請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93174完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳靜枝 | zh_TW |
| dc.contributor.advisor | Ching-Chin Chern | en |
| dc.contributor.author | 曹竣瑋 | zh_TW |
| dc.contributor.author | Chun-Wei Tsao | en |
| dc.date.accessioned | 2024-07-23T16:07:43Z | - |
| dc.date.available | 2024-07-24 | - |
| dc.date.copyright | 2024-07-23 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-18 | - |
| dc.identifier.citation | [1] Adenso‐Díaz, B., González‐Torre, P., and García, V., “A capacity management model in service industries,” International Journal of Service Industry Management, vol. 13, no. 3, pp. 286-302, 2002.
[2] Alqahtani, A., Ali, M., Xie, X., and Jones, M. W., “Deep Time-Series Clustering: A Review,” Electronics, vol. 10, no. 23, p. 3001, 2021. [3] Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., and Farhan, L., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” Journal of Big Data, vol. 8, no. 1, 2021. [4] Armistead, C. G. and Mapes, J., “Supply Networks and the Changing Role of Operations Managers,” in Achieving Competitive Edge: Getting Ahead Through Technology and People, D. Bennett, C. Lewis, Eds. Springer, London, pp. 48-53, 1991." [5] Baldi, P., “Autoencoders, unsupervised learning, and deep architectures.,” in Proceedings of the ICML Workshop on Unsupervised and Transfer Learning, PMLR 27, pp. 37-49, 2012." [6] Borovykh, A., Bohte, S., and Oosterlee, C. W., “Conditional time series forecasting with convolutional neural networks.,” arXiv:1703.04691, 2017. [7] Dasan, E. and Panneerselvam, I., “A novel dimensionality reduction approach for ECG signal via convolutional denoising autoencoder with LSTM,” (in English), Biomedical Signal Processing and Control, vol. 63, p. 102225, Jan 2021. [8] Davies, D. L. and Bouldin, D. W., “A Cluster Separation Measure,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-1, no. 2, pp. 224-227, 1979. [9] Elhanashi, A., Dini, P., Saponara, S., and Zheng, Q., “Integration of Deep Learning into the IoT: A Survey of Techniques and Challenges for Real-World Applications,” Electronics, vol. 12, no. 24, p. 4925, 2023. [10] Elmaghraby, S. E., “Manufacturing capacity and its measurement: A critical evaluation,” Computers & Operations Research, vol. 18, no. 7, pp. 615-627, 1991/01/01/ 1991. [11] Ghimire, S., Deo, R. C., Wang, H., Al-Musaylh, M. S., Casillas-Pérez, D., and Salcedo-Sanz, S., “Stacked LSTM Sequence-to-Sequence Autoencoder with Feature Selection for Daily Solar Radiation Prediction: A Review and New Modeling Results,” Energies, vol. 15, no. 3, p. 1061, 2022. [12] Zhang, G., Hu, M. Y., “Forecasting with artificial neural networks:: The state of the art,” International Journal of Forecasting,, vol. 14, no. 1, pp. 35-62, 1998. [13] Kriegel, H., Kröger, P., Sander, J., Zimek, A., “Density‐based clustering,” WIREs Data Mining and Knowledge Discovery, vol. 1, pp. 231-240, 2011. [14] Hochreiter, S. and Schmidhuber, J., “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. [15] Jia, W., Sun, M., Lian, J., and Hou, S., “Feature dimensionality reduction: a review,” Complex & Intelligent Systems, vol. 8, no. 3, pp. 2663-2693, 2022/06/01 2022. [16] Karingula, S. R., Ramanan, N., Tahmasbi, R., Amjadi, M., Jung, D., Si, R., Thimmisetty, C., Polania, L. F., Sayer, M., Taylor, J., and Coelho, C. N., “Boosted Embeddings for Time-Series Forecasting,” in Machine Learning, Optimization, and Data Science, Cham, G. Nicosia et al., Eds., 2022// 2022: Springer International Publishing, pp. 1-14. [17] Kim, S.