Dissertations / Theses on the topic 'Internet of things, Precision agriculture'

Precision Agriculture (PA) is an emerging technology which enables efficient irrigation by employing the Internet of Things (IoT). We split the thesis in two parts. The first part is estimation of humidity level via experimentation. We focus on measuring Received Signal Strength Indicator (RSSI) to obtain humidity level of the field. Thus, we aim at eliminating the humidity sensors which are very expensive and estimate soil moisture through the variation of RSSI values measured by wireless devices buried underground. In the second part of the thesis, we aim at building an accurate and reliable irrigation system by the help of IoT technology via simulations. The advantage brought by our Wireless Sensor Network (WSN) is twofold: it minimizes the amount of wasted water during irrigation in farming, and it increases the yield with efficient irrigation. For these purposes, we tested the performance of LoRa protocol in different scenarios in both parts of the thesis.

Les Réseaux de Capteurs Sans Fil (RCSF ou Wireless Sensor Network - WSN) sont l'une des technologies les plus importantes du 21ème siècle. La plupart des chercheurs et les analystes estiment que, dans un proche avenir, ces micro-capteurs seront intégrés partout dans l’environnement de notre vie quotidienne. Ces dernières années, l'Internet des Objets (Internet of Things - IoT) est également une des technologies émergentes qui se développe rapidement. Deux nouveaux standards permettent de déployer des réseaux sans fil de faible consommation énergétique connectés à internet : le protocole 6LowPAN (Low power Wireless Personal Area Networks) qui permet notamment d’apporter l’adressage IPv6 aux capteurs grâce à l’encapsulation et la compression des données et le protocole de routage RPL (IPv6 routing protocol for low-power and lossy network) qui permet à l’information de circuler dans les WSN de proche en proche à un faible coût énergétique. Bien que le développement de ces techniques soit extrêmement rapide, plusieurs problèmes causés principalement par le manque de ressources des micro-capteurs (puissance limitée de traitement, problèmes de bande passante et de connexion des liens avec perte de données, problème de ressource énergétique limitée) demeurent et doivent être résolus, notamment pour les applications agro-environnementales
The wireless sensor network (WSN) is one of the most important technologies of the 21st century. Most researchers and technical analysts believe that in the near future, these micro-sensors will be integrated into the environment of our daily lives. In recent years, the IoT (Internet of Things) and WoT (Web of Things) technologies also have great forwarding. Especially, the IPv6 over Low power Wireless Personal Area Networks (6LoWPAN) protocol has allowed the use of IPv6 protocol stack in the field of WSN, thanks to its encapsulation and compression mechanisms in IPv6 packet header. Moreover, the RPL (IPv6 Routing Protocol for Low-power and Lossy Network) provides such a powerful routing function that can be applied for a variety of application scenarios. These two key standards of IoT and WoT technologies for WSN can be used in an IPv6 stack, and they will successfully achieve the connection between Internet and micro-sensors. Thus, due to the availability of IPv6 address (128-bit), all the communicating objects, such as smart device, sensor, and actuator, can be connected to the Internet. That is the greatest advantage brought by the IoT. Although the progress of these techniques is extremely fast, several issues caused by resource constraints of micro-sensor (limited processing power, bandwidth and lossy connection link, and energy), such as QoS, energy efficient, robustness and lifetime of WSN, and the most important, the special requirement of agricultural applications. Notice that Precision Agriculture is are still very challenging and waiting to be solved. Essentially, these open questions would dabble in the aspects like telemedicine, remote home automation, industrial control etc. Thus, the results obtained in this work will have a significant impact on both economic and scientific. Economically, it can offer a solution for WSN to support sustainable development in the field of agriculture automation. While scientifically, we will contribute to the routing protocol standardization of wireless micro-sensors in the domain of environmental monitoring

Os processos de produção e distribuição agrícolas fazem uso de diversas tecnologias usadas para coleta de dados e gerenciamento de recursos e atividades, dentre as quais as Redes de Sensores Sem Fio, Identificação por Radiofrequência e o Wi-Fi. Devido a falhas na infraestrutura e variações ambientais, essas tecnologias possuem diversas limitações, como por exemplo, o atraso com que os dados chegam aos sistemas de gerenciamento, comprometendo a eficiência do processo. Uma solução com nós multitecnológicos, baseada nos princípios da Internet das Coisas, poderia oferecer dados de todo o processo produtivo e de distribuição, em tempo real; mas, para que esta solução seja realmente eficiente, necessita de um seletor adaptativo de tecnologias de comunicação para os \"objetos\" de campo que se adapte ao ambiente em tempo de execução. O objetivo deste trabalho é propor e avaliar a funcionalidade de um seletor adaptativo para esse fim. Para a proposição do seletor, buscou-se embasamento em técnicas adaptativas que oferecessem solução adequada para processos de aprendizagem pelo seletor. Dentre essas técnicas, elegeram-se as Árvores de Decisão Adaptativas para implementar a operação do seletor. A funcionalidade do seletor foi avaliada por simulações, tanto quanto ao aspecto de seleção da opção tecnológica mais adequada para o momento e a situação em questão, quanto à facilidade de se adaptar a mudanças de cenário. Os resultados das avaliações mostram que a simulação inicial, feita a partir de um cenário correspondente à fase inicial de uma cultura de milho não apresenta resultados satisfatórios. Entretanto, após alguns ciclos de aprendizagem do seletor, os resultados evoluem e superaram as exigências de qualidade propostas. Em uma segunda fase, novas simulações foram realizadas, alterando-se o cenário inicial para que, aos poucos, correspondesse à fase de colheita do milho. Nestas simulações, o processo de aprendizagem continuou ocorrendo sempre que as exigências de qualidade deixaram de ser satisfeitas, até que alcançassem a qualidade de comunicação exigida. Estes resultados permitiram concluir pela validade do seletor proposto.
Agricultural production and distribution processes employ different technologies. They are used for data collection and management of resources and activities, among which Wireless Sensor Networks, Radiofrequency Identification and WiFi. These technologies have several limitations due to flaws in infrastructure and environmental variability. For example, data arrive at management systems late, compromising process efficiency. Multi-technology nodes can be a solution to obtain real-time data from the production and distribution processes, particularly if Internet of Things principles are present. Yet, for this solution to be efficient, a communication technology selector for field \"objects\" must be necessary, which must adapt to the environment in run time. Therefore, the goal is to propose and to assess this Selector functionality. This proposition was based on adaptive techniques, which offered an appropriate solution for learning processes by the selector, such as the Adaptive Decision Tree. The selector uses an Adaptive Decision Tree to select the communication technology. The selector functionalities, such as the appropriate technology selection for the moment and how they adapt changes in scenario, were evaluated by the simulation method. Evaluation results show that simulations made from a scenario corresponding to the initial phase of a corn crop did not show satisfactory, but the results evolved and met the quality requirements after some learning cycles. In a second step, new simulations were conducted, changing the scenario slowly to the harvest phase. The learning process continued to occur whenever the quality requirements were no longer met. These results showed the validity of the proposed selector.

There is a remarkable growth in the field of Information Communication Technology (ICT) in Developing Countries (DCs). Telecommunication is one of the areas where ICT is recording an ongoing rapid change. Mobile phones are becoming pervasive in daily scenario; and among the beneficiaries of this are farmers. Farmers are using mobile phones in executing their farming business and daily life. At the same time, Wireless Sensor Networks (WSNs) are also showing a result in developed part of our world. WSNs potential in sensing various environmental condition, their affordability and applicability motivated conducting of this master thesis. Therefore, the objective of conducting this master thesis is to investigate and identify how the use of mobile phones in conjunction with WSN enable farmers in Ethiopia monitor and control their farm field. We use firsthand qualitative data we gathered during our field work in Ethiopia to design our proposed prototype. Functional requirements and system design guideless are obtained from observation we make and interviews we carry out on irrigation based farmers around town of Meki in region of Oromia. We use our prototype to demonstrate and evaluate how irrigation based farmers benefit from existence of such system.

7 pp.
In this publication, we will make the case of what Precision Agriculture (PA) technologies can do to enhance the productivity of farming systems, with particular attention to the case of irrigated agriculture in the semi-arid Arizona. This guide is intended to aid growers to select the right technology when considering the need to acquire new, or upgrade existing equipment.

Context: Smart farming, agritech, is growing in popularity and is starting to develop rapidly with some already existing technology that is implemented in agriculture for both industrial and private use. Objectives: The goal of this thesis is to investigate the benefits and issues with implementing technology in agriculture, agritech. In this thesis the investigation and research is performed by conduction a literature study and an experiment. Realization: A prototype was created to monitor the soil moisture level and calculating the average soil moisture value, then water the plants when needed. This was then compared to a manually watered pot to investigate if agritech could reduce the water usage when maintaining plants. Results: The result of the experiment indicates that it is possible to improve the use of resources such as human labor, time spent on maintaining the plants and water usage. Conclusions: The conclusion of this thesis is with the help of agritech, human workers can spend more time on other tasks and maintain the technology implemented. Instead of observing the plants to see if they need watering and watering them manually. Water usage may also be minimized with the help of sensors that make sure the plants only get watered when needed by constantly checking the soil moisture level.

The success of Internet of Things solutions allowed the establishment of new applications such as smart hydroponic agriculture. One typical problem in such an application is the rapid degradation of the deployed sensors. Traditionally, this problem is resolved by frequent manual maintenance, which is considered to be ineffective and may harm the crops in the long run. The main purpose of this thesis was to propose a machine learning approach for automating the detection of sensor fault drifts. In addition, the solution’s operability was investigated in a cloud computing environment in terms of the response time. This thesis proposes a detection algorithm that utilizes RNN in predicting sensor drifts from time-series data streams. The detection algorithm was later named; Predictive Sliding Detection Window (PSDW) and consisted of both forecasting and classification models. Three different RNN algorithms, i.e., LSTM, CNN-LSTM, and GRU, were designed to predict sensor drifts using forecasting and classification techniques. The algorithms were compared against each other in terms of relevant accuracy metrics for forecasting and classification. The operability of the solution was investigated by developing a web server that hosted the PSDW algorithm on an AWS computing instance. The resulting forecasting and classification algorithms were able to make reasonably accurate predictions for this particular scenario. More specifically, the forecasting algorithms acquired relatively low RMSE values as ~0.6, while the classification algorithms obtained an average F1-score and accuracy of ~80% but with a high standard deviation. However, the response time was ~5700% slower during the simulation of the HTTP requests. The obtained results suggest the need for future investigations to improve the accuracy of the models and experiment with other computing paradigms for more reliable deployments.

TORRES, A. B. B. Fusão de dados multinível para sistemas de internet das coisas em agricultura inteligente. 2017. 71 f. Dissertação (Mestrado em Engenharia de Teleinformática)–Centro de Tecnologia, Universidade Federal do Ceará, Fortaleza, 2017.
Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-09T02:35:28Z No. of bitstreams: 1 2017_dis_abbtorres.pdf: 4603894 bytes, checksum: 67f76d807aebb885f45a8f8bfd33f83a (MD5)
Rejected by Marlene Sousa (mmarlene@ufc.br), reason: Prezado Andrei, Existe uma orientação para que normalizemos as dissertações e teses da UFC, em suas paginas pré-textuais e lista de referencias, pelas regras da ABNT. Por esse motivo, sugerimos consultar o modelo de template, para ajudá-lo nesta tarefa, disponível em: http://www.biblioteca.ufc.br/educacao-de-usuarios/templates/ Vamos agora as correções sempre de acordo com o template: 1. A ordem da hierarquia institucional é nome da instituição, nome do CENTRO, nome do DEPARTAMENTO e nome do PROGRAMA DE PÓS-GRADUAÇÃO (sem siglas). 2. A pesar de não ser obrigatório, sugerimos colocar data da defesa na folha de aprovação. 3. Na lista de referencias os subtítulos não ficam em negrito. Quando as correções forem feitas enviaremos o nada consta por e-mail. Att. Marlene Rocha mmarlene2ufc.br on 2017-09-11T14:03:36Z (GMT)
Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-11T15:23:18Z No. of bitstreams: 1 2017_dis_abbtorres.pdf: 4603863 bytes, checksum: a65fcc425e4da3674e800515d8401764 (MD5)
Rejected by Marlene Sousa (mmarlene@ufc.br), reason: Prezado Andrei, Falta ainda corrigir a ordem da hierarquia institucional que deve ser assim : UNIVERSIDADE FEDERAL DO CEARÁ, CENTRO DE TECNOLOGIA, DEPARTAMENTO DE ENGENHARIA DE TELEINFORMÁTICA, PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA DE TELEINFORMÁTICA. Não precisa colocar que é mestrado acadêmico na capa. on 2017-09-11T17:14:05Z (GMT)
Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-11T19:02:13Z No. of bitstreams: 0
Rejected by Marlene Sousa (mmarlene@ufc.br), reason: Renato, não veio o arquivo anexado. Marlene on 2017-09-12T10:58:09Z (GMT)
Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-12T13:28:01Z No. of bitstreams: 1 2017_dis_abbtorres.pdf: 5480153 bytes, checksum: 9d72dc6e54ed32cc921eafab5b2af34b (MD5)
Approved for entry into archive by Marlene Sousa (mmarlene@ufc.br) on 2017-09-12T14:15:21Z (GMT) No. of bitstreams: 1 2017_dis_abbtorres.pdf: 5480153 bytes, checksum: 9d72dc6e54ed32cc921eafab5b2af34b (MD5)
Made available in DSpace on 2017-09-12T14:15:21Z (GMT). No. of bitstreams: 1 2017_dis_abbtorres.pdf: 5480153 bytes, checksum: 9d72dc6e54ed32cc921eafab5b2af34b (MD5) Previous issue date: 2017-07-11
The usage of Wireless Sensor Networks (WSN) to detect and monitor phenomena isn’t a new concept, with studies dating back to 1980, but it has gained momentum with the expansion of Internet of Things (IoT), which aims to enable day to day objects to sense, identify and analyze our world. For IoT to be viable, it is necessary for the objects/sensors to be low-cost, and that implies a series of limitations: low battery, low processing and storage capabilities, low accuracy, etc. In this context, data fusion techniques can be used to mitigate some of these limitations and make the adoption of low-cost sensors viable. This dissertation proposes a data fusion architecture for IoT, improving sensor accuracy, detecting events/anomalies (such as sensor failure) and enabling automated decision making. As a case study, experimental cultures of precocious dwarf cashew and coconut trees were monitored.
A utilização de Redes de Sensores Sem Fio (RSSF) para detecção de fenômenos e monitoramento de ambientes não é um conceito novo, com estudos iniciados na década de 1980, mas ele tem ganhado força pela expansão da Internet das Coisas (Internet of Things - IoT), que trata de capacitar os objetos ao nosso redor de sensoriar, identificar e analisar o mundo. Para tornar a IoT viável em larga escala, é necessário que os objetos/sensores sejam de baixo custo, e isso implica uma série de limitações: bateria limitada, baixa capacidade processamento e armazenamento, baixa acurácia, dentre outros. Nesse contexto, técnicas de fusão de dados podem ser utilizadas para mitigar algumas das limitações citadas e viabilizar a adoção de sensores de baixo custo. A proposta desta dissertação é uma arquitetura de fusão de dados multinível para IoT para melhorar a acurácia dos sensores, detectar eventos/anomalias (como a falha de sensores) e possibilitar tomadas de decisões automatizadas. Como estudo de caso, foram realizados experimentos em conjunto com a Embrapa em um projeto de pesquisa de Agricultura de Precisão no monitoramento de cultivos experimentais de coco e de caju anão-precoce.

La prochaine évolution de l’agriculture est l’Agriculture 4.0. Dans ce domaine, les nouvelles technologies de l’Internet des Objets (IdO) et les systèmes contextuels sont utilisés pour améliorer les performances des activités agricoles. Un système contextuel est un système capable de réagir automatiquement et adéquatement en fonction du contexte. Le fait d’utiliser un tel système permet non seulement de réduire la charge de travail des agriculteurs, mais aussi d’améliorer la précision des activités agricoles. Cependant, leur emploi dans le monde rencontre deux obstacles spécifiques. Le premier obstacle est le besoin de mettre régulièrement à jour le système contextuel sans changer sa fonctionnalité. Ce besoin s’appuie sur le fait que l’agriculture est une activité saisonnière, avec un lieu de travail externe, ce qui implique plusieurs facteurs imprévisibles qui influent sur les aspects logiciels et matériels du système. Le deuxième obstacle est l’hétérogénéité de données générées à partir du système contextuel. Dans le domaine agricole, on trouve des capteurs variés observant des phénomènes variés et produisant des données également variées. Représenter ces données est un fait nécessaire pour l’interopérabilité des dispositifs à l’intérieur un système contextuel, ou pour l’interopérabilité de plusieurs systèmes contextuels différents à l’intérieur l’écosystème de l’IdO. Cette thèse propose trois contributions. La première est une architecture s’appuyant sur le principe de microservice. Cette architecture est une pile de services pour les systèmes contextuels, qui permet aux développeurs d’un système de se focaliser sur les objectifs des services plutôt que leurs aspects logiciels et matériels. La deuxième contribution est une ontologie, intitulé CASO, dédiée aux systèmes contextuels. Cette ontologie fournit un vocabulaire pour modéliser les données générées par le système contextuel. De plus, elle inclut un mécanisme pour créer des règles de raisonnement. La troisième contribution est un système d’aide à la décision (SAD) pour l’irrigation automatique, développé à partir d’IRRINOV® , une méthode d’irrigation manuelle. Il fait partie d’un système contextuel dédié à l’irrigation de l’équipe TSCF d’INRAE. Ce SAD est basé sur la pile de services pour les systèmes contextuels,et utilise l’ontologie IRRIG, une spécialisation de CASO dédiée à l’irrigation. Les trois contributions vont être appliquées dans un système contextuel d’irrigation déployé dans l’AgroTechnoPôle, situé à Montoldre, en France
The next evolution of agriculture is Agriculture 4.0. Agriculture 4.0 is about using technologies ofthe Internet of Things (IoT) and Context-Aware Systems (CASs) to increase the performance offarming activities. A CAS can react automatically and adequately to the environment based onits context. Applying CASs in agriculture can reduce farm labor and increase the precision offarming activities. However, it encounters two challenges specific to agriculture. The firstchallenge relies on the need to upgrade a CAS regularly with new computing devices orsoftware programs without changing its functionality. Indeed, natural factors, such as violentweather and wild animals, can damage the computing devices located on farmland. Moreover,after each farming season, farmers may need to upgrade their system with new computingdevices and software programs. The second challenge is the data heterogeneity generated froma CAS. In agriculture, various phenomena involve the need to have different sensor devices thatmake numerous types of measurements and produce heterogeneous data. Representing all ofthese heterogeneous data is necessary for the interoperability of different computing devices ina CAS or the interoperability between different CASs in the IoT ecosystem. This thesis proposesthree contributions. The first contribution addresses the first challenge. It is a new architecturebased on the microservice mindset that allows system developers to focus on the services’goals rather than the computing devices and software programs of a CAS. This newarchitecture is called the stack of services for CASs. The second contribution addresses thesecond challenge. It is a new ontology for CASs named CASO. The ontology provides avocabulary to model heterogeneous data generated from CASs and embodies a mechanism tomake rules for reasoning. The third contribution is to build a decision support system (DSS) forthe irrigation CAS in the research unit TSCF, INRAE. The design of the DSS relies on the stackof services for CASs. Moreover, the DSS uses a new ontology called IRRIG, a specialization ofCASO for irrigation. The DSS is an automation version of the manual irrigation methodIRRINOV®. All the guidelines for farmers in IRRINOV® are transformed into rules for reasoning.The contributions of this thesis are going to be applied to build a smart irrigation CAS deployedin AgroTechnoPôle, located in Montoldre, France

This master thesis is exploring Beekeepers usage of Internet of Things, or “Internet of Bees”. Since most of the prior contributions are focusing on data gathering, the approach to focus on the users needs is central to take next steps in the field of using IoT for Beekeeping. After the introduction a chapter with an overview of current research and commercial solutions are presented. This is followed by a quantitative study with 222 responds, answering what beekeepers like to know about their bees, what platforms used by end users and what the beekeeper as a user expects. An demo of an existing commercial system is set up in real conditions, describing how to mount and configure a demo. Communication, synchronization and presentation is described. A closed user interface and a public user interface are a part of the demonstration. Potential users of this technique are interviewed to gain better understanding of users opinion of the demo. This is followed by another demo using a free of charge app where sound analysis processed with AI is tested. This thesis explains what beekeepers as users of Internet of Things could gain added value to their beekeeping.

