臺灣博碩士論文加值系統

長照2.0使用率低的原因為大多數民眾不了解長照系統，如何改善長照的認知與使用率為本研究主要目的。本研究提出整合LSI、K-means與K-NN於語意雲端架構(Integrating LSI, K-means and K-NN into Semantic Cloud Framework，簡稱ILKKSCF)來改善上述問題。利用機器學習(Machine Learning)中潛在語意索引(Latent Semantic Indexing，簡稱LSI)、K-means與K-NN結合語意網(Semantic Web)，架設於雲端運算進行大資料量(Big Data)分析為本系統主要核心。先搜集長照相關文章，利用Jieba套件將文章斷成單字。透過Matrix Market Format將字詞轉為矩陣向量，並利用TF-IDF計算字詞的權重，之後建立LSI模組找出字詞之間隱含的關聯，再將文章使用K-means演算法分群。本研究建構長照應用平台(Long-Term Care Application Platform，簡稱LCAP)，透過LCAP搜集使用者對長照2.0的問題，輸入至建置好的LSI模組，將問題使用K-NN演算法分類。最後透過餘弦相似性(Cosine Similarity)找出符合的文章以客製化方式回覆使用者。另外透過LCAP搜集使用者資訊與Open Data中的長照據點，整合至語意網推薦給使用者可能喜歡的長照據點與服務。由於日積月累形成龐大數據，使用Spark將機器學習和語意網整合至雲端運算提高速度，並比較Spark在LSI、K-means的K值設定與不同資料量下的雲端效能測試。本研究透過系統評估調查準確度與滿意度，根據結果顯示，LSI與K-means在K=300時較為符合系統所需，並在滿意度總分為5分得到4.15分，驗證了ILKKSCF的可行性。

The main reason for the low usage rate of long-term care 2.0 is that most people do not understand the long-term care 2.0 system, and how to improve the awareness and usage of long-term care is the main purpose of this study. This study proposes to Integrating LSI, K-means and K-NN into Semantic Cloud Framework (ILKKSCF) to solve the above problems. The main of the system is to use the Latent Semantic Indexing (LSI), K-means and K-NN in Machine Learning and combine the Semantic Web, and to analyze Big Data based on cloud computing. Collect articles related to long-term care and divide them into words through Jieba. Matrix Market Format is used to transform words into matrix vectors, and TF-IDF is used to calculate the weights of words. Then LSI module is established to find out the hidden association between words, and then K-means algorithm is used to cluster the words. This research constructs a Long-Term Care Application Platform (LCAP), collects the user's problems about Long-Term 2.0 through LCAP, inputs them to the built LSI module, and classifies the problems by through K-NN algorithm. Finally, find out the matching articles through the Cosine Similarity to reply to the user. In addition, the user information collected by LCAP and the long-term care sites in Open Data are integrated into the long-term care sites and services recommended by Semantic Web. Due to the huge amount of data accumulated over the years, Spark is used to integrate Machine Learning and Semantic Web into cloud computing to improve the speed, and the K-value settings of Spark in LSI, K-means and cloud performance tests under different data volumes are compared. In this study, the accuracy and satisfaction of the survey are evaluated systematically. According to the results, LSI and K-means can meet the needs of the system at K=300, and the total satisfaction score of 5 is 4.15, which verifies the feasibility of ILKKSCF.

