Lack of proper real-world data is a fundamental issue of deployed edge AI systems, which can lead to inaccurate AI model performance and, eventually, to system failures. Incremental learning (IL), in which the model is retrained on newly incoming data, can be used to overcome this issue. This study proposes a novel comprehensive self-supervised IL framework for resource-constrained image analysis applications. It focuses on insect segmentation and counting, fundamental operations for edge Internet of Things (IoT) devices deployed in pest control applications. The framework distributes actions between edge nodes, relying on low-power microcontrollers (MCU), and an edge server, implemented on a more powerful processor device, such as a Raspberry Pi. Segmentation and counting tasks are performed on edge nodes using a lightweight deep-learning (DL) model, while the edge server autonomously handles image reconstruction, mask generation, and pseudo labeling to incrementally retrain the AI model. This architectural concept eliminates the need for continuous manual labeling and enables continuous retraining on the edge without transferring large amounts of data to the cloud. Through a series of experiments, we demonstrate accuracy comparable to the manual annotation of images by humans, along with approximately a 10% improvement in segmentation and a threefold reduction in counting error over the base model. Additionally, the results reveal low retraining time (363.3 s) and power consumption (1.2 A at 5.1 V) on an embedded edge server, demonstrating that the framework is extremely suitable for agricultural setups lacking a fixed power supply or network connection, especially given that retraining is only needed occasionally.

The LoRa technology is becoming a matter of great interest in the research field of the Internet of Things (IoT). Due to the versatility of its technical characteristics, the range of its functionality may be calibrated. However, while many existing LoRa testbed schemes attempt to embrace the low-cost, low-power characteristics of the radio technology, many fail to recognize the need for scalability and easiness for the purposes of IoT research developments. In this demo paper, an open-source LoRaWAN emulator testbed is introduced and its main components and functionalities are briefly explained.

In this poster paper, we present a simulator for Time-Slotted (TS) LoRa networks for the Industrial Internet of Things (IIoT). The purpose of the simulator is to assess the performance under different conditions that cannot be easily assessed by prototypes which usually consist of limited number of devices. It allows the user to enter in different parameters such as the number of nodes, the simulation time, and the packet size. The simulator implements several functionalities such as registration, data transmissions in slots, desynchronizations due to clock drift, and a path-loss model. Detailed statistics are generated such as the number of packets lost, the energy consumption, and the average registration time. Its functionality is validated using a small-scale real-world experiment that shows similar results.

A train-arrival notification system's goal is to keep safe the personnel working on remotely located railroad when a train is approaching. This demo paper provides technical insights of the open hardware and software developments of this system which scientific merit is presented in [1]. Its main components, circuitry and design are discussed with a main focus on the radio communication parts.

This paper presents a portable, inexpensive, wireless and long range train arrival notification system for railway safety applications. The purpose of the system is to notify workers servicing the rails about the arrival of a train in both directions of a railway in order to avoid accidents. The system consists of several components: the train coordinates system, the portable station component, the worker's wearable, and an Android application. A description of each of the components of the system is given focus on the communication mechanisms between those components. The system has been deployed in an experimental environment in Kazakhstan and the first experiments showed a communication range of several kilometers as well as low repeated number of packet losses. Moreover, the proposed protocol for the wearables exhibited an over 99.5% packet reception ratio (PRR) for scenarios without the presence of major obstacles.

Due to the radio duty cycle restrictions in the sub- GHz unlicensed spectrum imposed in many regions, the downlink resources of the gateways in LoRaWAN are depleted fast even in the presence of moderate uplink traffic. To tackle the high demand for downlink traffic, additional gateways - from a pool of available positions - can be deployed. Not all gateways can initially be activated because of the extra operating costs that this action would cause. On the contrary, this paper studies the problem of dynamically activating the minimum estimated number of gateways in order to adapt the network to the traffic demands, and thus, improve the network reliability and energy consumption. The approach is based on theoretical foundations of downlink traffic as well as on empirical results and simple heuristics to select the gateway positions to be dynamically activated without taking into account the positions of the end-devices. Simulation results show that the proposed methodology in combination with the proposed heuristics exhibit a packet delivery ratio of over 90 % even with a single retransmission. The average energy consumption decreases considerably as well. Finally, the proposed approach presents similar results with an existing approach which, however, considers the positions of the end-devices as known.

