To reach the goal of sustainable agriculture, smart farming is taking advantage of the Unmanned Aerial Vehicles (UAVs) and Internet of Things (IoT) paradigm. These smart farms are designed to be run by interconnected devices and vehicles. Some enormous potentials can be achieved by the integration of different IoT technologies to achieve automated operations with minimum supervision. This paper outlines some major applications of IoT and UAV in smart farming, explores the communication technologies, network functionalities and connectivity requirements for Smart farming. The connectivity limitations of smart agriculture and it’s solutions are analysed with two case studies. In case study-1, we propose and evaluate meshed Long Range Wide Area Network (LoRaWAN) gateways to address connectivity limitations of Smart Farming. While in case study-2, we explore satellite communication systems to provide connectivity to smart farms in remote areas of Australia. Finally, we conclude the paper by identifying future research challenges on this topic and outlining directions to address those challenges.
This paper explores the potential of machine learning algorithms for weed and crop classification from UAV images. The identification of weeds in crops is a challenging task that has been addressed through orthomosaicing of images, feature extraction and labelling of images to train machine learning algorithms. In this paper, the performances of several machine learning algorithms, random forest (RF), support vector machine (SVM) and k-nearest neighbours (KNN), are analysed to detect weeds using UAV images collected from a chilli crop field located in Australia. The evaluation metrics used in the comparison of performance were accuracy, precision, recall, false positive rate and kappa coefficient. MATLAB is used for simulating the machine learning algorithms; and the achieved weed detection accuracies are 96% using RF, using SVM and using KNN. Based on this study, RF and SVM algorithms are efficient and practical to use, and can be implemented easily for detecting weed from UAV images.
Laboratory studies have suggested that the preferred cadence of walking is ∼120 steps/min, and the vertical acceleration of the head exhibits a dominant peak at this step frequency (2 Hz). These studies have been limited to short periods of walking along a predetermined path or on a treadmill, and whether such a highly tuned frequency of movement can be generalized to all forms of locomotion in a natural setting is unknown. The aim of this study was to determine whether humans exhibit a preferred cadence during extended periods of uninhibited locomotor activity and whether this step frequency is consistent with that observed in laboratory studies. Head linear acceleration was measured over a 10-h period in 20 subjects during the course of a day, which encompassed a broad range of locomotor (walking, running, cycling) and nonlocomotor (working at a desk, driving a car, riding a bus or subway) activities. Here we show a highly tuned resonant frequency of human locomotion at 2 Hz (SD 0.13) with no evidence of correlation with gender, age, height, weight, or body mass index. This frequency did not differ significantly from the preferred step frequency observed in the seminal laboratory study of Murray et al. (Murray MP, Drought AB, and Kory RC. J Bone Joint Surg 46A: 335–360, 1964). [1.95 Hz (SD 0.19)]. On the basis of the frequency characteristics of otolith-spinal reflexes, which drive lower body movement via the lateral vestibulospinal tract, and otolith-mediated collic and ocular reflexes that maintain gaze when walking, we speculate that this spontaneous tempo of locomotion represents some form of central “resonant frequency” of human movement.