請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99222完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 江昭皚 | zh_TW |
| dc.contributor.advisor | Joe-Air Jiang | en |
| dc.contributor.author | 陳奕醍 | zh_TW |
| dc.contributor.author | Yi-Ti Chen | en |
| dc.date.accessioned | 2025-08-21T16:52:15Z | - |
| dc.date.available | 2025-09-03 | - |
| dc.date.copyright | 2025-08-21 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-05 | - |
| dc.identifier.citation | Abou-Shaara, H. F. (2014). The foraging behaviour of honey bees, Apis mellifera: a review. Veterinarni medicina, 59(1).
Abrol, D. P. (2012). Pollination biology: biodiversity conservation and agricultural production (Vol. 792). Springer. Aharon, N., Orfaig, R., & Bobrovsky, B.-Z. (2022). Bot-sort: Robust associations multi-pedestrian tracking. arXiv preprint arXiv:2206.14651. Alex, A. J., Barnes, C. M., Machado, P., Ihianle, I., Markó, G., Bencsik, M., & Bird, J. J. (2025). Enhancing pollinator conservation: Monitoring of bees through object recognition. Computers and Electronics in Agriculture, 228, 109665. Aurell, D., Bruckner, S., Wilson, M., Steinhauer, N., & Williams, G. R. (2024). A national survey of managed honey bee colony losses in the USA: results from the Bee Informed Partnership for 2020–21 and 2021–22. Journal of Apicultural Research, 63(1), 1-14. Bjerge, K., Mann, H. M., & Høye, T. T. (2022). Real‐time insect tracking and monitoring with computer vision and deep learning. Remote Sensing in Ecology and Conservation, 8(3), 315-327. Bozek, K., Hebert, L., Portugal, Y., Mikheyev, A. S., & Stephens, G. J. (2021). Markerless tracking of an entire honey bee colony. Nature communications, 12(1), 1733. Camazine, S. (1991). Self-organizing pattern formation on the combs of honey bee colonies. Behavioral Ecology and Sociobiology, 28, 61-76. Campello, R. J., Moulavi, D., & Sander, J. (2013). Density-based clustering based on hierarchical density estimates. Pacific-Asia conference on knowledge discovery and data mining (pp. 160-172). Berlin, Heidelberg: Springer Berlin Heidelberg. Cao, J., Pang, J., Weng, X., Khirodkar, R., & Kitani, K. (2023). Observation-centric sort: Rethinking sort for robust multi-object tracking. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 9686-9696). Dennis vanEngelsdorp, M. D. M. (2010). A historical review of managed honey bee populations in Europe and the United States and the factors that may affect them. Journal of invertebrate pathology, 103, S80-S95. Du, Y., Zhao, Z., Song, Y., Zhao, Y., Su, F., Gong, T., & Meng, H. (2023). Strongsort: Make deepsort great again. IEEE Transactions on Multimedia, 25, 8725-8737. Gernat, T., Jagla, T., Jones, B. M., Middendorf, M., & Robinson, G. E. (2023). Automated monitoring of honey bees with barcodes and artificial intelligence reveals two distinct social networks from a single affiliative behavior. Sci Rep, 13(1), 1541. https://doi.org/10.1038/s41598-022-26825-4 Guo, X., Liu, X., Zhu, E., & Yin, J. (2017). Deep clustering with convolutional Autoencoders. In International conference on neural information processing (pp. 373-382). Cham: Springer International Publishing. Hepburn, H., Pirk, C., & Duangphakdee, O. (2014). Honeybee nests. Honeybee Nests. doi, 10, 978-973. Hillayová, M. K., Korený, Ľ., & Škvarenina, J. (2022). The local environmental factors impact the infestation of bee colonies by mite Varroa destructor. Ecological Indicators, 141, 109104. Huang, Z.-Y., Robinson1, G., & Borst, D. (1994). Physiological correlates of division of labor among similarly aged honey bees. Journal of Comparative Physiology A, 174, 731-739. Huang, Z.-Y.& Robinson, G. E. (1996). Regulation of honey bee division of labor by colony age demography. Behavioral Ecology and Sociobiology, 39, 147-158. Inspectors, A. U. a. A. A. (2024). 