國立虎尾科技大學 |

Deep Learning-Based Indoor Localization for IoT Applications.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Deep Learning-Based Indoor Localization for IoT Applications./
作者:	Ye, Qianwen.
面頁冊數:	1 online resource (174 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
Contained By:	Dissertations Abstracts International85-06A.
標題:	Web studies. -
電子資源:	click for full text (PQDT)
ISBN:	9798381034790

Deep Learning-Based Indoor Localization for IoT Applications.
Ye, Qianwen.

Deep Learning-Based Indoor Localization for IoT Applications. - 1 online resource (174 pages)

Source: Dissertations Abstracts International, Volume: 85-06, Section: A.

Thesis (Ph.D.)--University of Technology Sydney (Australia), 2023.

Includes bibliographical references

In recent years, localization-based Internet of Things (IoT) applications have been developed and deployed, such as interactive and personalized routing, car localization in underground parking systems and patient emergency localization. However, in indoor environment, Global Positioning System signal is not available because it is very sensitive to occlusion. Many researchers have been focusing on utilizing other technologies such as Wi-Fi (Wireless Fidelity), Radio Frequency Identifcation, Bluetooth and so on for localization services. Among these technologies, Wi-Fi has been most widely utilized for indoor localization due to its low cost and wide availability. There are various signal measurements for the Wi-Fi-based indoor localization such as Received Signal Strength (RSS), Time of Arrival, Time Diference of Arrival, Round Trip Time, Angle of Arrival, and Channel-State Information. However, RSS remains the most popular signal measurement used in Wi-Fi-based localization solution compared to other measurements, especially for localization of low-cost IoT devices with limited computing and storage resources.However, RSS-based indoor localization possesses many challenges due to multipath efects and noise, environment dynamics, device heterogeneity, limited highquality data, and security. To overcome these challenges, in this thesis, RSS fngerprintingbased indoor localization methods are developed using machine learning methods and deep learning methods. For RSS time-series data, the system of Kalman-DNN exploits the temporal dependency of these data by integrating the Kalman flter with deep neural networks, and experiment results validate efectiveness of the KalmanDNN system. However, for single RSS readings vector, a system called CapsLoc is proposed, which is an RSS fngerprinting-based indoor localization system based on CapsNet (Capsule Network). The experimental results show that CapsLoc can achieve accurate indoor localization, which outperforms some traditional machine learning methods and existing deep learning methods. Especially for heterogeneous IoT devices, RSS can be afected by superimposed challenges, i.e., device heterogeneity, database problem and energy efciency. In order to improve localization speed, EdgeLoc is proposed based on CapsNet and edge computing technology. Experiment results show that EdgeLoc outperforms state-of-the-art deep learning methods in performance of the localization accuracy and average positioning speed.Considering security issues in localization where malicious attacks at APs (Access Points) exist, a solution of SE-Loc is proposed for RSS fngerprinting-based indoor localization utilizing the deep learning methods. Extensive experiments show that SE-Locdemonstrates superior performance on secure indoor localization over the baseline methods. To address challenges including the multipath efects and noise, the environment dynamics, the device heterogeneity, data limitation, database problem and even malicious AP attacks, deep learning-based indoor localization methods are proposed. In the future, it is necessary to develop security-enhanced deep learning techniques when facing other various security problems such as AP hijacking, jamming, and man-in-the-middle attack.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381034790Subjects--Topical Terms:

1148502
Web studies.
Index Terms--Genre/Form:

554714
Electronic books.

Deep Learning-Based Indoor Localization for IoT Applications.
LDR:04591ntm a22003857 4500 001 1142129
005 20240414211953.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381034790
035 $a (MiAaPQ)AAI30757804
035 $a (MiAaPQ)TechSydney10453171933
035 $a AAI30757804
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ye, Qianwen. $3 1466334
245 1 0 $a Deep Learning-Based Indoor Localization for IoT Applications.
264 0 $c 2023
300 $a 1 online resource (174 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-06, Section: A.
500 $a Advisor: Fang, Gengfa.
502 $a Thesis (Ph.D.)--University of Technology Sydney (Australia), 2023.
504 $a Includes bibliographical references
520 $a In recent years, localization-based Internet of Things (IoT) applications have been developed and deployed, such as interactive and personalized routing, car localization in underground parking systems and patient emergency localization. However, in indoor environment, Global Positioning System signal is not available because it is very sensitive to occlusion. Many researchers have been focusing on utilizing other technologies such as Wi-Fi (Wireless Fidelity), Radio Frequency Identifcation, Bluetooth and so on for localization services. Among these technologies, Wi-Fi has been most widely utilized for indoor localization due to its low cost and wide availability. There are various signal measurements for the Wi-Fi-based indoor localization such as Received Signal Strength (RSS), Time of Arrival, Time Diference of Arrival, Round Trip Time, Angle of Arrival, and Channel-State Information. However, RSS remains the most popular signal measurement used in Wi-Fi-based localization solution compared to other measurements, especially for localization of low-cost IoT devices with limited computing and storage resources.However, RSS-based indoor localization possesses many challenges due to multipath efects and noise, environment dynamics, device heterogeneity, limited highquality data, and security. To overcome these challenges, in this thesis, RSS fngerprintingbased indoor localization methods are developed using machine learning methods and deep learning methods. For RSS time-series data, the system of Kalman-DNN exploits the temporal dependency of these data by integrating the Kalman flter with deep neural networks, and experiment results validate efectiveness of the KalmanDNN system. However, for single RSS readings vector, a system called CapsLoc is proposed, which is an RSS fngerprinting-based indoor localization system based on CapsNet (Capsule Network). The experimental results show that CapsLoc can achieve accurate indoor localization, which outperforms some traditional machine learning methods and existing deep learning methods. Especially for heterogeneous IoT devices, RSS can be afected by superimposed challenges, i.e., device heterogeneity, database problem and energy efciency. In order to improve localization speed, EdgeLoc is proposed based on CapsNet and edge computing technology. Experiment results show that EdgeLoc outperforms state-of-the-art deep learning methods in performance of the localization accuracy and average positioning speed.Considering security issues in localization where malicious attacks at APs (Access Points) exist, a solution of SE-Loc is proposed for RSS fngerprinting-based indoor localization utilizing the deep learning methods. Extensive experiments show that SE-Locdemonstrates superior performance on secure indoor localization over the baseline methods. To address challenges including the multipath efects and noise, the environment dynamics, the device heterogeneity, data limitation, database problem and even malicious AP attacks, deep learning-based indoor localization methods are proposed. In the future, it is necessary to develop security-enhanced deep learning techniques when facing other various security problems such as AP hijacking, jamming, and man-in-the-middle attack.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Web studies. $3 1148502
650 4 $a Information technology. $3 559429
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
650 4 $a Aerospace engineering. $3 686400
650 4 $a Wireless access points. $3 1466338
650 4 $a Access control. $3 813052
650 4 $a Data processing. $2 sears $3 840972
650 4 $a Radio frequency identification. $3 1466337
650 4 $a Neural networks. $3 1011215
650 4 $a Location based services. $3 1466336
650 4 $a Spread spectrum. $3 1466335
650 4 $a Wide area networks. $3 1372842
650 4 $a Deep learning. $3 1127428
650 4 $a Global positioning systems--GPS. $3 1372831
655 7 $a Electronic books. $2 local $3 554714
690 $a 0538
690 $a 0800
690 $a 0984
690 $a 0544
690 $a 0489
690 $a 0646
710 2 $a University of Technology Sydney (Australia). $3 1465278
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-06A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30757804 $z click for full text (PQDT)