-C., Horowitz, I., Young, K. K., and Buckley, T. A., “Analysis of capacity management of the intensive care unit in a hospital,” European Journal of Operational Research, vol. 115, no. 1, pp. 36-46, 1999/05/16/ 1999. [18] Lai, G., Chang, W.-C., Yang, Y., and Liu, H., “Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks,” presented at the The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, MI, USA, 2018. [Online]. Available: https://doi.org/10.1145/3209978.3210006. [19] Liu, X. and Wang, W., “Deep Time Series Forecasting Models: A Comprehensive Survey,” Mathematics, vol. 12, no. 10, p. 1504, 2024. [20] Pullman, M., “Capacity management for hospitality and tourism: A review of current approaches,,” International Journal of Hospitality Management,, vol. 29, no. 1, pp. 177-187, 2010. [21] Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G., “LSTM-based encoder-decoder for multi-sensor anomaly detection,” arXiv:1607.00148., 2016. [22] Mary, S. A. L. S., An, A. N., Rani, M. U., “Cluster validity measures dynamic clustering algorithms.,” ARPN Journal of Engineering and Applied Sciences,, vol. 10.9: 4009-4012., 2015. [23] MCINNES, L., et al., “hdbscan: Hierarchical density based clustering,” J. Open Source Softw., 2017. [24] Moshkovitz, M., Yang, Y.-Y., and Chaudhuri, K., “Connecting Interpretability and Robustness in Decision Trees through Separation,” presented at the Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2021. [Online]. Available: https://proceedings.mlr.press/v139/moshkovitz21a.html. [25] Mrabet, M. A. E., Makkaoui, K. E., and Faize, A., “Supervised Machine Learning: A Survey,” in 2021 4th International Conference on Advanced Communication Technologies and Networking (CommNet), 3-5 Dec. 2021 2021, pp. 1-10, doi: 10.1109/CommNet52204.2021.9641998. [Online].Available:https://ieeexplore.ieee.org/stampPDF/getPDF.jsp?tp=&arnumber=9641998&ref= [26] Ng, I. C. L., Wirtz, J., and Sheang Lee, K., “The strategic role of unused service capacity,” International Journal of Service Industry Management, vol. 10, no. 2, pp. 211-244, 1999. [27] Qiu, J., Tian, J., Chen, H., and Lu, X., “Prediction Method of Parking Space Based on Genetic Algorithm and RNN,” Springer International Publishing, 2018, pp. 865-876. [28] RAHMAN, M. F., et al., “Hdbscan: Density based clustering over location based services.,” arXiv: 1602.03730, 2016. [29] S Agatonovic-Kustrin, R. B., “Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research,” Journal of Pharmaceutical and Biomedical Analysis, vol. 22, no. 5, pp. 717-727, 2000. [30] Seyedan, M., Mafakheri, F., and Wang, C., “Order-up-to-level inventory optimization model using time-series demand forecasting with ensemble deep learning,” Supply Chain Analytics, vol. 3, p. 100024, 2023/09/01/ 2023. [31] Shemwell, D. J. and Cronin, J. J., “Services Marketing Strategies for Coping with Demand/Supply Imbalances,” Journal of Services Marketing, vol. 8, no. 4, pp. 14-24, 1994-12-01 1994. [32] Shutaywi, M. and Kachouie, N. N., “Silhouette Analysis for Performance Evaluation in Machine Learning with Applications to Clustering,” Entropy, vol. 23, no. 6, doi: 10.3390/e23060759. [33] Stewart , G. and Al-Khassaweneh, M., “An Implementation of the HDBSCAN* Clustering