Now showing 1 - 4 of 4
  • Publication
    Data Mining Techniques Applied to Wireless Sensor Networks for Early Forest Fire Detection
    Nowadays, forest fires are a serious threat to the environment and human life. The monitoring system for forest fires should be able to make a real-time monitoring of the target region and the early detection of fire threats. In this paper, we propose a new approach based on the integration of Data Mining techniques into sensor nodes for forest fire detection. This approach is based on the clustered WSN where each sensor node will individually decide on detecting fire using a classifier of Data Mining techniques. When a fire is detected, the correspondent node will send an alert through its cluster-head which will pass through gateways and other cluster-heads until it will reach the sink in order to inform the firefighters. We use the CupCarbon simulator to validate and evaluate our proposed approach. Through extensive simulation experiments, we show that our approach can provide a fast reaction to forest fires while consuming energy efficiently.
    Scopus© Citations 24  1048
  • Publication
    CupCarbon: A Multi-Agent and Discrete Event Wireless Sensor Network Design and Simulation Tool
    (Institute for Computer Science, Social Informatics and Telecommunications Engineering (ICST), 2014-03-19) ; ; ;
    This paper presents the first version of a Wireless Sensor Network simulator, called CupCarbon. It is a multi-agent and discrete event Wireless Sensor Network (WSN) simulator. Networks can be designed and prototyped in an ergonomic user-friendly interface using the OpenStreetMap (OSM) framework by deploying sensors directly on the map. It can be used to study the behaviour of a network and its costs. The main objectives of CupCarbon are both educational and scientific. It can help trainers to explain the basic concepts and how sensor networks work and it can help scientists to test their wireless topologies, protocols, etc. The current version can be used only to study the power diagram of each sensor and the overall network. The power diagrams can be calculated and displayed as a function of the simulated time. Prototyping networks is more realistic compared to existing simulators.
      1400Scopus© Citations 97
  • Publication
    Intelligent Data Mining Techniques for Emergency Detection in Wireless Sensor Networks
    Event detection is an important part in many Wireless Sensor Network (WSN) applications such as forest fire and environmental pollution. In this kind of applications, the event must be detected early in order to reduce the threats and damages. In this paper, we propose a new approach for early forest fire detection, which is based on the integration of Data Mining techniques into sensor nodes. The idea is to partition the node set into clusters so that each node can individually detect fires using classification techniques. Once a fire is detected, the corresponding node will send an alert to its cluster-head. This alert will then be routed via gateways and other cluster-heads to the sink in order to inform the firefighters. The approach is validated using the CupCarbon simulator. The results show that our approach can provide a fast reaction to forest fires with efficient energy consumption.
      308
  • Publication
    Finding the polygon hull in wireless sensor networks
    Finding the border of a wireless sensor network (WSN) is one of the most important issues today. This border can be used, for example, to monitor a frontier or a secured place of sensitive sites of a country. One of the methods that can be useful for this kind of problems is Jarvis algorithm which has to be adapted to take account of connected nodes in a Euclidean graph. For this kind of networks, the complexity is reduced from O(nh) to O(kh2), where n is the number of sensors, k is the maximum number of neighbors of a sensor in the network and h is the number of sensors of the envelope. The application of this algorithm to WSNs allows in each iteration to determine the next boundary neighbor of the current node. The advantage of this procedure is that each node knows its neighbor in a single operation. Then, each boundary node will periodically send a message to its neighbor, which should respond. If a response is not received, a situation of failure or intrusion will be triggered and network restructuring will be launched to find a new border. In this work, we have shown that the application of this algorithm in the presence of sub-absorbent graphs can lead to an infinite loop situation. We have also shown how to overcome this situation and how the algorithm can be applied to the case of WSNs.
      145