This paper examines the problem of supporting actuators in a LoRaWAN network. It proposes a novel autonomous mechanism to allow one-to-one and one-to-many direct communication between different nodes of the same network for actuating purposes. The proposed scheme, called ActLoRa, uses a synchronized subnetwork which coexists with LoRaWAN while the end-devices can still register to the same network following the typical over-the-air activation process consisting of a joinrequest and a join-accept message. ActLoRa is evaluated using simulations and testbed experiments. The simulation results show that the performance of the synchronized part of the network is not considerably affected even when the Aloha-part consists of many nodes. The experiments are used to show the feasibility of the approach through the development of a proof-of-concept.

Effective insect pest monitoring is a vital component of Integrated Pest Management (IPM) strategies. It helps to support crop productivity while minimising the need for plant protection products. In recent years, many researchers have considered the integration of intelligence into such systems in the context of the Smart Agriculture research agenda. This paper describes the development of a smart pest monitoring system, developed in accordance with specific requirements associated with the agricultural sector. The proposed system is a low-cost smart insect trap, for use in orchards, that detects specific insect species that are detrimental to fruit quality. The system helps to identify the invasive insect, Brown Marmorated Stink Bug (BMSB) or Halyomorpha halys (HH) using a Microcontroller Unit-based edge device comprising of an Internet of Things enabled, resource-constrained image acquisition and processing system. It is used to execute our proposed lightweight image analysis algorithm and Convolutional Neural Network (CNN) model for insect detection and classification, respectively. The prototype device is currently deployed in an orchard in Italy. The preliminary experimental results show over 70 percent of accuracy in BMSB classification on our custom-built dataset, demonstrating the proposed system feasibility and effectiveness in monitoring this invasive insect species.

LoRaWAN is an upcoming Low Power Wide Area Network (LPWAN) technology for Internet of Things implementations in various application domains. Despite its various advantages, LoRaWAN employs an Aloha-based MAC, which in terms of performance cannot guarantee high packet delivery ratio and low latency. To overcome this issue, we propose a time-slotted scheme, called TS-VP-LoRa, which supports multiple transmission times and packet sizes at the same time. In TS-VP-LoRa, scheduling is coordinated by the LoRa gateway, broadcasting beacon frames periodically for the synchronization of LoRa end-devices. A channel hopping mechanism is also proposed in order to minimize the occurrence of collisions and to evenly split the transmission load among all channels. TS-VP-LoRa is evaluated and compared to three other MAC-layer schemes in single gateway simulation scenarios with up to 500 nodes. The proposed scheme has proven to achieve low latency with high packet delivery ratios, significantly minimize collisions and maintain a relatively low energy consumption despite the scaling of the LoRa network.

This paper presents a long range wide area network (LoRaWAN) testbed for environmental monitoring of artefacts within a museum storage facility. The goal is to identify the optimum feasible wireless technology for this application by studying eight different wireless technologies. A testbed network was deployed inside a 5600 m2concrete building to validate the performance of the candidate wireless technologies by way of measurements. In addition, a LoRaWAN scalability approach was also used to simulate the packet delivery ratio for a 500 node network. The wireless communication performance of LoRa WAN was shown to offer the most optimal solution for wireless communication for museum artefact monitoring application.

Industrial Internet of Things applications require wireless networking protocols that can achieve high reliability, high scalability, and allow node mobility. To this end, this demo presents a testbed for TS-LoRa; a time-slotted and collision-free protocol for LoRa-based networks for applications that require frequent and extremely reliable transmissions. The demo consists of a gateway system as well as several end-nodes that can join the network, synchronise with it, and autonomously get a unique frame slot to perform transmissions. In this demo, a general description of the system along with its processes is provided.

