請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85584
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 謝宏昀(Hung-Yun Hsieh) | - |
dc.contributor.author | Sie-Kee Ting Raphael | en |
dc.contributor.author | 陳世紀 | zh_TW |
dc.date.accessioned | 2023-03-19T23:19:05Z | - |
dc.date.copyright | 2022-09-27 | - |
dc.date.issued | 2022 | - |
dc.date.submitted | 2022-09-26 | - |
dc.identifier.citation | [1] J.-X. Liao, “An Indoor Localization System for Cellular Networks Based on Transfer Learning with Reduced Cost on Site Survey,” 2021. [2] “LTE Physical Layer Overview.” Online Available at: https://rfmw.em.keysight.com/wireless/helpfiles/89600b/webhelp/sub systems/lte/content/lte_overview.htm [3] S. H. P. D. Marc Lichtman, Thaddeus Czauski and J. H. Reed, “Detection and Mitigation of Uplink Control Channel Jamming in LTE,” IEEE Sensors Journal, 2014. [4] “RSRQ TO SINR RELATION.” Online Available at: https://arimas.com/2 016/04/24/164-rsrq-to-sinr/ [5] “3gpp 36.213 - CQI Index, pg.49.” Online Available at: https: //tonic.ee.ntu.edu.tw/depot/raphael1997/3gpp_pusch_36.213.pdf [6] “3gpp 36.213 - CQI Index, pg.38.” Online Available at: https: //tonic.ee.ntu.edu.tw/depot/raphael1997/3gpp_pusch_36.213.pdf [7] “3gpp 36.213 - CQI Index, pg.39.” Online Available at: https: //tonic.ee.ntu.edu.tw/depot/raphael1997/3gpp_pusch_36.213.pdf [8] “MCS 3GPP-136.213 (pg 134).” Online Available at: https://www.crowdsup ply.com/lime-micro/limesdr/updates/oai-lte-demo [9] “LTE Power Control.” Online Available at: https://www.sharetechnote.co m/html/PowerControl_LTE.html [10] R. Akeela and B. Dezfouli, “Software-defined Radios: Architecture, State-ofthe-art, and Challenges,” arXiv, 2018. [11] “LTE Demo with LimeSDR and OpenAirInterface.” Online Available at: https://www.crowdsupply.com/lime-micro/limesdr/updates/oai-lte-demo [12] “SHAP documentation.” Online Available at: https://shap.readthedocs.io/ en/latest/index.html [13] 3GPP, “Feasibility study on new services and markets technology enablers; stage 1 (version 14.1.0 Release 14),” TR 22.891, June 2016. [14] H. Zhang, Z. Zhang, S. Zhang, S. Xu, and S. Cao, “Fingerprint-based localization using commercial LTE signals: A field-trial study,” in 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall). IEEE, 2019, pp. 1–5. [15] “All in one OpenAirInterface,” Sep. 2019. Online Available at: https: //open-cells.com/index.php/2019/09/22/all-in-one-openairinterface/ [16] “Software-defined radio.” Online Available at: https://en.wikipedia.org/wik i/Software-defined_radio [17] M. Sadiku and C. Akujuobi, “Software-defined radio: a brief overview,” IEEE Sensors Journal, 2004. [18] “OpenAirInterface5G Architecture.” Online Available at: https://openairint erface.org/getting-started/openairinterface-an-open-cellular-ecosystem/ [19] “Structure of nFAPI in OAI.” Online Available at: https://hackmd.io/@5jE Ymj05R8CIotDoN0S4AQ/Hke1V1oTX?type=view [20] H. Rizk, M. Abbas, and M. Youssef, “Device-independent cellularbased indoor location tracking using deep learning,” Pervasive and Mobile Computing, p. 101420, 2021. Online Available at: https: //doi.org/10.1016/j.pmcj.2021.101420 [21] F. Alhomayani and M. H. Mahoor, “Deep Learning Methods for FingerprintBased Indoor Positioning: A Review,” arXiv, 2022. [22] A.