Algorithm,” Applied Sciences, vol. 12, no. 5, doi: 10.3390/app12052405. [34] Su, S., “Method of Location and Capacity Determination of Intelligent Charging Pile Based on Recurrent Neural Network,” World Electric Vehicle Journal, vol. 13, no. 10, p. 186, 2022. [35] Surakhi, O., Zaidan, M. A., Fung, P. L., Hossein Motlagh, N., Serhan, S., AlKhanafseh, M., Ghoniem, R. M., and Hussein, T., “Time-Lag Selection for Time-Series Forecasting Using Neural Network and Heuristic Algorithm,” Electronics, vol. 10, no. 20, p. 2518, 2021. [36] Vakili, M. G., Rezaei, M., “Performance analysis and comparison of machine and deep learning algorithms for IoT data classification.,” arXiv preprint, vol. arXiv:2001.09636, 2020. [37] Van Houdt, G., Mosquera, C., and Nápoles, G., “A review on the long short-term memory model,” Artificial Intelligence Review, vol. 53, no. 8, pp. 5929-5955, 2020. [38] Velmurugan, T. S., “A survey of partition based clustering algorithms in data mining: An experimental approach.,” Information Technology Journal, pp. 478-484, 2011. [39] Vujović, Ž., et al., “Classification model evaluation metrics.,” International Journal of Advanced Computer Science and Applications, vol. 12.6: 599-606., 2021. [40] W.Earl Sasser, S. P. A., “Selling Jobs in the Service Sector,” Business Horizons, vol. 19, no. 3, pp. 61-65, 1976. [41] Xie, J. G., Ross; Farhadi, A., “Unsupervised deep embedding for clustering analysis,” International conference on machine learning, pp. p. 478-487, 2016. [42] Xu, D. and Tian, Y., “A Comprehensive Survey of Clustering Algorithms,” Annals of Data Science, vol. 2, no. 2, pp. 165-193, 2015/06/01 2015. [43] Jung, Y., Kim, B., Han, S., “Long short-term memory recurrent neural network for modeling temporal patterns in long-term power forecasting for solar PV facilities: Case study of South Korea,Journal of Cleaner Production,,” Journal of Cleaner Production, vol. 250, p. 119476, 2020. [44] Yu, Y., Chen, X., and Zhang, F., “Dynamic Capacity Management with General Upgrading,” Operations Research, vol. 63, no. 6, pp. 1372-1389, 2015. [45] Yu, Y., Si, X., Hu, C., and Zhang, J., “A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures,” Neural Computation, vol. 31, no. 7, pp. 1235-1270, 2019. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93174 | - |
| dc.description.abstract | 近年來，因為物聯網 (IoT, Internet of Things) 機器的出現，配備機器的服務業在收集資料的方式可以轉為自動化。除了可以精確的得到機器運轉的情況，也能過濾掉機器使用狀況異常的訊號。從物聯網感測器所收集到的資料具備大數據的性質，包含資料量(Volume)，以及速度(Velocity)，和多樣性(Variety)。這樣的資料性質可以針對特定機器的運轉情況作出客製化的處理，詳細記錄時間的資訊也能更有效地執行時間序列分析。
本研究使用洗衣租賃業所提供的物聯網機器資料，針對700多台洗衣機總共兩年的資料進行時間序列分析及預測，並期望幫助服務業避免使用經驗做出新增機器的決策，轉向使用資料輔助預測的方式達到資源分配的目的。我們首先利用物聯網機器狀態轉變的訊號進行處理，依照不同的時間段切分運轉情況。再針對所有的機器使用狀況建立深度學習模型，搭自編碼器(Autoencoder)技術處理複雜大量的物聯網資料，進行準確的時間序列預測，可以得出特定機器未來的運轉狀況。除此之外，我們提出兩階段的深度學習架構，使用分群演算法搭配分類演算法，可以使用所收集到的物聯網機器資料建立模型，幫助沒有歷史資料的機器，針對機器的性質，所要放置的地點進行預測，計算出未來可能的運轉情況。 根據本研究所提出的深度學習預測架構，企業可以針對物聯網機器所預測出的運轉情況和當前的資源分配做出比較，了解機器分配的情況並做出調整。不管特定機器是否有歷史資料，都能夠運用我們提出的架構，得到準確的運轉情況預測。 | zh_TW |
| dc.description.abstract | In recent years, the advent of Internet of Things (IoT) devices has revolutionized data collection in the service industry, enabling automation and precise monitoring of machine operations. IoT sensors generate large-scale data characterized by volume, velocity, and variety, which can be tailored to analyze specific machine performance and facilitate effective time series analysis.