TS-LoRa is an autonomous time-slotted communication protocol for LoRa-based networks. As with other synchronous protocols, TS-LoRa bases its operation on repeated frames where each frame consists of a number of slots while guard times are added in between successive transmissions to tolerate slight desynchronisations until the next synchronisation. The number of slots in the frames depends on the payload size, the radio duty cycle rules, the application duty cycle requirements, and the number of nodes in the network. Due to the low bitrate of LoRa transmissions, the guard times are much longer compared to other traditional time-division protocols. Those longer guard times lead to larger in size frames and, thus, to increased delay and lower capacity. In this paper, a delay and capacity analysis of TS-LoRa is provided and the possibility of using flexible guard times to mitigate the problem of the increased delay and the reduced network capacity is explored. The potential of the solution to improve the above-mentioned performance metrics is shown through numerical simulations while the practicality of the flexible guard times is assessed through testbed experiments.

Automation and data capture in manufacturing, known as Industry 4.0, requires the deployment of a large number of wireless sensor devices in industrial environments. These devices have to be connected via a reliable, low-latency, low-power and low operating-cost network. Although LoRaWAN provides a low-power and reasonable-cost network technology, its current ALOHA-based MAC protocol limits its scalability and reliability. A common practise in wireless networks is to solve this issue and improve scalability through the use of time-slotted communications. However, any time-slotted approach comes with overheads to compute and disseminate the transmission schedule in addition to ensuring global time synchronisation. Affording these overheads is not straight forward with LoRaWAN restrictions on radio duty-cycle and downlink availability. Therefore, in this work, we propose TS-LoRa, an approach that tackles these overheads by allowing devices to self-organise and determine their slot positions in a frame autonomously. In addition to that, only one dedicated slot in each frame is used to ensure global synchronisation and handle acknowledgements. Our experimental results with 25 nodes show that TS-LoRa can achieve more than 99% packet delivery ratio even for the most distant nodes. Moreover, our simulations with a higher number of nodes revealed that TS-LoRa exhibits a lower energy consumption than the confirmable version of LoRaWAN while not compromising the packet delivery ratio.

LoRaWAN promises to provide wide-area network access to low-cost devices that can operate for up to ten years on a single 1000-mAh battery. This makes LoRaWAN particularly suited for the data collection applications (e.g., monitoring applications), where device lifetime is a key performance metric. However, when supporting a large number of devices, LoRaWAN suffers from a scalability issue due to the high collision probability of its Aloha-based MAC layer. The performance worsens further when using acknowledged transmissions due to the duty-cycle restriction at the gateway. For this, we propose FREE, a fine-grained scheduling scheme for reliable and energy-efficient data collection in LoRaWAN. FREE takes advantage of applications that do not have hard delay requirements on data delivery by supporting the synchronized bulk data transmission. This means data are buffered for transmission in scheduled time slots instead of transmitted straight away. FREE allocates spreading factors, transmission powers, frequency channels, time slots, and schedules slots in frames for LoRaWAN end-devices. As a result, FREE overcomes the scalability problem of LoRaWAN by eliminating collisions and grouping acknowledgments. We evaluate the performance of FREE versus different legacy LoRaWAN configurations. The numerical results show that FREE scales well and achieves almost 100% data delivery and the device lifetime is estimated over ten years independent of traffic type and network size. In comparison to poor scalability, low data delivery and device lifetime of fewer than two years for acknowledged data traffic in the standard LoRaWAN configurations.

