Predictive Analytics of Hyper-Connected Collaborative Network

Predictive Analytics of Hyper-Connected Collaborative Network

Ehsan Alirezaei, Saeed Parsa, Zahra Vahedi
DOI: 10.4018/IJBDCN.2019010102
(Individual Articles)
No Current Special Offers


The foundation of the infrastructure of a collaborative network for ubiquitous connectivity will employ hyper-connected technologies in smart and sustainable cities. Typically, there are millions of items for processing and analytics on the massive generated data. The predictive analytics are indispensable for such volumes of which there are many drifts in data structures and contents. In order to make better decisions and future planning of ubiquity, a model, and correspondence implementation are designed and developed. It brings decision-making to the expected boundary of collaboration for different performance indexes. The selected method finds cause-and-effect between data to predict the optimum responses to incoming events. The core of approach focuses on Event-Condition-Action rules to build decision trees, which helps further planning. The method can summarize complexity via effective recommended decisions to local experts and analysts.
Article Preview

1. Introduction

The Hyper-Connected Collaborative Networks (HCNs) involve hundreds of people and millions of items for processing and analyzing the massive generated data through Collaborative Network (CN). Moreover, potential management functions will emerge quickly. Connecting up, analyzing and integrating the information produced by the various forms of every ware-devices, provides a more consistent and smart understanding of the ubiquitous city that enhances efficiency and sustainability (Hancke & Hancke, 2013). The HCN in ubiquitous city needs intelligent business processes that run across multiple organization and individuals. The intelligence in business processes has three levels of self-awareness, the performance monitoring, and interactions understanding. The intelligence of business processes in HCN also needs cognitive learning that implies an understanding of behavior, context, interaction and the ability to react to the internal and environmental changes. For the situation of changes, decisions are the products of complex interactions (Patterson, Weil & Patel, 2010) in performance monitoring.

The Big data of monitoring has potential to leverage intelligence via efficient decision making, which should bring new forms of data analytics to cope with data abundance (Kitchin, 2014). Today, the decision making attained by using traditional business intelligence tools (Williams & Williams, 2004), which such tools may not be responsive in the HCN. The HCN data analytics is the application of advanced analytic techniques to Big data sets. In an HCN, scenarios are dynamic, complex and uncertain, so that the old analytical method may not be appropriate. A variety of shared data (e.g., Smart Health, e-Government, Market Intelligence) made it challenging problem in the planning of HCN processes. The increasing number of cross-functional events of HCN is beyond one organization boundaries. Such events promoted an incredible expansion in data of business process performance monitoring. The real-time analytics (RADEN, 2003) include the capability to use all available assets in an organization to improve the tasks and quality of services provided by processes. Practical evaluation of data will provide new insights into the existence of operational aspects and expose optimization occasions. Additionally, informed decision making will be possible by considering these data on an unprecedented scale to future planning.

The challenges of such decision making are not easy to address, such as correlation of data across organizational boundaries, measuring and improving the overall performance of processes, and collaborative analysis for managing geographically separated individuals. The problem of this paper is predictive analytics and planning of data from different levels and complexities of HCN processes. Data may come from structured or unstructured processes activities of processing unit operation (e.g., smart phones), location-aware applications, organizational systems, and context-relevant analysis, in which there are different aspects to be analyzed. The situations like these make it hard to make a correct decision via predictive analytics. Also, advanced analytic of HCN is computationally intensive and creates performance problems for illustrative analytics such as dashboards when contesting of computing resources. The research questions of the present paper are:

  • What is the approach to predictive analytics of HCN business processes performance indicators?

  • How will the performance metrics be employed in planning and decision making?

Complete Article List

Search this Journal:
Volume 20: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 19: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 18: 2 Issues (2022): 1 Released, 1 Forthcoming
Volume 17: 2 Issues (2021)
Volume 16: 2 Issues (2020)
Volume 15: 2 Issues (2019)
Volume 14: 2 Issues (2018)
Volume 13: 2 Issues (2017)
Volume 12: 2 Issues (2016)
Volume 11: 2 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing