未來農業將進行一場轉型性變革，融合感測技術和高效能計算系統，展現其高效率且具成本效益的特點。在農業生產中實施物聯網（IoT）技術帶來許多好處，因其低成本和易於部署的通訊方式。雖然機器學習方法在智能農業領域取得了快速發展，具有廣泛的潛在應用，但仍存在一些未解決的研究問題。本研究旨在通過開發基於深度學習（DL）的物聯網智能農業系統模型，解決這些問題。這些模型利用先進的分析技術來分析過去的狀態，模擬未來的行為並表示當前的狀態。
為實現本論文的目標，研究將重點放在通過使用LoRaWAN網絡來增強物聯網智能農業網絡中各種物聯網設備的數據收集和實時監測的性能。目標是建立環境天氣條件與LoRaWAN通道性能指標（如接收信號強度指示器（RSSI）、信噪比（SNR）和封包接收率（PRR））之間的關聯性。這種關聯性有助於減輕極端天氣條件對LoRaWAN性能的影響。此外，通過實時估算通道性能指標，可以優化LoRaWAN終端設備的傳輸參數設置，特別是在設施完善的開放場地。
在缺乏網絡基礎設施的地區，本研究對由20個終端節點和1個網關節點組成的多跳LoRa網絡進行了網絡和鏈接級別性能分析。使用深度學習技術，該分析模擬了不同傳輸參數和環境條件對性能的影響。所開發的方法能夠準確估計RSSI、SNR和封包接收率（PRR），在傳統技術不適用的情況下具有重要意義。此外，該研究還能夠加快LoRa設備的網絡部署時間，實現對不同參數的更快估計。
因此，本論文的重點是開發一種基於深度學習的適應性資料速率算法，專為LoRa和LoRaWAN網絡在廣闊的物聯網（IoT）領域內進行智能資源分配。目標是實現這些網絡中的智能資源分配，以滿足不同的通信需求。此外，本研究還旨在克服可擴展性挑戰，同時研究各種因素對鏈接質量、網絡性能和鏈接級別性能的影響。先進的人工智能（AI）和機器學習（ML）技術被用於提高農業監測系統的效率和效果。這些技術使得從收集到的數據中提取有價值的見解成為可能，從而實現更高的產量並最小化對環境的影響。

The future of agriculture is poised to undergo a transformative shift with the integration of sensor technology and high-performance computing systems, which have proven to be efficient and cost-effective. The implementation of Internet of Things (IoT) technology in agricultural production offers numerous benefits, as it is a low-cost and easily deployable communication method. While machine learning methods have witnessed rapid growth in smart agriculture, there remain several unresolved research questions. However, the potential applications of machine learning in smart agriculture are vast. This research aims to address these gaps by developing deep learning (DL) models for Artificial Intelligence of Things (AIoT)-based smart agriculture systems. These models utilize sophisticated analytics to analyze previous states, model future behavior, and represent current states.
To achieve the objectives of this thesis, the study focuses on enhancing the performance of data collection and real-time monitoring of various IoT devices in smart agriculture networks through the use of LoRaWAN networks. The goal is to establish correlations between ambient weather conditions and LoRaWAN channel performance indicators such as received signal strength indicator (RSSI), signal-to-noise ratio (SNR), and packet reception rate (PRR). This correlation enables mitigating the impact of extreme weather conditions on LoRaWAN performance. Furthermore, real-time estimation of channel performance indicators optimizes LoRaWAN end device transmission parameter settings by enhancing the performance of the adaptive data rate (ADR) algorithm, particularly in open fields with accessible network infrastructure.
In areas lacking network infrastructure, network and link-level performance analysis of a multi-hop LoRa network, consisting of 20 end nodes and 1 gateway node, is conducted. This analysis models the impact of different transmission parameters and ambient conditions using DL techniques. The developed methodology accurately estimates RSSI, SNR, and packet reception rate (PRR) in situations where traditional techniques may not be applicable. Moreover, this study can expedite the network deployment time for LoRa devices by enabling faster estimation of different parameters.
Therefore, this thesis focuses on the development of a deep learning-based adaptive data rate algorithm tailored specifically for LoRa and LoRaWAN networks within the vast Internet of Things (IoT) domain. The objective is to facilitate intelligent resource allocation in these networks to meet diverse communication requirements. Additionally, this research aims to overcome scalability challenges while investigating the influence of various factors on link quality, network performance, and link-level performance. Advanced artificial intelligence (AI) and machine learning (ML) techniques are employed to enhance the efficiency and effectiveness of agriculture monitoring systems. These techniques enable the extraction of valuable insights from collected data, contributing to higher yields while minimizing environmental impact.

Contents
Abstract 3
中文摘要 5
Acknowledgement 6
List of Figures 11
List of Tables 13
1. Chapter 1: Introduction 14
1.1 Introduction 14
1.2 Artificial Intelligence as Revolutionary Tool for Agriculture 16
1.3 Big Data Operating Cycle in the Agriculture Environment 19
1.7 Exploring Smart Agriculture Ecosystem: Technological Overview 20
1.7.1 Harvesting Insights: Agricultural Data 20
1.7.2 Connecting Crops: The Importance of Communication Networks 22
1.7.4 Introduction to LoRa and LoRaWAN 24
2. Chapter 2: Literature Review 33
2.1 Objectives and Contribution to the Field 33
2.2 Objectives and Contribution to the Field 38
2.2.1 Correlating the Ambient Conditions and Performance Indicators of the LoRaWAN 38
2.2.2 Estimation of Channel Performance Indicators of LoRaWAN network using Surrogate Gaussian Process-based Bidirectional LSTM Stacked Autoencoder Model 39
2.2.3 Correlating the Ambient Conditions and Transmission Parameters with the Multi-hop LoRa Network and Link-Level Performance Indicators 39
2.2.4 Estimation of Multi-hop LoRa Network and Link-Level Performance using Bayesian Surrogate RF-based Deep Learning Model 39
2.7 Executive Summary 40
3. Chapter 3: Correlating the Ambient Conditions and Performance Indicators of the LoRaWAN via Surrogate Gaussian Process-based Bidirectional LSTM Stacked Autoencoder 42
3.1 An Overview of the LoRaWAN Performance and Impact of Environmental Factors in Open Field Settings 42
3.2 Methodology 45
3.2.1 The Multivariate Time Series Problem Statement 45
3.2.2 Deep Learning Model Development Preliminaries 46
3.2.3 Bayesian Optimization Algorithm 48
3.2.4 Experimental Setup and Data Collection 48
3.2.5 Bayesian Surrogate Gaussian Process Bidirectional LSTM Stacked Autoencoder (BSGP-BLSTM-SAE) 50
3.2.6 Model Complexity Analysis 53
3.3 Results and Discussion 55
3.3.1 Impact of Varying Ambient Parameters on RSSI and SNR 56
3.3.2 Predictions of Channel Performance Indicators 61
3.3.3 Weather Estimation 63
3.4 Discussion 63
3.5 Conclusion 65
4. Chapter 4: Multi-hop LoRa Network and Link-Level Performance Estimation and Correlating with the Ambient and Transmission Parameters via Bayesian Surrogate RF-based Deep Learning 67
4.1 Overview of the LoRa Multi-Hop Networks 67
4.2 Methodology: System Design and Implementation 69
4.2.1 Problem Statement 69
4.2.2 Random Forest Regression Algorithm 70
4.2.3 Random Forest-based Bayesian Optimization 71
4.2.4 Experiment Setup and Data Collection 75
4.2.5 Proposed Connectivity and Link-Quality Estimation Model 76
4.3 Result Analysis and Discussion 79
4.3.1 RSSI, SNR, and PRR as a Function of Transmission Parameters 79
4.3.2 RSSI and SNR as a Function of Ambient Weather Conditions 83
4.3.3 RSSI, SNR, and PRR as a Function of Onboard Temperature 85
4.3.4 PRR as a Function of RSSI and SNR 86
4.3.5 Statistical Significance of the Established Correlations 87
4.3.6 Estimation of Network and Link-Level Performance Metrics 88
4.3.7 Discussion 90
Conclusion 92
5. Chapter 5: Conclusions and Future Recommendations 94
List of Publications 97
Bibliography 98

1. Mc Carthy, U., et al., Global food security–Issues, challenges and technological solutions. Trends in Food Science & Technology, 2018. 77: p. 11-20.
2. Noireaux, V. and P. Ralet, Difficultés des canaux de distribution alimentaire en territoire rural: l’importance du leader. Économie rurale, 2019: p. 21-39.
3. FAO (2018b), Initiative de passage à l’échelle supérieure de l’agroécologie.; Available from: http://www.fao.org/3/I9049FR/i9049fr.pdf.
4. FAO (2019) Digital Technologies in Agriculture and Rural Areas.; Available from: http://www.fao.org/3/ca4887en/ca4887en.pdf.
