簡易檢索 / 詳目顯示

研究生: 楊沛霖
Yang, Pei-Lin
論文名稱: MuBox: 具學習群組喜好功能的智能YouTube播放系統
MuBox: An intelligent group-based YouTube player by learning group interest
指導教授: 蘇淑茵
Sou, Sok-Ian
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年: 2020
畢業學年度: 108
語文別: 英文
論文頁數: 34
中文關鍵詞: 群體性音樂播放裝置音樂喜好YouTubeChrome擴充套件資料收集與分析
外文關鍵詞: Group-based, Music player, Music preferences, YouTube, Chrome extension, Data collection and analysis
相關次數: 點閱:141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
  • 現代人離不開音樂,習慣在任何時刻都能聽到音樂,用餐時也是如此。目前在大多數餐廳所播放的音樂仍是由店家自行決定;但也因為不了解顧客音樂喜好,因此餐廳撥放的音樂可能出現顧客較不喜歡的音樂類型。但是如果單純由顧客選擇喜歡的音樂,則可能出現客人所選擇的音樂類型或內容不適合於該餐廳內播放。
    為此,我們構建了一個解決該問題的系統: (1)實作一個可以讓使用者選擇音樂並進行互動的音樂播放裝置MuBox。 (2)為了讓使用者們能夠收聽自己喜歡的歌曲,我們建立了一個Chomre擴充套件MuTube,用於收集使用者YouTube 音樂偏好並藉此建立了我們自己的資料集。 (3)除此之外我們建立了一個推薦系統,利用收集到的資料進行推薦,讓使用者們都能在餐廳聽到他們喜歡的音樂。

    People nowadays are inseparable from music. They listen to music at all times, even during meals. While dining in a restaurant, the background music being played is mostly at the discretion of the store. The restaurants do not consider customer’s music preferences. Consequently, the music may not accommodate the customers’ tastes. However, if the music is chosen by the customers, the music genre or some explicit content in the lyrics could be inappropriate to be played in public.
    Hence, we constructed a system to solve this problem by: (1)Implementing an interactive music player, MuBox, which can take song requests from the users. (2)Learning users’ music preferences by collecting their YouTube listening history via a Chrome extension, called MuTube. (3)Setting up a recommendation system which uses the collected music data to generate suitable music recommendations.

    Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .i List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .iii List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .iv 1 Introduction 1 1.1 Research Background . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 1.2 Research Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 1.3 Research Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . .2 2 Related Works 3 3 System Architecture 5 3.1 MuBox . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .5 3.2 MuTube . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .7 3.3 Server . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .7 3.4 Database . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .7 4 Design and Implementation 8 4.1 MuBox song request and recommendation . . . . . . . . . . . . . . . .8 4.1.1 How MuBox works . . . . . . . . . . . . . . . . . . . . . . . . .9 4.1.2 How Recommendation Work . . . . . . . . . . . . . . . . . . . .11 4.1.3 MuBox Application . . . . . . . . . . . . . . . . . . . . . . . . .14 4.2 MuTube collect user usage data . . . . . . . . . . . . . . . . . . . . . .14 4.2.1 Difficulties in development . . . . . . . . . . . . . . . . . . . . .15 4.2.2 How MuTube work . . . . . . . . . . . . . . . . . . . . . . . . .15 4.2.3 How MuTube saves and sends data . . . . . . . . . . . . . . . .18 4.2.4 Additional functions of MuTube . . . . . . . . . . . . . . . . . .19 5 Dataset 21 5.1 Data collection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .21 5.2 Data Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .24 5.3 Data analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .25 6 CONCLUSION 31 Bibliography 32

    [1]J. K. Vuoskoski and T. Eerola, “Measuring music-induced emotion: A compari-son of emotion models, personality biases, and intensity of experiences,”MusicaeScientiae, vol. 15, no. 2, pp. 159–173, 2011.
    [2]J. K. Vuoskoski and T. Eerola, “Measuring music-induced emotion: Acomparison of emotion models, personality biases, and intensity of experiences,”Musicae Scientiae, vol. 15, no. 2, pp. 159–173, 2011. [Online]. Available:https://doi.org/10.1177/1029864911403367
    [3]R. E. Milliman, “Using background music to affect the behavior of supermarketshoppers,”Journal of Marketing, vol. 46, no. 3, pp. 86–91, 1982. [Online].Available: http://www.jstor.org/stable/1251706
    [4]R. Yalch and E. Spangenberg, “Effects of store music on shopping behavior,”Journal of Consumer Marketing, vol. 7, no. 2, pp. 55–63, 1990.
    [5]小池直也, “「マクドナルドの店内bgm」のディープさに感動して“中の人”に直撃したら本当にスゴかった話,” https://www.businessinsider.jp/post-190596,accessed May. 14, 2019.
    [6]M. Kontukoski, M. Paakki, J. Thureson, H. Uimonen, and A. Hopia, “Imaginedsalad and steak restaurants: Consumers’colour, music and emotion associationswith different dishes,”International Journal of Gastronomy and Food Science,vol. 4, pp. 1–11, 2016.
    [7]A. A. Fox, “The jukebox of history: Narratives of loss and desire in the discourseof country music,”Popular Music, vol. 11, no. 1, pp. 53–72, 1992.
    [8]Last.fm, “「last.fm,” https://www.last.fm/, accessed May. 14, 2020.32
    [9]O. Celma,Music Recommendation and Discovery in the Long Tail. Springer,2010.
    [10]T. Bertin-Mahieux, D. P. Ellis, B. Whitman, and P. Lamere, “The million songdataset,” inProceedings of the 12th International Conference on Music Informa-tion Retrieval (ISMIR 2011), 2011.
    [11]G. Dror, N. Koenigstein, Y. Koren, and M. Weimer, “The yahoo! music datasetand kdd-cup’11,” inProceedings of the 2011 International Conference on KDDCup 2011-Volume 18, 2011, pp. 3–18.
    [12]J. Suzuki and T. Kitahara, “A bluetooth-networked music player for playing mu-sical pieces stored in separate devices,” in2016 Eighth International Conferenceon Knowledge and Systems Engineering (KSE). IEEE, 2016, pp. 234–238.
    [13]J. F. McCarthy and T. D. Anagnost, “Musicfx: an arbiter of group preferencesfor computer supported collaborative workouts,” inProceedings of the 1998 ACMconference on Computer supported cooperative work, 1998, pp. 363–372.
    [14]Youtube-8m: A large and diverse labeled video dataset for video understandingresearch. https://research.google.com/youtube8m/index.html.
    [15]Welcome to python.org. [Online]. Available: https://www.python.org/
    [16]Raspberry pi 3 model b+. [Online]. Available: https://www.raspberrypi.org/products/raspberry-pi-3-model-b-plus/
    [17]Raspbian for raspberry pi. [Online]. Available: https://www.raspberrypi.org/downloads/raspbian/
    [18]I. Harvey, “Read one-dimensional barcodes and qr codes. contribute toNaturalHistoryMuseum/pyzbar development by creating an account on GitHub.”[Online]. Available: https://github.com/NaturalHistoryMuseum/pyzbar/
    [19]Seleniumhq browser automation. [Online]. Available: https://www.selenium.dev/
    [20]Omxplayer: An accelerated command line media player. [Online]. Available: https://www.raspberrypi.org/documentation/raspbian/applications/omxplayer.md33
    [21]willprice, “omxplayer-wrapper is a project to control omxplayer from python overdbus.” [Online]. Available: https://github.com/NaturalHistoryMuseum/pyzbar/
    [22]Mqtt is a machine-to-machine (m2m)/”internet of things” connectivity protocol.[Online]. Available: http://mqtt.org/
    [23]“Qrcode.js is javascript library for making qrcode.” [Online]. Available:https://github.com/davidshimjs/qrcodejs
    [24]Node.js. [Online]. Available: https://nodejs.org/en/
    [25]React‒a javascript library for building user interfaces. [Online]. Available:https://reactjs.org/
    [26]Express - node.js web application framework. [Online]. Available: https://expressjs.com/
    [27]The most popular database for modern apps | mongodb. [Online]. Available:https://www.mongodb.com/

    下載圖示 校內:2025-08-19公開
    校外:2025-08-19公開
    QR CODE