Multi-Sensor Data Fusion in Cluster based Wireless Sensor Networks Using Fuzzy Logic Method

Manjunatha, P.; Verma, Akshay; Srividya, A.

doi:10.1109/iciinfs.2008.4798453

Cited by 92 publications

(54 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the sake of clarity of machine learning domain the correlated sensor data used for a detection of fi re are converted to nominal types [12]. Input data are defi ned as IF-THEN rules based on heuristic information that mainly comes from expert knowledge of the fi re detection systems.…”

Section: Figurementioning

confidence: 99%

Comparative Analysis of Data Mining Techniques Applied to Wireless Sensor Network Data for Fire Detection

Maksimović¹,

Vujović²

2013

JITA

View full text Add to dashboard Cite

Abstract:Wireless sensor networks (WSN) are a rapidly growing area for research and commercial development with very wide range of applications. Using WSNs many critical events like fi re can be detected earlier to prevent loosing human lives and heavy structural damages. Integration of soft computing techniques on sensor nodes, like fuzzy logic, neural networks and data mining, can signifi cantly lead to improvements of critical events detection possibility. Using data mining techniques in process of patterns discovery in large data sets it's not often so easy. A several algorithms must be applied to application before a suitable algorithm for selected data types can be found. Therefore, the selection of a correct data mining algorithm depends on not only the goal of an application, but also on the compatibility of the data set. This paper focuses on comparative analysis of various data mining techniques and algorithms and in that purpose three different experiments on WSN fi re detection data are proposed and performed. The primary goal was to see which of them has the best classifi cation accuracy of fuzzy logic generated data and is the most appropriate for a particular application of fi re detection.

show abstract

Section: Figurementioning

confidence: 99%

Comparative Analysis of Data Mining Techniques Applied to Wireless Sensor Network Data for Fire Detection

Maksimović¹,

Vujović²

2013

JITA

View full text Add to dashboard Cite

show abstract

“…However, greater benefits can be achieved if the engine is implemented in a distributed manner over the nodes. A relevant example uses cluster heads to host inference engine to fuse collected data and identify the event [50]. Fuzzy logic is often used in conjunction with Artificial Neural Networks.…”

Section: Fuzzy Logicmentioning

confidence: 99%

An Objective Based Classification of Aggregation Techniques for Wireless Sensor Networks

Tariq

Ahmed

Zia

2012

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract.This paper presents a comprehensive survey of aggregation techniques that can be used in distributed manner to improve lifetime and energy conservation of wireless sensor networks. These techniques are designed to achieve some improvement objective e.g. reducing data size, minimizing transmission energy, enhancing accuracy etc. Main contribution of this work is proposal of a novel classification of such techniques based on the type of improvement they offer when applied to WSNs. We first review the meaning of term aggregation and then associate it with the proposed classes. Each class is presented with a brief literature review of example applications in WSN.Keywords: Aggregation, wireless sensor networks, data fusion, energy conservation, accuracy IntroductionWireless Sensor Networks (WSNs) are adhoc networks comprising of resource constrained nodes, mostly of small size and low cost, with sensing and communication capabilities. The nodes collect sensor readings and communicate them to sink, mostly outside network, also known as Base Station (BS), via neighbouring nodes. BS processes the data to get conclusions about the state of sensed environment. WSN has been identified as one of the most important technologies of 21st century and has gained popularity due to their applications in social, environmental, military, medical, disaster relief, search and rescue domains. The nature of WSN applications requires nodes to be small and cheap which sets limitations on the available resources and capacity of these nodes. However, irrespective of resource constraints the nodes are bound to handle and transmit large amount of sensed data. Hence, a number of optimization techniques are used to minimize energy consumption, improve bandwidth utilization and increase throughput.Aggregation is one of the common methods used to improve network lifetime in WSNs. Aggregation is a term that has been defined in literature in a number of ways, sometimes synonymously with (data or sensor) fusion. Van Renesse [1] describes aggregation as "… programmable composition of the raw data into less voluminous refined data…". Similarly, it is stated as a combination of data from different sources to eliminate redundancy in [2]. Data fusion has also been defined as the combination of data from multiple sensors to achieve improved accuracy and inferences [3]. However, some researchers choose for a more generic connotation and express the output information of fusion process to be better in 'quality ' [4] or 'some sense' [5]. The criteria of betterment may be qualitative or quantitative.We share this generic view and define aggregation as a process which, when applied on a set of data, results in an output that is an improved representation of input. The improvements are suggested to be in the form of accuracy, completeness, relevance, reliability, energy conservation, efficiency etc. In sensor networks, the input may comprise of data sensed by one sensor, collected over a period, also called temporal aggregation, or from a number of se...

show abstract

“…A fire detection technique using neural network and fuzzy inference is introduced in [2]. Type-1 fuzzy system is used to detect fire in WSN [3], in this paper author have used four parameters temperature, humidity, light intensity and carbon mono-oxide density to find out the probability of fire using type-1 fuzzy inference.…”

Section: Related Workmentioning

confidence: 99%

“…For detecting fire we have taken four input factors in our account as in [3] i.e. temperature, light intensity, humidity and carbon mono-oxide density.…”

Section: Figure 5 Representation Of a Type-2 Membership Function Usimentioning

confidence: 99%

Forest Fire Detection through Wireless Sensor Network using Type-2 Fuzzy System

Singh¹,

Singh²

2012

IJCA

View full text Add to dashboard Cite

Fire detection is always been a crucial challenge for human, moreover detecting fire using automated sensors definitely requires efficient and accurate ways. Since fire depends on more than one physical/environmental condition simultaneously, so in this paper we have used fuzzy type-2 logic for fire detection. Fuzzy gives best results in such cases because there is an uncertainty about how much extent of a factor like temperature, humidity and light intensity should be involved to cause a fire. In addition to this interval type-2 fuzzy system is used to make the results accurate and error free so that there would be no uncertainty in decision making.

show abstract

Multi-Sensor Data Fusion in Cluster based Wireless Sensor Networks Using Fuzzy Logic Method

Cited by 92 publications

References 12 publications

Comparative Analysis of Data Mining Techniques Applied to Wireless Sensor Network Data for Fire Detection

Comparative Analysis of Data Mining Techniques Applied to Wireless Sensor Network Data for Fire Detection

An Objective Based Classification of Aggregation Techniques for Wireless Sensor Networks

Forest Fire Detection through Wireless Sensor Network using Type-2 Fuzzy System

Contact Info

Product

Resources

About