請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/17095完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭卜壬 | |
| dc.contributor.author | Chin-Hui Chen | en |
| dc.contributor.author | 陳晉暉 | zh_TW |
| dc.date.accessioned | 2021-06-07T23:56:17Z | - |
| dc.date.copyright | 2013-08-26 | |
| dc.date.issued | 2013 | |
| dc.date.submitted | 2013-08-20 | |
| dc.identifier.citation | [1] M. S. Ahmed and A. R. Cook. Analysis of freeway traffic time-series data by using box-jenkins techniques. Transportation Research Record, (722), 1979.
[2] E. S. Gardner. Exponential smoothing: The state of the art. Journal of forecasting, 4(1):1--28, 1985. [3] D. L. Gerlough and M. J. Huber. Traffic flow theory. Technical report, 1976. [4] S. Ishak and C. Alecsandru. Optimizing traffic prediction performance of neural net- works under various topological, input, and traffic condition settings. Journal of trans- portation engineering, 130(4):452--465, 2004. [5] P.S.Kalekar.Timeseriesforecastingusingholt-wintersexponentialsmoothing.Kan- wal Rekhi School of Information Technology, 4329008:1--13, 2004. [6] T.C.Mills.Timeseriestechniquesforeconomists.CambridgeUniversityPress,1991. [7] B. Pan, U. Demiryurek, and C. Shahabi. Utilizing real-world transportation data for accurate traffic prediction. In Data Mining (ICDM), 2012 IEEE 12th International Conference on, pages 595--604. IEEE, 2012. [8] M.ShokouhiandK.Radinsky.Time-sensitivequeryauto-completion.InProceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, pages 601--610. ACM, 2012. [9] B. M. Williams, P. K. Durvasula, and D. E. Brown. Urban freeway traffic flow pre- diction: application of seasonal autoregressive integrated moving average and expo- nential smoothing models. Transportation Research Record: Journal of the Trans- portation Research Board, 1644(1):132--141, 1998. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/17095 | - |
| dc.description.abstract | Traditionally, researchers apply the latest data to predict the near future of Time Series Data prediction. However, we proposed a novel framework to use not only latest data but also potential accurate predicted results. And it also be able to predict much further results for enhancing the prediction. The framework adopts generic predict methods and extract specific features ac- cording to the data property. Three type of feature sets are designed to capture the Statistic, Reliability and Periodicity of the Time Series Data. Short-Term and Long-Term Prediction Enhancement algorithms are also introduced to im- prove the prediction performance. The experiments show that Short-Term En- hancement increases the accuracy of +20.04% and Long-Term Enhancement +9.59% compared to well-known baseline approaches, ARIMA and HW-ES. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-07T23:56:17Z (GMT). No. of bitstreams: 1 ntu-102-R98922059-1.pdf: 1862583 bytes, checksum: 56f5c3cd4363fb70888250f253a30c1a (MD5) Previous issue date: 2013 | en |
| dc.description.tableofcontents | 致謝 i
Abstract iii 1 Motivation 1 1.1 TimeSeries ................................. 1 1.2 PredictTimeSeries............................. 3 1.3 MultiplePrediction ............................. 3 2 Related Works 11 2.1 MachineLearningBased .......................... 11 2.1.1 NeuralNetwork........................... 11 2.2 RegressionBased.............................. 11 2.2.1 Autoregressive Integrated Moving Average . . . . . . . . . . . . 11 2.2.2 Holt-WintersExponentialSmoothing . . . . . . . . . . . . . . . 12 3 Framework 15 3.1 Overview .................................. 15 3.2 Short-TermEnhancement.......................... 15 3.2.1 FeatureSet ............................. 16 3.2.2 S1:StatisticFeature ........................ 16 3.2.3 S2:ReliabilityFeature ....................... 19 3.2.4 PeriodicityFeature ......................... 19 3.2.5 FeatureSetwithPeriodicity .................... 19 3.2.6 S1:StatisticFeaturewithPeriodicity . . . . . . . . . . . . . . . 21 3.2.7 S2:ReliabilityFeaturewithPeriodicity . . . . . . . . . . . . . . 21 3.3 Long-TermEnhancement.......................... 22 3.3.1 LTE-R (Long-Term Enhancement Regression) . . . . . . . . . . 22 3.3.2 LTE-NR (Long-Term Enhancement NRegression) . . . . . . . . 22 3.3.3 Comparison............................. 23 4 Experiment 25 4.1 ExperimentSetting ............................. 25 4.1.1 Dataset ............................... 25 4.1.2 Model................................ 27 4.2 STE..................................... 27 4.3 FeatureAnalysis .............................. 28 4.4 LTE-R.................................... 28 4.5 LTE-NR................................... 29 5 Conclusion 31 Bibliography 33 | |
| dc.language.iso | zh-TW | |
| dc.subject | 預測模型 | zh_TW |
| dc.subject | 時序資料 | zh_TW |
| dc.subject | 時間序列 | zh_TW |
| dc.subject | Time Series Data | en |
| dc.subject | Time Series Prediction | en |
| dc.subject | Framework | en |
| dc.title | 增進時序資料預測效能之一般化模型 | zh_TW |
| dc.title | A General Framework for Enhancing Prediction Performance on Time Series Data | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 101-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林正偉,邱志義 | |
| dc.subject.keyword | 時序資料,時間序列,預測模型, | zh_TW |
| dc.subject.keyword | Time Series Data,Time Series Prediction,Framework, | en |
| dc.relation.page | 33 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2013-08-20 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-102-1.pdf 未授權公開取用 | 1.82 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。