Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Sifat Shahriar Khan Thesis.pdf (10.94 MB)
ETD Abstract Container
Abstract Header
Power Outage Management using Social Sensing
Author Info
Khan, Sifat Shahriar
ORCID® Identifier
http://orcid.org/0000-0002-9358-3641
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=akron1556833736835808
Abstract Details
Year and Degree
2019, Master of Science in Engineering, University of Akron, Electrical Engineering.
Abstract
In this thesis, a real-time situational-awareness mechanism is developed to detect the ongoing power outages and extract useful information for power outage management using social sensing. In this detection mechanism, different natural language processing techniques and predictive modeling algorithms are exploited. To validate the robustness of the event detection mechanism, numerical analysis is performed on not only power outage datasets, but also datasets associated with natural disasters, such as earthquakes, floods, and wildfires. Furthermore, to identify whether the detected power outages are ongoing events, a temporal analysis mechanism is proposed. In this temporal analysis mechanism, a modified version of Kleinberg's burst detection algorithm is proposed that employs a novel approach of calculating the probability of event occurrence based on the detection of relevant tweets. To evaluate the effectiveness of the proposed work, the performance of the proposed social sensing-enabled mechanism and that of the established work is compared. The experimental analysis shows that multilayer perceptron outperforms the other popular predictive models and vector representation of tweets outperforms statistical features. This study paves the way for future innovation in efficient and effective real-time event detection using social sensing.
Committee
Jin Kocsis, PhD (Committee Chair)
Joan Carletta, PhD (Committee Member)
Yilmaz Sozer, PhD (Committee Member)
Pages
98 p.
Subject Headings
Artificial Intelligence
;
Computer Science
;
Electrical Engineering
Keywords
Event Detection, Machine Learning, Natural Language Processing, Neural Network, Power Outage, Social Sensing
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Khan, S. S. (2019).
Power Outage Management using Social Sensing
[Master's thesis, University of Akron]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=akron1556833736835808
APA Style (7th edition)
Khan, Sifat Shahriar.
Power Outage Management using Social Sensing.
2019. University of Akron, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=akron1556833736835808.
MLA Style (8th edition)
Khan, Sifat Shahriar. "Power Outage Management using Social Sensing." Master's thesis, University of Akron, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=akron1556833736835808
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
akron1556833736835808
Download Count:
179
Copyright Info
© 2019, all rights reserved.
This open access ETD is published by University of Akron and OhioLINK.