Modern CNNs for IoT Based Farms
This work addresses the need for efficient deep learning tools in agriculture to handle massive IoT data, but it is incremental as it focuses on review and taxonomy rather than new methods.
The paper tackles the challenge of selecting and applying modern Convolutional Neural Networks (CNNs) for IoT-based agricultural data analysis by proposing a classification taxonomy and reviewing state-of-the-art architectures, resulting in a benchmarking guide for end-users and developers.
Recent introduction of ICT in agriculture has brought a number of changes in the way farming is done. This means use of Internet of Things(IoT), Cloud Computing(CC), Big Data (BD) and automation to gain better control over the process of farming. As the use of these technologies in farms has grown exponentially with massive data production, there is need to develop and use state-of-the-art tools in order to gain more insight from the data within reasonable time. In this paper, we present an initial understanding of Convolutional Neural Network (CNN), the recent architectures of state-of-the-art CNN and their underlying complexities. Then we propose a classification taxonomy tailored for agricultural application of CNN. Finally, we present a comprehensive review of research dedicated to applications of state-of-the-art CNNs in agricultural production systems. Our contribution is in two-fold. First, for end users of agricultural deep learning tools, our benchmarking finding can serve as a guide to selecting appropriate architecture to use. Second, for agricultural software developers of deep learning tools, our in-depth analysis explains the state-of-the-art CNN complexities and points out possible future directions to further optimize the running performance.