Fire Data Analysis and Feature Reduction Using Computational Intelligence Methods

Bahrepour, Majid; Zwaag, Berend Jan van der; Meratnia, Nirvana; Havinga, Paul J.M.

doi:10.1007/978-3-642-14616-9_28

Cited by 23 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, sensor nodes are vulnerable to failure because the WSNs are often deployed in harsh environments [18][19][20][21]. Outliers are commonly found in datasets collected by the WSNs installed in harsh environments [22,23].…”

Section: Outlier Detection In Wsn Applicationsmentioning

confidence: 99%

Bayesian-Optimization-Based Peak Searching Algorithm for Clustering in Wireless Sensor Networks

Zhang

Zhao

Shin

et al. 2018

JSAN

View full text Add to dashboard Cite

Abstract:We propose a new peak searching algorithm (PSA) that uses Bayesian optimization to find probability peaks in a dataset, thereby increasing the speed and accuracy of clustering algorithms. Wireless sensor networks (WSNs) are becoming increasingly common in a wide variety of applications that analyze and use collected sensing data. Typically, the collected data cannot be directly used in modern data analysis problems that adopt machine learning techniques because such data lacks additional information (such as data labels) specifying its purpose of users. Clustering algorithms that divide the data in a dataset into clusters are often used when additional information is not provided. However, traditional clustering algorithms such as expectation-maximization (EM) and k-means algorithms require massive numbers of iterations to form clusters. Processing speeds are therefore slow, and clustering results become less accurate because of the way such algorithms form clusters. The PSA addresses these problems, and we adapt it for use with the EM and k-means algorithms, creating the modified PSEM and PSk-means algorithms. Our simulation results show that our proposed PSEM and PSk-means algorithms significantly decrease the required number of clustering iterations (by 1.99 to 6.3 times), and produce clustering that, for a synthetic dataset, is 1.69 to 1.71 times more accurate than it is for traditional EM and enhanced k-means (k-means++) algorithms. Moreover, in a simulation of WSN applications aimed at detecting outliers, PSEM correctly identified the outliers in a real dataset, decreasing iterations by approximately 1.88 times, and PSEM was 1.29 times more accurate than EM at a maximum.

show abstract

Section: Outlier Detection In Wsn Applicationsmentioning

confidence: 99%

Bayesian-Optimization-Based Peak Searching Algorithm for Clustering in Wireless Sensor Networks

Zhang

Zhao

Shin

et al. 2018

JSAN

View full text Add to dashboard Cite

show abstract

“…Our approach is based on implementing classification techniques on wireless sensor nodes attached to patients' body, online evaluation of the classification results on individual nodes, and fusing results of various nodes to resolve possible conflicts between sensor nodes and reach a consensus. Previously in Bahrepour, Zhang et al 2009;Bahrepour, van der Zwaag et al 2010), we have shown capability of machine learning based classification techniques in distributed detection of environmental events such as fire. There is no reason to believe that classification techniques used in other domains are not applicable for medical domain.…”

Section: Introductionmentioning

confidence: 99%

Sensor Fusion-Based Activity Recognition for Parkinson Patients

Bahrepour¹,

Meratnia²,

Taghikhaki³

et al. 2011

Sensor Fusion - Foundation and Applications

Self Cite

View full text Add to dashboard Cite

“…Fire #1 dataset is real dataset containing three types of fires, i.e., flaming fires (fires that produce massive heat), smoldering fires (fires that produce massive smoke) and nuisances (fire-like incidents such as smoking a cigarette or toasting a bread) [108]. The dataset is obtained from the National Institute of Standard and Technology (NIST) website [109] by merging two smoldering fire datasets (SDC31, SDC40), two flaming fire datasets (SDC10, SDC14) and two nuisance resource datasets (MHN06, MHN16).…”

Section: Fire #1 Datasetmentioning

confidence: 99%

“…Later on in this chapter, we also discuss † † This chapter is partially published with the title: "Fire data analysis and feature reduction using computational intelligence methods". In: Advances in Intelligent Decision Technologies -Proceedings of the Second KES International Symposium IDT 2010, 28-30 July 2010, Baltimore, Maryland, USA [108].…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence based event detection in wireless sensor networks

Bahrepour¹

Self Cite

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) are composed of large number of small, inexpensive devices, called sensor nodes, which are equipped with sensing, processing, and communication capabilities. While traditional applications of wireless sensor networks focused on periodic monitoring, the focus of more recent applications is on fast and reliable identification of out-of-ordinary situations and events. This new functionality of wireless sensor networks is known as event detection. Due to the fact that collecting all sensor data centrally to perform event detection is inefficient in many occasions, the new trend in event detection in wireless sensor networks is to perform detection in the network. Design of in-network event detection methods for wireless sensor networks is by no means straightforward, as it needs to efficiently cope with various challenges and concerns including unreliability, heterogeneity, adaptability, and resource constraints. In this thesis, we tackle this problem by proposing fast, accurate, innetwork, and intelligent event detection methods using artificial intelligence (AI) and machine learning (ML) approaches. To this end, the main objective of this thesis is to analyze, investigate applicability, and optimize artificial intelligence (AI) and machine learning (ML) methods for efficient, distributed, local and in-network event detection in wireless sensor networks (WSNs). The main contributions of the thesis can be summarized as: Feature extraction and reduction in three datasets for event detection in WSNs. We choose three datasets containing sensory data from real V Acknowledgment Give light, and the darkness will disappear of itself. Desiderius Erasmus (1466-1536) known as Erasmus of Rotterdam, Dutch Renaissance humanist, Catholic priest, social critic, teacher, and theologian.

show abstract

Fire Data Analysis and Feature Reduction Using Computational Intelligence Methods

Cited by 23 publications

References 15 publications

Bayesian-Optimization-Based Peak Searching Algorithm for Clustering in Wireless Sensor Networks

Bayesian-Optimization-Based Peak Searching Algorithm for Clustering in Wireless Sensor Networks

Sensor Fusion-Based Activity Recognition for Parkinson Patients

Artificial intelligence based event detection in wireless sensor networks

Contact Info

Product

Resources

About