Die kontinuierliche Überwachung von Pflanzenparametern spielt eine wichtige Rolle in der Präzisionslandwirtschaft. Als in situ Monitoring-Systeme erscheinen drahtlose Sensornetzwerke (engl. Wireless Sensor Networks (WSNs)) geeignet, um den Zustand von Kulturpflanzen zu erfassen und diesen in stets aktuelle Parameterkarten zu transformieren. Derartige Karten können potenzielle wachstums- und ertragsmindernde Faktoren frühzeitig identifizieren und Entscheidungshilfen geben, die zu einer ortsdifferenzierten, zielgerichteten und nachhaltigen Bewirtschaftung landwirtschaftlicher Produktionsflächen beitragen. Die vorliegende kumulative Dissertation beschäftigt sich in diesem Zusammenhang mit der automatisierten und kosteneffizienten in situ Erfassung eines wichtigen Pflanzenparameters, dem sogenannten Blattflächenindex (engl. Leaf Area Index (LAI)). Mittels handelsüblicher WSN-Hardware wird zunächst ein kostengünstiger Sensor-Prototyp für eine passive, transmissionsbasierte LAI-Erfassung konzipiert und, begleitet durch Feldkampagnen, experimentell weiterentwickelt. Im Verlauf der Arbeit wird eine auf die spezielle Anwendung zugeschnittene Netzwerkarchitektur entworfen, die den Prototypen in ein ganzheitliches Langzeit-Monitoring-System überführt. Durch exemplarisch realisierte Deployments an zwei unterschiedlichen Standorten und den daraus erfassten empirischen Datensätzen wird das Potenzial drahtloser Sensornetzwerke für eine kontinuierliche und zeitlich hochauflösende LAI-Erfassung analysiert. Dabei werden effektive Methoden zur Prozessierung und Filterung von in situ Sensordaten entwickelt und untersucht, inwieweit diese die Qualität der abgeleiteten LAI-Schätzung verbessern. Ein Schwerpunkt der empirischen Potenzialanalyse liegt dabei auf der differenzierten Erfassung von sortenspezifischen und trockenstressbedingten Veränderungen. Weiterhin wird der Einfluss von Umwelt und Vegetation auf die Qualität drahtloser Verbindungen in landwirtschaftlichen WSN-Deployments betrachtet. Basierend auf dem empirischen Datensatz wird gezeigt, dass das Pflanzenwachstum die Qualität exemplarischer Verbindungen beeinträchtigt. Aus dieser Beobachtung wird ein Modell für ein signalstärkebasiertes Pflanzen-Monitoring abgeleitet und die generelle Machbarkeit dieses neuartigen Ansatzes untersucht.

碩士
中華科技大學
資訊服務與創新應用產業碩士專班
104
The climate change affect crops growth cycle and results in significant impact of the global economy. The agriculture production of Taiwan is expected to be suffered from the high temperature, drought, temperature difference between day and night, uneven rainfall intensity, the change of underground water level. This study is based on IoT technology to obtain instant, global, and long-term monitoring of environment and provide warning message even take proper actions automatically. We also try to build up a best cultivation parameters finding mechanism through the big data analysis technology. The analysis results can be utilized as real time advise which is corresponding to the environmental change in the field of corps growing.

碩士
國立雲林科技大學
創業管理碩士學位學程
103
Agriculture and Internet of Things have gained popularity in recent years. With advanced technology, people can process, store and transfer all kinds of information at an unprecedented rate. Internet of Things (IoT),which is the network of physical objects embedded with sensors, has become one of the hottest topics in many countries, among which Taiwan sees the rapid development of information technology. Taiwan is located in the subtropical and tropical regions with abundant rainfall, moderate climate and high mountains that give it a temperate climate. Suitable to grow different kinds of fruits, Taiwan lays its foundation on agriculture and therefore is well known for its agriculture technique. However, with high labor cost and aging agricultural population, agriculture has faced many difficulties. For example, when vising the farm during the internship, the author found that many farmers do not know how to take advantage of technology, which may lead to low efficiency in farm management. This research aims to investigate the use of IoT in agriculture and find out the most feasible IoT application in Taiwan agriculture industry. With reference to The Council of Agriculture under Executive Yuan, related news and questionnaires, this research identifies potential IoT agricultural problems, refers to successful examples on OnFarm, Semios, Cropx and Libelium websites for analysis and discussion and finally proposes an IoT-based solution for Taiwan's agriculture. Keywords: Agriculture, Farm Management, Internet of Things

