1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 基於個人電腦使用者操作情境之音樂推薦
Context-based Music Recommendation for Desktop Users
作者 謝棋安
Hsieh, Chi An
貢獻者 沈錳坤
Shan, Man Kwan
謝棋安
Hsieh, Chi An
關鍵詞 音樂
推薦
情境
個人電腦
MAML
演算法
music
recommendation
context
desktop
MAML
algorithm
日期 2009
上傳時間 9-May-2016 12:02:32 (UTC+8)
摘要 隨著電腦音樂技術的蓬勃發展，合乎情境需求的音樂若被能自動推薦給使用者，將是知識工作者所樂見的。我們提出了一個定義使用者操作情境的情境塑模，定義使用者操作情境，並利用累計專注視窗的轉變，找出使用者的操作情境。同時，我們也提出了音樂推薦塑模，依據使用者的操作情境與聆聽的音樂，分析探勘情境與音樂特徵間的關聯特性，利用探勘出的關聯推薦適合情境的音樂給使用者。在此音樂推薦塑模中，我們採用Content-based Recommendation的作法。我們分析音樂的特徵值，並發展MAML(Multi-attribute Multi-label)的分類演算法以及Probability Measure二種方法來探勘情境屬性與音樂特徵間的關聯特性。根據探勘出的關聯特性，找出適合情境的音樂特徵，再從音樂資料庫中推薦符合音樂特徵的音樂給使用者。本論文的符合使用者操作情境的音樂推薦系統是利用Windows Hook API實作。經實驗證明，本論文方法在符合情境的音樂推薦上，擁有近七成準確率。
With the development of digital music technology, knowledge workers will be delighted if the music recommendation system is able to automatically recommend music based on the operating context in the desktop. The context model and context identification algorithm are proposed to define the operating context of users and to detect the transition of context based on the changes of focused windows. Two association discovery mechanisms, MMAL (Multi-attribute Multi-label) algorithm and PM (Probability Measure), are proposed to discover the relationships between context features and music features. Based on the discovered rules, the proposed music recommendation mechanism recommends music to the user from the music database according to the operating context of users. The context-based recommendation system is implemented using Windows Hook API. Experimental results show that near 70% accuracy can be achieved.
參考文獻 [1] 高臺茜、倪珮晶，華語文網路言論負向情緒用詞檢核軟體研發，第三屆全球華文網路教育研討會(ICICE2003)論文集，2003。
     [2] G. D. Abowd, A. K. Dey, P. J. Brown, N. Davies, M. Smith, and P. Steggles, “Towards a Better Understanding of Context and Context-Awareness,” Proceedings of IEEE International Symposium on Handheld and Ubiquitous Computing, 1999.
     [3] M. G. Brown, “Supporting User Mobility,” Proceeding of International Federation for Information Processing on Mobile Communications, 1996.
     [4] R. Cai, C. Zhang, C. Wang, L. Zhang, and W. Y. Ma, “MusicSense: Contextual Music Recommendation Using Emotional Allocation Modeling,” Proceedings of ACM International Conference on Multimedia, 2007.
     [5] R. Cai, C. Zhang, L. Zhang, and W. Y. Ma, “Scalable Music Recommendation by Search,” Proceedings of ACM International Conference on Multimedia, 2007.
     [6] P. Cano, M. Koppenberger, and N. Wack, “Content-based Music Audio Recommendation,” Proceedings of ACM International Conference on Multimedia, 2005.
     [7] H. C. Chen and A. L. P. Chen, “A Music Recommendation System Based on Music Data Grouping and User Interests,” Proceedings of ACM International Conference on Information and Knowledge Management, 2001.
     [8] W. W. Cohen, and W. Fan, “Web-collaborative Filtering: Recommending Music by Crawling the Web,” International Journal of Computer and Telecommunications Networking, Volume 33, Issue 1-6, 2000.
     [9] J. R. Cooperstock, K. Tanikoshi, G. Beirne, T. Narine, and W. Buxton, “Evolution of a Reactive Environment,” Proceedings of ACM International Conference on Human
     55
     Factors in Computing Systems, 1995.
     [10] B. Cui, L. Liu, C. Pu, J. Shen., and K. L. Tan, “QueST: Querying Music Databases by Acoustic and Textual Features,” Proceedings of ACM International Conference on Multimedia, 2007.
     [11] A. K. Dey, “Understanding and Using Context,” Personal and Ubiquitous Computing, Volume 5, Issue 1, 2001.
     [12] S. Elrod, G. Hall, R. Costanza, M. Dixon, and J. D. Rivières, “Responsive Office Environments,” Communications of the ACM, Volume 36, Issue 7, 1993.
     [13] S. Fickas, G. Kortuem, and Z. Segall, “Software Organization for Dynamic and Adaptable Wearable Systems” Proceedings of IEEE International Symposium on Wearable Computers, 1997.
     [14] R. Hull, P. Neaves, and J. Bedford-Roberts, “Towards Situated Computing,” Proceedings of IEEE International Symposium on Wearable Computers, 1997.
     [15] J. S. Jang, Audio Signal Processing and Recognition, http://neural.cs.nthu.edu.tw/jang/books/audioSignalProcessing/index.asp.
     [16] D. Kirovski and H. Attias, “Beat-id: Identifying Music via Beat Analysis,” Proceeding of IEEE Workshop on Multimedia Signal Processing, 2002.
     [17] P. Knees, E. Pampalk, and G. Widmer, “Artist Classification with Web-based Data,” Proceedings of International Symposium on Music Information Retrieval, 2004.
     [18] F. F. Kuo, M. F. Chiang., M. K. Shan, and S. Y. Lee, “Emotion-based Music Recommendation by Association Discovery from Film Music,” Proceedings of ACM International Conference on Multimedia, 2005.
     [19] Q. Li, B. M. Kim, D. H. Guan, and D. W. Oh, “A Music Recommender Based on Audio Features,” Proceedings of ACM International Conference on Research and Development
     56
     in Information Retrieval, 2004.
     [20] G. C. Li, K.Y. Liu and Y. K. Zhang, “Identifying Chinese Word and Processing Different Meaning Structures”, Journal of Chinese Information Processing, Volume 2, 1988.
     [21] N.Y. Liang, “Knowledge of Chinese Word Segmentation”, Journal of Chinese Information Processing, Volume 4, Issue 2, 1990
     [22] B. Liu, W. Hsu, and Y. Ma, “Integrating Classification and Association Rule Mining,” Proceeding of ACM International Conference on Knowledge Discovery and Data Mining, 1998.
     [23] B. Logan, “Music Recommendation from Song Sets,” Proceedings of ACM International Conference on Music Information Retrieval, 2004.
     [24] J MacQueen, "Some Methods for Classification and Analysis of Multivariate Observations,” Proceedings of Berkeley Symposium on Mathematical Statistics and Probability, 1967.
     [25] D. Mcennis, C. Mckay, I. Fujinaga, and P. Depalle, “jAudio: a Feature Extraction Library,” Proceeding of International Conference on Music Information Retrieval, 2005.
     [26] J. Y. Pan, H. J. Yang, C. Faloutsos, and P. Duygulu, “Automatic Multimedia Cross-modal Correlation Discovery,” Proceeding of ACM International Conference on Knowledge Discovery and Data Mining, 2004.
     [27] H. S. Park, J. O. Yoo, and S. B. Cho, “A Context-Aware Music Recommendation System Using Fuzzy Bayesian Networks with Utility Theory,” Proceeding of Fuzzy Systems and Knowledge Discovery, 2007.
     [28] J. Pascoe, “Adding Generic Contextual Capabilities to Wearable Computers,” Proceedings of IEEE International Symposium on Wearable Computers, 1998.
     [29] J Rekimoto, Y. Ayatsuka, and K. Hayashi, “Augment-able Reality: Situated
     57
     Communication through Physical and Digital Spaces,” Proceedings of IEEE International Symposium on Wearable Computers, 1998.
     [30] B. Schilit, N. Adams, and R. Want, “Context-Aware Computing Applications,” Proceeding of IEEE Workshop on Mobile Computing Systems and Applications, 1994.
     [31] B. Schilit and M. Theimer, “Disseminating Active Map Information to Mobile Hosts,” IEEE Network, Volume 8, Issue 5, 1994.
     [32] U. Shardanand, “Social Information Filtering for Music Recommendation,” Master Thesis, Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 1994.
     [33] J. Shen, L. Li and T. G. Dietterich, “Real-Time Detection of Task Switches of Desktop Users,” Processing of International Joint Conference on Artificial Intelligence, 2007.
     [34] T. Li, M. Ogihara, and Q. Li, “A Comparative Study on Content-Based Music Genre Classification,” Proceedings of ACM SIGIR Conference on Research and Development in Informaion Retrieval, 2003.
     [35] R. E. Thayer, The Biopsychology of Mood and Arousal, Oxford University Press, ISBN 0195051629, 1989.
     [36] F. A. Thabtah and P. I. Cowling, “A Greedy Classification Algorithm Based on Association Rule,” Applied Soft Computing, Volume 7, Issue 3, 2007.
     [37] F. A. Thabtah, P. I. Cowling, and P. Yonghong, “MMAC: a New Multi-Class, Multi-Label Associative Classification Approach,” Proceeding of IEEE International Conference on Data Mining, 2004.
     [38] G. Tzanetakis and P. Cook, “Musical Genre Classification of Audio Signals,” IEEE Transactions on Speech and Audio Processing, Volume 10, Issue 5, 2002.
     [39] Y. H. Yang, Y. C. Lin, Y. F. Su, and H. H. Chen, “A Regression Approach to Music
     58
     Emotion Recognition,” IEEE Transactions on Audio, Speech, and Language Processing, Volume 16, Issue 2, 2007.
     [40] Y. Yang and G. Webb, “Proportional k-Interval Discretization for Naive-Bayes Classifiers,” Proceeding of European Conference on Machine Learning, 2001.
     [41] K. Yoshii, M. Goto, K. Komatani, T. Ogata, and H. Okuno, “Hybrid Collaborative and Content-based Music Recommendation Using Probabilistic Model with Latent User Preferences,” Proceeding of International Conference on Music Information Retrieval, 2006.
     [42] Feeling Words: http://eqi.org/fw.htm
     [43] Last.fm. http://www.last.fm/.
描述 碩士
國立政治大學
資訊科學學系
95753007
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0095753007
資料類型 thesis
dc.contributor.advisor 沈錳坤zh_TW
dc.contributor.advisor Shan, Man Kwanen_US
dc.contributor.author (Authors) 謝棋安zh_TW
dc.contributor.author (Authors) Hsieh, Chi Anen_US
dc.creator (作者) 謝棋安zh_TW
dc.creator (作者) Hsieh, Chi Anen_US
dc.date (日期) 2009en_US
dc.date.accessioned 9-May-2016 12:02:32 (UTC+8)-
dc.date.available 9-May-2016 12:02:32 (UTC+8)-
dc.date.issued (上傳時間) 9-May-2016 12:02:32 (UTC+8)-
dc.identifier (Other Identifiers) G0095753007en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/94859-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 95753007zh_TW
dc.description.abstract (摘要) 隨著電腦音樂技術的蓬勃發展，合乎情境需求的音樂若被能自動推薦給使用者，將是知識工作者所樂見的。我們提出了一個定義使用者操作情境的情境塑模，定義使用者操作情境，並利用累計專注視窗的轉變，找出使用者的操作情境。同時，我們也提出了音樂推薦塑模，依據使用者的操作情境與聆聽的音樂，分析探勘情境與音樂特徵間的關聯特性，利用探勘出的關聯推薦適合情境的音樂給使用者。在此音樂推薦塑模中，我們採用Content-based Recommendation的作法。我們分析音樂的特徵值，並發展MAML(Multi-attribute Multi-label)的分類演算法以及Probability Measure二種方法來探勘情境屬性與音樂特徵間的關聯特性。根據探勘出的關聯特性，找出適合情境的音樂特徵，再從音樂資料庫中推薦符合音樂特徵的音樂給使用者。本論文的符合使用者操作情境的音樂推薦系統是利用Windows Hook API實作。經實驗證明，本論文方法在符合情境的音樂推薦上，擁有近七成準確率。zh_TW
dc.description.abstract (摘要) With the development of digital music technology, knowledge workers will be delighted if the music recommendation system is able to automatically recommend music based on the operating context in the desktop. The context model and context identification algorithm are proposed to define the operating context of users and to detect the transition of context based on the changes of focused windows. Two association discovery mechanisms, MMAL (Multi-attribute Multi-label) algorithm and PM (Probability Measure), are proposed to discover the relationships between context features and music features. Based on the discovered rules, the proposed music recommendation mechanism recommends music to the user from the music database according to the operating context of users. The context-based recommendation system is implemented using Windows Hook API. Experimental results show that near 70% accuracy can be achieved.en_US
dc.description.tableofcontents 摘要 ........................................................................................................................ i
     目錄 ....................................................................................................................... ii
     圖目錄 .................................................................................................................. iv
     表目錄 ................................................................................................................... v
     第一章 概論 ......................................................................................................... 1
     1.1 動機 .......................................................................................................... 1
     1.2 使用者操作情境的定義 ......................................................................... 2
     1.3 情境感知計算 ......................................................................................... 3
     1.4 論文架構.................................................................................................. 4
     第二章 相關研究 ................................................................................................. 5
     第三章 研究方法及步驟 ..................................................................................... 9
     3.1 情境塑模................................................................................................ 11
     3.1.1 取得事件記錄 ............................................................................... 12
     3.1.2 情境識別 ....................................................................................... 14
     3.2 情境特徵值擷取 .................................................................................... 18
     iv
     3.2.1 內容特徵值擷取 ........................................................................... 19
     3.2.2 音樂特徵值的選擇 ....................................................................... 20
     3.2.3 音樂特徵值的離散化 ................................................................... 22
     3.3 音樂推薦塑模 ........................................................................................ 23
     3.3.1 問題描述及定義 ........................................................................... 23
     3.3.2 MAML分類演算法 ...................................................................... 25
     3.3.3利用MAML分類器推薦音樂 ..................................................... 33
     3.3.4利用Probability Measure推薦音樂 ............................................. 35
     第四章 系統實作 ............................................................................................... 37
     4.1 事件記錄的擷取 .................................................................................... 37
     4.2 情境識別實作 ........................................................................................ 39
     4.3 情境特徵值擷取 .................................................................................... 40
     4.4 建置音樂特徵資料庫及音樂塑模 ........................................................ 41
     4.5 音樂推薦 ................................................................................................ 41
     第五章 實驗 ....................................................................................................... 44
     5.1 實驗設計 ................................................................................................ 44
     5.2 情境識別的參數選定 ............................................................................ 45
     5.3 MAML分類演算法的效果 ................................................................... 46
     v
     5.4 Probability Measure的效果 ................................................................... 50
     5.5 討論 ........................................................................................................ 51
     結論與未來研究 ................................................................................................. 53
     參考文獻 ............................................................................................................. 54		zh_TW
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0095753007en_US
dc.subject (關鍵詞) 音樂zh_TW
dc.subject (關鍵詞) 推薦zh_TW
dc.subject (關鍵詞) 情境zh_TW
dc.subject (關鍵詞) 個人電腦zh_TW
dc.subject (關鍵詞) MAMLzh_TW
dc.subject (關鍵詞) 演算法zh_TW
dc.subject (關鍵詞) musicen_US
dc.subject (關鍵詞) recommendationen_US
dc.subject (關鍵詞) contexten_US
dc.subject (關鍵詞) desktopen_US
dc.subject (關鍵詞) MAMLen_US
dc.subject (關鍵詞) algorithmen_US
dc.title (題名) 基於個人電腦使用者操作情境之音樂推薦zh_TW
dc.title (題名) Context-based Music Recommendation for Desktop Usersen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] 高臺茜、倪珮晶，華語文網路言論負向情緒用詞檢核軟體研發，第三屆全球華文網路教育研討會(ICICE2003)論文集，2003。
     [2] G. D. Abowd, A. K. Dey, P. J. Brown, N. Davies, M. Smith, and P. Steggles, “Towards a Better Understanding of Context and Context-Awareness,” Proceedings of IEEE International Symposium on Handheld and Ubiquitous Computing, 1999.
     [3] M. G. Brown, “Supporting User Mobility,” Proceeding of International Federation for Information Processing on Mobile Communications, 1996.
     [4] R. Cai, C. Zhang, C. Wang, L. Zhang, and W. Y. Ma, “MusicSense: Contextual Music Recommendation Using Emotional Allocation Modeling,” Proceedings of ACM International Conference on Multimedia, 2007.
     [5] R. Cai, C. Zhang, L. Zhang, and W. Y. Ma, “Scalable Music Recommendation by Search,” Proceedings of ACM International Conference on Multimedia, 2007.
     [6] P. Cano, M. Koppenberger, and N. Wack, “Content-based Music Audio Recommendation,” Proceedings of ACM International Conference on Multimedia, 2005.
     [7] H. C. Chen and A. L. P. Chen, “A Music Recommendation System Based on Music Data Grouping and User Interests,” Proceedings of ACM International Conference on Information and Knowledge Management, 2001.
     [8] W. W. Cohen, and W. Fan, “Web-collaborative Filtering: Recommending Music by Crawling the Web,” International Journal of Computer and Telecommunications Networking, Volume 33, Issue 1-6, 2000.
     [9] J. R. Cooperstock, K. Tanikoshi, G. Beirne, T. Narine, and W. Buxton, “Evolution of a Reactive Environment,” Proceedings of ACM International Conference on Human
     55
     Factors in Computing Systems, 1995.
     [10] B. Cui, L. Liu, C. Pu, J. Shen., and K. L. Tan, “QueST: Querying Music Databases by Acoustic and Textual Features,” Proceedings of ACM International Conference on Multimedia, 2007.
     [11] A. K. Dey, “Understanding and Using Context,” Personal and Ubiquitous Computing, Volume 5, Issue 1, 2001.
     [12] S. Elrod, G. Hall, R. Costanza, M. Dixon, and J. D. Rivières, “Responsive Office Environments,” Communications of the ACM, Volume 36, Issue 7, 1993.
     [13] S. Fickas, G. Kortuem, and Z. Segall, “Software Organization for Dynamic and Adaptable Wearable Systems” Proceedings of IEEE International Symposium on Wearable Computers, 1997.
     [14] R. Hull, P. Neaves, and J. Bedford-Roberts, “Towards Situated Computing,” Proceedings of IEEE International Symposium on Wearable Computers, 1997.
     [15] J. S. Jang, Audio Signal Processing and Recognition, http://neural.cs.nthu.edu.tw/jang/books/audioSignalProcessing/index.asp.
     [16] D. Kirovski and H. Attias, “Beat-id: Identifying Music via Beat Analysis,” Proceeding of IEEE Workshop on Multimedia Signal Processing, 2002.
     [17] P. Knees, E. Pampalk, and G. Widmer, “Artist Classification with Web-based Data,” Proceedings of International Symposium on Music Information Retrieval, 2004.
     [18] F. F. Kuo, M. F. Chiang., M. K. Shan, and S. Y. Lee, “Emotion-based Music Recommendation by Association Discovery from Film Music,” Proceedings of ACM International Conference on Multimedia, 2005.
     [19] Q. Li, B. M. Kim, D. H. Guan, and D. W. Oh, “A Music Recommender Based on Audio Features,” Proceedings of ACM International Conference on Research and Development
     56
     in Information Retrieval, 2004.
     [20] G. C. Li, K.Y. Liu and Y. K. Zhang, “Identifying Chinese Word and Processing Different Meaning Structures”, Journal of Chinese Information Processing, Volume 2, 1988.
     [21] N.Y. Liang, “Knowledge of Chinese Word Segmentation”, Journal of Chinese Information Processing, Volume 4, Issue 2, 1990
     [22] B. Liu, W. Hsu, and Y. Ma, “Integrating Classification and Association Rule Mining,” Proceeding of ACM International Conference on Knowledge Discovery and Data Mining, 1998.
     [23] B. Logan, “Music Recommendation from Song Sets,” Proceedings of ACM International Conference on Music Information Retrieval, 2004.
     [24] J MacQueen, "Some Methods for Classification and Analysis of Multivariate Observations,” Proceedings of Berkeley Symposium on Mathematical Statistics and Probability, 1967.
     [25] D. Mcennis, C. Mckay, I. Fujinaga, and P. Depalle, “jAudio: a Feature Extraction Library,” Proceeding of International Conference on Music Information Retrieval, 2005.
     [26] J. Y. Pan, H. J. Yang, C. Faloutsos, and P. Duygulu, “Automatic Multimedia Cross-modal Correlation Discovery,” Proceeding of ACM International Conference on Knowledge Discovery and Data Mining, 2004.
     [27] H. S. Park, J. O. Yoo, and S. B. Cho, “A Context-Aware Music Recommendation System Using Fuzzy Bayesian Networks with Utility Theory,” Proceeding of Fuzzy Systems and Knowledge Discovery, 2007.
     [28] J. Pascoe, “Adding Generic Contextual Capabilities to Wearable Computers,” Proceedings of IEEE International Symposium on Wearable Computers, 1998.
     [29] J Rekimoto, Y. Ayatsuka, and K. Hayashi, “Augment-able Reality: Situated
     57
     Communication through Physical and Digital Spaces,” Proceedings of IEEE International Symposium on Wearable Computers, 1998.
     [30] B. Schilit, N. Adams, and R. Want, “Context-Aware Computing Applications,” Proceeding of IEEE Workshop on Mobile Computing Systems and Applications, 1994.
     [31] B. Schilit and M. Theimer, “Disseminating Active Map Information to Mobile Hosts,” IEEE Network, Volume 8, Issue 5, 1994.
     [32] U. Shardanand, “Social Information Filtering for Music Recommendation,” Master Thesis, Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 1994.
     [33] J. Shen, L. Li and T. G. Dietterich, “Real-Time Detection of Task Switches of Desktop Users,” Processing of International Joint Conference on Artificial Intelligence, 2007.
     [34] T. Li, M. Ogihara, and Q. Li, “A Comparative Study on Content-Based Music Genre Classification,” Proceedings of ACM SIGIR Conference on Research and Development in Informaion Retrieval, 2003.
     [35] R. E. Thayer, The Biopsychology of Mood and Arousal, Oxford University Press, ISBN 0195051629, 1989.
     [36] F. A. Thabtah and P. I. Cowling, “A Greedy Classification Algorithm Based on Association Rule,” Applied Soft Computing, Volume 7, Issue 3, 2007.
     [37] F. A. Thabtah, P. I. Cowling, and P. Yonghong, “MMAC: a New Multi-Class, Multi-Label Associative Classification Approach,” Proceeding of IEEE International Conference on Data Mining, 2004.
     [38] G. Tzanetakis and P. Cook, “Musical Genre Classification of Audio Signals,” IEEE Transactions on Speech and Audio Processing, Volume 10, Issue 5, 2002.
     [39] Y. H. Yang, Y. C. Lin, Y. F. Su, and H. H. Chen, “A Regression Approach to Music
     58
     Emotion Recognition,” IEEE Transactions on Audio, Speech, and Language Processing, Volume 16, Issue 2, 2007.
     [40] Y. Yang and G. Webb, “Proportional k-Interval Discretization for Naive-Bayes Classifiers,” Proceeding of European Conference on Machine Learning, 2001.
     [41] K. Yoshii, M. Goto, K. Komatani, T. Ogata, and H. Okuno, “Hybrid Collaborative and Content-based Music Recommendation Using Probabilistic Model with Latent User Preferences,” Proceeding of International Conference on Music Information Retrieval, 2006.
     [42] Feeling Words: http://eqi.org/fw.htm
     [43] Last.fm. http://www.last.fm/.		zh_TW