-H. Ala’a Al-Habashna and G. Wainer, “Machine Learning EnabledLocalization in 5G and LTE using Image Classification and Deep Learning,” Researchgate, 2021. [23] T. T. Cai and R. Ma, “Performance Evaluation of Single Base Station ToAAoA Localization in an LTE Testbed,” IEEE Sensors Journal, 2021. [24] P. J. M. Z. S. Y. W. Alejandro Blanco, Norbert Ludant and J. Widmer, “Performance Evaluation of Single Base Station ToA-AoA Localization in an LTE Testbed,” IEEE Sensors Journal, 2019. [25] F. Zafari, A. Gkelias, and K. K. Leung, “A Survey of Indoor Localization Systems and Technologies,” IEEE Communications Surveys Tutorials, vol. 21, no. 3, pp. 2568–2599, 2019. [26] Z. Yang, Z. Zhou, and Y. Liu, “From RSSI to CSI: Indoor Localization via Channel Response,” ACM Comput. Surv., vol. 46, no. 2, Dec. 2013. Online Available at: https://doi.org/10.1145/2543581.2543592 [27] M. R. Emanuele Goldoni, Alberto Savioli and P. Gamba, “Experimental analysis of RSSI-based indoor localization with IEEE 802.15.4,” IEEE Sensors Journal, 2010. [28] W.-S. Hwang, “Multipath Mitigation.” Online Available at: http: //wshnt.kuas.edu.tw/network/s9/Multipath-Mitigation.htm [29] W. Stallings, Data and Computer Communications. Pearson Education, 2007. [30] M. Aljumaily, “A survey on WiFi Channel State Information (CSI) utilization in Human Activity Recognition,” researchgate, 2016. [31] N. Elkum and M. M. Shoukri, “Signal-to-noise ratio (SNR) as a measureof reproducibility: design, estimation, and application,” Researchgate, 2008. [32] K. B. A. Jović and N. Bogunović, “A review of feature selection methods with applications,” IEEE Sensors Journal, 2015. [33] “Different between PCA and LDA.” Online Available at: https: //blog.csdn.net/sinat_30353259/article/details/81569550 [34] “Linear discriminant analysis (LDA) Introduction.” Online Available at: https://en.wikipedia.org/wiki/Linear_discriminant_analysis [35] T. T. Cai and R. Ma, “Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data,” arXiv, 2022. [36] L. van der Maaten and G. Hinton, “Visualizing Data using t-SNE,” Journal of Machine Learning Research (JMLR), 2008. [37] “Confusion matrix.” Online Available at: https://en.wikipedia.org/wiki/Co nfusion_matrix [38] X. H. S. M. Yecheng Lyu, Student Member and Z. Zhang, “Revisiting 2D Convolutional Neural Networks for Graph-based Applications,” IEEE Sensors Journal, 2021. [39] J. Chang and S. Jin, “An efficient implementationof 2D convolution in CNN,” researchgate, 2017. [40] M. M. T. A. O. N. AMEL MOHAMED, MOHAMED THARWAT and M. YOUSSEF, “DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks using Deep Learning,” IEEE Sensors Journal, 2021. [41] R. N. Michael Hölzl and G. Ostermayer, “Localization in an Industrial Environment: A Case Study on the Difficulties for Positioning in a Harsh Environment,” SAGE Journal, 2015. [42] H. Y. R. R. K. A. A. K. M. Z. Y. P. K. C. Rai, Prabhat Kumar; Idsoe and L. Reddy, “Localization and Activity Classification of Unmanned Aerial Vehicle Using mmWave FMCW Radars,” IEEE Sensors Journal, 2021. [43] J.-Y. C. CHAUR-HEH HSIEH and B.-H. NIEN, “Deep Learning-Based Indoor Localization Using Received Signal Strength and Channel State Information,” IEEE Sensors Journal, 2019. [44] “CSI Report - Overview.” Online Available at: https://www.sharetechnote. com/html/Handbook_LTE_CSI_Report_Overview.html [45] “LTE PUCCH-Physical Uplink Control Channel.” Online Available at: https://www.rfwireless-world.com/Terminology/LTE-PUCCH-Physica l-Uplink-Control-Channel.html [46] S. L. Malik Muhammad Usman Gul and X. Ma, “Robust synchronization for OFDM employing Zadoff-Chu sequence,” IEEE Sensors Journal, 2012. [47] M. M. Mansour, “Optimized Architecture for Computing Zadoff-Chu Sequences with Application to LTE,” IEEE Sensors Journal, 2009. [48] G. X. Lopamudra Kundu and J. Cho, “Physical Uplink Control Channel Design for 5G New Radio,” IEEE Sensors Journal, 2018. [49] R. M. V. Kevin McDermott and R. M. Buehrer, “Cooperative UTDOA Positioning in LTE Cellular