5. De Clercq, M., A. Vats, and A. Biel, Agriculture 4.0: The future of farming technology. Proceedings of the World Government Summit, Dubai, UAE, 2018: p. 11-13.
6. Carlsen, L. and R. Bruggemann, The 17 United Nations’ sustainable development goals: a status by 2020. International Journal of Sustainable Development & World Ecology, 2022. 29(3): p. 219-229.
7. Organization, W.H., The State of Food Security and Nutrition in the World 2021: Transforming food systems for food security, improved nutrition and affordable healthy diets for all. Vol. 2021. 2021: Food & Agriculture Org.
8. Lian., P. How AI can improve agriculture for better food security. International Telecommunication Union (ITU). [cited 2023 03/16]; Available from: https://www.itu.int/hub/2020/02/how-ai-can-improve-agriculture-for-better-food-security/.
9. Misra, N., et al., IoT, big data, and artificial intelligence in agriculture and food industry. IEEE Internet of things Journal, 2020. 9(9): p. 6305-6324.
10. Ayus, I. and N. Panigrahi, A Decision Support System Using Rule-Based Expert System for COVID-19 Prediction and Diagnosis. Applications of Artificial Intelligence in COVID-19, 2021: p. 119-140.
11. Goyache, F., et al., The usefulness of artificial intelligence techniques to assess subjective quality of products in the food industry. Trends in Food Science & Technology, 2001. 12(10): p. 370-381.
12. Waltl, B., G. Bonczek, and F. Matthes, Rule-based information extraction: Advantages, limitations, and perspectives. Jusletter IT (02 2018), 2018.
13. Gupta, S., et al., Artificial intelligence for decision support systems in the field of operations research: review and future scope of research. Annals of Operations Research, 2022. 308(1): p. 215-274.
14. Patel, K. and H.B. Patel. A Comparative Analysis of Supervised Machine Learning Algorithm for Agriculture Crop Prediction. in 2021 Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT). 2021. IEEE.
15. Chen, M., et al., A reinforcement learning approach to irrigation decision-making for rice using weather forecasts. Agricultural Water Management, 2021. 250: p. 106838.
16. Michalski, R.S., J.G. Carbonell, and T.M. Mitchell, Machine learning an artificial intelligence approach. 1984: Springer.
17. Liakos, K.G., et al., Machine learning in agriculture: A review. Sensors, 2018. 18(8): p. 2674.
18. Farooq, M.S., et al., A Survey on the Role of IoT in Agriculture for the Implementation of Smart Farming. Ieee Access, 2019. 7: p. 156237-156271.
19. Bhat, S.A. and N.-F. Huang, Big data and ai revolution in precision agriculture: Survey and challenges. IEEE Access, 2021. 9: p. 110209-110222.
20. Sarker, M.N.I., et al. Big data driven smart agriculture: Pathway for sustainable development. in 2019 2nd international conference on artificial intelligence and big data (ICAIBD). 2019. IEEE.
21. Brook, A., et al., A smart multiple spatial and temporal resolution system to support precision agriculture from satellite images: Proof of concept on Aglianico vineyard. Remote Sensing of Environment, 2020. 240: p. 111679.
22. Minet, J., et al., Crowdsourcing for agricultural applications: A review of uses and opportunities for a farmsourcing approach. Computers and Electronics in Agriculture, 2017. 142: p. 126-138.
23. Wasson, T., et al. Integration of RFID and sensor in agriculture using IOT. in 2017 International Conference On Smart Technologies For Smart Nation (SmartTechCon). 2017. IEEE.
24. Liu, H., S.-H. Lee, and J.S. Chahl, A review of recent sensing technologies to detect invertebrates on crops. Precision Agriculture, 2017. 18: p. 635-666.
25. Saleem, M.H., J. Potgieter, and K.M. Arif, Automation in agriculture by machine and deep learning techniques: A review of recent developments. Precision Agriculture, 2021. 22: p. 2053-2091.
26. Zhao, W., et al., Ground-level mapping and navigating for agriculture based on IoT and computer vision. IEEE Access, 2020. 8: p. 221975-221985.
27. Pylianidis, C., S. Osinga, and I.N. Athanasiadis, Introducing digital twins to agriculture. Computers and Electronics in Agriculture, 2021. 184: p. 105942.
28. Purcell, W. and T. Neubauer, Digital Twins in Agriculture: A State-of-the-art review. Smart Agricultural Technology, 2022: p. 100094.
