Semisupervised Classification Based Clustering Approach in WSN for Forest Fire Detection

Forest fire is a very considerable problem of ecological system. This paper depicts a novel technique which detects the high active(HA) zone (nearer to the epicenter of fire) in the forest and transmits all sensed data to the base station through wireless communication as early as possible. Fire office takes necessary action to prevent the spreading of fire. For this purpose sensors are deployed in forest zone to sense different data which are necessary for detecting forest fire and divides it into different clusters. A semisupervised rule-based classification model is proposed in this paper to detect whether its zone is high active, medium active (MA) or low active (LA) cluster in the forest. We train our proposed integrated model in such a way when only one parameter of sensed data is transmitted by the sensor nodes due to energy constraint to the initiator of that zone, initiator can be able to predict the state of (HA,MA,LA) zone with 96% accuracy. All the sensor nodes in HA cluster transmit their packet through cluster head to the base station continuously applying greedy forwarding technique. Authors consider energy saving strategy during cluster head selection and data transmission in HA zone. On the other hand, sensors in MA zone transmit packet periodically and LA zone avoids to transmit the sensed data. This way proposed technique transmits the sensed data from HA zone efficiently and quickly to forest office for forest fire prevention and saves the energy of all sensor nodes in the forest.

[1]  Paramasivan Saratchandran,et al.  Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm , 1998, IEEE Trans. Neural Networks.

[2]  R. B. Patel,et al.  EEHC: Energy efficient heterogeneous clustered scheme for wireless sensor networks , 2009, Comput. Commun..

[3]  Biao Qin,et al.  DTU: A Decision Tree for Uncertain Data , 2009, PAKDD.

[4]  Leonidas J. Guibas,et al.  Locating and Bypassing Holes in Sensor Networks , 2006, Mob. Networks Appl..

[5]  Sachin Tripathi,et al.  Energy Aware Fuzzy Based Multi-Hop Routing Protocol Using Unequal Clustering , 2017, Wirel. Pers. Commun..

[6]  Suman Saha,et al.  Distributed Event Detection in Wireless Sensor Networks for Forest Fires , 2013, 2013 UKSim 15th International Conference on Computer Modelling and Simulation.

[7]  Palvinder Singh Mann,et al.  Energy-Efficient Hierarchical Routing for Wireless Sensor Networks: A Swarm Intelligence Approach , 2017, Wirel. Pers. Commun..

[8]  M Buscema,et al.  Back propagation neural networks. , 1998, Substance use & misuse.

[9]  Nirvana Meratnia,et al.  Outlier Detection Techniques for Wireless Sensor Networks: A Survey , 2008, IEEE Communications Surveys & Tutorials.

[10]  Ajay K. Sharma,et al.  Hybrid Energy Efficient Distributed Protocol for Heterogeneous Wireless Sensor Network , 2010 .

[11]  Poonam Tyagi,et al.  Comparative Analysis of Cluster Based Routing Protocols used in Heterogeneous Wireless Sensor Network , 2011 .

[12]  Khaled Elleithy,et al.  Optimized Algorithm for Fire Detection over WSN using Micaz Motes , 2012 .

[13]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[14]  Ahmad Khademzadeh,et al.  Increasing Lifetime and Fault Tolerance Capability in Wireless Sensor Networks by Providing a Novel Management Framework , 2017, Wirel. Pers. Commun..

[15]  Iman Saleh,et al.  A Fault Tolerance Management Framework for Wireless Sensor Networks , 2006 .

[16]  Zahir Tari,et al.  By-Passing Infected Areas in Wireless Sensor Networks Using BPR , 2015, IEEE Transactions on Computers.

[17]  Kai-Ten Feng,et al.  Greedy Anti-Void Routing Protocol for Wireless Sensor Networks , 2007, IEEE Communications Letters.

[18]  Zhang Jun-gu,et al.  Forest fire detection system based on ZigBee wireless sensor network. , 2007 .

[19]  Vandana Mohindru,et al.  Detection of forest fires using machine learning technique: A perspective , 2015, 2015 Third International Conference on Image Information Processing (ICIIP).

[20]  Ahmed Yassin Al-Dubai,et al.  A new energy efficient Cluster Based Protocol for Wireless Sensor Networks , 2015, 2015 Federated Conference on Computer Science and Information Systems (FedCSIS).

[21]  Dirk Timmermann,et al.  Low energy adaptive clustering hierarchy with deterministic cluster-head selection , 2002, 4th International Workshop on Mobile and Wireless Communications Network.

[22]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[23]  Ashish Kumar Srivastava,et al.  An energy efficient framework for detection and monitoring of forest fire using mobile agent in wireless sensor networks , 2014, 2014 IEEE International Conference on Computational Intelligence and Computing Research.

[24]  Nirvana Meratnia,et al.  Sensor fusion-based event detection in Wireless Sensor Networks , 2009, 2009 6th Annual International Mobile and Ubiquitous Systems: Networking & Services, MobiQuitous.

[25]  Mohammad Ghavami,et al.  A new approach for event detection using k-means clustering and neural networks , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).