政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/139315

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/139315

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | 全文筆數/總筆數 : 113451/144438 (79%)
造訪人次 : 51303795 線上人數 : 865

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

搜尋範圍

查詢小技巧：

您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果

若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料

進階搜尋

主頁 ‧ 登入 ‧ 上傳 ‧ 說明 ‧ 關於政大典藏 ‧ 管理

到手機版

政大機構典藏 > 資訊學院 > 資訊科學系碩士在職專班 > 學位論文 > Item 140.119/139315

請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/139315

題名:	軟體工作量預估技術於硬體開發時程的追蹤 Tracking of the Hardware Development Schedule based on Software Workload Estimation
作者:	吳欣純 Wu, Sin-Chun
貢獻者:	張宏慶 Jang, Hung-Chin 吳欣純 Wu, Sin-Chun
關鍵詞:	軟體工作量預估硬體研發時程追蹤專案時間管理機器學習深度學習 Software Effort Estimation Hardware Development Effort Tracking Project Schedule Management Machine Learning Deep Learning
日期:	2022
上傳時間:	2022-03-01 18:21:51 (UTC+8)
摘要:	精準預估開發工作時間一直是專案管理的重點，準確預估能有效掌握資源與控管成本，軟體工作量預估 Software Effort Estimation）早在1960年 L.Farr [5] 和E.A.Nelson [16] 的研究中提出，早期的研究重點著重於建立標準化的估算模型，透過統計迴歸分析或是專家經驗法則預估完成任務的工作時數，後來隨著機器學習與深度學習的發展，透過機器學習與深度學習訓練模型預估工作時間取代原本預估方式。本研究主要提出軟體工作量預估的概念也可延伸應用在電腦製造產業，使用機器學習與深度學習訓練模型預估硬體研發過程中工作任務需要的時間，進而精準掌握產品研發進度與量產上市時程。本文實驗運用語意分析透過自然語言處理（Natural Language Processing, NLP）抽取問題關鍵字當特徵分析，使用機器學習 Machine Learning, ML）的決策樹 Decision Tree）、隨機森林 Random Forest）、XGBoost eXtreme Gradient Boosting）與深度學習 Deep Learning, DL）的RNN模型分析比較精準度、MMRE與PRED(25)，實驗發現決策樹 Decision Tree）比其他三個模型顯示較高的準確度。在此研究證明軟體工作量預估技術也可以用在硬體開發過程中的工作追蹤上。 The accuracy of the development effort estimation on the project management is important. If we predict working effort precisely, we could effectively allocated the company`s resource and development`s cost. Software Effort Estimation (SEE) has been proposed from L.Farr [5] and E.A.Nelson [16] researches since 1960s. Those researches in 1960s are focus on building standard estimation model. Through statistical regression analysis and expert`s experience to predict how long to take to finish development tasks. With the rapid development of Machine Learning and Deep Learning, in recent year researches replace statistical regression analysis and expert`s experience estimation technology by training Machine Learning and Deep Learning model. In this article, prove Software Effort Estimation technology can not only use on predict software development task but also on use computer`s hardware manufacturing development. By using training Machine Learning and Deep Learning`s model to predict working effort on hardware research and development tasks to control the product development schedule and launch time precisely. This article experiment uses the Machine Learning`s model Decision Tree, Random Forest, XGBoost (eXtreme Gradient Boosting) and Deep Learning RNN model predict working effort and compare the accuracy. And found that Decision Tree model gets the better accuracy and lower error rate than other three models. This article experiment prove Software Effort Estimation can use on hardware development effort tracking.
參考文獻:	[1] L. Breiman, “Random forests”, Machine learning, vol 45, no 1, bll 5–32, 2001. [2] N. V. Chawla, K. W. Bowyer, L. O. Hall, en W. P. Kegelmeyer, “SMOTE: synthetic minority over-sampling technique”, Journal of artificial intelligence research, vol 16, bll 321–357, 2002. [3] T. Chen en C. Guestrin, “XGBoost: A Scalable Tree Boosting System”, arXiv [cs.LG], 08-Mrt-2016. [4] K. Cho et al., “Learning phrase representations using RNN encoder-decoder for statistical machine translation”, arXiv preprint arXiv:1406. 1078, 2014. [5] L. Farr, H. J. Zagorski, en M. Santa, Factors that Affect the Cost of Computer Programming. Volume Ii. a Quantitative Analysis. 1964. [6] J. H. Friedman, “Greedy function approximation: A gradient boosting machine”, Ann. Stat., vol 29, no 5, bll 1189–1232, Okt 2001. [7] Y. Goldberg, “A primer on neural network models for natural language processing”, J. Artif. Intell. Res., vol 57, bll 345–420, Nov 2016. [8] I. Goodfellow, Y. Bengio, en A. Courville, Deep Learning. London, England: MIT Press, 2016. [9] T. K. Ho, “Random decision forests”, in Proceedings of 3rd international conference on document analysis and recognition, 1995, vol 1, bll 278–282. [10] F. K. Jomana Khaseep en R. Assaf, Non-Algorithmic Software Effort Estimation-Challenges and Solutions. . [11] H. Lee, Speech.ee.ntu.edu.tw. [Online]. Available: https://speech.ee.ntu.edu.tw/~tlkagk/document/Basic.pdf. [12] Y. Mahmood, N. Kama, A. Azmi, en M. Ali, “Improving estimation accuracy prediction of software development effort: A proposed ensemble model”, in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Istanbul, Turkey, 2020. [13] C. McCormick, “Word2vec tutorial-the skip-gram model”, Apr-2016. [Online]. Available: http://mccormickml. com/2016/04/19/word2vec-tutorial-the-skip-gram-model, 2016. [14] T. Mikolov, I. Sutskever, K. Chen, G. Corrado, en J. Dean, “Distributed Representations of Words and Phrases and their Compositionality”, arXiv [cs.CL], 16-Okt-2013. [15] T. Mikolov, K. Chen, G. Corrado, en J. Dean, “Efficient estimation of word representations in vector space”, arXiv [cs.CL], 16-Jan-2013. [16] E. A. Nelson en M. Santa, Management handbook for the estimation of computer programming costs. 1967. [17] M. Pandey, R. Litoriya, en P. Pandey, “Validation of existing software effort estimation techniques in context with mobile software applications”, Wirel. Pers. Commun., vol 110, no 4, bll 1659–1677, Feb 2020. [18] J. R. Quinlan, “Induction of decision trees”, Mach. Learn., vol 1, no 1, bll 81–106, Mrt 1986. [19] P. Rai, S. Kumar, en D. K. Verma, “Prediction of Software Effort in the Early Stage of Software Development: A Hybrid Model Prévision de l’effort logiciel dans la première phase de développement d’un logiciel : Un modèle hybride”, IEEE Can. J. Electr. Comput. Eng., vol 44, no 3, bll 376–383, 2021. [20] J. Ramos, “Using tf-idf to determine word relevance in document queries”, Proceedings of the first instructional conference on machine learning, vol 242, bll 29–48, 2003. [21] S. Raschka, “Model evaluation, model selection, and algorithm selection in machine learning”, arXiv [cs.LG], 13-Nov-2018. [22] S. Tariq, M. Usman, en A. C. M. Fong, “Selecting best predictors from large software repositories for highly accurate software effort estimation”, J. Softw. (Malden), vol 32, no 10, Okt 2020. [23] "CS 230 - Recurrent Neural Networks Cheatsheet", Stanford.edu. [Online]. Available: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks. [24] "GitHub - fxsjy/jieba: 结巴中文分词", GitHub, 2021. [Online]. Available: https://github.com/fxsjy/jieba. [25] "jieba分詞詳解_鴻煊的學習筆記 - MdEditor", Gushiciku.cn, 2021. [Online]. Available: https://www.gushiciku.cn/pl/gCaO/zh-tw. [26] "Random Forest - Roshan Talimi", Roshan Talimi. [Online]. Available: http://talimi.se/ml/random-forest/. [27] "tf-idf - 维基百科，自由的百科全書", Zh.wikipedia.org. [Online]. Available: https://zh.wikipedia.org/wiki/Tf-idf.
描述:	碩士國立政治大學資訊科學系碩士在職專班 108971006
資料來源:	http://thesis.lib.nccu.edu.tw/record/#G0108971006
資料類型:	thesis
DOI:	10.6814/NCCU202200264
顯示於類別:	[資訊科學系碩士在職專班] 學位論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
100601.pdf		2745Kb	Adobe PDF2	0	檢視/開啟

在政大典藏中所有的資料項目都受到原著作權保護.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - 回饋