29. Carvalho, C., et al., Improving prediction accuracy for WSN data reduction by applying multivariate spatio-temporal correlation. Sensors, 2011. 11(11): p. 10010-10037.
30. Bhat, S.A., et al., Correlating the Ambient Conditions and Performance Indicators of the LoRaWAN via Surrogate Gaussian Process based Bidirectional LSTM Stacked Autoencoder Showkat. IEEE Transactions on Network and Service Management, 2023.
31. Elijah, O., et al., Effect of weather condition on LoRa IoT communication technology in a tropical region: Malaysia. IEEE Access, 2021. 9: p. 72835-72843.
32. Osorio, A., et al., Routing in LoRaWAN: Overview and challenges. IEEE Communications Magazine, 2020. 58(6): p. 72-76.
33. Boano, C.A., M. Cattani, and K. Römer. Impact of Temperature Variations on the Reliability of LoRa - An Experimental Evaluation. in International Conference on Sensor Networks. 2018.
34. Cattani, M., C.A. Boano, and K. Römer, An experimental evaluation of the reliability of lora long-range low-power wireless communication. Journal of Sensor and Actuator Networks, 2017. 6(2): p. 7.
35. Foubert, B. and N. Mitton. Routing Over Multiple Technologies with RODENT. in 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). 2021. IEEE.
36. Baccelli, E., Internet of Things (IoT): Societal Challenges & Scientific Research Fields for IoT. 2021.
37. World first Australian IoT uses satellites to monitor farmers’ tanks, rain levels. . Available from: https://which-50.com/world-first-australian-iot-uses-satellites-to-monitor-farmers-tanks-rain-levels/.
38. SELLER, O.B. and N. Sornin, Low power long range transmitter. 2016, Google Patents.
39. Haxhibeqiri, J., et al., A survey of LoRaWAN for IoT: From technology to application. Sensors, 2018. 18(11): p. 3995.
40. SX1272/73—860 MHz to 1020 MHz Low Power Long Range Transceiver. [cited 2023 20-02]; Available from: https://www.semtech.com/uploads/documents/sx1272.pdf.
41. LoRaWAN. What Is It? A Technical Overview of LoRA and LoRaWAN. [cited 2023 20-02]; Available from: https://www.loraalliance.org/.
42. ETSI, E.T., Electromagnetic compatibility and radio spectrum matters (erm); short range devices (srd); radio equipment to be used in the 25 mhz to 1 000 mhz frequency range with power levels ranging up to 500 mw. European harmonized standard EN, 2012. 300(220): p. v2.
43. Alliance, L., Lorawan regional parameters v1. 1. LoRa Alliance: Fremont, CA, USA, 2016.
44. Sornin, N., et al., LoRaWAN Specification V1. 0. LoRa Alliance; Fremont, CA. USA: 2015. Technical Report.[Google Scholar].
45. LoRa Alliance, I., LoRaWAN TM 1.0. 2 Regional Parameters. San Ramon, CA, 2017.
46. Loukil, S., et al., Analysis of LoRaWAN 1.0 and 1.1 protocols security mechanisms. Sensors, 2022. 22(10): p. 3717.
47. Corpoartion., S. Understanding the LoRa®Adaptive Data Rate. Technical paper, December-2019. [cited 2023 12-01]; Available from: https://lora-developers.semtech.com/uploads/documents/files/Understanding_LoRa_Adaptive_Data_Rate_Downloadable.pdf.
48. Corporation., S. LoRaWAN® Mobile Applications: Blind ADR. . Available from: https://lora-developers.semtech.com/uploads/documents/files/LoRaWAN_Mobile_Apps-Blind_ADR_Downloadable.pdf.
49. Brown, M.E., Satellite remote sensing in agriculture and food security assessment. Procedia Environmental Sciences, 2015. 29: p. 307.
50. Chinchilla-Romero, N., et al., Collision avoidance resource allocation for LoRaWAN. Sensors, 2021. 21(4): p. 1218.
51. Mroue, H., et al., LoRa+: An extension of LoRaWAN protocol to reduce infrastructure costs by improving the Quality of Service. Internet of Things, 2020. 9: p. 100176.
52. Bankov, D., E. Khorov, and A. Lyakhov, LoRaWAN modeling and MCS allocation to satisfy heterogeneous QoS requirements. Sensors, 2019. 19(19): p. 4204.