碩士
國立成功大學
製造資訊與系統研究所
106
Due to the large area and difficult wiring of traditional farms, it is difficult to supply power to the farm. If the farm is divided into districts, further assisting farmers in farm management and mastering crop growth information can greatly reduce labor costs and increase production efficiency. In the past, users were unable to effectively understand the history of crops. If setting up a remote monitoring platform, provide users with information about the crop growth environment, history and other information to make the farm transparent and improve its management model. Therefore, this study proposes an automated information management system based on the Internet of Things (IOT) and fog computing architecture, which contains the following research and development projects: (1) building modules with sensors and motors . The area can be controlled in an environment that is not conducive to growth conditions, and introduces the structure of the atomization operation and implements atomization operations in the module to reduce the load on the web server. (2) An unmanned aerial vehicle (UAV) with a photographic function is introduced to capture an image of plant growth and record it to monitor the farm environment. (3) The power supply mode is based on the introduction of the solar energy system to provide power operation for the Wi-Fi modules in each block. (4) The information collected in each area will be stored in the cloud database by wireless transmission, allowing users to view the growth records of each area of the farm through the Internet and allow users to monitor in real time. This study uses Raspberry Pi series devices to achieve wireless network transmission, and establish a connection with the Server/Client architecture, using regional network features and Linux firewall features to prevent malicious intrusions. To achieve low cost, high efficiency and convenience.

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies
Since its rst appearance the Internet of Things has been subject to constant evolution, development and change. Now it has stepped out of its infancy with billions of devices embedded in the world wide web. However, IoT providers mostly de ne their own data formats and protocols and there is still a lack of a common standard that connects these devices in an interoperable manner. There are several organisations dedicated to developing common standards for IoT devices and research is focusing on de ning an e ective standard to be used by embedded devices. Unsurprisingly, IoT has also found its way into the spatial web and into environmental monitoring and sensing platforms connected over the web by wireless sensor networks are now a common way to monitor natural phenomena. This study compares three open Web Standards in the use case of SEnviro for Agriculture, a full stack IoT for monitoring vineyards. The interoperability potential of the OGC's Sensor Observation Service and SensorThings API are evaluated by integrating Web Standard implementations for each standard and contrasting their qualitative and quantitative traits. In a further step the Mozilla Corporation's Web Thing API was implemented and evaluated in an environmental monitoring and Smart Farming context. The results of the study show that the SensorThings API proves to be the most adequate Web Standard for SEnviro and IoT applications for environmental monitoring and Smart Farming in terms of interoperability. It outperforms the contesting Web Standards in terms of exibility and scalability, which strongly impacts on developer and user experience.

博士
國立臺灣大學
生物產業機電工程學研究所
105
Internet of Things (IoTs) is network architecture consisting of a number of key elements such as sensing, network and application layers. Devices can perform sensing, control and other activities, and can communicate with a gateway or other devices for data transmission through the internet. The main mission of the network layer is information transmission, routing and control. Application layer provides information processing, computing and other basic services to achieve the goal of the Internet of things with a variety of applications. Recently, the applications of IoTs mainly focus on smart home, smart industrial manufacturing and public construction of the smart city, and researchers and manufacturers have pay attention to the development of the applications. The application of the IoTs, however, should not be confined to these areas. In view of this, it is necessary to develop a total solution for different areas of research with the IoTs technology. In order to meet the requirements described above, in Chapter III, a wireless sensor network-based monitoring system with a dynamic convergecast tree algorithm for precision cultivation management in orchid greenhouses is present. The data delivery rate could be improved by using the proposed algorithm and the system could automatically monitor the environmental parameters of an orchid greenhouse. Moreover, the distributions of the environmental parameters could be reconstructed with the sensor data to find the hotspot in the greenhouse, and provide important monitoring information to the industry to improve greenhouse practices. Internet of things-based applications designed for smart grids are discussed in Chapter IV. In this chapter, an Internet of things-based grid-wide safety monitoring (SM) system for extra-high voltage (EHV) power grids is proposed. The proposed SM system includes three major parts: a front-end wireless sensor network consisting of EHV sensor modules, a backbone communication network comprising gateways, and a smart management service cloud for EHV power grids. To verify the functionalities of the proposed SM system, a number of experiments were conducted in an actual EHV environment. Both the presented cases of smart agriculture and smart grid are evaluated via computer simulation and real world tests. The experimental results show that the two proposed cases can provide a total solution in that area.

