請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88920
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳柏華 | zh_TW |
dc.contributor.advisor | Albert Y. Chen | en |
dc.contributor.author | 鍾慕捷 | zh_TW |
dc.contributor.author | Mu-Chieh Chung | en |
dc.date.accessioned | 2023-08-16T16:21:51Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-08-16 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-08-08 | - |
dc.identifier.citation | [1] Q. Luo, M. Gee, B. Piccoli, D. Work, and S. Samaranayake, “Managing public transit during a pandemic: The trade-off between safety and mobility,” Transportation Research Part C: Emerging Technologies, vol. 138, p. 103592, May 2022. [Online]. Available: https://doi.org/10.1016/j.trc.2022.103592
[2] J. Lu, A. Lin, C. Jiang, A. Zhang, and Z. Yang, “Influence of transportation network on transmission heterogeneity of COVID-19 in china,” Transportation Research Part C: Emerging Technologies, vol. 129, p. 103231, Aug. 2021. [Online]. Available: https://doi.org/10.1016/j.trc.2021.103231 [3] Y. Ding, S. Wandelt, and X. Sun, “TLQP: Early-stage transportation lock- down and quarantine problem,” Transportation Research Part C: Emerging Technologies, vol. 129, p. 103218, Aug. 2021. [Online]. Available: https: //doi.org/10.1016/j.trc.2021.103218 [4] S. Hu, C. Xiong, M. Yang, H. Younes, W. Luo, and L. Zhang, “A big- data driven approach to analyzing and modeling human mobility trend under non-pharmaceutical interventions during COVID-19 pandemic,” Transportation Research Part C: Emerging Technologies, vol. 124, p. 102955, Mar. 2021. [Online]. Available: https://doi.org/10.1016/j.trc.2020.102955 [5] K. D. Vo, W. H. Lam, and Z.-C. Li, “A mixed-equilibrium model of individual and household activity–travel choices in multimodal transportation networks,” Transportation Research Part C: Emerging Technologies, vol. 131, p. 103337, Oct. 2021. [Online]. Available: https://doi.org/10.1016/j.trc.2021.103337 [6] Y. Liu, L. C. Tong, X. Zhu, and W. Du, “Dynamic activity chain pattern estimation under mobility demand changes during COVID-19,” Transportation Research Part C: Emerging Technologies, vol. 131, p. 103361, Oct. 2021. [Online]. Available: https://doi.org/10.1016/j.trc.2021.103361 [7] M. Battifarano and S. Qian, “Behavioral inference from non-stationary policies: Theory and application to ridehailing drivers during COVID-19 lockdowns,” Transportation Research Part C: Emerging Technologies, vol. 151, p. 104118, Jun. 2023. [Online]. Available: https://doi.org/10.1016/j.trc.2023.104118 [8] C. Kamga, R. Tchamna, P. Vicuna, S. Mudigonda, and B. Moghimi, “An estimation of the effects of social distancing measures on transit vehicle capacity and operations,” Transportation Research Interdisciplinary Perspectives, vol. 10, p. 100398, Jun. 2021. [Online]. Available:https://doi.org/10.1016/j.trip.2021.100398 [9] D. A. Hensher, C. Balbontin, M. J. Beck, and E. Wei, “The impact of working from home on modal commuting choice response during COVID-19: Implications for two metropolitan areas in australia,” Transportation Research Part A: Policy and Practice, vol. 155, pp. 179–201, Jan. 2022. [Online]. Available:https://doi.org/10.1016/j.tra.2021.11.011 [10] X. Tian, C. An, Z. Chen, and Z. Tian, “Assessing the impact of COVID- 19 pandemic on urban transportation and air quality in canada,” Science of The Total Environment, vol. 765, p. 144270, Apr. 2021. [Online]. Available: https://doi.org/10.1016/j.scitotenv.2020.144270 [11] S. Muhammad, X. Long, and M. Salman, “COVID-19 pandemic and environmental pollution: A blessing in disguise?” Science of The Total Environment, vol. 728, p. 138820, Aug. 2020. [Online]. Available: https://doi.org/10.1016/j.scitotenv.2020. 