Search

Forest fires are the main cause of desertification, and they have a disastrous impact on agricultural and forest ecosystems. Modern fire detection and warning systems rely on several techniques: satellite monitoring, sensor networks, image processing, data fusion, etc. Recently, Artificial Intelligence (AI) algorithms have been applied to fire recognition systems, enhancing their efficiency and reliability. However, these devices usually need constant data transmission along with a proper amount of computing power, entailing high costs and energy consumption. This paper presents the prototype of a Video Surveillance Unit (VSU) for recognising and signalling the presence of forest fires by exploiting two embedded Machine Learning (ML) algorithms running on a low power device. The ML models take audio samples and images as their respective inputs, allowing for timely fire detection. The main result is that while the performances of the two models are comparable when they work independently, their joint usage according to the proposed methodology provides a higher accuracy, precision, recall and F 1 score ( 96.15 %, 92.30 %, 100.00 %, and 96.00 %, respectively). Eventually, each event is remotely signalled by making use of the Long Range Wide Area Network (LoRaWAN) protocol to ensure that the personnel in charge are able to operate promptly. [ABSTRACT FROM AUTHOR]

Low Power Wide Area Networks (LPWANs) play crucial roles in the implementation of low-power and low-cost wide area distributed systems. Currently, two enabling technologies are the main competitors within the connectivity field for the Internet of Things (IoT), primarily because of their scalability, wide range and low power features: Long Range Wide Area Network (LoRaWAN) and Narrowband IoT (NB-IoT). In this paper, a brand new network architecture is presented, which combines both aforementioned technologies. Such a network accounts for sensor nodes, multi-protocol gateways, an a cloud infrastructure. Sensor nodes may be alternatively provided with LoRaWAN or NB-IoT. Multi-protocol gateways can receive and demodulate LoRaWAN packets and upload them to the cloud via the Message Queue Telemetry Transport (MQTT) protocol over NB-IoT. The cloud is transparent with respect to the transmission technology, meaning that data are acquired and stored regardless of the exploited technique (i.e., LoRaWAN or NB-IoT). Indeed, sensor nodes using NB-IoT can send data to the cloud and can directly communicate with other NB-IoT nodes setting up a fog computing paradigm on peer-to-peer subnetworks. This approach may be crucial for the development of complex IoT infrastructures while providing high flexibility. [ABSTRACT FROM AUTHOR]

The narrowband Internet-of-Things (NB-IoT) communication standard is gaining momentum within the big picture of the Internet-of-Things (IoT) owing to its capabilities of ensuring pervasive and wide coverage while limiting power consumption. Therefore, it turns out to be a valuable enabling technology within a considerable number of applications. Apart from traditional remote monitoring and data acquisition purposes where comparable Low Power Wide Area Network (LPWAN) facilities have ruled for years, NB-IoT can potentially carve out space within specific alcoves in which low latency, low power, high data-rates and ubiquitous coverage are fundamentals requirements. Long term asset tracking definitely falls within such niches, and in particular NB-IoT can become a valuable alternative to be exploited by both replacing the conventional Global Position System (GPS) system, or supporting it. To this end, this paper proposes an innovative tracking system prototype for asset shipping which relies on two enabling technologies: GPS and NB-IoT. While position transmission is always put into effect via NB-IoT, it can be fetched by resorting to both GPS (like a standard tracker) or NB-IoT (thus establishing a GPS-less method). As a result, two localization techniques are arranged: the former one is preciser but energy hungrier, while the latter one is coarser but more low power. Such working principles were successfully tested on the field by means of two road tests in as much itineraries. Tests results are in agreement with the expectations underlying the two working principles since the finer one provides a more accurate tracking. In addition, a consumption analysis was also performed aiming at assessing the prototype lifetime. Finally, tests pursuing the assessment of the tracking error were carried out underling the fact that it strongly depends on the geographic deployment of NB-IoT towers. [ABSTRACT FROM AUTHOR]

Long Range Wide Area Network (LoRaWAN) has rapidly become one of the key enabling technologies for the development of Internet of Things (IoT) architectures. A wide range of different solutions relying on this communication technology can be found in the literature: nevertheless, the most part of these architectures focus on single task systems. Conversely, the aim of this paper is to present the architecture of a LoRaWAN infrastructure gathering under the same network different typologies of services within one of the most significant sub-systems of the Smart City ecosystem (i.e., the Smart Waste Management). The proposed architecture exploits the whole range of different LoRaWAN classes, integrating nodes of growing complexity according to the different functions. The lowest level of this architecture is occupied by smart bins that simply collect data about their status. Moving on to upper levels, smart drop-off containers allow the interaction with users as well as the implementation of asynchronous downlink queries. At the top level, Video Surveillance Units (VSUs) are provided with machine learning capabilities for the detection of the presence of fire nearby bins or drop-off containers, thus fully implementing the Edge Computing paradigm. The proposed network infrastructure and its subsystems have been tested in a laboratory and in the field. This study has enhanced the readiness level of the proposed technology to Technology Readiness Level (TRL) 3. [ABSTRACT FROM AUTHOR]

The emergence of Internet of Things (IoT) architectures and applications has been the driver for a rapid growth in wireless technologies for the Machine-to-Machine domain. In this context, a crucial role is being played by the so-called Low Power Wide Area Networks (LPWANs), a bunch of transmission technologies developed to satisfy three main system requirements: low cost, wide transmission range, and low power consumption. This last requirement is especially crucial as IoT infrastructures should operate for long periods on limited quantities of energy: to cope with this limitation, energy harvesting is being applied every day more frequently, and several different techniques are being tested for LPWAN systems. The aim of this survey paper is to provide a detailed overview of the the existing LPWAN systems relying on energy harvesting for their powering. In this context, the different LPWAN technologies and protocols will be discussed and, for each technology, the applied energy harvesting techniques will be described as well as the architecture of the power management units when present. [ABSTRACT FROM AUTHOR]

In this paper the authors discuss the realization of a Long Range Wide Area Network (LoRaWAN) network infrastructure to be employed for monitoring activities within the marine environment. In particular, transmission ranges as well as the assessment of parameters like Signal to Noise Ratio (SNR) and Received Signal Strength Indicator (RSSI) are analyzed in the specific context of an aquaculture industrial plant, setting up a transmission channel from an offshore monitoring structure provided with a LoRaWAN transmitter, to an ashore receiving device composed of two LoRaWAN Gateways. A theoretical analysis about the feasibility of the transmission is provided. The performances of the system are then measured with different network parameters (in particular the Spreading Factor—SF) as well as with two different heights for the transmitting antenna. Test results prove that efficient data transmission can be achieved at a distance of 8.33 km even using worst case network settings: this suggests the effectiveness of the system even in harsher environmental conditions, thus entailing a lower quality of the transmission channel, or for larger transmission ranges. [ABSTRACT FROM AUTHOR]