2023-2024 U.S. beekeeping colony loss survey results. https://apiaryinspectors.org/US-beekeeping-survey-23-24 Iqbal, K., Alabdullah, B., Al Mudawi, N., Algarni, A., Jalal, A., & Park, J. (2024). Empirical Analysis of Honeybees Acoustics as Biosensors Signals for Swarm Prediction in Beehives. IEEE Access. Kimura, T., Ohashi, M., Okada, R., & Ikeno, H. (2011). A new approach for the simultaneous tracking of multiple honeybees for analysis of hive behavior. Apidologie, 42, 607-617. Klein, A. M., Vaissiere, B. E., Cane, J. H., Steffan-Dewenter, I., Cunningham, S. A., Kremen, C., & Tscharntke, T. (2007). Importance of pollinators in changing landscapes for world crops. Proc Biol Sci, 274(1608), 303-313. https://doi.org/10.1098/rspb.2006.3721 Kongsilp, P., Taetragool, U., & Duangphakdee, O. (2024). Individual honey bee tracking in a beehive environment using deep learning and Kalman filter. Scientific reports, 14(1), 1061. Kremen, C., Williams, N. M., & Thorp, R. W. (2002). Crop pollination from native bees at risk from agricultural intensification. Proceedings of the National Academy of Sciences, 99(26), 16812-16816. Maggiolino, G., Ahmad, A., Cao, J., & Kitani, K. (2023). Deep oc-sort: Multi-pedestrian tracking by adaptive re-identification. 2023 IEEE International conference on image processing (ICIP) (pp. 3025-3029). IEEE. Miaoli District Agricultural Research and Extension Station. Ministry of Agriculture, T. (2017). 設施栽培作物蜂授粉技術與效益. https://www.moa.gov.tw/ws.php?id=2506847 Ngo, T. N., Rustia, D. J. A., Yang, E.-C., & Lin, T.-T. (2021). Automated monitoring and analyses of honey bee pollen foraging behavior using a deep learning-based imaging system. Computers and Electronics in Agriculture, 187. https://doi.org/10.1016/j.compag.2021.106239 Ngo, T. N., Wu, K.-C., Yang, E.-C., & Lin, T.-T. (2019). A real-time imaging system for multiple honey bee tracking and activity monitoring. Computers and Electronics in Agriculture, 163, 104841. Nguyen, D.-T., Le, T.-N., Phung, T.-H., Nguyen, D.-M., Nguyen, H.-Q., Pham, H.-T., Phan, T.-T.-H., Vu, H., & Le, T.-L. (2024). Improving pollen-bearing honey bee detection from videos captured at hive entrance by combining deep learning and handling imbalance techniques. Ecological Informatics, 82, 102744. Nunes-Silva, P., Costa, L., Campbell, A. J., Arruda, H., Contrera, F. A. L., Teixeira, J. S. G., Gomes, R. L. C., Pessin, G., Pereira, D. S., & de Souza, P. (2020). Radiofrequency identification (RFID) reveals long-distance flight and homing abilities of the stingless bee Melipona fasciculata. Apidologie, 51, 240-253. Nunes-Silva, P., Hrncir, M., Guimarães, J., Arruda, H., Costa, L., Pessin, G., Siqueira, J., De Souza, P., & Imperatriz-Fonseca, V. (2019). Applications of RFID technology on the study of bees. Insectes sociaux, 66, 15-24. Page Jr, R. E.& Peng, C. Y.-S. (2001). Aging and development in social insects with emphasis on the honey bee, Apis mellifera L. Experimental gerontology, 36(4-6), 695-711. Ratnayake, M. N., Dyer, A. G., & Dorin, A. (2021). Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring. PloS one, 16(2), e0239504. Rozenbaum, E., Shrot, T., Daltrophe, H., Kunya, Y., & Shafir, S. (2024). Machine learning-based bee recognition and tracking for advancing insect behavior research. Artificial Intelligence Review, 57(9), 245. Ru, Z.& Duan, F. (2024). Hierarchical Spatial–Temporal Window Transformer for Pose-Based Rodent Behavior Recognition. IEEE Transactions on Instrumentation and Measurement, 73, 1-14. Service, U. S. F. a. W. (2024). Pollinators benefit agriculture. https://www.fws.gov/initiative/pollinators/pollinators-benefit-agriculture Song, C., Liu, F., Huang, Y., Wang, L., & Tan, T. (2013, November). Auto-encoder based data clustering. Auto-encoder based data clustering. Iberoamerican congress on pattern recognition (pp. 117-124). Berlin, Heidelberg: Springer Berlin Heidelberg. Sutskever, I. (2014). Sequence to Sequence Learning with Neural Networks. arXiv preprint arXiv:1409.3215. VanEngelsdorp, D., Underwood, R., Caron, D., & Hayes, J., Jr. (2007). An estimate of managed colony losses in the winter of 2006-2007: A Report Commissioned by the Apiary Inspectors of America. Varghese, R.