138820 [12] J. Xiang, E. Austin, T. Gould, T. Larson, J. Shirai, Y. Liu, J. Marshall, and E. Seto, “Impacts of the COVID-19 responses on traffic-related air pollution in a northwestern US city,” Science of The Total Environment, vol. 747, p. 141325, Dec. 2020. [Online]. Available:https://doi.org/10.1016/j.scitotenv.2020.141325 [13] G. He, Y. Pan, and T. Tanaka, “The short-term impacts of COVID-19 lockdown on urban air pollution in china,” Nature Sustainability, vol. 3, no. 12, pp. 1005–1011, Jul. 2020. [Online]. Available: https://doi.org/10.1038/s41893-020-0581-y [14] M. E. Maron, “Automatic indexing: an experimental inquiry,” Journal of the ACM (JACM), vol. 8, no. 3, pp. 404–417, 1961. [15] A. Mnih and G. Hinton, “A scalable hierarchical distributed language model,” in Proceedings of the 21st International Conference on Neural Information Processing Systems, ser. NIPS’08. Red Hook, NY, USA: Curran Associates Inc., 2008, p. 1081–1088. [16] M. E. Peters, W. Ammar, C. Bhagavatula, and R. Power, “Semi-supervised sequence tagging with bidirectional language models,” 2017. [Online]. Available: https://arxiv.org/abs/1705.00108 [17] O. Melamud, J. Goldberger, and I. Dagan, “context2vec: Learning generic context embedding with bidirectional LSTM,” in Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning. Berlin, Germany: Association for Computational Linguistics, Aug. 2016, pp. 51–61. [Online]. Available:https://aclanthology.org/K16-1006 [18] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Minneapolis, Minnesota: Association for Computational Linguistics, Jun. 2019, pp. 4171–4186. [Online]. Available: https://aclanthology.org/N19-1423 [19] S. Rath and J. Y. Chow, “Worldwide city transport typology prediction with sentence-BERT based supervised learning via wikipedia,” Transportation Research Part C: Emerging Technologies, vol. 139, p. 103661, Jun. 2022. [Online]. Available: https://doi.org/10.1016/j.trc.2022.103661 [20] W. Yao and S. Qian, “From twitter to traffic predictor: Next-day morning traffic prediction using social media data,” Transportation Research Part C: Emerging Technologies, vol. 124, p. 102938, Mar. 2021. [Online]. Available: https://doi.org/10.1016/j.trc.2020.102938 [21] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” 2017. [Online]. Available: https://arxiv.org/abs/1706.03762 [22] C. Lewis, Industrial and business forecasting methods. Oxford, England: Butterworth-Heinemann, Jan. 1982. [23] A. Y. Chen, T.-Y. Lu, M. H.-M. Ma, and W.-Z. Sun, “Demand forecast using data analytics for the preallocation of ambulances,” IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 4, pp. 1178–1187, Jul. 2016. [Online]. Available: https://doi.org/10.1109/jbhi.2015.2443799 [24] CDC, “Taiwan centers for disease control press releases.” [Online]. Available:https://www.cdc.gov.tw/Bulletin/List/MmgtpeidAR5Ooai4-fgHzQ [25] M. Taipei, “Metro taipei ridership counts.” [Online]. Available: https://english. metro.taipei/cp.aspx?n=C702FF0562802D53 [26] W. A. Q. I. W. Project, “Air quality historical data platform.” [Online]. Available:https://aqicn.org/data-platform/register/ | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88920 | - |
dc.description.abstract | COVID-19 的疫情對我們生活上的各個層面皆帶來重大的影響,其中包含了 交通運輸以及交通運輸所帶來的空氣污染量。許多研究指出上述的兩項指標與疫 情的嚴峻程度具有高度相關,然而僅透過確診數作為判斷疫情嚴峻程度的依據, 可能忽略因為政府的相關政策而產生的變化。
本研究旨在從文本資料的角度分析疫情下之交通運量以及空氣污染量的改 變。我們使用基於 BERT 的自然語言處理模型,從台灣疾病管制署(CDC)每日 發佈的新聞稿中收集文本數據,以捕捉人們在疫情相關的資訊和政策之下在交通 行為上的變化,並針對台北捷運在疫情期間的運量以及各項與交通運輸相關的空 氣污染指標進行預測,藉此分析疫情在這些不同層面上所帶來的影響。 本研究示範並比較了透過文本資料分析疫情對台北捷運運量及空氣污染量的 影響的多種方法及其相對應的結果,並在捷運運量的預測上得到 18.8% 的平均絕 對百分比誤差,而在空氣污染量的方面,則分別得到一氧化碳 14.4%、二氧化氮 19.9%、二氧化硫 14.9%、臭氧 25.6% 以及 PM10 19.1% 的平均絕對百分比誤差。 政策制定者可以參考我們的研究結果,提供有效的運輸服務,以應對人們在疫情 期間不斷變化的交通需求。 | zh_TW |
dc.description.abstract | The COVID-19 pandemic has had a significant impact on various aspects of our lives, including transportation and the associated air pollution levels. Many studies have indi- cated a strong correlation between these two indicators and the severity of the pandemic. However, relying solely on the number of confirmed cases as a measure of the severity of the pandemic may overlook changes resulting from government policies.
