Early Detection of Natural Disaster using IoT Sensors / (Record no. 9059)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 05497nam a22002537a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 210530b2020 a|||f mb|| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Original cataloging agency | EG-CaNU |
| Transcribing agency | EG-CaNU |
| 041 0# - Language Code | |
| Language code of text | eng |
| Language code of abstract | eng |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 658.4 |
| 100 0# - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Nesreen Mansour |
| 245 1# - TITLE STATEMENT | |
| Title | Early Detection of Natural Disaster using IoT Sensors / |
| Statement of responsibility, etc. | Nesreen Mansour |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Date of publication, distribution, etc. | 2020 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 146 p. |
| Other physical details | ill. |
| Dimensions | 21 cm. |
| 500 ## - GENERAL NOTE | |
| Materials specified | Supervisor:<br/> Mohamed Ezzat,<br/> Mohamed M. Awny |
| 502 ## - Dissertation Note | |
| Dissertation type | Thesis (M.A.)—Nile University, Egypt, 2020 . |
| 504 ## - Bibliography | |
| Bibliography | "Includes bibliographical references" |
| 505 0# - Contents | |
| Formatted contents note | Contents:<br/>Chapter 1 Introduction 2<br/>1.1 The organization of the thesis 3<br/>Chapter 2 Crises’ Types and IoT 4<br/>2.1 Phases of a Crisis 4<br/>2.2 Crises’ Types 4<br/>2.2.1 Technological Crisis 4<br/>2.2.2 Confrontation 5<br/>2.2.3 Malevolence 5<br/>2.2.4 Organizational Misdeeds 5<br/>2.2.5 Workplace Violence 5<br/>2.2.6 Rumors 6<br/>2.2.7 Terrorist attack 6<br/>2.2.8 Natural Disaster 6<br/>2.2.8.1 Natural Disasters in Egypt 11<br/>2.3 Internet of Things (IoT) 13<br/>2.4 IoT for detecting an unusual severe event 15<br/>2.4.1 Flood Detection 15<br/>2.4.2 IoT for severe weather condition 16<br/>2.4.3 IoT for handling car accident 17<br/>Chapter 3 Natural Disaster Detection 19<br/>3.1 Introduction 19<br/>3.2 Disaster Detection Studies 19<br/>3.2.1 Detection of Flooded Areas using Machine Learning Techniques 19<br/>VI<br/>3.2.2 Analysis of satellite images for disaster detection 19<br/>3.2.3 Towards cross-lingual alerting for bursty epidemic events 20<br/>3.2.4 A Systematic Classification Investigation of Rapid Intensification of Atlantic Tropical Cyclones with the SHIPS Database 20<br/>3.2.5 An approach to improve the performance of the earthquake early warning system for the 2018 Hualien earthquake in Taiwan 20<br/>3.2.6 Real-Time Seismic Event Detection Using Voice Activity Detection Techniques 20<br/>3.2.7 Real-time estimation of wildfire perimeters from curated crowdsourcing 21<br/>3.2.8 Design of Information Monitoring System Flood Based Internet of Things (IoT) 21<br/>3.2.9 A disaster information and monitoring system utilizing earth observation 21<br/>3.2.10 Smart Disaster Detection and Response System for Smart Cities 21<br/>3.3 Early Detection Gap 22<br/>Chapter 4 Problem Definition and Objectives 23<br/>4.1 Introduction 23<br/>4.2 Problem Definition 23<br/>4.3 Research Objective 26<br/>4.4 Research Method 27<br/>Chapter 5 Data Gathering and Analysis 28<br/>5.1 Introduction 28<br/>5.2 Data analysis and storm path development 29<br/>Chapter 6 Software Solution Development 35<br/>6.1 Introduction 35<br/>6.2 Backend 36<br/>6.2.1 Database Schema 37<br/>6.2.2 REST API 40<br/>6.2.3 Entity Framework 41<br/>6.2.4 Orleans Framework 42<br/>6.2.5 Roslyn Compiler (RC) 43<br/>6.2.6 Basic Forecasting 44<br/>6.3 Frontend (Dashboard) 48<br/>6.4 Validation of the Software Solution 50<br/>VII<br/>Chapter 7 Analysis and Discussion of Results 52<br/>7.1 Introduction 52<br/>7.2 Detection Results 52<br/>7.2.1 Hurricane Dorian 52<br/>7.2.2 Hurricane Michael 60<br/>7.2.3 Tropical Storm Florence 65<br/>7.3 Forecasting Results 67<br/>Chapter 8 Conclusion and Future Research 68<br/>8.1 Introduction 68<br/>8.2 Conclusion 68<br/>8.3 Limitation 69<br/>8.4 Future Work 69<br/>References 70<br/>Appendices 73<br/>Appendix A Hurricane Michael Weather Underground Data 73<br/>Appendix B Hurricane Dorian Weather Underground Data 76<br/>Appendix C Hurricane Florence Weather Underground Data 83<br/>Appendix D Hurricane Michael Research Results 87<br/>Appendix E Hurricane Dorian Research Results 111<br/>Appendix F Hurricane Florence Research Results |
| 520 3# - Abstract | |
| Abstract | Abstract:<br/>There are a lot of lives and financial losses due to the late detection of natural disaster occurrence and lack of prediction accuracy. This research work has demonstrated that through the use of the Internet of Things (IoT), natural disaster detection could be done with higher accuracy and at much earlier time than the current processes. These improvements would enhance the authorities’ ability to mobilize their resources to save lives and properties in a timely fashion.<br/>This research work focused on hurricanes and tropical storms type disasters. Classifications of hurricane categories are made based on the wind speed, using Saffir Simpson scale. Wind speed data gathered from already planted sensors around the USA, and for that matter around the world, is fed to a developed “Software Solution”. The developed software solution manipulates the data and displays any abnormal status on a dashboard provided to the authorized operator.<br/>The dashboard shows a map for the detected abnormal status(s) location(s), the counts of impacted cities and areas, and summarized information regarding the abnormal status(s). The software solution developed, has also a feature that provides basic prediction using different types of regressions such as linear and quadratic.<br/>In order to validate the effectiveness of the developed software solution for early detection, a simulator was developed that used the collected sensors’ readings from many locations that suffered from some hurricanes such as Dorian (2019), Michael (2018), and Florence (2018). The simulator sends the sensors’ readings periodically as if it is happening at runtime. The developed software solution was able to detect abnormal status for Dorian, Michael, and Florence hurricanes in many states in the USA by several hours up to 21 hours earlier than the current processes. |
| 546 ## - Language Note | |
| Language Note | Text in English, abstracts in English. |
| 650 #4 - Subject | |
| Subject | MOT |
| 655 #7 - Index Term-Genre/Form | |
| Source of term | NULIB |
| focus term | Dissertation, Academic |
| 690 ## - Subject | |
| School | MOT |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | Thesis |
| 650 #4 - Subject | |
| -- | 309 |
| 655 #7 - Index Term-Genre/Form | |
| -- | 187 |
| 690 ## - Subject | |
| -- | 309 |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Date acquired | Total Checkouts | Full call number | Date last seen | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | Not For Loan | Main library | Main library | 05/30/2021 | 658.4 / N.M.E /2020 | 05/30/2021 | 05/30/2021 | Thesis |