Hotspots Analysis Using Cyber-Physical-Social System for a Smart City

Abstract

Internet of things plays a vital role in providing various services to users. Significant volumes of data are generated from the communication between a large numbers of heterogeneous devices over the Internet. Big data technology is generally used to handle the large volume of data. Complex networks are graphs (networks) having non-trivial topological features, such as random graphs and lattices. Big data of complex networks concerns big data methods that can be used to analyze massive structural data sets, including considerably large networks and sets of graphs. This study is based on the critical phenomenon arising in complex networks that enable us to analytically predict the hotspots in smart cities. Hotspots are places with significantly high communication traffic relative to others. In this study, we propose a cyber-physical-social system for the analysis of high communication traffic hotspots using telecom data. The proposed model constructs a graph, and perform social network analysis on it. The process of hotspot extraction is performed, followed by social network analysis, which is conducted by quantifying the importance of each hotspot based on network metrics. These metrics aid in determining the importance of each hotspot in a telecom data network. Our objective is to prioritize different areas and detect hotspots quickly. Our results indicate that the proposed model has an efficiency comparable with that of state of the art methods. This research study will be helpful for urban planning and development, as well as in upgrading telecommunication infrastructure.

Optimizing Prediction of YouTube Video Popularity Using XGBoost

“…Researcher in [43] using telecom data, a cyber physical social system is used to analyze high communication traffic areas. The suggested model creates a graph and analyses it using social network analysis.…”

“…Hence, in this work, more features/categories are added, and for dimensionality reduction, the fusion technique is utilized. As in [43], the data set used for prediction is performed on data of long time period and its performance can be improved by shortening the prediction time. In our proposed model, predictions are performed on data of short time period as compared to [43].…”

Know Your Stars Before They Fall Apart: A Social Network Analysis of Telecom Industry to Foster Employee Retention Using Data Mining Technique

“…Since it is a directional measure we calculated the out-degree centrality for HiPos and in-degree centralities for influencer identification. The higher the numbers are on degree measure, the more central the employees are in their network [58]. In-degree centrality refers to the number of incoming ties directed towards the focal node whereas out-degree centrality refers to the number of outgoing ties which the focal node directs towards others in their network [59].…”

An effective method for determining consensus in large collectives

“…Another example is Internet of Things (IoT). It has given rise to large amounts of continuous data collected from the physical world [4], [5]. IoT has pervasively penetrated most areas of human life, such as homes, cities, industry, organizations, agriculture, hospitals, and healthcare [6], [7], [8].…”