Precision agriculture is a rapidly developing field aimed at addressing current concerns about agricultural sustainability. Machine learning is the cutting edge technology underpinning precision agriculture, enabling the development of advanced disease detection and classification methods. This paper presents a review of the application of machine learning and deep learning techniques in precision agriculture, specifically for detecting and classifying plant diseases. We propose a novel classification scheme that categorizes all relevant works in the associated classes. We separate the studies into two main categories depending on the methodology that they use (i.e., classification or object detection). In addition, we present the available datasets for plant disease detection and classification. Finally, we perform an extensive computational study on five state-of-the-art object detection algorithms on PlantDoc dataset to detect diseases present on the leaves, and eighteen state-of-the-art classification algorithms on PlantDoc dataset to predict whether or not there is a disease in a leaf. Computational results show that object detection accuracy is high with YOLOv5. For the image classification task, the networks ResNet50 and MobileNetv2 have the most optimal trade-off on accuracy and training time.

Agriculture plays a critical role in society, providing sustenance, contributing to economic growth, and addressing global hunger and malnutrition challenges. However, the environmental impact of agriculture, including water consumption, greenhouse gas emissions, and soil pollution, poses significant challenges. The advent of agriculture revolution 4.0, characterized by automated and data-driven smart farming, offers opportunities to enhance sustainability and climate resilience. Information and communication technologies (ICT), particularly Next Generation Internet of Things (NG-IoT), coupled with remote sensing, robotics, and artificial intelligence (AI), facilitate data-driven decision-making and optimization of agricultural activities. This paper reviews emerging ICT technologies in agriculture to provide a comprehensive understanding of the challenges and opportunities in achieving sustainable agriculture through these technologies. Furthermore, we emphasize the significance of human-centered systems and explainable AI for achieving sustainability in agriculture, highlighting the essential role of user-centric design and transparent decision-making processes in shaping the future of smart farming. Finally, we present real projects in Greece that utilize many of the aforementioned technologies, showcasing their outstanding performance in the field of smart agriculture and providing future directions towards incorporating human involvement, enhancing reliability, and explainability.

Long range wide area networks (LoRaWANs) have recently received intense scientific, research, and industrial interest. LoRaWANs play a pivotal role in Internet of Things (IoT) applications due to their capability to offer large coverage without sacrificing the energy efficiency and, thus the battery life, of end-devices. Most published contributions assume that LoRaWAN gateways (GWs) are plugged into the energy grid; thus, neglecting the network lifetime constraint due to power storage limitations. However, there are several verticals, including precision agriculture, forest protection, and others, in which it is difficult or even impossible to connect the GW to the power grid or to perform battery replacement at the end-devices. Consequently, maximizing the networks’ energy efficiency is expected to have a crucial impact on maximizing the network lifetime. Motivated by this, as well as the observation that the overall LoRaWAN network energy efficiency is significantly affected by the selected communication protocol, in this paper, we identify and discuss critical aspects and research challenges involved in the design of a LoRaWAN communication protocol, under an energy efficiency perspective. Building upon our findings, research directions towards a novel GreenLoRaWAN communication protocol are given, focusing on achieving energy efficiency, robustness, and scalability.

In opportunistic networks (OppNets), routing and data forwarding among mobile devices are facilitated by relays or next‐hop forwarders. To guarantee end‐to‐end data delivery it is important to provide participation. However, in sparsely connected OppNets, it is extremely challenging to monitor the behaviour of the relays and identify selfish/malicious relays cooperating with each other in order to forge routing information or drop useful data. Cooperation enforcement schemes are seen as a lightweight alternative to conventional secure forwarding techniques that involve cryptographically signed certificate exchanges, providing a ‘softer’ security layer to protect basic networking operations. In general, cooperation enforcement schemes fall into two broad categories: trust establishment via a reputation system and pricing or credit‐based schemes. This study offers a comprehensive survey of representative cooperation enforcement schemes that exploit a reputation system. The authors analyse their distinct features, identify and discuss critical challenges that should be efficiently addressed when designing such mechanisms, indicating at the same time potential solutions and provide an informative table to display the authors’ findings. From this analysis, they examine issues and concerns surrounding the field of cooperation enforcement in OppNets, and provide guidelines and directions for future researchers.