A novel algorithm for mining behavioral patterns from wireless sensor networks
- Authors: Rashid, Md. Mamunur , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2014
- Type: Text , Conference paper
- Relation: 2014 International Joint Conference on Neural Networks, IJCNN 2014; Beijing, China; 6th-11th July 2014 p. 1-7
- Full Text: false
- Reviewed:
- Description: Due to recent advances in wireless sensor networks (WSNs) and their ability to generate huge amount of data in the form of streams, knowledge discovery techniques have received a great deal of attention to extract useful knowledge regarding the underlying network. Traditionally sensor association rules measure occurrence frequency of patterns. However, these rules often generate a huge number of rules, most of which are non-informative or fail to reflect the true correlation among data objects. In this paper, we propose a new type of sensor behavioral pattern called associated sensor patterns that captures association-like co-occurrences and the strong temporal correlations implied by such co-occurrences in the sensor data. We also propose a novel tree structure called as associated sensor pattern tree (ASPT) and a mining algorithm, associated sensor pattern (ASP) which facilitates frequent pattern (FP) growth-based technique to generate all associated sensor patterns from WSN data with only one scan over the sensor database. Extensive performance study shows that our algorithm is very efficient in finding associated sensor patterns than the existing significant algorithms.
A technique for parallel share-frequent sensor pattern mining from wireless sensor networks
- Authors: Rashid, Md. Mamunur , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2014
- Type: Text , Conference paper
- Relation: 14th Annual International Conference on Computational Science, ICCS 2014; Cairns, Australia; 10th-12th June 2014; published in Procedia Computer Science p. 124-133
- Full Text:
- Reviewed:
- Description: WSNs generate huge amount of data in the form of streams and mining useful knowledge from these streams is a challenging task. Existing works generate sensor association rules using occurrence frequency of patterns with binary frequency (either absent or present) or support of a pattern as a criterion. However, considering the binary frequency or support of a pattern may not be a sufficient indicator for finding meaningful patterns from WSN data because it only reflects the number of epochs in the sensor data which contain that pattern. The share measure of sensorsets could discover useful knowledge about numerical values associated with sensor in a sensor database. Therefore, in this paper, we propose a new type of behavioral pattern called share-frequent sensor patterns by considering the non-binary frequency values of sensors in epochs. To discover share-frequent sensor patterns from sensor dataset, we propose a novel parallel technique. In this technique, we develop a novel tree structure, called parallel share-frequent sensor pattern tree (PShrFSP-tree) that is constructed at each local node independently, by capturing the database contents to generate the candidate patterns using a pattern growth technique with a single scan and then merges the locally generated candidate patterns at the final stage to generate global share-frequent sensor patterns. Comprehensive experimental results show that our proposed model is very efficient for mining share-frequent patterns from WSN data in terms of time and scalability.
Dynamic clusters graph for detecting moving targets using WSNs
- Authors: Armaghani, Farzaneh , Gondal, Iqbal , Kamruzzaman, Joarder , Green, David
- Date: 2012
- Type: Text , Conference paper
- Relation: 76th IEEE Vehicular Technology Conference, VTC Fall 2012; Quebec City, Canada; 3rd-6th September 2012 p. 1-5
- Full Text: false
- Reviewed:
- Description: Efficient target tracking applications require active sensor nodes to track a cluster of moving targets. Clustering could lead to significant cost improvement as compared to tracking individual targets. This paper presents accurate clustering of targets for both coherent and incoherent movement patterns. We propose a novel clustering algorithm that utilises an implicit dynamic time frame to assess the relational history of targets in creating a weighted graph of connected components. The proposed algorithm employs key features of localisation algorithms in target tracking, namely, estimated current and predicted locations to determine the relational directions and distances of moving targets. Our simulation results show a significant improvement on the clustering accuracy and computation time by dynamically adjusting the history-window size and predicting the relationships among targets.
Cross layer modeling of contention-based MAC and deterministic routing protocols in multi-hop WSNs
- Authors: Bhuiyan, Mohammad
- Date: 2011
- Type: Text , Conference paper
- Relation: International Conference on Information Networking 2011, ICOIN 2011; Kuala Lumpur, Malaysia; 26th-28th January 2011 p. 74-79
- Full Text: false
- Reviewed:
- Description: Analytical studies of Medium Access Control (MAC) layer protocols can be used to improve the performance of multi-hop Wireless Sensor Networks (WSNs) in the presence of hidden stations. The selected MAC layer protocol should conform to the distributed nature of the WSNs. The IEEE 802.11 MAC layer with Distributed Coordination Function (DCF) is well suited to WSNs. Analytical studies of IEEE 802.11 DCF in the presence of hidden stations in multi-hop WSNs is very crucial as it is widely used. In this paper, an analytical model considering hidden stations in a multi-hop WSN has been developed to study the cross layer performance of IEEE 802.11 DCF under a deterministic routing protocol. Using this model, theoretically measurements like probability of collision, medium access delay, end to end success probability, and end to end delay of each sensor node in the network can be achieved. Accuracy of the analytical model has been verified with simulation results. The model can be used to determine whether a specific WSN can achieve the expected performance.
Dual-channel based energy efficient event clustering and data gathering in WSNs
- Authors: Bhuiyan, Mohammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2011
- Type: Text , Conference paper
- Relation: 17th Asia Pacific Conference on Communications, APCC 2011; Sabah, Malaysia; 2nd-5th October 2011 p. 241-246
- Full Text: false
- Reviewed:
- Description: Wireless sensor networks (WSNs), now-a-days, are deployed in environmental data collection as well as in critical event monitoring. Successful data collection requires reliability while reliable event detection necessitates timeliness. Simultaneous data gathering and event monitoring is not well studied in literature. In this paper, we propose a system model that works on homogeneous data gathering WSNs. When an event occurs, an event cluster with a different transmission channel is formed and both data gathering and event monitoring are performed at the same time. The proposed model has a novel routing strategy with a built-in congestion control technique to provide timely delivery of event data. Experimental results show that the proposed method performs better than known similar techniques in terms of reliable data gathering and reliable timely event monitoring. It also enhances the network lifetime significantly compared to other existing methods.
I-MAC: energy efficient intelligent MAC protocol for wireless sensor networks
- Authors: Bhuiyan, Mohammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2011
- Type: Text , Conference paper
- Relation: 17th Asia Pacific Conference on Communications, APCC 2011; Sabah, Malaysia; 2nd-5th October 2011 p. 133-138
- Full Text: false
- Reviewed:
- Description: Energy efficiency is a vital aspect of resource constrained wireless sensor networks (WSNs). All protocols designed for WSNs must be energy aware in order to prolong the network lifetime. In this paper, we have designed a novel MAC layer protocol (I-MAC: Intelligent MAC) for WSNs. By exercising intelligent sleep and wake-up schedule, I-MAC saves energy of the resource constrained sensor nodes greatly. At the same time, I-MAC does not compromise its operational performances. Both analytical study and simulation prove that I-MAC is not only highly energy efficient but also its operational performances are better than similar protocols.