An important requirement for Internet of Things applications is the ability to provide fast and energy efficient data collection from wireless sensors. When sensor nodes are located far from the data collection point, currently available long range protocols present challenges associated with a very low data rate and often unreliable connections resulting in excessive energy consumption related to data transmission. To address this problem, we propose a simple and energy-efficient data collection architecture for smart agricultural purposes which require wireless sensing. The architecture involves data collection from nodes located in remote fields or on animals leveraging off the use of drones as a data collection mechanism. In particular, drones can fly over the desired areas (points) and collect high volumes of data that would be otherwise difficult to transfer directly to the sink in a reasonable amount of time and using reasonable amounts of energy. We describe the different components and stages that constitute the proposed architecture emphasizing the networking component. We propose the use of different communication technologies, such as LoRa and WiFi, depending on the data collection requirements. We present an in-lab development of this architecture as a proof-of-concept as well as preliminary results for the architecture. The results reveal that the proposed solution is potentially capable of achieving data collection at high volume, however, the performance does not consider the highest spreading factors of LoRa.

LoRaWAN is a recently proposed MAC layer protocol which manages communications between LoRa-based gate-ways and end-devices. It has attracted much scientific attention due its physical layer characteristics, but mainly due to its versatile configuration parameters. However, it is known that LoRaWAN-based transmissions suffer from extensive collisions due to the unregulated access to the medium. For this reason, various techniques that alleviate the burst of collisions have been proposed in the literature. In this paper, we deal with the problem of fast data delivery in LoRa-based networks. We model a network where transmissions follow a Poisson process. We compute the average packet success probability per Spreading Factor (SF) assuming orthogonal transmissions. We, then, formulate an SF optimization problem to maximize the success probability given an amount of data per node and a maximum data collection time window. We show - both theoretically and using simulations - that the overall success probability can be improved by approximately 100% using optimal SF assignments. We validate our findings using a 10-node testbed and extensive experiments. Despite that experiments reveal the existence of inter-SF interference, our solution still provides the best performance compared to other LoRaWAN configurations.

LoRa-based transmissions suffer from extensive collisions even for low node numbers due to unregulated access to the medium. In order to tackle this problem, we propose a collision-free time-slotted scheduling approach where each node autonomously decides when to transmit a packet based on its unique identifier which is converted to a slot number using a modulo operation. We report through simulations and real experiments that this approach can provide very high reliability when the nodes are synchronized. Moreover, it does not require any additional communication overhead apart from a broadcast packet emitted by the gateway. Our comparison with the native LoRa, as well as to a slotted-LoRa version, shows significant performance gains in terms of packet delivery ratio, especially in the case of low node populations.

The IEEE 802.15.4 Time Slotted Channel Hopping (TSCH) networks suffer considerably from the high interference caused by the presence of nearby external devices, such as from the presence of IEEE 802.11b/g/n Access Points. Frequency hopping and blacklisting of radio channels that temporarily or consistently present bad performance are the two main approaches to cope with interference and increase the chances of successful packet delivery. However, the blacklisting of a number of channels and the scheduling of transmissions so that two or more neighboring links do not use the same frequency at the same time is a challenging problem, since in IEEE 802.15.4 TSCH many parallel transmissions may occur. Blacklisting algorithms may be applied either locally or globally in IEEE 802.15.4 networks. In this paper, we first present the weaknesses of a localized blacklisting solution presented in the literature for multi-hop networks, and we propose a new distributed solution to overcome these issues. Both analytical and simulation evaluation under heavy interference show the superiority of the proposed scheme. In particular, the packet delivery ratio is improved while achieving minimum delay.

Time Slotted Channel Hopping (TSCH) has been proposed in various wireless protocols as a solution to combat external interference, path-loss fading and static jamming attacks. However, since TSCH algorithms generate a deterministic and periodic pattern of channel hops, they are still subject to jamming attacks. Proactive randomization of the channel generation process could provide a good solution against jamming attacks, however due to the strict time constraints of the timeslots, practical solutions should be very efficient. In this paper, we propose R-TSCH, a randomized radio channel generation algorithm that can be used to proactively protect wireless nodes from jamming attacks. Based on a cryptographic hash function and a secret key, R-TSCH produces a new pseudo-random channel sequence, which looks as truly random to anyone who has no access to the key. Our simulation results show that the attacked links of the TSCH network enhanced with the proposed mechanism can achieve an over 90% Packet Reception Rate (PRR) in presence of multiple jammers.

