Large-scale WiFi-based indoor localization
Navigating in an unfamiliar environment has been made easy through the advancement in smartphone technologies. With the help of embedded Global Positioning System (GPS) sensor in smartphone, a person’s location can be easily located. However, in an indoor environment, GPS is unable to get an accurat...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/73925 |
| _version_ | 1811681816488181760 |
|---|---|
| author | Chan, Jun Yan |
| author2 | Pan Jialin, Sinno |
| author_facet | Pan Jialin, Sinno Chan, Jun Yan |
| author_sort | Chan, Jun Yan |
| collection | NTU |
| description | Navigating in an unfamiliar environment has been made easy through the advancement in smartphone technologies. With the help of embedded Global Positioning System (GPS) sensor in smartphone, a person’s location can be easily located. However, in an indoor environment, GPS is unable to get an accurate location. Also, the large amount of energy consumed by GPS sensor resulted in a need to research on an alternative way to solve this localization problem. An alternative information that can be make use of to solve this localization problem is Wi-Fi signals. WiFi signals are readily available indoor and with the help of supervised machine learning technique, an effective Wi-Fi based localization model can be built. Wi-Fi signals which are widely available indoor is one alternative data that can be used for localization. However, in order to use supervised machine learning technique, large amount of labeled data is required. This involves a lot of human efforts which in practice is not feasible. To tackle this problem, a new localization algorithm can be designed based on advanced machine learning techniques. In this project, a Wi-Fi based localization model for Nanyang Technological University campus is built using supervised learning technique. Semi-supervised learning technique is then recommended for future research to improve the accuracy and performance of the localization model. |
| first_indexed | 2024-10-01T03:46:57Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/73925 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:46:57Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/739252023-03-03T20:41:30Z Large-scale WiFi-based indoor localization Chan, Jun Yan Pan Jialin, Sinno School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Navigating in an unfamiliar environment has been made easy through the advancement in smartphone technologies. With the help of embedded Global Positioning System (GPS) sensor in smartphone, a person’s location can be easily located. However, in an indoor environment, GPS is unable to get an accurate location. Also, the large amount of energy consumed by GPS sensor resulted in a need to research on an alternative way to solve this localization problem. An alternative information that can be make use of to solve this localization problem is Wi-Fi signals. WiFi signals are readily available indoor and with the help of supervised machine learning technique, an effective Wi-Fi based localization model can be built. Wi-Fi signals which are widely available indoor is one alternative data that can be used for localization. However, in order to use supervised machine learning technique, large amount of labeled data is required. This involves a lot of human efforts which in practice is not feasible. To tackle this problem, a new localization algorithm can be designed based on advanced machine learning techniques. In this project, a Wi-Fi based localization model for Nanyang Technological University campus is built using supervised learning technique. Semi-supervised learning technique is then recommended for future research to improve the accuracy and performance of the localization model. Bachelor of Engineering (Computer Science) 2018-04-19T07:47:32Z 2018-04-19T07:47:32Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/73925 en Nanyang Technological University 28 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Chan, Jun Yan Large-scale WiFi-based indoor localization |
| title | Large-scale WiFi-based indoor localization |
| title_full | Large-scale WiFi-based indoor localization |
| title_fullStr | Large-scale WiFi-based indoor localization |
| title_full_unstemmed | Large-scale WiFi-based indoor localization |
| title_short | Large-scale WiFi-based indoor localization |
| title_sort | large scale wifi based indoor localization |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | http://hdl.handle.net/10356/73925 |
| work_keys_str_mv | AT chanjunyan largescalewifibasedindoorlocalization |