This study aims to analyze changes in transportation volume and air pollution levels during the pandemic from a textual data perspective. We utilize a BERT-based natural language processing model to collect textual data from daily press releases issued by the Taiwan Centers for Disease Control (CDC). The data allow us to capture changes in peo- ple’s transportation behaviors under pandemic-related information and policies. We then predict the traffic volume and various air pollution indicators related to the Taipei Metro during the pandemic, thereby analyzing the impact of the pandemic on these different aspects. This study demonstrates and compares multiple methods for analyzing the impact of the pandemic on Taipei Metro ridership and air pollution levels using textual data. In terms of metro ridership prediction, an average absolute percentage error of 18.8% was obtained. For air pollution levels, the average absolute percentage errors were as follows: 14.4% for CO, 19.9% for NO2, 14.9% for NO2, 25.6% for O3, and 19.1% for PM10. Policy makers can refer to our research findings to provide effective transportation services to meet the changing demands of people during the pandemic. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-16T16:21:51Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-08-16T16:21:51Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i
Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xiii List of Tables xvii Denotation xix Chapter 1 INTRODUCTION 1 1.1 Metro Systems 1 1.2 Traffic Related Air Pollution (TRAP) 4 1.3 Objective 5 Chapter 2 LITERATURE REVIEW 7 2.1 Transportation Under COVID-19 7 2.2 TRAP Under COVID-19 8 2.3 NLP 9 2.4 Research Gap 10 Chapter 3 METHODOLOGY 13 3.1 NLP with the BERT Model 14 3.2 Data Managing Approaches 16 3.2.1 Random Split vs. Chronological Split 16 3.2.2 Non-Adaptive vs. Adaptive 17 3.2.3 Smoothing with Simple Moving Average 18 3.3 Measure of Prediction 18 3.3.1 Mean Absolute Error 19 3.3.2 Mean Absolute Percentage Error 19 Chapter 4 RESULTS 21 4.1 Data Collection and Preprocessing 21 4.1.1 Daily Press Release Data 21 4.1.2 Daily Volume of the Taipei Metro 23 4.1.3 Daily Amount of TRAP 23 4.2 Results and Comparison 24 4.2.1 MRT Ridership 26 4.2.2 CO 32 4.2.3 NO2 38 4.2.4 SO2 44 4.2.5 O3 50 4.2.6 PM10 55 4.3 Summary 61 Chapter 5 CONCLUSION 65 5.1 Contribution 65 5.2 Limitations66 5.3 Future Works 66 5.4 Summary 67 References 69 | - |
dc.language.iso | zh_TW | - |
dc.title | 利用自然語言深度學習及 COVID-19 之 CDC 每日新聞稿預測交通量及空氣污染量 | zh_TW |
dc.title | Traffic Volume and Traffic Related Air Pollution (TRAP) Estimation through Deep Learning Natural Language Processing of COVID-19 CDC Press Release | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 謝尚賢;周建成;許聿廷 | zh_TW |
dc.contributor.oralexamcommittee | Shang-Hsien Hsieh;Chien-Cheng Chou;Yu-Ting Hsu | en |
dc.subject.keyword | COVID-19疫情,交通量預測,空氣污染,深度學習,自然語言處理,BERT, | zh_TW |
dc.subject.keyword | COVID-19 Pandemic,Traffic Prediction,Air Pollution,Deep Learning,Natural Language Processing (NLP),BERT, | en |
dc.relation.page | 73 | - |
dc.identifier.doi | 10.6342/NTU202303637 | - |
dc.rights.note | 同意授權(全球公開) | - |
dc.date.accepted | 2023-08-10 | - |
dc.contributor.author-college | 工學院 | - |
dc.contributor.author-dept | 土木工程學系 | - |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf | 5.99 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。