Systems,” IEEE Sensors Journal, 2015. [50] A. T. C. M. M. D. Alessandro Pin, Roberto Rinaldo, A. Biason, and A. D. Torre, “LTE Ranging Measurement Using Uplink Opportunistic Signals and the SAGE algorithm,” IEEE Sensors Journal, 2019. [51] “LTE Uplink TOA Opportunistic Measurement Based on DM-RS.” [52] “Book: Physical Uplink Control Channel.” Online Available at: https: //www.crowdsupply.com/lime-micro/limesdr/updates/oai-lte-demo [53] “PUCCH Format 1,1a,1b Location.” Online Available at: https://www.shar etechnote.com/html/Handbook_LTE_PUCCH_Format1_Location.html [54] “Physical uplink control channel Power in 3GPP TS 36.213 version 8.8.0 Release 8, pg12.” Online Available at: https://www.etsi.org/deliver/etsi_ts /136200_136299/136213/08.08.00_60/ts_136213v080800p.pdf [55] 3GPP, “Requirements for support of radio resource management (version 15.9.0 Release 15),” TS 36.133, pp. 634–635, Feb. 2020. Online Available at: https://www.etsi.org/deliver/etsi_ts/136100_136199/136133/15.09.00 _60/ts_136133v150900p.pdf [56] ——, “Physical layer procedures (version 15.9.0 Release 15),” TS 36.213, pp. 15–39, Apr. 2020. Online Available at: https://www.etsi.org/deliver/ets i_ts/136200_136299/136213/15.09.00_60/ts_136213v150900p.pdf [57] “LTE Tutorials: Physical Channel Structure.” Online Available at: https://www.artizanetworks.com/resources/tutorials/phy_cha.html [58] “LTE Quick Reference: CQI.” Online Available at: https://www.sharetechn ote.com/html/Handbook_LTE_CQI.html [59] “CSI Report.” Online Available at: https://www.sharetechnote.com/html/5 G/5G_CSI_Report.html [60] “MCS and Modulation Order.” Online Available at: https://www.sharetechnote.com/html/Handbook_LTE_MCS_Modu lationOrder.html#Uplink_MCS [61] “BOOK: FROM GSM TO LTE-ADVANCED PRO AND 5G (An Introduction to QAM Modulation for LTE).” Online Available at: https://blog.wirel essmoves.com/2016/10/an-introduction-qam-modulation-for-lte.html [62] “LTE Power Control.” Online Available at: https://www.sharetechnote.co m/html/Handbook_LTE_MCS_ModulationOrder.html#Uplink_MCS [63] “Entropy and Information Gain to Build Decision Trees in Machine Learning.” Online Available at: https://www.section.io/engineering-educati on/entropy-information-gain-machine-learning/ [64] A. Z. H. T. E. Taqwa Ahmed Alhaj, Maheyzah Md Siraj and F. Elha, “Feature Selection Using Information Gain for Improved Structural-Based Alert Correlation,” Researchgate, 2016. [65] B.Azhagusundari and A. S. Thanamani, “Feature Selection Based on Information Gain,” ijitee, 2013. [66] “An introduction to explainable AI with Shapley values.” Online Available at: https://shap.readthedocs.io/en/latest/example_notebooks/overviews/ An%20introduction%20to%20explainable%20AI%20with%20Shapley%20val ues.html [67] V. N. N. Wei Zhao, Tarun Joshi and A. Sudjianto, “SHAP values for Explaining CNN-based Text Classification Models,” arXiv, 2020 | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85584 | - |
dc.description.abstract | 室內定位已經提出了多年,但常見的室內定位都是在理想環境下去進行的。在 理想環境下能準確定位的信號通常在有人類活動干擾下的定位精度會有所下 降。為了解決這個問題,我們研究行動通訊網路基地台傳送的信號,期望找出 通用而穩健的特徵,能夠在理想和人類活動的室內環境中進行定位。 首先,我們對在環境內人類活動時有反應的信號收集下來作為我們的訓練特 徵,接著我們設計了一種算法來比較卡方 (CHI2)、信息增益(Information Gain)和可解釋 AI (Shap) 三個特徵選擇的結果,來選出我們收集的特徵的重 要性和關係。在比較了本文提出的三個特徵選擇的重要特徵之後,我們將最後 選擇的特徵作為輸入資料,通過機器學習方法進行訓練:卷積神經網絡 (CNN2D)和全連接神經網絡(FCNN)來定位使用者的位置。為了解釋 CNN2D 模型是如何訓練數據集,我們使用算法 Shap 來觀察特徵在 CNN2D 模型訓練中 具有的重要性和該特徵在模型的訓練起到了正面或負面幫助。這 67 個原始特徵 資料量通過我們設計的算法,最後選擇了 11 個特徵用於室內定位。選擇的 11 個特徵具有通用性,可以在理想與人類活動干擾的環境下定位。最終,訓練維 度總共下降了 84%,訓練時間複雜度也比 67 維減少了 6 倍左右。與預比較的 論文中使用的特徵定位結果相比,定位精度提高了 49%,而且我們只使用了 11 個特徵進行定位, 與我們比較的論文則使用了 23 個特徵。 | zh_TW |
