學術產出-Theses
Article View/Open
Publication Export
-
題名 使用隨機漫步的監督式學習
Random Walk-based Supervised Learning作者 羅嘉承
Lo, Chia-Cheng貢獻者 周珮婷<br>陳怡如
羅嘉承
Lo, Chia-Cheng關鍵詞 監督式學習
分類
相似度
隨機漫步
馬可夫鏈
OutRank
Supervised Learning
Classification
Similarity
Random walk
Markov Chain
OutRank日期 2023 上傳時間 6-Jul-2023 17:05:14 (UTC+8) 摘要 OutRank 原是一種基於對像相似性所進行的異常偵測方法。不同於以距離或是密度來偵測的形式，OutRank 以計算資料點間的相似性，來找出在資料中的異常小族群。本論文延伸此概念，擴展應用到分類、監督式學習的問題上。根據 OutRank 的性質，我們可以得到各筆資料間的相似度，因此我們假設同一族群間的相似度會較接近。在本論文中，我們會針對不同的資料去做驗證，並且與經典的分類方法 :Random Forest 去做比較。
OutRank was originally developed as an anomaly detection method based on object similarity. Unlike distance or density-based detection approaches, OutRank calculates the similarity between data points to identify small anomaly groups within the data. This study extends the concept of OutRank and applies it to classification and supervised learning problems. Based on the nature of OutRank, we assume that the similarity between data points within the same group will be higher. In this study,we verify this assumption using different datasets and compare the results with the classic classification method, Random Forest.參考文獻 Ahmed, M., Kashem, M. A., Rahman, M., and Khatun, S. (2020). Review and analysisof risk factor of maternal health in remote area using the internet of things (iot). InInECCE2019: Proceedings of the 5th International Conference on Electrical, Control& Computer Engineering, Kuantan, Pahang, Malaysia, 29th July 2019, pages 357–365.Springer.Ait Mohamed, L., Cherfa, A., Cherfa, Y., Belkhamsa, N., and Alim-Ferhat, F. (2021).Hybrid method combining superpixel, supervised learning, and random walk for gliomasegmentation. International journal of imaging systems and technology, 31(1):288–301.Bachelier, L. (1900). Théorie de la spéculation. In Annales scientifiques de l’École normale supérieure, volume 17, pages 21–86.Backstrom, L. and Leskovec, J. (2011). Supervised random walks: predicting and recommending links in social networks. In Proceedings of the fourth ACM internationalconference on Web search and data mining, pages 635–644.Breiman, L. (2001). Random forests. Machine learning, 45:5–32.Charytanowicz, M., Niewczas, J., Kulczycki, P., Kowalski, P. A., Łukasik, S., and Żak, S.(2010). Complete gradient clustering algorithm for features analysis of x-ray images.In Information Technologies in Biomedicine: Volume 2, pages 15–24. Springer.Chotard, A. and Auger, A. (2019). Verifiable conditions for the irreducibility and aperiodicity of markov chains by analyzing underlying deterministic models.Chua, L. O. and Roska, T. (1993). The cnn paradigm. IEEE Transactions on Circuits andSystems I: Fundamental Theory and Applications, 40(3):147–156.ÇINAR, İ., Koklu, M., and Taşdemir, Ş. (2020). Classification of raisin grains usingmachine vision and artificial intelligence methods. Gazi Mühendislik Bilimleri Dergisi,6(3):200–209.Codling, E. A., Plank, M. J., and Benhamou, S. (2008). Random walk models in biology.Journal of the Royal society interface, 5(25):813–834.Cunningham, P., Cord, M., and Delany, S. J. (2008). Supervised learning. Machinelearning techniques for multimedia: case studies on organization and retrieval, pages21–49.Er, M. B. and Aydilek, I. B. (2019). Music emotion recognition by using chroma spectrogram and deep visual features. International Journal of Computational IntelligenceSystems, 12(2):1622–1634.Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annalsof eugenics, 7(2):179–188.King, R., Orlowska, M., and Studer, R. (2003). On the move to meaningful internetsystems 2003.Kleinbaum, D. G., Dietz, K., Gail, M., Klein, M., and Klein, M. (2002). Logistic regression. Springer.Li, J. (2019). Regression and classification in supervised learning. In Proceedings of the2nd International Conference on Computing and Big Data, pages 99–104.Liu, K., Xu, H. L., Liu, Y., and Zhao, J. (2013). Opinion target extraction using partiallysupervised word alignment model. In IJCAI, volume 13, pages 2134–2140.Liu, X., Yi, W., Xi, B., Dai, Q., et al. (2022). Identification of drug-disease associationsusing a random walk with restart method and supervised learning. Computational andMathematical Methods in Medicine, 2022.Lu, W., Zhuang, Y., and Wu, J. (2009). Discovering calligraphy style relationships bysupervised learning weighted random walk model. Multimedia systems, 15:221–242.Moghaddam, F. B., Bigham, B. S., et al. (2018). Extra: Expertise-boosted model for trustbased recommendation system based on supervised random walk. Comput. Informatics,37(5):1209–1230.Moonesinghe, H. and Tan, P.