Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator
Wi-Fi localization is an active research topic, and various challenges are not yet resolved in this field. Researchers develop models and use benchmark datasets for Wi-Fi or fingerprinting to create a quantitative comparative evaluation. These benchmarking datasets are limited by their failure to su...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2018
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/84553/1/MonaRizaMohd2018_InfiniteTermMemoryClassifierforWiFiLocalization.pdf |
| _version_ | 1796863870185242624 |
|---|---|
| author | Al-Khaleefa, Ahmed Salih Ahmad, Mohd. Riduan Md. Isa, Azmi Awang Mohd. Esa, Mona Riza Al-Saffar, Ahmed Aljeroudi, Yazan |
| author_facet | Al-Khaleefa, Ahmed Salih Ahmad, Mohd. Riduan Md. Isa, Azmi Awang Mohd. Esa, Mona Riza Al-Saffar, Ahmed Aljeroudi, Yazan |
| author_sort | Al-Khaleefa, Ahmed Salih |
| collection | ePrints |
| description | Wi-Fi localization is an active research topic, and various challenges are not yet resolved in this field. Researchers develop models and use benchmark datasets for Wi-Fi or fingerprinting to create a quantitative comparative evaluation. These benchmarking datasets are limited by their failure to support dynamical navigation. As a result, Wi-Fi models are only evaluated as usual classifiers without including actual navigation maneuvers in the evaluation, which makes the models incapable of handling the actual navigation behavior and its impact on the performance. One common navigation behavior is the cyclic dynamic behavior, which occurs frequently in the indoor environment when a person visits the same place or location multiple times or repeats the same trajectory or similar one more than once. For this purpose, we developed two models: a simulation model for generating time series data to support actual conducted navigation scenarios and a Wi-Fi classification model to handle dynamical scenarios generated by the simulator under cyclic dynamic behavior. Various testing scenarios were conducted for evaluation, and a comparison with benchmarks was performed. Results show the superiority of our developed model which is infinite-term memory online sequential extreme learning machine (OSELM) to the benchmarks with a percentage of 173% over feature adaptive OSELM and 1638% over OSELM. |
| first_indexed | 2024-03-05T20:33:11Z |
| format | Article |
| id | utm.eprints-84553 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:33:11Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | utm.eprints-845532020-02-27T03:05:08Z http://eprints.utm.my/84553/ Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator Al-Khaleefa, Ahmed Salih Ahmad, Mohd. Riduan Md. Isa, Azmi Awang Mohd. Esa, Mona Riza Al-Saffar, Ahmed Aljeroudi, Yazan TK Electrical engineering. Electronics Nuclear engineering Wi-Fi localization is an active research topic, and various challenges are not yet resolved in this field. Researchers develop models and use benchmark datasets for Wi-Fi or fingerprinting to create a quantitative comparative evaluation. These benchmarking datasets are limited by their failure to support dynamical navigation. As a result, Wi-Fi models are only evaluated as usual classifiers without including actual navigation maneuvers in the evaluation, which makes the models incapable of handling the actual navigation behavior and its impact on the performance. One common navigation behavior is the cyclic dynamic behavior, which occurs frequently in the indoor environment when a person visits the same place or location multiple times or repeats the same trajectory or similar one more than once. For this purpose, we developed two models: a simulation model for generating time series data to support actual conducted navigation scenarios and a Wi-Fi classification model to handle dynamical scenarios generated by the simulator under cyclic dynamic behavior. Various testing scenarios were conducted for evaluation, and a comparison with benchmarks was performed. Results show the superiority of our developed model which is infinite-term memory online sequential extreme learning machine (OSELM) to the benchmarks with a percentage of 173% over feature adaptive OSELM and 1638% over OSELM. Institute of Electrical and Electronics Engineers Inc. 2018-09-15 Article PeerReviewed application/pdf en http://eprints.utm.my/84553/1/MonaRizaMohd2018_InfiniteTermMemoryClassifierforWiFiLocalization.pdf Al-Khaleefa, Ahmed Salih and Ahmad, Mohd. Riduan and Md. Isa, Azmi Awang and Mohd. Esa, Mona Riza and Al-Saffar, Ahmed and Aljeroudi, Yazan (2018) Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator. IEEE Access, 6 . pp. 54769-54785. ISSN 2169-3536 http://dx.doi.org/10.1109/ACCESS.2018.2870754 DOI:10.1109/ACCESS.2018.2870754 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Al-Khaleefa, Ahmed Salih Ahmad, Mohd. Riduan Md. Isa, Azmi Awang Mohd. Esa, Mona Riza Al-Saffar, Ahmed Aljeroudi, Yazan Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator |
| title | Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator |
| title_full | Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator |
| title_fullStr | Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator |
| title_full_unstemmed | Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator |
| title_short | Infinite-term memory classifier for Wi-Fi localization based on dynamic wi-fi simulator |
| title_sort | infinite term memory classifier for wi fi localization based on dynamic wi fi simulator |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/84553/1/MonaRizaMohd2018_InfiniteTermMemoryClassifierforWiFiLocalization.pdf |
| work_keys_str_mv | AT alkhaleefaahmedsalih infinitetermmemoryclassifierforwifilocalizationbasedondynamicwifisimulator AT ahmadmohdriduan infinitetermmemoryclassifierforwifilocalizationbasedondynamicwifisimulator AT mdisaazmiawang infinitetermmemoryclassifierforwifilocalizationbasedondynamicwifisimulator AT mohdesamonariza infinitetermmemoryclassifierforwifilocalizationbasedondynamicwifisimulator AT alsaffarahmed infinitetermmemoryclassifierforwifilocalizationbasedondynamicwifisimulator AT aljeroudiyazan infinitetermmemoryclassifierforwifilocalizationbasedondynamicwifisimulator |