dc.description.abstract | Indoor localization has been proposed for many years, but common indoor localization is localized in an ideal environment. The signals that can be accurately located in the ideal environment have a decrease in the accuracy of localization under the interference of human activities. To address this problem, we study the signals transmitted by base stations in cellular networks, hoping to find general and robust features that enable localization in ideal and human-active indoor environments. We collect the signal that has responded to human activity to be our training features. We design an algorithm to compare three feature selection result which is Chi-Square (CHI2), Information Gain, and Shap to select the importance and relation features we had collected. After comparing the importance of the three feature selection selected features, we use the selected features and train them by machine learning methods: Convolutional Neural Network and Fully Connected Neural Network to locate the position of UE. To explain how the CNN2D model trains the dataset, we use the algorithm Shap to draw out the positive or negative data important to observing the feature importance in CNN2D training. The algorithm we propose selected 11 features for indoor localization from the original features amount of 67 and these features are generality and can be localized in environments ideally interfering with human activity. Finally, the training dimension will decrease by 84%, and the training time complexity will decrease six times than 67-dimension. The localization accuracy has improved by 49% compared to the localization baseline approach, and we are only using 11 features for localization where baseline approach uses 23 features. | en |
dc.description.provenance | Made available in DSpace on 2023-03-19T23:19:05Z (GMT). No. of bitstreams: 1
U0001-2209202222451600.pdf: 5672867 bytes, checksum: 21ad8d0307b8d0825b23cd107c4a4435 (MD5) Previous issue date: 2022 | en |
dc.description.provenance | Item reinstated by admin ntu (admin@lib.ntu.edu.tw) on 2023-04-20T03:41:36Z
Item was in collections: 電信工程學研究所 (ID: 4da2ee9f-836d-4376-85eb-0fa264704c5c) No. of bitstreams: 1 U0001-2209202222451600.pdf: 5672867 bytes, checksum: 21ad8d0307b8d0825b23cd107c4a4435 (MD5) | en |
dc.description.tableofcontents | ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii CHAPTER 1 INTRODUCTION . . . . . . . . . . . . . . . . . . . 1 CHAPTER 2 BACKGROUND AND RELATED WORK . . . . 5 2.1 LTE Signal Localization Techniques . . . . . . . . . . . . . . . . 5 2.1.1 Received Signal Strength Indicator (RSSI) . . . . . . . . 5 2.1.2 Channel State Information (CSI) . . . . . . . . . . . . . 6 2.1.3 Signal To Noise Ratio (SNR) . . . . . . . . . . . . . . . . 7 2.1.4 Comparison and Conclusion . . . . . . . . . . . . . . . . 8 2.2 Feature Selection Method . . . . . . . . . . . . . . . . . . . . . . 9 2.3 Location Distribution Observation Method . . . . . . . . . . . . 16 2.3.1 T-Distributed Stochastic Neighbor Embedding (TSNE) . 16 2.3.2 Confusion Matrix . . . . . . . . . . . . . . . . . . . . . . 20 2.4 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.4.1 Feature Selection and CNN model Training for Indoor Localization . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.4.2 Uplink Features Localization . . . . . . . . . . . . . . . . 24 2.4.3 Activity Environmental Localization . . . . . . . . . . . . 25 CHAPTER 3 UPLINK LTE FEATURES FOR LOCALIZATION 27 3.1 Environment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 3.2 LTE Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 3.2.1 PUCCH Channel . . . . . . . . . . . . . . . . . . . . . . 