53. Wixted, A.J., et al. Evaluation of LoRa and LoRaWAN for wireless sensor networks. in 2016 IEEE SENSORS. 2016. IEEE.
54. Parri, L., et al., Offshore lorawan networking: Transmission performances analysis under different environmental conditions. IEEE Transactions on Instrumentation and Measurement, 2020. 70: p. 1-10.
55. Luomala, J. and I. Hakala. Effects of temperature and humidity on radio signal strength in outdoor wireless sensor networks. in 2015 Federated Conference on Computer Science and Information Systems (FedCSIS). 2015. IEEE.
56. Boano, C.A., K. Römer, and N. Tsiftes. Mitigating the adverse effects of temperature on low-power wireless protocols. in 2014 IEEE 11th International Conference on Mobile Ad Hoc and Sensor Systems. 2014. IEEE.
57. Boano, C.A., et al. Low-power radio communication in industrial outdoor deployments: The impact of weather conditions and ATEX-compliance. in Sensor Applications, Experimentation, and Logistics: First International Conference, SENSAPPEAL 2009, Athens, Greece, September 25, 2009, Revised Selected Papers 1. 2010. Springer.
58. Marfievici, R., et al. How environmental factors impact outdoor wireless sensor networks: a case study. in 2013 IEEE 10th international conference on mobile ad-hoc and sensor systems. 2013. IEEE.
59. Zitouni, R., et al., IEEE 802.15. 4 transceiver for the 868/915 MHz band using Software Defined Radio. arXiv preprint arXiv:1304.8028, 2013.
60. Benkahla, N., et al., Review and experimental evaluation of ADR enhancements for LoRaWAN networks. Telecommunication Systems, 2021. 77: p. 1-22.
61. Cuomo, F., et al. EXPLoRa: Extending the performance of LoRa by suitable spreading factor allocations. in 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob). 2017. IEEE.
62. Abdelfadeel, K.Q., V. Cionca, and D. Pesch. Fair adaptive data rate allocation and power control in LoRaWAN. in 2018 IEEE 19th International Symposium on" A World of Wireless, Mobile and Multimedia Networks"(WoWMoM). 2018. IEEE.
63. Park, J., et al., EARN: Enhanced ADR with coding rate adaptation in LoRaWAN. IEEE Internet of Things Journal, 2020. 7(12): p. 11873-11883.
64. Farhad, A. and J.-Y. Pyun, HADR: A Hybrid Adaptive Data Rate in LoRaWAN for Internet of Things. ICT Express, 2022. 8(2): p. 283-289.
65. Dias, J. and A. Grilo, LoRaWAN multi-hop uplink extension. Procedia computer science, 2018. 130: p. 424-431.
66. Abrardo, A. and A. Pozzebon, A multi-hop lora linear sensor network for the monitoring of underground environments: The case of the medieval aqueducts in Siena, Italy. Sensors, 2019. 19(2): p. 402.
67. Pycom, Pymesh—LoRa Full-Mesh Network Technology, 2020. . [cited 2023 12/02]; Available from:
https://docs.pycom.io/pymesh/.
68. Ochoa, M.N., et al. Evaluating LoRa energy efficiency for adaptive networks: From star to mesh topologies. in 2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob). 2017. IEEE.
69. Sherazi, H.H.R., et al., Energy-efficient LoRaWAN for industry 4.0 applications. IEEE Transactions on Industrial Informatics, 2020. 17(2): p. 891-902.
70. Citoni, B., et al., Internet of Things and LoRaWAN-enabled future smart farming. IEEE Internet of Things Magazine, 2019. 2(4): p. 14-19.
71. Terleev, A.V., A.A. Khalturin, and V.A. Shpenst. LoRaWAN gateway coverage evaluation for smart city applications. in 2021 3rd International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE). 2021. IEEE.
72. Ferrari, P., et al., On the use of LoRaWAN and cloud platforms for diversification of mobility-as-a-service infrastructure in smart city scenarios. IEEE Transactions on Instrumentation and Measurement, 2022. 71: p. 1-9.
73. Boano, C.A., M. Cattani, and K. Römer. Impact of temperature variations on the reliability of LoRa. in Proc. 7th Int. Conf. Sensor Netw. 2018.
74. Di Renzone, G., et al., Assessment of LoRaWAN transmission systems under temperature and humidity, gas, and vibration aging effects within IIoT contexts. IEEE Transactions on Instrumentation and Measurement, 2021. 71: p. 1-11.
75. Di Renzone, G., et al. LoRaWAN transmission system capability assessment in industrial environment under temperature and humidity characterization. in 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). 2021. IEEE.
