研究生: |
施俊宇 Shih, Chun-Yu |
---|---|
論文名稱: |
應用機器學習於公共物聯網之初階研究 An Initial Study of Applying Machine Learning to Civil Internet of Things |
指導教授: |
李坤洲
Lee, Kun-Chou |
學位類別: |
碩士 Master |
系所名稱: |
工學院 - 系統及船舶機電工程學系 Department of Systems and Naval Mechatronic Engineering |
論文出版年: | 2022 |
畢業學年度: | 110 |
語文別: | 中文 |
論文頁數: | 105 |
中文關鍵詞: | 人工智慧 、機器學習 、深度學習 、公共物聯網 |
外文關鍵詞: | artificial intelligence, machine learning, deep learning, civil internet of things |
相關次數: | 點閱:122 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來人工智慧使用機器學習與深度學習技術,應用於各領域進行分析已有顯著成效,更在智慧型手機、第五代行動通訊與物聯網興起後,加速各領域人工智慧相關應用的發展,如自駕車、智慧製造、智慧醫療等…。
國人習慣以LINE為主要通訊工具,LINE官方統計2018年台灣活躍用戶數達2,100萬人,基於LINE之移動性與普及性,目前已有各種以LINE為傳播媒介之智慧應用形式,如使用LINE Notify之系統或設備異常通知、自動化廣告通知等…,及使用LINE Bot之客服機器人、預訂機器人、股票分析機器人等…。因此,本論文擬以LINE Notify及LINE Bot當成公共物聯網之傳播媒介。
本論文是應用機器學習於公共物聯網之初階研究,機器學習的方法包括可推算最佳分群數之K-Means聚類分析、閘式循環神經網路、長短期記憶神經網路。本研究為此領域之初階研究,初期分析的資料包括地震及空氣品質等政府機構提供的公開資料,先使用程式自動抓取政府機構提供的公開資料,接著再用程式做機器學習分析,最後再利用Line Notify及Line Bot發佈給大眾,達到「應用機器學習於公共物聯網」之目標。本研究所建立的流程,可輕易推廣到其他機器學習方法與政府機構提供的其他公開資料,希望對公共物聯網有所貢獻。
SUMMARY
Recently, the artificial intelligence utilized techniques of machine learning and deep learning, and had significant achievements in different fields. Due to the invention of smart phones and the fifth generation mobile communication, the artificial intelligence is easily applied to autonomous cars, smart manufacture, smart healthcare, …, etc.
LINE is the most popular communication software in Taiwan. In 2018, there are 21 million users of LINE in Taiwan. This is due to the mobility and convenience of LINE. In particular, functions of “LINE Notify” and “LINE Bot” are usually applied to different fields such as machinery monitoring, advertisement, customer service, shopping, investment, …, etc. This then motivates us to utilize “LINE Notify” and “LINE Bot” as the communication tools to distribute information for civil internet of things.
This thesis is an initial study of applying machine learning to civil internet of things. The machine learning techniques include K-Means Clustering with optimal number of clusters, GRU (Gate Recurrent Unit), LSTM (Long Short-Term Memory). This thesis is a preliminary research. We get data of earthquake and air quality from public websites of the government. Next, we analyze the data by machine learning programming. Finally, we utilize “LINE Notify” and “LINE Bot” to implement civil internet of things. The research flowchart of this study can be extended to deal with many other public data of the government. This thesis is expected to have contribution in civil internet of things.
[1] 臺灣之災害性地震災害情形及臺灣最嚴重的震災情形,
https://scweb.cwb.gov.tw/zh-TW/Guidance/FAQ/3
(Retrieved on June 28, 2022).
[2] 因應地震災害之都市智慧防災策略藍圖初探,
https://www.abri.gov.tw/News_Content_Table.aspx?n=807&s=140239
(Retrieved on June 28, 2022).
[3] 許金城,基於AIOT架構之穿戴式裝置跌倒偵測系統研究,國立臺北科技大學電機工程系所碩士學位論文,110年。
[4] 施浩宇,透過聊天機器人技術建立LINE BOT族語學習系統過程之研究–以建和卑南族語為例,國立臺東大學教育學系所碩士學位論文,110年。
[5] P. Novianti, D. Setyorini and U. Rafflesia, “K-Means cluster analysis in earthquake epicenter clustering,” International Journal of Advances in Intelligent Informatics, vol. 3, no. 2, pp. 81-89, July 2017.
[6] 李林芳、石耀霖、程術,「長短時記憶神經網路在中期地震預報中的探索———以川滇地區為例」,地球物理學報,第65卷第1期,12-25頁,2022年1月。
[7] K Srinivasa Rao, Dr. G. Lavanya Devi and N. Ramesh, “Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks,” International Journal of Intelligent Systems and Applications, vol. 11, no. 2, pp. 18-24, February 2019.
[8] LINE Notify API Document,
https://notify-bot.line.me/doc/en/
(Retrieved on June 23, 2022).
[9] LINE Developers Messaging API Documentation,
https://developers.line.biz/en/reference/messaging-api
(Retrieved on June 4, 2022).
[10] 文淵閣工作室,Pythn初學特訓班,第三版,臺北市:碁峰資訊股份有限公司,2019。
[11] C. C. Lee, Application of Statistical Variance Analyses and Nonlinear Probabilistic Models to Earthquakes in Taiwan, Project Reports of National Science and Technology Council, Taiwan, NSC (MOST) 105-2815-C-002-177-M, March 2017.
[12] Y. Cheng, “Mean shift, mode seeking, and clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 790-799, August 1995.
[13] C. Chinrungrueng and C.H. Sequin, “Optimal adaptive k-means algorithm with dynamic adjustment of learning rate,” IEEE Transactions on Neural Networks, vol. 6, no. 1, pp. 157-169, January 1995.
[14] GADM圖資檔,
https://gadm.org/index.html
(Retrieved on May 4, 2022).
[15] Understanding LSTM Networks. [online]
http://colah.github.io/posts/2015-08-Understanding-LSTMs
(Retrieved on June 1, 2022).
[16] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735-1780, November 1997.
[17] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Gated feedback recurrent neural networks,” arXiv:1502.02367, February 2015.