博士
國立臺灣大學
生物產業機電工程學研究所
105
Recently, Internet of things (IoT) technologies have been rapidly developed. IoTs create a new world which is transparent with faster speeds of information flows and innovation. IoTs are able to implement intelligent identification and information management, and they can be integrated to various applications. All industries try to employ IoT technologies to reduce labor costs, improve the quality and yield of products, and increase the value of their industries. For example, in recent years, agricultural issues have continuously gained attention from humans. All countries in the world are considering the development of agriculture, and wondering if food can be produced in more efficient and safe ways by putting their effort on improving agricultural food safety and enhancing the value of agricultural products. Smart agriculture that utilizes IoT technologies provides an excellent solution. This paper presents serval agricultural IoT applications in facility agriculture and pest management. The paper describes the solutions in accordance with the demand of each case and analyzes the benefits of using the IoT applications. In the applications of facility agriculture, this paper actually deployed an IoT-based monitoring system in an orchid greenhouse and plant factories. In the greenhouse, for example, this paper has successfully monitored the growth of orchids and analyzed the relations between the environment factors and the growth of orchid leaf areas. The analyzed results indicate that the growth of the areas would slow down in a highly humid environment, thereby influenced the blossom quality. And, the analyzed results provided by the IoT-based monitoring system can help greenhouse owners update their farming strategies. For plant factories, an IoT-based monitoring system was able to detect and ventilate local high temperature areas in plant factories. The analyzed results indicate that the fresh weights and sales of the Boston lettuce both increased while the proposed IoT-based monitoring system was used in the plant factories. For pest management, this paper has also actually deployed serval IoT-based monitoring systems in orchards and vegetable producing areas around Taiwan to monitor the population of different insect pests, including the oriental fruit fly (Bactrocera dorsalis) and tobacco cutworm (Spodoptera litura). The IoT-based monitoring system can monitor the oriental fruit fly or the tobacco cutworm in orchards or vegetable producing areas by using self-organizing maps to establish classification models. The experimental results show that the efficiency of the classification models was excellent, and the models can help the monitoring system identify whether a pest outbreak event or an error in the monitoring data occurs. Compared to traditional monitoring methods, the proposed IoT-based monitoring system can efficiently improve temporal and spatial resolutions of monitoring and reduce labor costs.

Nowadays, the saving of natural resources is increasingly a concern, and water scarcity is a fact that has been occurring in more areas of the globe. One of the main strategies used to counter this trend is the use of new technologies. In this topic the Internet of Things has been highlighted, these solutions are characterized by offering robustness and simplicity, while being low cost. In this dissertation was presented the study and development of an automatic irrigation control system for agricultural fields. The developed solution had a wireless sensors and actuators network, based on previous studies at the level of modules and communication protocols used, a mobile application for iOS that offers the user the capability of consulting not only the data collected in real time but also their history and also act in accordance with the data it analyses. In order to adapt the water management, Machine Learning algorithms were studied to predict the best time of day for water administration, of the studied algorithms (Decision Trees, Extreme Gradient Boosting (XGBoost), Random Forest, Neural Networks and Support Vectors Machines) the one that obtained the best results was XGBoost, presenting results of 87.73% of accuracy. Besides the ML solution, a script was also developed to calculate the amount of water needed to manage the fields under analysis. Through the implementation of the system it was possible to realize that the developed solution is effective and can achieve up to 60% of water savings.
Nos tempos que correm, a poupança de recursos naturais é cada vez mais uma preocupação, sendo a escassez de água um facto que se tem verificado em cada vez mais zonas do globo. Uma das principais estratégias utilizadas para contrariar esta tendência é o recurso a novas tecnologias. Neste tópico tem se destacado a Internet das Coisas, sendo estas caracterizadas por oferecerem robustez e simplicidade, sendo ao mesmo tempo de baixo custo. Nesta dissertação foi apresentado o estudo e desenvolvimento de um sistema de controlo automático para rega de campos agrícolas. A solução desenvolvida contou com uma rede de sensores e atuadores wireless, tendo por base estudos anteriores ao nível dos módulos e protocolos de comunicação utilizados, uma aplicação movel para iOS que oferece ao utilizador a possibilidade de consultar os dados coletados em tempo real e o histórico dos mesmos e ainda atuar em conformidade. De forma a adequar a administração de água, foram estudados algoritmos de Machine Learning que prevejam a melhor hora do dia para a administração de água, dos algoritmos estudados (Decision Trees, Extreme Gradient Boosting (XGBoost), Random Forest, Redes Neuronais e Support Vectors Machines) o que obteve melhores resultados foi o XGBoost, apresentando resultados de precisão de 87.73%. Para alem da solução de ML foi também desenvolvido um script que calcule a quantidade de água necessária a administrar ao terreno em analise. Através da implementação do sistema foi possível perceber que a solução desenvolvida é eficaz, conseguindo atingir valores de 60% de poupança de água.