Abstract

Wireless sensor networks are usually deployed for monitoring given physical phenomena taking place in a specific space and over a specific duration of time. The spatio-temporal distribution of these phenomena often correlates to certain physical events. To appropriately characterise these events-phenomena relationships over a given space for a given time frame, we require continuous monitoring of the conditions. WSNs are perfectly suited for these tasks, due to their inherent robustness. This paper presents a subtractive fuzzy cluster means algorithm and its application in data stream mining for wireless sensor systems over a cloud-computing-like architecture, which we call sensor cloud data stream mining. Benchmarking on standard mining algorithms, the k-means and the FCM algorithms, we have demonstrated that the subtractive fuzzy cluster means model can perform high quality distributed data stream mining tasks comparable to centralised data stream mining.

Highlights

  • Wireless sensor networks (WSNs) are usually deployed to measure given physical phenomena over a certain space, within a specific time frame

  • First criteria: If the potential value ratio of the current data point to the original first cluster centre is larger than the accept ratio, the current data point is chosen as a cluster centre

  • The results presented regarding performance evaluation of the application and the network services are based on averages of 10 to 15 simulation runs with realistic parameters obtained from experimental tests

Read more

Summary

Introduction

Wireless sensor networks (WSNs) are usually deployed to measure given physical phenomena over a certain space, within a specific time frame. The spatio-temporal distribution of these phenomena often correlates with certain physical events To appropriately characterise these events-phenomena relationships over a given space for a specific time frame, continuous monitoring of the conditions is Sensors 2014, 14 required. Spatio-temporal distribution of weather conditions over a forestry area closely correlate with the likelihood of forest fire events in the area. The computation of the likelihood of these events can be automated and graphically presented This problem falls under the general category of multivariate spatial condition mapping, with the added complexity of continuously streaming data. FWI is used to estimate fuel moisture content and generate a series of relative fire behaviour indices based on weather observations.

Spatial Condition Clustering
Data Stream Mining Algorithm
Subtractive Clustering Method
Fuzzy C-Means Clustering
The SUBFCM Algorithm
Simulation and Analysis
SUBFCM Performance Characterisation
Results and Discussion
Stream Rate Results
Cluster Density
Non-Uniform Cluster Density
Average Energy Consumption
Average Data Delivery Delay
Packet Delivery Ratio
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call