Special Issue on The Big Data Era in IoT-enabled Smart Farming: Re-defining Systems, Tools, and Techniques
• 大类 : 工程技术 - 3区
• 小类 : 计算机：硬件 - 3区
• 小类 : 计算机：信息系统 - 3区
• 小类 : 工程：电子与电气 - 3区
• 小类 : 电信学 - 3区
The continuous generation of data from multiple sources has created numerous opportunities in different domains including agriculture. However, the state of the art in Smart Farming should be redefined and revisited since new technologies and tools are coming in the agriculture domain bringing novel and innovative paths for improving the resilience and the efficiency of agriculture. Smart Farming has started to be materialized and not being simply a vague futuristic concept, as different fields such as image processing and machine learning have found a prosperous area of application. Apart from the technical aspects that Smart Farming presents, it also affects the agricultural sector beyond the conventional farming activities, influencing a series of dependent industries, such as food supply chains, weather and climate change, natural resources management and environmental impact.
New and various technologies have invaded the agricultural sector as they can offer new and unprecedented opportunities. Smart Farming uses a combination of technological advances, such as sensors, drones, variable-rate application machinery, satellite navigation and positioning technology, and the Internet of Things (IoT), among others. All the aforementioned technologies produce a massive amount of data capable of changing the current status of the agriculture sector, but a series of effective actions have to be developed and established for their efficient exploitation.
The Big Data era has arrived for the agriculture sector reflecting its changes to a numerous of research fields. The incorporation and the usage of Geographic Information System (GIS) in the agriculture sector takes place for at least a decade as well as the adoption of sensors for monitoring reasons. Furthermore, driven by advanced GIS technologies, emerging image processing techniques adopt neural networks and deep learning approaches for providing new areas of application in the field of computer vision. Tasks such as crop identification and weed discrimination have become easier than ever thanks to the state-of-the-art classification algorithms. Apart from the advantages image processing techniques offer in the field of agriculture, other related areas have significantly benefited as well. Land mapping, insurance of animal feed quality, weather and climate change studies, grassland identification and earth observation are some of the areas where image processing techniques and algorithms have been successfully applied.
The farm industry and Smart Farming expand from the strict limits of the farm location and affect a series of related fields, such as supply chain management, food availability, biodiversity, farmers'decision making and insurance, environmental studies and various Earth sciences among others. All of the aforementioned fields have significant benefits when they follow a data-driven approach under the condition that the used systems, tools and techniques that will be used have been designed to handle the volume and foremost the variety of the data.
Often, smart farming systems are running on unmonitored areas, due to which any attempted or successful breaches go unreported. Worse, since this sector is traditionally not cybersecurity aware, security and privacy by design is not incorporated into the solution requirements. For example, security attacks are feasible by gaining access to irrigation control systems of either a plant or a farm. In the most cases, IoT devices and systems can be manipulated and personal data can be disclosed without the farmer knowing. Even worse, adversaries can gain access to other connected third-party systems, e.g., energy, administration and irrigation systems.
This Special Issue seeks to make an in-depth, critical contribution to this evolving field of agriculture in the era of Big Data. We therefore aim to bring together the state-of-the-art research contributions towards providing new insights in the application and benefits of the emerging methods and technologies in the Big Data-driven agriculture sector. The topics that can be addressed include (but are not limited to) the following ones.
Cloud- and edge-based systems in smart farming.
Management of heterogeneous Big Data in smart farming.
Crop models and decision support systems in smart farming.
Study of man-machine dialogue systems.
Data-driven methods for anomaly detection, diagnosis, and prognosis.
Role of Big Data in sustainable agriculture.
Big data innovation in sustainable agriculture.
Environmental Big Data integration.
Smart Farming and its application in Big Data processing.
Big data in agricultural disaster management.
Cyber threats and anomaly detection in smart farming.
Data privacy preserving systems in smart farming.
Deep packet inspection in security systems for Smart Farming applications.
IoT tools and techniques for sustainable agriculture.
Emerging tools for precision agriculture.
Big data analysis tools and machine learning techniques in Smart Farming tools.
Big data online stream processing for precision agriculture and Smart Farming
Machine learning applications in improving Key Performance Indicators (KPIs) in Smart Farming.
Statistical analysis and modeling in Smart Farming applications.
Geospatial analysis in Smart Farming applications.
Advanced image processing techniques and applications in the agricultural domain.
Spectral matching tools in Smart Farming.
Intrusion detection tools.
Security Information and Event Management (SIEM) tools for smart farming monitoring.
Modern GIS and remote sensing techniques in agriculture.
Classification and change detection of cultivated land.
Data mining and statistical issues in precision agriculture.
Intelligent computational techniques in precision agriculture.
Knowledge discovery in agriculture databases.
Cloud-enabled techniques and in-the-field integration for sustainable agriculture.
Network-based analysis in Smart Farming.
Trust-enabling techniques and methods.
Blockchain techniques for ensuring trust amongst IoT devices in Smart Farming.
Network forensics techniques for Smart Farming applications.