Cloud computing has recently gained widespread attention owing to its use in applications involving the Internet of Things (IoT). However, the transmission of massive volumes of data to a cloud server often results in overhead. Fog computing has emerged as a viable solution to address this issue. This study implements an Artificial Intelligence of Things (AIoT) system based on fog computing on a smart farm. Three experiments are conducted to evaluate the performance of the AIoT system. First, network traffic volumes between systems employing and not employing fog computing are compared. Second, the performance of the communication protocols—hypertext transport protocol (HTTP), message queuing telemetry transport protocol (MQTT), and constrained application protocol (CoAP)—commonly used in IoT applications is assessed. Finally, a convolutional neural network-based algorithm is introduced to determine the maturity level of coffee tree images. Experimental data are collected over ten days from a coffee tree farm in the Republic of Korea. Notably, the fog computing system demonstrates a 26% reduction in the cumulative data volume compared with a non-fog system. MQTT exhibits stable results in terms of the data volume and loss rate. Additionally, the maturity level determination algorithm performed on coffee fruits provides reliable results.

Wireless body area networks (WBANs) are an important application in wireless sensor networks (WSNs). Specifically, in healthcare monitoring systems, it is important to screen the patient’s biometric signals. For example, the elderlies’ vital signs, such as ECG (Electrocardiogram), blood pressure, heart rate, and blood glucose, can be used as measures of their well-being and are all critically important for remote elderly care in tracking their physical and cognitive capabilities. Therefore, WBANs require higher energy efficiency and data transmission. This paper proposes a cluster-based routing protocol which is suitable for WBANs while analyzing energy efficiency issue in data transmission. Considering the importance of sensor nodes in a specific environment for improving the network’s lifetime, the protocol based on the LEACH (low energy adaptive clustering hierarchy) algorithm is proposed. Due to its avoidance of long-distance transmission, the clustering technique is an efficient algorithm for prolonging the lifetimes of sensor networks. Therefore, this paper suggests an enhanced LEACH-dual fuzzy logic (ELEACH-DFL) protocol based-on clustering for CH (cluster head) selection and cluster configuration in wireless sensor networks. The simulation and analysis results address that the enhanced algorithm reduces the energy consumption effectively and extends the lifespan of the entire network. For wired sensors, attaching sensors to the user may cause problems and inconvenience of mobility. This leads to the use of wireless sensors to proceed with body sensors, which should consider the problem of battery efficiency, which concerns the configuration of wireless sensors. The LEACH protocol is energy efficient until the first node dead is generated. However, there is a sharp drop in energy efficiency after that. The ELEACH-DFL protocol has the advantage of maintaining energy efficiency even after the first node dead is generated, with the utmost consideration being given to stability in consideration of cluster selection and cluster head selection. In a field of 50 × 50, the FND efficiency improvement rate of ELEACH-DFL versus LEACH protocol is approximately 32%. In addition, in a field of 50 × 150, the FND efficiency improvement rate of ELEACH-DFL versus LEACH protocol is approximately 159%.