One of the most recent and reliable MAC protocols for low-rate wireless personal area networks is the IEEE802.15.4-TSCH. The formation of an IEEE802.15.4-TSCH network depends on the periodic transmission of Enhanced Beacons (EBs), and, by extension, on the scheduling of EB transmissions. In this paper, we present and analyze a negative phenomenon that can occur in most of the autonomous EB scheduling methods proposed in the literature. This phenomenon, which we call full collision, takes place when all the neighboring EB transmissions of a joining node collide. As a consequence, a node may not be able to join the network fast, consuming a considerable amount of energy as well. In order to eliminate collisions during EB transmissions, and, thus, to avoid the occurrence of this phenomenon, we propose a novel autonomous collision-free EB scheduling policy. The results of our simulations demonstrate the superiority of our policy compared to two other recently proposed policies.

In this paper, we tackle the optimal energy replenishment problem (OERP) using a given number of flying drones, in order to efficiently recharge wireless sensor nodes. We present a linear program that maximizes the amount of harvested energy to the sensors. We show that the model is solved to optimality in a few seconds for sensor networks with up to 50 nodes. The small number of available drones is shown to be optimally deployed at low altitude in order to efficiently recharge the batteries of at least half of the sensor nodes.

A major advantage of wirelessly powered devices is the use of wire-free and sometimes battery-free nodes that can operate for extremely long times. However, to achieve infinite network lifetime a set of chargers is needed to periodically transmit energy to the nodes through the emission of RF signals. In this paper, we study the problem of finding the optimal number of chargers so that a group of nodes can operate without using power sources other than wireless charging. We show that this problem is equivalent to the set-cover problem which is NP-Complete. We propose an efficient heuristic that bypasses the high computational cost of finding the overlapping segments of the harvesting sensor disks and we compare to optimal and non-optimal set-cover solutions. The results show significant performance gains in terms of execution time while keeping the number of chargers close to the optimal.

Wireless sensor networks (WSNs) consist of nodes with limited power resources. A potential method to prolong the lifespan of a node is the use of an antenna which can harvest energy from radio frequency (RF) signals. In this paper, we model a network consisting of nodes with energy harvesting capabilities and a number of dedicated energy transmitters (ETs) which send data to the nodes. We identify those parameters which affect the consumption of the nodes and we design a method to achieve multi-hop energy transfer between the nodes. However, the ultimate purpose of this paper is to examine whether the cost of the investment of using energy harvesting nodes can be covered by achieving a lower operation cost; that is longer operation times and, thus, less frequent maintenance. We consider three scenarios with different node densities and transmitter populations. Simulation results show that the use of RF-energy harvesting nodes can save a significant amount of energy, while the cost of the investment can be covered in less than 8 years for dense networks.

Wireless charging brings forward some new principles in designing energy efficient networks. A number of energy transmitters are placed in all over the network to recharge power constrained nodes. Since a few only nodes can remarkably benefit from the transmitter power emission, we organize the nodes in clusters and we propose an efficient localized algorithm as well as a centralized one to compute the charger position such that the cluster lifetime is maximized. Simulation results are presented to show the effectiveness of the approaches.

Controlled mobility is one of the most complex challenges in Wireless Sensor Networks (WSN). Only a few routing protocols consider controlled mobility in order to extend the network lifetime. They are all designed to optimize the physical route topology from a source to a destination. However, there is often more than one sensor which reports an event to the sink in WSN. In existing solutions, this leads to oscillation of nodes which belong to different routes and their premature death. Experiments show that the need of a routing path merge solution is high. As a response we propose the first routing protocol which locates and uses paths crossing to adapt the topology to the network traffic in a fully localized way while still optimizing energy efficiency. Furthermore the protocol makes the intersection to move away from the destination, getting closer to the sources, allowing higher data aggregation and energy saving. Our approach outperforms existing solutions and extends network lifetime up to 37%.