摘要.................................................i
Abstract.................................................ii
誌謝.................................................iii
目錄.................................................iv
表目錄.................................................vi
圖目錄.................................................vii
第一章 簡介.................................................1
1.1 研究背景.................................................1
1.2 研究動機.................................................2
1.3 研究目的.................................................2
第二章 研究技術探討.................................................3
2.1 語意網(Semantic Web).................................................3
2.1.1 RDF.................................................4
2.1.2 Ontology.................................................4
2.1.3 Rule.................................................4
2.1.4 Jena.................................................4
2.2 開放資料(Open Data).................................................5
2.3 結巴斷詞(Jieba).................................................5
2.4 Matrix Market Format.................................................6
2.5 TF-IDF(Term Frequency-Inverse Document Frequency).................................................7
2.6 潛在語意索引(Latent Semantic Indexing).................................................8
2.7 K-means演算法.................................................9
2.8 K-NN演算法.................................................10
2.9 餘弦相似性.................................................11
2.10 Hadoop.................................................11
2.10.1 Hadoop分散式檔案系統.................................................12
2.10.2 Hadoop YARN.................................................13
2.11 Apache Spark.................................................14
2.11.1 彈性分散式資料集.................................................15
2.11.2 Spark叢集管理器.................................................15
2.12 相關研究.................................................16
第三章 系統設計與研究步驟.................................................17
3.1 系統設計.................................................17
3.1.1 一般性架構.................................................17
3.1.2 系統架構.................................................19
3.1.3 開發環境.................................................20
3.2 研究步驟.................................................21
3.2.1 資料搜集與前處理.................................................21
3.2.2 向量矩陣.................................................23
3.2.3 機器學習.................................................25
3.2.4 餘弦相似性.................................................27
3.2.5 建置語意網進行推論.................................................28
3.2.6 整合機器學習與語意網結合雲端運算.................................................32
第四章 系統實作.................................................34
4.1 應用場景.................................................34
4.2 系統特色.................................................34
4.3 手機App.................................................35
第五章 系統實驗與評估.................................................39
5.1 雲端運算環境架構.................................................39
5.1.1 測試環境.................................................39
5.1.2 雲端運算叢集架構.................................................40
5.2 雲端運算效能測試.................................................42
5.2.1 測試數據.................................................42
5.2.2 測試一 Spark Standalone叢集模式.................................................43
5.2.3 測試二 Spark on YARN叢集模式.................................................44
5.3 測試總結.................................................45
5.4 系統評估.................................................46
第六章 結論.................................................49
參考文獻.................................................50
Extended Abstract.................................................54

[1]內政部. (2018). 中華民國內政部全球資訊網-相關資訊. Available: https://www.moi.gov.tw/chi/chi_news/news_detail.aspx?type_code=02&sn=13723
[2]衛生福利部. (2018-12-20). 長照十年計畫2.0 ─ 社區整體照顧模式. Available: https://1966.gov.tw/LTC/cp-4006-42523-201.html
[3]K. Park, M. C. Nguyen, and H. Won, "Web-based collaborative big data analytics on big data as a service platform," in 2015 17th International Conference on Advanced Communication Technology (ICACT), 2015, pp. 564-567: IEEE.
[4]İ. AYDIN, S. Mehmet, and M. U. SALUR, "Detection of Fake Twitter Accounts with Machine Learning Algorithms," in 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 2018, pp. 1-4: IEEE.
[5]I. A. T. Hashem, I. Yaqoob, N. B. Anuar, S. Mokhtar, A. Gani, and S. U. J. I. s. Khan, "The rise of “big data” on cloud computing: Review and open research issues," vol. 47, pp. 98-115, 2015.
[6]N. K. Pandey, S. Chaudhary, and N. Joshi, "Resource allocation strategies used in cloud computing: a critical analysis," in 2016 2nd International Conference on Communication Control and Intelligent Systems (CCIS), 2016, pp. 213-216: IEEE.
[7]M. Klusch, P. Kapahnke, S. Schulte, F. Lecue, and A. J. K.-K. I. Bernstein, "Semantic web service search: a brief survey," vol. 30, no. 2, pp. 139-147, 2016.
[8]B. Yu, C. Zhang, Y. Li, and J. Sun, "Research and implementation of data fusion method based on RDF," in 2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA), 2018, pp. 87-91: IEEE.
[9]A. Ramaprasad and S. S. Papagari, "Ontological design," presented at the Proceedings of the 4th International Conference on Design Science Research in Information Systems and Technology, Philadelphia, Pennsylvania, 2009.
[10]G. Mehdi et al., "Semantic rule-based equipment diagnostics," in International Semantic Web Conference, 2017, pp. 314-333: Springer.
[11]D. Corsar and P. Edwards, "Challenges of Open Data Quality: More Than Just License, Format, and Customer Support %J J. Data and Information Quality," vol. 9, no. 1, pp. 1-4, 2017.
[12]GitHub. (2016). Jieba. Available: https://github.com/ldkrsi/jieba-zh_TW
[13]N. I. o. S. a. Technology. (2013). Matrix Market Exchange Formats. Available: https://math.nist.gov/MatrixMarket/formats.html
[14]Wikipedia. (2019). TF-IDF. Available: https://en.wikipedia.org/wiki/Tf%E2%80%93idf
[15]D. Talia, "Making knowledge discovery services scalable on clouds for big data mining," in 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM), 2015, pp. 1-4: IEEE.
[16]R. Yang. (2017). 潛在語意索引. Available: https://raymondyangsite.wordpress.com/2017/05/03/110/
[17]N. Akter, A. S. Hoque, R. Mustafa, and M. S. Chowdhury, "Accuracy analysis of recommendation system using singular value decomposition," in 2016 19th International Conference on Computer and Information Technology (ICCIT), 2016, pp. 405-408: IEEE.
[18]B. K. Mishra, A. Rath, N. R. Nayak, and S. Swain, "Far efficient K-means clustering algorithm," presented at the Proceedings of the International Conference on Advances in Computing, Communications and Informatics, Chennai, India, 2012.
[19]N. García-Pedrajas, J. A. R. del Castillo, G. J. I. t. o. n. n. Cerruela-García, and l. systems, "A Proposal for Local $ k $ Values for $ k $-Nearest Neighbor Rule," vol. 28, no. 2, pp. 470-475, 2017.
[20]G. Qian, S. Sural, Y. Gu, and S. Pramanik, "Similarity between Euclidean and cosine angle distance for nearest neighbor queries," presented at the Proceedings of the 2004 ACM symposium on Applied computing, Nicosia, Cyprus, 2004.
[21]F. S. Al-Anzi, D. J. J. o. K. S. U.-C. AbuZeina, and I. Sciences, "Toward an enhanced Arabic text classification using cosine similarity and Latent Semantic Indexing," vol. 29, no. 2, pp. 189-195, 2017.
[22]J. J. P. c. s. Anuradha, "A brief introduction on Big Data 5Vs characteristics and Hadoop technology," vol. 48, pp. 319-324, 2015.
[23]D. Ramesh, N. Patidar, G. Kumar, and T. Vunnam, "Evolution and analysis of distributed file systems in cloud storage: Analytical survey," in 2016 International Conference on Computing, Communication and Automation (ICCCA), 2016, pp. 753-758: IEEE.
[24]C. Smith and A. J. A. S. N. Albarghouthi, "MapReduce program synthesis," vol. 51, no. 6, pp. 326-340, 2016.
[25]A. Azqueta-Alzúaz, M. Patiño-Martinez, I. Brondino, and R. Jimenez-Peris, "Massive data load on distributed database systems over HBase," in Proceedings of the 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, 2017, pp. 776-779: IEEE Press.
[26]V. R. Eluri, M. Ramesh, A. S. M. Al-Jabri, and M. Jane, "A comparative study of various clustering techniques on big data sets using Apache Mahout," in 2016 3rd MEC International Conference on Big Data and Smart City (ICBDSC), 2016, pp. 1-4: IEEE.
[27]M. R. Ghazi and D. J. P. C. S. Gangodkar, "Hadoop, MapReduce and HDFS: a developers perspective," vol. 48, pp. 45-50, 2015.
[28]J.-C. Lin, I. C. Yu, E. B. Johnsen, and M.-C. Lee, "ABS-YARN: A formal framework for modeling Hadoop YARN clusters," in International Conference on Fundamental Approaches to Software Engineering, 2016, pp. 49-65: Springer.
[29]X. Meng et al., "Mllib: Machine learning in apache spark," vol. 17, no. 1, pp. 1235-1241, 2016.
[30]A. Abu-Dbai, D. Breitgand, G. Gershinsky, A. Glikson, and K. Ahmed, "Enterprise Resource Management in Mesos Clusters," presented at the Proceedings of the 9th ACM International on Systems and Storage Conference, Haifa, Israel, 2016.
[31]X. Ling, J. Yang, D. Wang, J. Chen, and L. Li, "Fast community detection in large weighted networks using graphx in the cloud," in 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), 2016, pp. 1-8: IEEE.
[32]R. K. Mishra, "Spark Architecture and the Resilient Distributed Dataset," in PySpark Recipes: Springer, 2018, pp. 85-114.
[33]H. Koezuka, "Utilization of IoT in the long-term care field in Japan," in 2016 2nd International Conference on Cloud Computing and Internet of Things (CCIOT), 2016, pp. 166-169: IEEE.
[34]M. Alodadi and V. P. Janeja, "Similarity in patient support forums using tf-idf and cosine similarity metrics," in 2015 International Conference on Healthcare Informatics, 2015, pp. 521-522: IEEE.
[35]X. Jin, W. Ma, and Y. Li, "Medical Record Text Analysis Based on Latent Semantic Analysis," in 2015 8th International Symposium on Computational Intelligence and Design (ISCID), 2015, vol. 2, pp. 108-110: IEEE.
[36]K. Niu, Z. Gao, H. Jiao, and N. Deng, "K-means+: A developed clustering algorithm for big data," in 2016 4th International Conference on Cloud Computing and Intelligence Systems (CCIS), 2016, pp. 141-144: IEEE.
[37]P. S. Kumar and S. Pranavi, "Performance analysis of machine learning algorithms on diabetes dataset using big data analytics," in 2017 International Conference on Infocom Technologies and Unmanned Systems (Trends and Future Directions)(ICTUS), 2017, pp. 508-513: IEEE.
[38]S. Adinugroho, Y. A. Sari, M. A. Fauzi, and P. P. Adikara, "Optimizing K-means text document clustering using latent semantic indexing and pillar algorithm," in 2017 5th International Symposium on Computational and Business Intelligence (ISCBI), 2017, pp. 81-85: IEEE.
[39]S. Sharma, A. Kumar, and V. Rana, "Ontology based informational retrieval system on the semantic web: Semantic Web Mining," in 2017 International Conference on Next Generation Computing and Information Systems (ICNGCIS), 2017, pp. 35-37: IEEE.
[40]D. Sobhy, Y. El-Sonbaty, and M. A. Elnasr, "MedCloud: healthcare cloud computing system," in 2012 International Conference for Internet Technology and Secured Transactions, 2012, pp. 161-166: IEEE.
[41]P. Merla and Y. Liang, "Data analysis using hadoop MapReduce environment," in 2017 IEEE International Conference on Big Data (Big Data), 2017, pp. 4783-4785: IEEE.
[42]A. V. Hazarika, G. J. S. R. Ram, and E. Jain, "Performance comparision of Hadoop and spark engine," in 2017 International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud)(I-SMAC), 2017, pp. 671-674: IEEE.
[43]L. Richardson. (2015). Beautiful Soup Documentation. Available: https://www.crummy.com/software/BeautifulSoup/bs4/doc/
[44]GitHub. (2017). 以 jieba 探索文本主題 Available: https://github.com/youngmihuang/lyrics_application/blob/master/lyrics_2.ipynb
[45]T. Rattanasawad, M. Buranarach, K. R. Saikaew, T. J. I. T. o. I. Supnithi, and Systems, "A comparative study of rule-based inference engines for the semantic web," vol. 101, no. 1, pp. 82-89, 2018.