Smart agriculture technologies are effective instruments for increasing farm sustainability and production. They generate many spatial, temporal, and time-series data streams that, when analysed, can reveal several issues on farm productivity and efficiency. In this context, the detection of anomalies can help in the identification of observations that deviate from the norm. This paper proposes an adaptation of an ensemble anomaly detector called enhanced locally selective combination in parallel outlier ensembles (ELSCP). On this basis, we define an unsupervised data-driven methodology for smart-farming temporal data that is applied in two case studies. The first considers harvest data including combine-harvester Global Positioning System (GPS) traces. The second is dedicated to crop data where we study the link between crop state (damaged or not) and detected anomalies. Our experiments show that our methodology achieved interesting performance with Area Under the Curve of Precision-Recall (AUCPR) score of 0.972 in the combine-harvester dataset, which is $58.7\%$ better than that of the second-best approach. In the crop dataset, our analysis showed that $30\%$ of the detected anomalies could be directly linked to crop damage. Therefore, anomaly detection could be integrated in the decision process of farm operators to improve harvesting efficiency and crop health.

This paper proposes a three-computing-layer architecture consisting of Edge, Fog, and Cloud for remote health vital signs monitoring. The novelty of this architecture is in using the Narrow-Band IoT (NB-IoT) for communicating with a large number of devices and covering large areas with minimum power consumption. Additionally, the architecture reduces the communication delay as the edge layer serves the health terminal devices with initial decisions and prioritizes data transmission for minimizing congestion on base stations. The paper also investigates different authentication protocols for improving security while maintaining low computation and transmission time. For data analysis, different machine learning algorithms, such as decision tree, support vector machines, and logistic regression, are used on the three layers. The proposed architecture is evaluated using CloudSim, iFogSim, and ns3-NB-IoT on real data consisting of medical vital signs. The results show that the proposed architecture reduces the NB-IoT delay by 59.9%, the execution time by an average of 38.5%, and authentication time by 35.1% for a large number of devices. This paper concludes that the NB-IoT combined with edge, fog, and cloud computing can support efficient remote health monitoring for large devices and large areas.