New Framework For Parallel Machine Learning

The expressiveness of the GraphLab framework is demonstrated by designing and implementing parallel versions of belief propagation, Gibbs sampling, Co-EM, Lasso and Compressed Sensing and it is shown that using GraphLab the authors can achieve excellent parallel performance on large scale real-world problems.

Hierarchical structure and the prediction of missing links in networks

This work presents a general technique for inferring hierarchical structure from network data and shows that the existence of hierarchy can simultaneously explain and quantitatively reproduce many commonly observed topological properties of networks.

Latent Dirichlet Allocation

CrowdForge: crowdsourcing complex work

This work presents a general purpose framework for accomplishing complex and interdependent tasks using micro-task markets, a web-based prototype, and case studies on article writing, decision making, and science journalism that demonstrate the benefits and limitations of the approach.

Moving Navy Command and Control into the Future

  • Moving Navy Command and Control into the Future
  • 2013

Moving Navy Command and Control into the Future

  • January 2013.
  • 2013

Ozone Platform

  • Ozone Platform

Performance Evaluation Review

  • Performance Evaluation Review
  • 2014