31 3.2.2 PUSCH Channel . . . . . . . . . . . . . . . . . . . . . . 37 3.2.3 Assignment Of Downlink Index . . . . . . . . . . . . . . 42 3.3 Feature Input . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 CHAPTER 4 MACHINE LEARNING MODEL COMPARISON AND TUNE UP . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 4.1 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . 47 4.1.1 Z-Score Standardization . . . . . . . . . . . . . . . . . . 47 4.1.2 Min-Max Normalization . . . . . . . . . . . . . . . . . . 48 4.1.3 Data Preprocessing For Localization . . . . . . . . . . . . 49 4.2 Baseline Localization . . . . . . . . . . . . . . . . . . . . . . . . 50 4.3 Model Tune Up . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 4.3.1 Convolutional Neural Network (CNN2D) Tune Up . . . . 52 4.3.2 Different Time Unit Localization Of Features . . . . . . . 55 4.3.3 Features Shifting . . . . . . . . . . . . . . . . . . . . . . 57 CHAPTER 5 FEATURE SELECTION . . . . . . . . . . . . . . . 61 5.1 Feature Selection Metric And Features Ranking . . . . . . . . . 61 5.1.1 CHI-Square . . . . . . . . . . . . . . . . . . . . . . . . . 62 5.1.2 Information Gain . . . . . . . . . . . . . . . . . . . . . . 64 5.1.3 Shap Value . . . . . . . . . . . . . . . . . . . . . . . . . . 68 5.2 Feature Importance For Localization . . . . . . . . . . . . . . . . 76 5.2.1 CHI-Square Importance Localization . . . . . . . . . . . 78 5.2.2 Information Gain Importance Localization . . . . . . . . 82 5.2.3 Shap value Importance Localization . . . . . . . . . . . . 85 5.3 Selecting Feature For Localization . . . . . . . . . . . . . . . . . 91 CHAPTER 6 PERFORMANCE EVALUATION . . . . . . . . . 99 6.1 Data on Different Days Localization . . . . . . . . . . . . . . . . 99 6.2 Features In Activity And Ideal Environment . . . . . . . . . . . 103 6.2.1 Activity Environment . . . . . . . . . . . . . . . . . . . . 103 6.2.2 Activity Environment Localization . . . . . . . . . . . . . 106 6.2.3 Ideal Environment Features Comparison . . . . . . . . . 109 6.3 Selected Features For Localization . . . . . . . . . . . . . . . . . 109 6.3.1 Selected Features In Ideal And Activity Environment . . 109 6.3.2 Selected Model Localization In Ideal And Activity Environment . . . . . . . . . . . . . . . . . . . . . . . . . . . 112 6.3.3 Model Confusion Matrix And Location . . . . . . . . . . 118 6.4 Localization Model On Testing Point . . . . . . . . . . . . . . . 120 6.4.1 Testing Point Localization In Ideal Environment . . . . . 121 6.4.2 Testing Point Localization In Activity Environment . . . 122 CHAPTER 7 CONCLUSION AND FUTURE WORK . . . . . 126 REFERENCES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 127 APPENDIX A — ENVIRONMENT OF HARDWARE SETUP AND SOFTWARE INSTALLATION . . . . . . . . . . . . . . . 132 | - |
dc.language.iso | en | - |
dc.title | 行動通訊室內定位系統下考慮人類活動之強健無線電特徵選擇 | zh_TW |
dc.title | Selecting Robust Features for Cellular Indoor Localization in Environments with Human Activities | en |
dc.type | Thesis | - |
dc.date.schoolyear | 110-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 李佳翰(Chia-Han Lee),蘇炫榮(Hsuan-Jung Su) | - |
dc.subject.keyword | 室內定位,行動通訊,特徵選擇, | zh_TW |
dc.subject.keyword | Indoor Localization,Cellular,Feature Selection, | en |
dc.relation.page | 142 | - |
dc.identifier.doi | 10.6342/NTU202203854 | - |
dc.rights.note | 同意授權(全球公開) | - |
dc.date.accepted | 2022-09-27 | - |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
dc.date.embargo-lift | 2022-09-27 | - |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-2209202222451600.pdf | 5.54 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。