76. Jeftenić, N., M. Simić, and Z. Stamenković. Impact of Environmental Parameters on SNR and RSS in LoRaWAN. in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE). 2020. IEEE.
77. Souza Bezerra, N., et al., Temperature impact in LoRaWAN—A case study in Northern Sweden. Sensors, 2019. 19(20): p. 4414.
78. Ameloot, T., P. Van Torre, and H. Rogier. Periodic LoRa signal fluctuations in urban and suburban environments. in 2019 13th European Conference on Antennas and Propagation (EuCAP). 2019. IEEE.
79. Basford, P.J., et al., LoRaWAN for smart city IoT deployments: A long term evaluation. Sensors, 2020. 20(3): p. 648.
80. Bregar, K. and M. Mohorčič, Improving indoor localization using convolutional neural networks on computationally restricted devices. IEEE Access, 2018. 6: p. 17429-17441.
81. Sun, W., et al., WNN-LQE: Wavelet-neural-network-based link quality estimation for smart grid WSNs. IEEE Access, 2017. 5: p. 12788-12797.
82. Demetri, S., et al. Automated estimation of link quality for LoRa: A remote sensing approach. in 2019 18th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN). 2019. IEEE.
83. Cerar, G., et al., Machine learning for wireless link quality estimation: A survey. IEEE Communications Surveys & Tutorials, 2021. 23(2): p. 696-728.
84. Hochreiter, S. and J. Schmidhuber, Long short-term memory. Neural computation, 1997. 9(8): p. 1735-1780.
85. Goldoni, E., et al., Correlation between weather and signal strength in LoRaWAN networks: An extensive dataset. Computer Networks, 2022. 202: p. 108627.
86. Saidi, R., W. Bouaguel, and N. Essoussi, Hybrid feature selection method based on the genetic algorithm and pearson correlation coefficient. Machine learning paradigms: theory and application, 2019: p. 3-24.
87. Kufakunesu, R., G.P. Hancke, and A.M. Abu-Mahfouz, A survey on adaptive data rate optimization in lorawan: Recent solutions and major challenges. Sensors, 2020. 20(18): p. 5044.
88. Slabicki, M., G. Premsankar, and M. Di Francesco. Adaptive configuration of LoRa networks for dense IoT deployments. in NOMS 2018-2018 IEEE/IFIP Network Operations and Management Symposium. 2018. IEEE.
89. Mekki, K., et al., A comparative study of LPWAN technologies for large-scale IoT deployment. ICT express, 2019. 5(1): p. 1-7.
90. Centelles, R.P., et al., Beyond the star of stars: An introduction to multihop and mesh for LoRa and LoRaWAN. IEEE Pervasive Computing, 2021. 20(2): p. 63-72.
91. Adelantado, F., et al., Understanding the limits of LoRaWAN. IEEE Communications magazine, 2017. 55(9): p. 34-40.
92. Attia, T., et al. Experimental characterization of LoRaWAN link quality. in 2019 IEEE Global Communications Conference (GLOBECOM). 2019. IEEE.
93. Yegin, A., et al., LoRaWAN protocol: specifications, security, and capabilities, in LPWAN Technologies for iot and m2m applications. 2020, Elsevier. p. 37-63.
94. Van de Velde, B., Multi-hop LoRaWAN: including a forwarding node. 2018.
95. Ameloot, T., P. Van Torre, and H. Rogier, Variable link performance due to weather effects in a long-range, low-power lora sensor network. Sensors, 2021. 21(9): p. 3128.
96. Frazier, P.I., A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811, 2018.
97. Santner, T.J., et al., The design and analysis of computer experiments. Vol. 1. 2003: Springer.
98. Tian, P., et al. Environmental impact on the long-term connectivity and link quality of an outdoor LoRa network. in Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems. 2021.
99. Schober, P., C. Boer, and L.A. Schwarte, Correlation coefficients: appropriate use and interpretation. Anesthesia & Analgesia, 2018. 126(5): p. 1763-1768.
100. Gnawali, O., et al. Collection tree protocol. in Proceedings of the 7th ACM conference on embedded networked sensor systems. 2009.
101. Rappaport, T.S., Wireless communications: principles and practice. Vol. 2. 1996: prentice hall PTR New Jersey.
102. Zuniga, M. and B. Krishnamachari. Analyzing the transitional region in low power wireless links. in 2004 First Annual IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks, 2004. IEEE SECON 2004. 2004. IEEE.