請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69516
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 江昭皚(Joe-Air Jiang) | |
dc.contributor.author | Sheng-Hao Chen | en |
dc.contributor.author | 陳聖皓 | zh_TW |
dc.date.accessioned | 2021-06-17T03:17:57Z | - |
dc.date.available | 2020-08-24 | |
dc.date.copyright | 2020-08-24 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-19 | |
dc.identifier.citation | Aleksandr Diment, Emre Çakır, Toni Heittola, and Tuomas Virtanen. Automatic Recognition of Environmental Sound Events Using All-pole Group Delay Features. In 23rd European Signal Processing Conference (EUSIPCO 2015). Nice, France, September 2015. Amlathe, P. (2018). Standard machine learning techniques in audio beehive monitoring: Classification of audio samples with logistic regression, K-nearest neighbor, random forest and support vector machine. Amro Qandour, Iftekhar Ahmad, Daryoush Habibi, and Mark Leppard. (2014). Remote Beehive Monitoring using Acoustic Signals. Acoustics Australia / Australian Acoustical Society, 42(3), 204-209. Bowen-Walker, P. L., Martin, S. J., Gunn, A. (1999). The Transmission of Deformed Wing Virus between Honeybees (Apis melliferaL.) by the Ectoparasitic MiteVarroa jacobsoniOud. Journal of invertebrate pathology, 73(1), 101-106. Cejrowski, T., Szymański, J., Mora, H., Gil, D. (2018, March). Detection of the bee queen presence using sound analysis. In Asian Conference on Intelligent Information and Database Systems (pp. 297-306). Springer, Cham. Chen, C., Yang, E. C., Jiang, J. A., Lin, T. T. (2012). An imaging system for monitoring the in-and-out activity of honey bees. Computers and electronics in agriculture, 89, 100-109. Chikkerur, S., Cartwright, A. N., Govindaraju, V. (2007). Fingerprint enhancement using stft analysis. Pattern recognition, 40(1), 198-211. D. Atauri Mezquida and J. Llorente Martínez. (2009). Short communication.Platform for bee-hives monitoring based on sound analysis.A perpetual warehouse for swarm’s daily activity. Agricultural Research, 7(4), 824-828. David Heise, Nicole Miller-Struttmann, Candace Galen, Johannes Schul. (2017). Acoustic Detection of Bees in the Field Using CASA with Focal Templates. Instrumentation and Measurement Society prior to the acceptance and publication. Dennis, J., Tran, H. D., Li, H. (2010). Spectrogram image feature for sound event classification in mismatched conditions. IEEE signal processing letters, 18(2), 130-133. Emre Çakır, Toni Heittola, Heikki Huttunen, and Tuomas Virtanen. Polyphonic Sound Event Detection Using Multi Label Deep Neural Networks. In International Joint Conference on Neural Networks (IJCNN 2015). Killarney, Ireland, July 2015 Emre Çakır, Toni Heittola, Heikki Huttunen, and Tuomas Virtanen. Multi-label vs. Combined Single-label Sound Event Detection with Deep Neural Networks. In 23rd European Signal Processing Conference (EUSIPCO 2015). Nice, France, September 2015. Emre Çakır, Giambattista Parascandolo, Toni Heittola, Heikki Huttunen and Tuomas Virtanen. (2017). Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection. IEEE Transactions on Audio, Speech and Language Processing: Special issue on Sound Scene and Event Analysis. 10.1109/TASLP.2017.2690575 Faludi, R. (2010) Building wireless sensor networks. O’Reilly Media, Inc., Sebastopol Gates, B. N. (1914). The temperature of the bee colony (No. 96). US Department of Agriculture. Genersch, E., Von Der Ohe, W., Kaatz, H., Schroeder, A., Otten, C., Büchler, R., ... Meixner, M. (2010). The German bee monitoring project: a long term study to understand periodically high winter losses of honey bee colonies. Apidologie, 41(3), 332-352. Golub, G. H., Reinsch, C. (1971). Singular value decomposition and least squares solutions. In Linear Algebra (pp. 134-151). Springer, Berlin, Heidelberg. Hajian-Tilaki, K. (2013). Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian journal of internal medicine, 4(2), 627. Hayes Jr, J., Underwood, R. M., Pettis, J. (2008). A survey of honey bee colony losses in the US, fall 2007 to spring 2008. PloS one, 3(12), e4071. INDEXBOX (2017). World: Honey - Market Report. Analysis And Forecast To 2025. Retrieved May 29, 2018, from https://www.indexbox.io/store/world-honey-market-report-analysis-and-forecast-to-2020/ Jiang, J. A., Wang, C. H., Chen, C. H., Liao, M. S., Su, Y. L., Chen, W. S., ... Chuang, C. L. (2016). A WSN-based automatic monitoring system for the foraging behavior of honey bees and environmental factors of beehives. Computers and Electronics in Agriculture, 123, 304-318. Lindauer, M. (1955). The water economy and temperature regulation of the honeybee colony. Bee World, 36(5), 81-92. Meikle, W. G., Holst, N. (2015). Application of continuous monitoring of honeybee colonies. Apidologie, 46(1), 10-22. Nicolás Pérez, Florencia Jesús, Cecilia Pérez, Silvina Niell, Alejandro Draper, Nicolás Obrusnik, Pablo Zinemanas, Yamandú Mendoza Spina, Leonidas Carrasco Letelier, Pablo Monzón. (2016). Continuous monitoring of beehives’ sound for environmental pollution control. Ecological Engineering, 90, 326-330. Peng, C. Y. J., Lee, K. L., Ingersoll, G. M. (2002). An introduction to logistic regression analysis and reporting. The journal of educational research, 96(1), 3-14. Pérez, N., Jesús, F., Pérez, C., Niell, S., Draper, A., Obrusnik, N., ... Monzón, P. (2016). Continuous monitoring of beehives’ sound for environmental pollution control. Ecological engineering, 90, 326-330. Qandour, A., Ahmad, I., Habibi, D., Leppard, M. (2014). Remote beehive monitoring using acoustic signals. Setiawan, E., Muttaqin, A. (2015). Implementation of K-Nearest Neighbors face recognition on low-power processor. Telkomnika, 13(3), 949. S. Ferrari, M. Silva, M. Guarino, D. Berckmans. (2008). Monitoring of swarming sounds in bee hives for early detection of the swarming period. Computers and Electronics in Agriculture, 64(1), 72-77. Sklearn. 2017. sklearn.metrics.accuracy_score. Available at: http://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html. Accessed 10 August 2017. Sklearn. 2017. sklearn.metrics.precision_recall_fscore_support. Available at: http://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html. Accessed 10 August 2017. Smith, Kristine M., et al. 'Pathogens, pests, and economics: Drivers of honey bee colony declines and losses.' EcoHealth 10.4 (2013): 434-445. Stanley, J., Preetha, G. (2016). Pesticide toxicity to pollinators: exposure, toxicity and risk assessment methodologies. In Pesticide toxicity to non-target organisms (pp. 153-228). Springer, Dordrecht. Steinhauer, N., Rennich, K., Lee, K., Pettis, J., Tarpy, D. R., Rangel, J., ... Wilkes, J. T. (2015). Colony loss 2014–2015: preliminary results. beeinformed. org. http://beeinformed.org/results/colony-loss-2014-2015-preliminary-results/.Accessed, 26 W. G. MEIKLE, N. HOLST (2015). Application of continuous monitoring of honeybee colonies. Apidologie, Volume 46. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69516 | - |
dc.description.abstract | 目前,人類食物中約有三分之一來自開花植物,而其中80%的植物需要蜜蜂授粉。然而,蜜蜂和養蜂業正在遭受全球性危機了解蜂箱狀況是許多研究的目標,開發新的監測系統 以改善蜂巢管理使其更為有效。因此,在這項研究中,建立了一個蜂巢音頻監視系統來記錄蜜蜂的聲音。此外,音頻監控系統會在收集音頻數據後立即對資料進行分析以了解目前蜂群的狀態,這表示本系統能夠即時的回傳蜜蜂狀態。以往的文獻中已證實蜂群聲音在異常狀態將與正常狀態下有很大不同,並且針對失王、分蜂等問題多有研究,但是,它們大多數只聚焦於蜜蜂的單個異常狀態而並非針對多種蜜蜂異常現象進行研究。因此,在這項研究中,我們提出了一種結合機器學習系統的音頻監控系統,用於數據分析和分類模型的建立。除了能夠同時對三種不同的蜜蜂異常進行分類外,包括失王,病毒和農藥。該系統具有許多功能例如實時分類,遠程控制和分類模型的自動更新。為了使養蜂人或用戶更輕鬆地管理蜂群,實時音頻監視系統可以準確,快速地檢測當前蜂箱的狀態。隨著數據收集的增加,系統本身的分類模型將不斷得到改進和糾正。 | zh_TW |
dc.description.abstract | Currently, about one-third of human food comes from flowering plants, and 80% of the plants need honey bees for pollination. However, bees and beekeeping are suffering a global crisis. Constant information on beehives’ conditions would be a key to study new diseases like colony collapse disorder and to develop new beekeeping tools to improve the hive management and make it more efficient. Therefore, in this study, a beehive audio monitoring system is established to record the sound of bees. Furthermore, the audio monitoring system will classify the condition of the beehives as soon as it collects the audio data, which means that the system is able to return the real-time honey bee conditions. Previous studies on bee sound have confirmed that the bee sound in an abnormal state will be very different from the normal state. However, most of them only focused on a single abnormal state of bees. Therefore, in this study, we propose an audio monitoring system combined with a machine learning system for data analysis and classification model establishment. In addition to being able to classify three different bee abnormalities at the same time, including queenless, virus, and pesticides. The system has many functions, such as real-time classification, remote control, and automatic updating of the classification model. To allow beekeepers or users to manage bee colonies more easily, the real-time audio monitoring system can accurately and quickly detect the status of the current beehive. The classification model of the system itself is continuously improved and corrected as the data collection increases. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T03:17:57Z (GMT). No. of bitstreams: 1 U0001-1808202012185000.pdf: 4995719 bytes, checksum: f0423baf7e8ebc5daec0b86718e3481a (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 誌謝 i 摘要 ii Abstract iii Table of Contents v List of Figure x Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation and purposes of the study 3 1.3 Thesis organization 4 Chapter 2 Literature Review 5 2.1 Threats that honey bees face 5 2.1.1The impacts of queenless beehives 5 2.1.2The influence of deformed wing virus 5 2.1.3The effect of pesticides 7 2.1.4Conclusion for the subsection 9 2.2 Continuous monitoring of the sounds in beehives 10 2.3 Abnormal bee sounds 11 2.3.1 Bee sounds of a queenless beehive 11 2.3.2 Bee sounds of swarming 12 2.3.3 The sound of a bee parasitized by Varroa destructors 14 2.3.4 Conclusion of subsection 17 2.4 Machine learning techniques for Raspberry Pi 18 Chapter 3 Materials and Methods 21 3.1 Honey bee audio monitoring system 21 3.1.1 Selection of sensors used in the audio monitoring system 21 3.1.2 Continuously recording 23 3.1.3 Real-time classification 23 3.1.4 Low network traffic 23 3.1.5 High data recovery stability 24 3.1.6 Data backup 25 3.1.7 Remote control 25 3.1.8 Automatically updating the classification model 26 3.1.9 Pseudocode for the honey bee audio monitoring system 27 3.2 Bee Counter System 30 3.3 Data processing 32 3.3.1 Short-time Fast Fourier transform 32 3.3.2 Spectrogram of honey bee audio 32 3.3.3 Melspectrogram 35 3.3.4 Mel Frequency Cepstral Coefficient 36 3.4 Methods of classification 38 3.4.1 K-Nearest Neighbor 38 3.4.2 Logistic regression 40 3.4.3 Singular Value Decomposition 40 3.4.4 Data analysis flow chart 41 3.5 Classification performance metric 43 3.5.1 Receiver Operating Characteristic Curve 43 3.5.2 Precision, recall, and f1-Score 45 3.6 System Architecture 46 3.7 Experimental Design 48 3.7.1 Queenless experiment 48 3.7.2 Deformed wing virus experiment 49 3.7.3 Pesticide experiment 51 Chapter 4 Results and Discussion 53 4.1 Sound audio of bees 53 4.1.1 Sound data analysis 53 4.1.2 Classification error analysis 55 4.2 Queenless experiment 59 4.2.1 Sound analysis of normal and queenless 60 4.2.2 Sound analysis before and after the bees lose the queen in the same beehive 63 4.2.3 Sound analysis of normal bees 65 4.3 Deformed wing virus experiment 67 4.3.1 Sound analysis of normal bees and bees infected with Deformed wing virus 67 4.3.2 Sound analysis of normal bees and bees infected with Deformed wing virus under medicine treatment 71 4.3.3 Sound analysis of normal bees and bees infected with Deformed wing virus without medicine treatment 73 4.3.4 Sound analysis of normal bees which under medicine treatment and without medicine treatment 76 4.3.5 Sound analysis of infected bees which under medicine treatment and without medicine treatment 79 4.4 Pesticide experiment 82 4.4.1 Sound analysis of normal bees and bee sounds invaded by pesticides at various concentrations 82 4.4.2 Bee sound analysis of 1 ppm pesticide contamination 83 4.4.3 Bee sound analysis of 10 ppm pesticide contamination 85 4.4.4 Bee sound analysis of 100 ppm pesticide contamination 87 4.5 Comprehensive result 90 4.6 Real-time dynamic bee colony audio monitoring management system 93 Chapter 5 Conclusions and Future Work 95 References 97 | |
dc.language.iso | en | |
dc.title | 開發物聯網系統以即時監測音頻並評估蜂群狀態 | zh_TW |
dc.title | Developing an IoT-based Audio Monitoring System for Evaluation of Honey Bee Colony Conditions in Real-time | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 楊恩誠(En-Cheng Yang),周呈霙(Cheng-Ying Zhou),吳岳隆(Yue-Long Wu),盧美君(Mei-Jun Lu) | |
dc.subject.keyword | 音頻監測系統,蜜蜂,健康指標, | zh_TW |
dc.subject.keyword | Audio monitoring system,Honey bee,Colony health indicator, | en |
dc.relation.page | 100 | |
dc.identifier.doi | 10.6342/NTU202003948 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-20 | |
dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
dc.contributor.author-dept | 生物機電工程學系 | zh_TW |
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 | |
---|---|---|---|
U0001-1808202012185000.pdf 目前未授權公開取用 | 4.88 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。