This study leverages IoT data from a laundromat industry, analyzing over two years of data from more than 700 washing machines. The goal is to transition from experience-based decision-making to data-driven predictions for resource allocation. We process signals from IoT devices to segment machine operations over different temporal dependencies. Using deep learning models and autoencoder technique, we accurately forecast time series data to predict future machine performance. Additionally, we propose a two-phase deep learning framework that combines clustering and classification algorithms. This approach allows us to build predictive models for machines without historical data, estimating future performance based on related features such as machine characteristics and deployment locations. Our predictive framework enables businesses to compare forecasted machine operations with current resource allocation, optimizing machine distribution and adjustments. Whether or not a machine has historical data, our approach provides accurate performance predictions. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-23T16:07:43Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-23T16:07:43Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 謝辭 i
論文摘要 ii THESIS ABSTRACT iii Table of Contents iv List of Tables vii List of Figures viii Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Research Objectives 2 1.3 Research Scope and Limitation 3 Chapter 2 Literature Review 5 2.1 Capacity Planning 5 2.2 Combination of IoT message and Deep Learning 6 2.3 Deep Learning for Time Series Analysis 6 2.4 Clustering Algorithms 8 Chapter 3 Problem Description 10 3.1 Raw Data Preprocessing 10 3.2 Feature Extraction 11 3.3 Time Series Model Selection and Evaluation 14 3.3.1 Time Series Data Model Selection 15 3.3.2 Time Series Data Model Evaluation 16 3.4 Clustering Data Model Selection and Evaluation 17 3.4.1 Clustering Data Model Selection 17 3.4.2 Clustering Data Model Evaluation 19 Chapter 4 Model Building 20 4.1 Feature Engineering 20 4.1.1 Feature Selection 20 4.1.2 Machine Identifier 21 4.2 Time Series Dataset preparation 22 4.3 Deep Clustering Dataset preparation 24 4.3.1 First Phase Unsupervised Clustering 24 4.3.2 Second Phase Supervised Deep Learning Classification 26 4.4 Time Series Model building and Evaluation 27 4.4.1 Time Series Forecasting Model building 27 4.4.2 Time Series Forecasting Model Evaluation 30 4.5 Deep Clustering Model Building and Evaluation 31 4.5.1 Deep Clustering Model Building 31 4.5.2 Deep Clustering Model Evaluation 34 Chapter 5 Experiment Result 38 5.1 Feature Selection 38 5.2 Time Series Model Performance Evaluation 40 5.2.1 Dataset Characteristic 40 5.2.2 Time Series Model Performance Evaluation 45 5.3 Deep Clustering Model Performance Evaluation 49 5.3.1 First Phase: Unsupervised Learning Model Performance 49 5.3.2 Second Phase Supervised Learning Model Performance 53 Chapter 6 Conclusion 55 6.1 Conclusion 55 6.2 Managerial Implication 56 6.3 Future work 57 Reference 58 Appendix 63 | - |
| dc.language.iso | en | - |
| dc.title | 適用於物聯網機器服務業的深度學習輔助容量管理 | zh_TW |
| dc.title | Deep Learning Assisted Capacity Management for IoT-Enabled Services Industries | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 蕭鉢;黃奎隆 | zh_TW |
| dc.contributor.oralexamcommittee | Bo Hsiao;Kwei-Long Huang | en |
| dc.subject.keyword | 物聯網機器,大數據,時間序列分析,深度學習, | zh_TW |
| dc.subject.keyword | IoT machine data,Big Data,Autoencoder,Deep Learning, | en |
| dc.relation.page | 64 | - |
| dc.identifier.doi | 10.6342/NTU202401885 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-07-18 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf | 2.16 MB | Adobe PDF | 檢視/開啟 |
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。