博碩士論文 etd-0613115-111710 詳細資訊


[回到前頁查詢結果 | 重新搜尋]

姓名 梁晉銘(Jin-ming Liang) 電子郵件信箱 E-mail 資料不公開
畢業系所 資訊管理學系研究所(Information Management)
畢業學位 碩士(Master) 畢業時期 103學年第2學期
論文名稱(中) 運用混合式類神經網路推估軟體工作量
論文名稱(英) Using Hybrid Artificial Neural Network to Estimate Software Effort
檔案
  • etd-0613115-111710.pdf
  • 本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
    請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
    論文使用權限

    紙本論文:5 年後公開 (2020-07-30 公開)

    電子論文:使用者自訂權限:校內立即公開、校外 5 年後公開

    論文語文/頁數 中文/40
    統計 本論文已被瀏覽 5377 次,被下載 1 次
    摘要(中) 摘 要
    本研究以一典型前向類神經網路作為軟體工作量推估模型之主體,並混合模糊集與群集理論作為參、係數演算之依據,以求能使模型兼具精確與時效之特質;所提之混合類神經網路模型除能取得較為客觀之初始參係數外,亦能藉由群集間之簡單線性組合方式得出最終輸出結果。為評量新模型之建置效能,本研究分別利用多項(MAE, MMRE, RMSE, pred25)評估標準,並以常用之NASA數據作為實證分析,使發展之新模型與多種工作量推估模型(Halstead、Walston-Felix、Bailey-Basili及Doty)進行成效比較。結果顯示,本研究之新模型較能精準推估軟體工作量。
    摘要(英) Abstract
    In this study, we propose a hybrid artificial neural network for software effort estimation , which developed by fuzzy set, clustering theory and least squared estimation algorithm. The new model can work efficiently and robustly, and also easily aggregated by different algorithms to obtain the finally output. To evaluate the performance of estimation of software effort, we will compare the proposed model with some traditional models (Halstead、Walston-Felix、Bailey-Basili及Doty). Most accuracy measure of fitting (MAE, MMRE, RMSE, pred25) are improved by novel model.
    關鍵字(中)
  • 群集理論
  • 混合類神經網路
  • 模糊集
  • 推估
  • 軟體工作量
  • 關鍵字(英)
  • Software Effort
  • Estimate
  • Clustering Theory
  • Fuzzy Set
  • Hybrid Artificial Neural Network
  • 論文目次 目 錄
    論文審定書 i
    謝誌 ii
    中文摘要 iii
    英文摘要 iv
    第 一 章 前言 1
    第 二 章 文獻回顧 3
    第 三 章 混合式類神經網路實證模型 7
    3.1 模型建置 8
    3.1.1模型拓樸與參、係數之訓練 9
    3.1.2模型之驗證 13
    3.2 實證數據 14
    3.3 評估指標 18
    第 四 章 結果與討論 20
    4.1 結果 20
    4.2 討論 23
    第 五 章 結論與建議 24
    5.1 結論 24
    5.2 建議 24
    參考文獻 26

    圖 次
    圖3.1 典型前向式類神經網路實證模型示意圖(1個m維輸入層-i個j維隱藏層-1個l維輸出層) 8
    圖3.2 軟體工作量推估流程與混合式類神經網路實證模型對應圖(以二維輸入項為例) 8
    圖3.3 模型拓樸與參、係數之檢定及驗證流程 14
    圖3.4 實際建置完成之模型結構 16
    圖3.5 群集分析於檢定與驗證階段θ對應NRMSE值走勢 17
    圖3.6 檢定階段下實際工作量與模型推估工作量對應(n=13) 17
    圖3.7 驗證階段下實際工作量與模型推估工作量對應(n=5) 18
    圖4.1 新模型(HANN)與文獻各模型之根均方誤差值(RMSE)直方圖 20
    圖4.2 新模型(HANN)與文獻各模型所得之平均絕對誤差值(MAE)直方圖 21
    圖4.3 新模型(HANN)與文獻各模型所得之平均相對誤差值(MMRE)直方圖 21
    圖4.4 新模型(HANN)與文獻各模型所得之所有專案數量中相對誤差小於等於0.25之比率(pred(25))直方圖 22
    圖4.5 新模型(HANN)與文獻各模型所得絕對誤差(AE)值鬚盒圖 22

    表 次
    表3.1 模糊最小最大群集法演算說明 11
    表3.2 NASA實證數據(n=18) 14
    表3.3 NASA實證數據內各專案工作量及其相關因子統計參數(n=18) 15
    表3.4新模型(HANN)與其他模型於驗證階段(n=5)工作量推估值對應 18
    表4.1 新模型(HANN)與文獻各模型所得各項評估指標比較表 20
    參考文獻 參考文獻
    一、中文部分
    洪浩青(民 97)。差分演算法實作軟體工作量預估之研究。大同大學資訊工程學所碩士論文,未出版,臺北市。
    孫文祥(民 89)。談軟體專案失敗的六大關鍵。
    許兆榕(民 93)。多因子資料分群對軟體工作量預估值精確性影響之研究。國立臺灣科技大學資訊管理學研究所碩士論文,未出版,臺北市。
    陳建勳(民 92)。以功能點分析為基礎之改良式軟體委外成本估算架構。臺中健康暨管理學院資訊科技與管理學研究所碩士論文,未出版,臺中市。
    張祚佳(民 94)。應用模擬退火法於軟體工作量預估之研究。國立臺灣科技大學資訊管理學研究所碩士論文,未出版,臺北市。
    梁晉銘(民 91)。複合型類神經網路建構集水區水文模式之研究。國立臺灣大學生物環境系統工程學研究所博士論文,未出版,臺北市。
    梁晉銘(民 104)。運用混合式類神經網路推估軟體工作量。2015年「管理思維與實務」暨「應用科學」研討會,臺北。
    張鴻林(民 90)。動態軟體工作量估算模式之研究。國立臺灣科技大學資訊管理學研究所碩士論文,未出版,臺北市。
    黃培倫(民 96)。準確評估軟體成本之研究。國立成功大學資訊工程學研究所碩士論文,未出版,臺南市。
    游喬評(民 92)。堆疊基的軟體開發程序度量方法之研究。佛光大學資訊學研究所碩士論文,未出版,宜蘭縣。
    黃聖祐(民 98)。基因演算法混合支援向量迴歸於軟體工作量評估。大同大學資訊工程學所碩士論文,未出版,臺北市。
    楊連瑛(民 83)。台灣訂製型軟體成本估算模式之研究。國立交通大學資訊管理學研究所碩士論文,未出版,新竹市。
    劉亦真(民 91)。軟體專案資料分類對工作量預估值精確性之影響。國立臺灣科技大學資訊管理學研究所碩士論文,未出版,臺北市。
    鄭宇修(民 90)。模糊類神經網路軟體工作量預估模式。國立臺灣科技大學資訊管理系所碩士論文,未出版,臺北市。
    二、英文部分
    Ahn, B. S., Cho, S. S., & Kim, C. Y. (2000). The integrated methodology of rough set theory and artificial neural network for business failure prediction. Expert Systems with Applications, 18, 65-74.
    Atiya, A.(2001). Bankruptcy prediction for credit risk using neural networks: A survey and new results. IEEE Transactions on Neural Networks, 12(4), 925-935.
    Bailey, J. W., & Basili, V. R. (1981). A meta model for software development resource expenditure. Int. Proceedings of the International Conference on Software Engineering, 107-115.
    Boehm, B. W. (1981). Software Engineering Economics. Englewood Cliff, NJ: Prentice-Hall.
    Boehm, B. W. (1984). Software Engineering Economics. IEEE Transactions on Software Engineering, 10(1), 4-21.
    Bollerslev, T. (1986). A generalized autoregressive conditional heterskedasticity, Journal of Econometrics, 31, 307-327.
    Chang, F. -J., Liang, J. -M., & Chen, Y. -C. (2001). Flood forecasting using radial basis function neural network. IEEE Trans. Sys., Man and Cyber. Part C., 31(4), 530-535.
    Chang, F. -J., Chen, Y. -C., & Liang, J. -M. (2002). Fuzzy clustering neural network as flood forecasting model. Nordic Hydrology, 33(3), 275-290.
    Chrissis, M., Konrad, M., & Shrum, S. (2003). CMMI: Guidelines for process intergration and product improvement. Addison-Wesley Porfessional.
    Cortez, P., & Rocha, M. (2004). Evolving time series forecasting ARMA models. Journal of Heuristics, 10, 415-429.
    Duda, R. O., Hart, P. E., & Stork, D. E. (2000). Pattern Classification. New York:Wiley.
    Engle, R. F. (1982). Autoregressive conditional heteroskedasticity with estimates of the variance of UK inflation. Econometrica , 50, 987-1008.
    Finnie, G. R., Wittig, G. E., & Desharnais, J. -M. (1997). A Comparison of Software Effort Estimation Techniques: Using Function Point with Neural Network, Case-Based Reasoning and Regression Models. J. Software System, 39, 281-289.
    Fu, L. (1994). Neural networks in computer intelligence. New York: McGraw-Hill.
    Gately, E. (1996). Neural networks for financial forecasting. New York: Wiley.
    Green, H., & Pearson, M. (1994). Neural nets for foreign exchange trading. New York: Wiley.
    Guerre, F. A., & Coelho, L. S. (2005). Radial basis neural network learning based on particle swarm optimization to multistep prediction of chaotic Lorenz’s system. Proc. IEEE 5th Int. Conf. on Hybrid Intelligent systems, Rio de Janeiro, RJ, Brazil, 521-524.
    Heiat, A.(2002). Comparison of artificial neural network and regression models for estimating software development effort. Information and Software Technology, 44, 911-922.
    Hsieh, D. A. (1989). Testing for nonlinear dependence in daily foreign exchange rates. Journal of Business, 62(3), 339-368.
    Hua, L. C., Jan, Z. X., Qi, H. W., &Yi, C. G. (2009). A novel multi-objective optimization algorithm based on artificial immune system. IEEE International Conference on Natural Computation, Tianjin, 4, 569-574.
    Huang, S.-J. (2000). An Immune-Based Optimization Method to Capacitor Placement in a Radial Distribution System. IEEE Transactions on Power Delivery, 15(2), 744-749.
    Huang, S.-J., & Chiu, N.-H. (2009). Applying fuzzy neural network to estimate software development effort. Applied Intelligence, 73-83.
    Kaur, J., Singh, S., Kahlon, K. S., & Bassi, P. (2010) Neural Network - A novel technique for software effort estimation. International Journal of Computer Theory and Engineering, 2(1), 17-19.
    Kean, J. (1993). Treasury bond yields: a neural net analysis approach. Technical Analysis of Stocks and Commodities, 11(4), 78-84.
    Kennedy, J., & Eberhart, R. C. (1995). Particle Swarm Optimization? Proc. IEEE Int. Conf. on Neural Networks (Perth, Australia), IEEE Service Center, Piscataway, NJ, 4, 1942-1948.
    Kitchenham, B. A., Pfleeger, S. L., McColl, B., & Eagan, S. (2002). An empirical study of maintenance and development estimation accuracy. Journal of Systems and Software, 64, 57-77.
    Ko, P. -C., & Lin, P. -C. (2006). An evolution-based approach with modularized evaluations to forecast financial distress. Knowledge-Based Systems, 19, 84-91.
    Lacerda, E., Carvalho, A. C. P. L. F., Braga, A. P., & Ludermir, T. B. (2005). Evolutionary radial basis functions for credit assessment. Applied Intelligence, 22, 167-181.
    Li, Y., Hw, D. J., & Wu, T. (2004). Optimal coordinated voltage control of power systems an immune algorithm solution. IEEE Asian Control Conference, 3, 1398-1403.
    Lin, F. Y., & McClean, S. (2001). A data mining approach to the prediction of corporate failure. Knowledge-Based System, 14, 189-195.
    Lu, Y., Wu, X., Dai, R., & Xia, G. (2010). A new immune genetic algorithm. IEEE International Conference on Computer and Automation Engineering Singapore, 1, 714-718.
    Luh, G. -C., & Cheng, W. -C. (2002). Behavior-based intelligence mobile robot using an immunized reinforcement adaptive learning mechanism. Advanced Engineering Informatics, 16(2), 85-98.
    Luh, G. -C., & Chueh, C. -H. (2004). Multi-objective optimal design of truss structure with immune algorithm. Computers and Structures, 82, 829-844.
    Mair. C., Kadoda, G., Lefley, M., Phalp, K., Schofield, C., Shepperd, M., & Webster, S. (2000). An investigation of machine learning based prediction systems. Journal of Systems and Software, 53, 23-29.
    Mcloone, S., Brown, M. D., Irwin, G., & Lightbody, A. (2009). A hybrid linear /nonlinear training algorithm for feedforward neural networks. IEEE Transactions on Neural Networks, 9(4), 669-684.
    Meese. R. A., & Rose, A. (1991). An empirical assessment of non-linearity in models of exchange rate determination. Rev. Econ. Stud., 58, 603-619.
    Mehta, M. (1995). Foreign exchange markets. New York:Wiley.
    Narendra, K., & Parthasarathy, K. (1990). Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1(1), pp.4-27.
    Rapel, D. H., & Sayers, C. L. (1990). Non-linear dynamics and exchange rate frequency. Technology Report, Department of Economics, Univ. of Houston, Texus.
    Rumelhart, D. E., & McClelland, J. L. (1986). Parallel distributed processing: exploration in the microstructure of cognition, 1-2, MIT Press.
    Sexton, R. S., Alidaee, B., & Dorsey, R. E. (1998). Global optimization for artificial neural networks: a tabu search application. European Journal of Operational Research,106(2/3), 570-584.
    Sexton, R. S., & Gupta, J. N. D. (2000). Comparative evaluation of genetic algorithm and backpropagation for training neural networks. Information Sciences, 129, 45-59.
    Simpson, P. K. (1993). Fuzzy min-max neural networks – part 2: Clustering. IEEE Transactions on Fuzzy Systems, 1(1), 32-45.
    Sousa, T., Silva, A., & Neves, A. (2004). Particle swarm based data mining algorithms for classification tasks. Parallel Computing, 30, 767-783.
    Trippi, R. & Turban, E. (1996). Neural networks in finance and investing. Irwin Professional Publishing.
    Versace, M., Bhatt, R., Hinds, O., & Shiffer, M. (2004). Predicting the exchange traded fund DIA with a combination of genetic algorithms and neural networks. Expert Systems with Applications, 27, 417-425.
    Walczak, S. (2001). An empirical analysis of data requirements for financial forecasting with neural networks. Journal of Management Information Systems,17(4), pp.203-222.
    Walczak, S., & Cerpa, N. (1999). Heuristic principles for the design of artificial neural networks. Information and Software Technology, 41(2), 107-117.
    White, H. (1990). Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings. Neural Networks, 3(5), 535-549.
    White, H. (1996). Economics prediction using neural networks: The case of IBM daily stock return. Proc. of IEEE Int. Conf. on Neural Networks, II, 451-459.
    Widrow, B., Rumelhart, D. E., & Lehr, M. A. (1994). Neural networks: Applications in industry, business and science. Communications of the ACM, 37(3), 93-105.
    Zhang, G., Patuwo, E. B., & Hu, M. Y. (1994). Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting, 14, 35-62.
    口試委員
  • 趙善中 - 召集委員
  • 陳嘉玫 - 委員
  • 鄭炳強 - 指導教授
  • 口試日期 2015-07-21 繳交日期 2015-07-30

    [回到前頁查詢結果 | 重新搜尋]


    如有任何問題請與論文審查小組聯繫