& Sambath, M. (2024). Yolov8: A novel object detection algorithm with enhanced performance and robustness. 2024 International conference on advances in data engineering and intelligent computing systems (ADICS) (pp. 1-6). IEEE. Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems. Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008, July). Extracting and composing robust features with denoising Autoencoders. Proceedings of the 25th international conference on Machine learning. Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., & Sun, L. (2022). Transformers in time series: A survey. arXiv preprint arXiv:2202.07125. Zhang, X., Chen, J., Zhang, L., & Zhai, Y. (2024). Application of a Kernel Method Autoencoder-Based Clustering Approach Combining DBSCAN and K-means for Rail Transit Station Classification. 2024 6th International Conference on Frontier Technologies of Information and Computer (ICFTIC). Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022). Bytetrack: Multi-object tracking by associating every detection box. European conference on computer vision. In European conference on computer vision (pp. 1-21). Cham: Springer Nature Switzerland. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99222 | - |
| dc.description.abstract | 蜜蜂(Apis mellifera)在農作物中扮演重要的授粉者角色，對農產業具有重要影響力。然而近年來，蜜蜂數量大幅減少，對農業產量造成嚴重威脅。因此，了解影響蜜蜂的習性、行為和生長因素等，對於幫助蜜蜂族群永續生存至關重要。先前研究多著重於監測巢外蜜蜂行為，或僅針對巢內少數個體進行觀測與分析，對整體巢內活動的系統性探討仍相對不足。本研究旨在結合影像辨識技術與多目標追蹤演算法，並應用無監督與監督式機器學習進行比較分析，探索蜜蜂巢內行為之模式及巢內分工與區域之對應關係。檢測與追蹤方面，研究比較YOLOv8五種變體表現，並選擇表現最優的YOLOv8x（mAP50 = 98.84%，Precision = 97.29%）與ByteTrack MOT結合，確保蜜蜂個體追蹤穩定性（MOTA = 89.34%，IDF1 = 93.41%）。接續進行兩種特徵學習策略：一是無監督式方法，採用Transformer-based Autoencoder對連續時序下的軌跡進行特徵擷取與編碼，並以HDBSCAN聚類演算法進行行為分群與趨勢分析，PCC與ICR達90%，錯誤率降低80%；二是監督式方法，以觀察紀錄為基礎進行蜜蜂爬行軌跡特徵分析與真實行為對應，並使用Transformer架構同樣對連續時序下的軌跡進行訓練與分析，各項指標均超過85%。為了驗證分析結果的準確性與實用性，最後以人工紀錄之巢房功能分區作為驗證與比較依據，評估兩種模型的分析結果。結果顯示，無監督模型適合探索大規模運動動態，監督模型則有助於解析行為與巢區的關聯。總體而言，本研究證明了蜂箱內行為分析的可行性，為非侵入式、即時監測系統奠定基礎，有助智慧養蜂與生態永續。無監督模型捕捉集體運動趨勢的能力，顯示其在蜂群崩解症（CCD）早期預警上具有潛力，而監督模型若進一步研究與開發，將可實現更高效且友善的蜂群管理系統，兩種模型各有優缺，為蜜蜂生態研究提供支持。 | zh_TW |
| dc.description.abstract | Honey bees (Apis mellifera) are vital pollinators in agriculture, yet recent population declines threaten crop yields. Understanding in-hive behavior and factors affecting colony sustainability is therefore critical. Previous studies have largely focused on foraging or limited in-hive observations, leaving overall colony dynamics underexplored. This study integrates computer vision with multi-object tracking (MOT) and compares unsupervised and supervised machine learning approaches to analyze in-hive behavior and the correspondence between behavioral roles and hive regions. YOLOv8x (mAP50 = 98.84%, Precision = 97.29%) combined with ByteTrack (MOTA = 89.34%, IDF1 = 93.41%) enabled reliable individual tracking. The unsupervised framework used a Transformer-based autoencoder with HDBSCAN clustering to extract and group trajectory features, achieving 90% on PCC and ICR with an 80% error reduction. The supervised framework trained a Transformer classifier on annotated data, achieving over 85% across all metrics. Analyses were validated against manually annotated hive functional regions. Results shows that the unsupervised model effectively captures large-scale movement patterns, whereas the supervised model clarifies behavior-region associations. Overall, this study demonstrates the feasibility of in-hive behavior monitoring, providing a foundation for non-invasive, real-time systems that support smart beekeeping and ecological sustainability. The unsupervised approach may serve as an early-warning indicator for Colony Collapse Disorder (CCD), while supervised models could enhance colony management efficiency, highlighting complementary strengths for bee ecological research. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-21T16:52:15Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-21T16:52:15Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii Abstract iii Table of Contents iv List of Figures vii List of Tables xi Chapter 1 Introduction 1 1.1 Research Background 1 1.2 Research Purposes 2 1.3 Thesis Organization 3 Chapter 2 Literature Review 5 2.1 Honey Bee - Apis mellifera 5 2.1.1 The Importance of Honey Bees as Pollinators 5 2.1.2 Global Declines in Honey Bees Populations 6 2.1.3 The Social Organization of Honey Bees 7 2.2 Computer Vision in Bee Tracking 8 2.2.1 YOLO-based Object Detection Model for Bee Detection 9 2.2.2 Multi-Object Tracking Algorithm for Bee Tracking and Behavior Analysis 11 2.3 Machine Learning for Bee Behavior Analysis 12 2.3.1 Transformer Model 13 2.3.2 Unsupervised Machine Learning for Clustering 13 2.3.3 Supervised Machine Learning for Labeling 14 Chapter 3 Materials and Methods 16 3.1 Research Framework 16 3.2 Data Collection and Image Processing 17 3.3 Computer Vision in Bee Tracking 23 3.3.1 YOLOv8 Object Detection 23 3.3.2 Multi-Object Tracking 25 3.3.3 Incorporating YOLOv8 and ByteTrack MOT for Tracking Bees in the Hive 28 3.3.4 Training Setup and Dataset Preparation 28 3.3.5 Evaluation Metrics for Evaluating Computer Vision Performance 29 3.4 Unsupervised Machine Learning for Bee Behavior Clustering 33 3.4.1 Transformer-based Autoencoder for Extracted Features from Bee Trajectories 33 3.4.2 HDBSCAN for Bee Behavior Clustering 36 3.4.3 Training Setup and Dataset Preparation 37 3.4.4 Evaluation Metrics for Unsupervised Learning 40 3.5 Supervised Machine Learning for Bee Behavior Classifying 43 3.5.1 Transformer-Based Classification Model 43 3.5.2 Training Setup and Dataset Preparation 45 3.5.3 Evaluation Metrics for Supervised Learning 46 3.6 Bee Behavior Analysis and Comparison 46 Chapter 4 Results and Discussion 47 4.1 Data Preprocessing 47 4.2 Object Detection Results of YOLOv8 Variants 48 4.3 Multi-Object Tracking Results 55 4.4 Unsupervised Machine Learning Results 56 4.4.1 Transformer-based Autoencoder for Extracted Features Results 56 4.4.2 HDBSCAN Clustering Results 64 4.5 Supervised Machine Learning Results 68 4.5.1 Annotation for Bee Behavior Labels 68 4.5.2 Transformer Model Classification Results 70 4.6 Visual Analysis of In-Hive Honey Bee Behavior 81 Chapter 5 Conclusions 97 References 99 Appendices 105 Appendix A. Performance Comparison between YOLOv8 and YOLOv11 105 | - |
| dc.language.iso | en | - |
| dc.subject | 巢內蜜蜂追蹤 | zh_TW |
| dc.subject | 巢內蜜蜂行為 | zh_TW |
| dc.subject | 多目標追蹤 | zh_TW |
| dc.subject | Transformer | zh_TW |
| dc.subject | 自編碼器 | zh_TW |
| dc.subject | 密度聚類法 | zh_TW |
| dc.subject | 智慧蜂巢管理 | zh_TW |
| dc.subject | In-hive Honey Bee Behavior | en |
| dc.subject | Beehive Management | en |
| dc.subject | HDBSCAN Clustering | en |
| dc.subject | Autoencoder | en |
| dc.subject | Transformer | en |
| dc.subject | Multi-Object Tracking | en |
| dc.subject | In-Hive Honey Bee Tracking | en |
| dc.title | 應用YOLOv8-ByteTrack與Transformer於巢內蜜蜂行為之影像分析 | zh_TW |
| dc.title | Visual Analysis of In-Hive Honey Bee Behavior Using YOLOv8-ByteTrack and Transformer Models | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 楊恩誠;王人正;王永鐘;周呈霙 | zh_TW |
| dc.contributor.oralexamcommittee | En-Cheng Yang;Jen-Cheng Wang;Yung-Chung Wang;Cheng-Ying Chou | en |
| dc.subject.keyword | 巢內蜜蜂追蹤,巢內蜜蜂行為,多目標追蹤,Transformer,自編碼器,密度聚類法,智慧蜂巢管理, | zh_TW |
| dc.subject.keyword | In-Hive Honey Bee Tracking,In-hive Honey Bee Behavior,Multi-Object Tracking,Transformer,Autoencoder,HDBSCAN Clustering,Beehive Management, | en |
| dc.relation.page | 106 | - |
| dc.identifier.doi | 10.6342/NTU202503944 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-08-11 | - |
| dc.contributor.author-college | 生物資源暨農學院 | - |
| dc.contributor.author-dept | 生物機電工程學系 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 生物機電工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 30.92 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。