Overlap Function Based Fuzzified Aquatic Behaviour Information Extracted Tsunami Prediction Model

Overlap Function Based Fuzzified Aquatic Behaviour Information Extracted Tsunami Prediction Model

Nikita Jain (University School of Information, Communication and Technology, Gobind Singh Indraprastha Universty, Delhi, India & Bharati Vidyapeeth's College of Engineering , New Delhi, India), Deepali Virmani (Department of Computer Science and Engineering, Bhagwan Parshuram Institute of Technology, Delhi, India) and Ajith Abraham (Machine Intelligence Research Labs (MIR Labs), Auburn, USA)
Copyright: © 2019 |Pages: 26
DOI: 10.4018/IJDST.2019010105

Abstract

Past natural hazards have produced numerous biological and physical indicators that can be used to predict similar instances in the future. These indicators can be sensed dynamically underwater or on land to generate real time alerts. This article proposes the first validated fuzzified system to predict tsunamis (FABETP) using an overlap-based algorithm. This proposed algorithm can predict seismicity based on underwater marine animal's anomalous behavior, characterized and implemented as biological indicators (i.e., aquatic animal behavioral attributes). Relevant information is extracted from these attributes and used to design fuzzy rules that generate opinion-based alerts. More precisely, the proposed algorithm, Overlap-based Fuzzified rated Marine Behavior, (OBF_MB), derives alert rules when executed on a sea turtle behavior dataset obtained from an online repository. The deployed underwater sensor-collected dataset includes the following measurements: induced electromagnetic field, undersea turtle count, and angle of deviation (in terms of the turtles' navigation direction formulated per month and per day). These values are used as the inputs to the proposed system. To generate an opinion, an information gain-based opinion score is used to calculate the opinion deviations from the generated opinions of the default rule. For future data values, 2004 is used here as the default opinion year and the scenarios is the default rule. This paper formulates three classes of opinions using the proposed algorithm: Alert, Pre-Alert and No-Alert. These opinions can be used in the future to generate real-time alerts based on aquatic animal behavior.
Article Preview
Top

Introduction

The South Asian Tsunami is the common name given by the scientific community to a massive underwater earthquake that occurred in 2004 along the western coasts of Sumatra and Indonesia (Munich RE, 2013), and was one of the deadliest events in history. Several countries: Indonesia, Srilanka, India and Thailand were victimized by this terrible event (Lay et al., 2005; Lovholt et al., 2006). This tsunami lead to the deployment of the Indian Ocean Tsunami Warning System (TWS) (Joseph, 2011) which was designed to predict tsunamis in real time and well in advance and generate warning messages for alerts or for mandatory evacuations. Despite the existence of this developed and operational tsunami warning system, there have been past instances when the expected alert warning messages were not generated (Lovholt et al., 2014). One such example stems from a recent report by the BBC, where the well-established Tsunami Early Warning System (TEWS) failed to generate any warning in response to a 7.8-scale earthquake that struck off the coast of West Sumatra on March 2, 2016 (BBC News, 2016). While many rationales (NewsNow, 2016) were cited for this catastrophic failure, distinctive gaps based on on-site experiences were addressed in a recent report (Lassa, 2016) by a research activist that addressed the following topics:

  • 1.

    Failure of tsunami sirens in remote areas;

  • 2.

    Forcing local authorities to revisit the monitoring of sea coasts and the effectiveness and authenticity of the generated warning messages;

  • 3.

    The dependency of local communities on buoys that analyze ocean wave behavior as the critical and sole indicators of tsunamis.

Similarly (as mentioned above) inspections have also been cited as culprits in various other scenarios (VoaNews, 2011) where experts have highlighted the inefficacy of prevailing warning systems. It is important to note that these warning systems were developed only after devastating events that had occurred years before (Lay et al., 2005; Lovholt, 2006) Figure 1a (Tsunami Bulletin, 2010) shows a still image taken after the fatal tsunami that hit Japan in 2011.

Clearly, such recent phenomena, which caused worldwide surprise and fear, highlight the dire need for efficient, alternative and complementary warning systems that would be effective in preparing for similar future tsunami events (UNISDR 2005). It is interesting to note that post-occurrence analysis of various historic tsunami events from various parts of world report on signs and signals produced by nature prior to such events. Anomalous and ambiguous behavioral responses towards seismicity have been cited in both animals and plants. These reports have been surveyed and debated by various researchers, scientists and risk reduction organizations (Waltham, 2005; Mott, 2005; Corea, 2008; Yamauchi et al., 2011).

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 11: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing