The olive fruit fly can damage up to 100% of the harvested fruit and can cause up to 80% reduction of the value of the resulting olive oil. Therefore, it is important to early detect its presence in the olive orchard to take the appropriate chemical or biological countermeasures as early as possible. Traps filled with attractant pheromones are typically deployed across the orchard to attract and capture the flies. Traditionally, the captured flies were manually counted which is error prone. Recently, the traps are employed with cameras and communication devices to send pictures of the captured flies to experts for analysis which is also error prone and inefficient. Consequently, machine and deep learning have been exploited to develop fully automated and accurate detection that does not include human in the loop. Such a learning problem is challenging due to the small size of the detected object, the differences in the light conditions at which pictures were taken, and the lack of enough data to train the learning model. In this paper, we present a deep learning framework for detecting and counting the number of olive fruit flies that exploits data augmentation to increase the dataset size, includes negative samples in the training to improve the detection accuracy, and normalizes the images to the color of the trap background, i.e., yellow, to unify the illumination conditions. The results of the proposed framework show a precision of 0.84, a recall of 0.97, an F1-score of 0.9 and mean Average Precision (mAP) of 96.68% which significantly outperforms existing pest detection systems.

Wireless Sensor Networks have been often used in the context of Greenhouse architectures. In this paper, an architecture is proposed for two Greenhouses based on Networked Control Systems. This architecture is IoT-based and built on top of switched Ethernet and Wi-Fi. Some sensors in the proposed architecture require a one-second real-time deadline. Riverbed simulations prove that there is zero packet loss and no over-delayed packets. An important contribution of this work is the design of a channel allocation scheme that prevents interference in this relatively large Greenhouse system. Another contribution of this work is the introduction of fault tolerance at the controller level. If one controller fails in one of the Greenhouses, the other controller automatically takes over the entire operation of the two-Greenhouse system. Riverbed simulations again show that this fault-tolerant system does not suffer any packet loss or over-delayed packets. Continuous Time Markov Chains are then developed to calculate the reliability as well as the steady state availability of the two-Greenhouse system. The Coverage parameter is taken into account. Finally, a case study is presented to quantitatively assess the advantage of fault tolerance in terms of downtime reduction; this is expected to be attractive especially in developing countries.

Scalability and the highly dynamic topology of Vehicular Ad Hoc Networks (VANETs) are the biggest challenges that slow the roll-out of such a promising technology. Adopting an effective VANET clustering algorithm can tackle these issues in addition to benefiting routing, security and media access management. In this paper, we propose a general-purpose resilient double-head clustering (DHC) algorithm for VANET. Our proposed approach is a mobility-based clustering algorithm that exploits the most relevant mobility metrics such as vehicle speed, position, and direction, in addition to other metrics related to the communication link quality such as the link expiration time (LET) and the signal-to-noise ratio (SNR). The proposed algorithm has enhanced performance and stability features, especially during the cluster maintenance phase, through a set of procedures developed to achieve these objectives. An extensive evaluation methodology is followed to validate DHC and compare its performance with another algorithm using different existing and newly proposed evaluation metrics. These metrics are analyzed under various mobility scenarios, vehicle densities, and radio channel models such as log-normal shadowing and two-ray ground loss with and without Nakagami-m fading model. The proposed algorithm DHC has proven its ability to be more stable and efficient under different simulation scenarios.

Collision avoidance and road safety applications require highly accurate vehicle localization techniques. Unfortunately, the existing localization techniques are not suitable for road safety applications as they rely on the error-prone Global Positioning System (GPS). Likewise, cooperative localization techniques that use intervehicle communications experience high errors due to hidden vehicles and the limited sensing/communication range. Recently, GPS-free localization based on vehicle communication with a low cost infrastructure installed on the roadsides has emerged as a more accurate alternative. However, existing techniques require the vehicle to communicate with two roadside units (RSUs) in order to achieve high localization accuracy. In contrast, this paper presents a GPS-free localization framework that uses two-way time of arrival to locate the vehicles based on communication with a single RSU. Furthermore, our framework uses the vehicle kinematics information obtained via the vehicles onboard inertial navigation system (INS) to further improve the accuracy of the vehicle location using Kalman filters. Our results show that the localization error of the proposed framework is as low as 1.8 meters. The resulting localization accuracy is up to 65% and 47.5% better than GPS-based techniques used without/with INS, respectively. This accuracy gain becomes around 73.3% when compared to existing RSU-based techniques.

Museum contents are vulnerable to bad ambience conditions and human vandalization. Preserving the contents of museums is a duty towards humanity. In this paper, we develop an Internet of Things (IoT)-based system for museum monitoring and control. The developed system does not only autonomously set the museum ambience to levels that preserve the health of the artifacts and provide alarms upon intended or unintended vandalization attempts, but also allows for remote ambience control through authorized Internet-enabled devices. A key differentiating aspect of the proposed system is the use of always-on and power-hungry sensors for comprehensive and precise museum monitoring, while being powered by harvesting the Radio Frequency (RF) energy freely available within the museum. This contrasts with technologies proposed in the literature, which use RF energy harvesting to power simple IoT sensing devices. We use rectenna arrays that collect RF energy and convert it to electric power to prolong the lifetime of the sensor nodes. Another important feature of the proposed system is the use of deep learning to find daily trends in the collected environment data. Accordingly, the museum ambience is further optimized, and the system becomes more resilient to faults in the sensed data.