-N. (2006). Outlier detection using random walks. In 200618th IEEE international conference on tools with artificial intelligence (ICTAI’06),pages 532–539. IEEE.Page, L., Brin, S., Motwani, R., and Winograd, T. (1999). The pagerank citation ranking:Bringing order to the web. Technical report, Stanford infolab.Pillai, S. U., Suel, T., and Cha, S. (2005). The perron-frobenius theorem: some of itsapplications. IEEE Signal Processing Magazine, 22(2):62–75.Rish, I. et al. (2001). An empirical study of the naive bayes classifier. In IJCAI 2001workshop on empirical methods in artificial intelligence, volume 3, pages 41–46.Scalas, E. (2006). The application of continuous-time random walks in finance and economics. Physica A: Statistical Mechanics and its Applications, 362(2):225–239. 描述 碩士
國立政治大學
統計學系
110354010資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110354010 資料類型 thesis dc.contributor.advisor 周珮婷<br>陳怡如 zh_TW dc.contributor.author (Authors) 羅嘉承 zh_TW dc.contributor.author (Authors) Lo, Chia-Cheng en_US dc.creator (作者) 羅嘉承 zh_TW dc.creator (作者) Lo, Chia-Cheng en_US dc.date (日期) 2023 en_US dc.date.accessioned 6-Jul-2023 17:05:14 (UTC+8) - dc.date.available 6-Jul-2023 17:05:14 (UTC+8) - dc.date.issued (上傳時間) 6-Jul-2023 17:05:14 (UTC+8) - dc.identifier (Other Identifiers) G0110354010 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/145944 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 統計學系 zh_TW dc.description (描述) 110354010 zh_TW dc.description.abstract (摘要) OutRank 原是一種基於對像相似性所進行的異常偵測方法。不同於以距離或是密度來偵測的形式，OutRank 以計算資料點間的相似性，來找出在資料中的異常小族群。本論文延伸此概念，擴展應用到分類、監督式學習的問題上。根據 OutRank 的性質，我們可以得到各筆資料間的相似度，因此我們假設同一族群間的相似度會較接近。在本論文中，我們會針對不同的資料去做驗證，並且與經典的分類方法 :Random Forest 去做比較。 zh_TW dc.description.abstract (摘要) OutRank was originally developed as an anomaly detection method based on object similarity. Unlike distance or density-based detection approaches, OutRank calculates the similarity between data points to identify small anomaly groups within the data. This study extends the concept of OutRank and applies it to classification and supervised learning problems. Based on the nature of OutRank, we assume that the similarity between data points within the same group will be higher. In this study,we verify this assumption using different datasets and compare the results with the classic classification method, Random Forest. en_US dc.description.tableofcontents 摘要 iAbstract ii目次 iii圖目錄 iv表目錄 v第 一 章 緒論 1第 二 章 文獻回顧 22.1 隨機漫步 22.2 馬可夫鏈性質 32.3 隨機漫步與監督式學習的結合 42.4 總結 5第 三 章 研究方法 63.1 OutRank 方法介紹 63.1.1 馬可夫矩陣 63.1.2 隨機漫步 73.1.3 相聯性 (Connectivity) 73.1.4 監督式學習方法 83.2 隨機森林 (Random Forest) 8第 四 章 實證結果 94.1 評估準則 94.2 資料集介紹 104.3 預測結果 184.4 結論 20第 五 章 結論與建議 21參考文獻 22 zh_TW dc.format.extent 850300 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110354010 en_US dc.subject (關鍵詞) 監督式學習 zh_TW dc.subject (關鍵詞) 分類 zh_TW dc.subject (關鍵詞) 相似度 zh_TW dc.subject (關鍵詞) 隨機漫步 zh_TW dc.subject (關鍵詞) 馬可夫鏈 zh_TW dc.subject (關鍵詞) OutRank zh_TW dc.subject (關鍵詞) Supervised Learning en_US dc.subject (關鍵詞) Classification en_US dc.subject (關鍵詞) Similarity en_US dc.subject (關鍵詞) Random walk en_US dc.subject (關鍵詞) Markov Chain en_US dc.subject (關鍵詞) OutRank en_US dc.title (題名) 使用隨機漫步的監督式學習 zh_TW dc.title (題名) Random Walk-based Supervised Learning en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Ahmed, M., Kashem, M. A., Rahman, M., and Khatun, S. (2020). Review and analysisof risk factor of maternal health in remote area using the internet of things (iot). InInECCE2019: Proceedings of the 5th International Conference on Electrical, Control& Computer Engineering, Kuantan, Pahang, Malaysia, 29th July 2019, pages 357–365.Springer.Ait Mohamed, L., Cherfa, A., Cherfa, Y., Belkhamsa, N., and Alim-Ferhat, F. (2021).Hybrid method combining superpixel, supervised learning, and random walk for gliomasegmentation. International journal of imaging systems and technology, 31(1):288–301.Bachelier, L. (1900). Théorie de la spéculation. In Annales scientifiques de l’École normale supérieure, volume 17, pages 21–86.Backstrom, L. and Leskovec, J. (2011). Supervised random walks: predicting and recommending links in social networks. In Proceedings of the fourth ACM internationalconference on Web search and data mining, pages 635–644.Breiman, L. (2001). Random forests. Machine learning, 45:5–32.Charytanowicz, M., Niewczas, J., Kulczycki, P., Kowalski, P. A., Łukasik, S., and Żak, S.(2010). Complete gradient clustering algorithm for features analysis of x-ray images.In Information Technologies in Biomedicine: Volume 2, pages 15–24. Springer.Chotard, A. and Auger, A. (2019). Verifiable conditions for the irreducibility and aperiodicity of markov chains by analyzing underlying deterministic models.Chua, L. O. and Roska, T. (1993). The cnn paradigm. IEEE Transactions on Circuits andSystems I: Fundamental Theory and Applications, 40(3):147–156.ÇINAR, İ., Koklu, M., and Taşdemir, Ş. (2020). Classification of raisin grains usingmachine vision and artificial intelligence methods. Gazi Mühendislik Bilimleri Dergisi,6(3):200–209.Codling, E. A., Plank, M. J., and Benhamou, S. (2008). Random walk models in biology.Journal of the Royal society interface, 5(25):813–834.Cunningham, P., Cord, M., and Delany, S. J. (2008). Supervised learning. Machinelearning techniques for multimedia: case studies on organization and retrieval, pages21–49.Er, M. B. and Aydilek, I. B. (2019). Music emotion recognition by using chroma spectrogram and deep visual features. International Journal of Computational IntelligenceSystems, 12(2):1622–1634.Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annalsof eugenics, 7(2):179–188.King, R., Orlowska, M., and Studer, R. (2003). On the move to meaningful internetsystems 2003.Kleinbaum, D. G., Dietz, K., Gail, M., Klein, M., and Klein, M. (2002). Logistic regression. Springer.Li, J. (2019). Regression and classification in supervised learning. In Proceedings of the2nd International Conference on Computing and Big Data, pages 99–104.Liu, K., Xu, H. L., Liu, Y., and Zhao, J. (2013). Opinion target extraction using partiallysupervised word alignment model. In IJCAI, volume 13, pages 2134–2140.Liu, X., Yi, W., Xi, B., Dai, Q., et al. (2022). Identification of drug-disease associationsusing a random walk with restart method and supervised learning. Computational andMathematical Methods in Medicine, 2022.Lu, W., Zhuang, Y., and Wu, J. (2009). Discovering calligraphy style relationships bysupervised learning weighted random walk model. Multimedia systems, 15:221–242.Moghaddam, F. B., Bigham, B. S., et al. (2018). Extra: Expertise-boosted model for trustbased recommendation system based on supervised random walk. Comput. Informatics,37(5):1209–1230.Moonesinghe, H. and Tan, P.-N. (2006). Outlier detection using random walks. In 200618th IEEE international conference on tools with artificial intelligence (ICTAI’06),pages 532–539. IEEE.Page, L., Brin, S., Motwani, R., and Winograd, T. (1999). The pagerank citation ranking:Bringing order to the web. Technical report, Stanford infolab.Pillai, S. U., Suel, T., and Cha, S. (2005). The perron-frobenius theorem: some of itsapplications. IEEE Signal Processing Magazine, 22(2):62–75.Rish, I. et al. (2001). An empirical study of the naive bayes classifier. In IJCAI 2001workshop on empirical methods in artificial intelligence, volume 3, pages 41–46.Scalas, E. (2006). The application of continuous-time random walks in finance and economics. Physica A: Statistical Mechanics and its Applications, 362(2):225–239. zh_TW
