When integrating the Internet of Things (IoT) with Unmanned Aerial Vehicles (UAVs) occurred, tens of applications including smart agriculture have emerged to offer innovative solutions to modernize the farming sector. This paper aims to present a low-cost platform for comprehensive environmental parameter monitoring using flying IoT. This platform is deployed and tested in a real scenario on a farm in Medenine, Tunisia, in the period of March 2020 to March 2021. The experimental work fulfills the requirements of automated and real-time monitoring of the environmental parameters using both under- and aboveground sensors. These IoT sensors are on a farm collecting vast amounts of environmental data, where it is sent to ground gateways every 1 h, after which the obtained data is collected and transmitted by a drone to the cloud for storage and analysis every 12 h. This low-cost platform can help farmers, governmental, or manufacturers to predict environmental data over the geographically large farm field, which leads to enhancement in crop productivity and farm management in a cost-effective, and timely manner. Obtained experimental results infer that automated and human-made sets of actions can be applied and/or suggested, due to the innovative integration between IoT sensors with the drone. These smart actions help in precision agriculture, which, in turn, intensely boost crop productivity, saving natural resources.

Featured Application: The method presented in this paper can be applied in medical computer systems for supporting medical diagnosis. Abstract: Thoracic radiography (chest X-ray) is an inexpensive but effective and widely used medical imaging procedure. However, a lack of qualified radiologists severely limits the applicability of the technique. Even current Deep Learning-based approaches often require strong supervision, e.g., annotated bounding boxes, to train such systems, which is impossible to harvest on a large scale. In this work, we proposed the classification and prediction of lung pathologies of frontal thoracic X-rays using a modified model MobileNet V2. We considered using transfer learning with metadata leverage. We used the NIH Chest-Xray-14 database, and we did a comparison of performance of our approach to other state-of-the-art methods for pathology classification. The main comparison was by Area under the Receiver Operating Characteristic Curve (AUC) statistics and analyzed the differences between classifiers. Overall, we notice a considerable spread in the achieved result with an average AUC of 0.811 and an accuracy above 90%. We conclude that resampling the dataset gives a huge improvement to the model performance. In this work, we intended to create a model that is capable of being trained, and modified devices with low computing power because they can be implemented into smaller IoT devices.

This paper presents a method for designing a new two-element ultra-wideband (UWB) multiple-input-multiple-output (MIMO) antenna. We propose the design of an ultra-wideband antenna has been proposed with a study of its properties. An isolation technique using well-designed metamaterials is presented to achieve the miniaturization and performance of the two antennas and ensure proper operation of the MIMO system with a very small spacing between radiating elements ( $\lambda $ /12) where $\lambda $ is the length waves in a vacuum. The metamaterials used considerably reduce the coupling of multi-antennas. The application of these materials called split-ring resonator (SRR) on the antenna patch plane has contributed to the increase in the performance of the antenna studied in terms of S parameters, multiplexing efficiency, diversity gain (DG), radiation properties and envelope correlation coefficient (ECC). This increases the transmission rate. This antenna system offers advantages such as reduction in weight and bulk, which facilitates its integration into a receiver, dedicated to 5G and connected objects.

One of the most expensive and fatal natural disasters in the world is forest fires. For this reason, early discovery of forest fires helps minimize mortality and harm to ecosystems and forest life. The present research enriches the body of knowledge by evaluating the effectiveness of an efficient wildfire and smoke detection solution implementing ensembles of multiple convolutional neural network architectures tackling two different computer vision tasks in a stage format. The proposed architecture combines the YOLO architecture with two weights with a voting ensemble CNN architecture. The pipeline works in two stages. If the CNN detects the existence of abnormality in the frame, then the YOLO architecture localizes the smoke or fire. The addressed tasks are classification and detection in the presented method. The obtained model’s weights achieve very decent results during training and testing. The classification model achieves a 0.95 F1-score, 0.99 accuracy, and 0.98e sensitivity. The model uses a transfer learning strategy for the classification task. The evaluation of the detector model reveals strong results by achieving a 0.85 mean average precision with 0.5 threshold (mAP@0.5) score for the smoke detection model and 0.76 mAP for the combined model. The smoke detection model also achieves a 0.93 F1-score. Overall, the presented deep learning pipeline shows some important experimental results with potential implementation capabilities despite some issues encountered during training, such as the lack of good-quality real-world unmanned aerial vehicle (UAV)-captured fire and smoke images.

Nowadays, the implementation of Artificial Intelligence (AI) in medical diagnosis has attracted major attention within both the academic literature and industrial sector. AI would include deep learning (DL) models, where these models have been achieving a spectacular performance in healthcare applications. According to the World Health Organization (WHO), in 2020 there were around 25.6 million people who died from cardiovascular diseases (CVD). Thus, this paper aims to shad the light on cardiology since it is widely considered as one of the most important in medicine field. The paper develops an efficient DL model for automatic diagnosis of 12-lead electrocardiogram (ECG) signals with 27 classes, including 26 types of CVD and a normal sinus rhythm. The proposed model consists of Residual Neural Network (ResNet-50). An experimental work has been conducted using combined public databases from the USA, China, and Germany as a proof-of-concept. Simulation results of the proposed model have achieved an accuracy of 97.63% and a precision of 89.67%. The achieved results are validated against the actual values in the recent literature.

Healthcare is one of the most promising domains for the application of Internet of Things- (IoT-) based technologies, where patients can use wearable or implanted medical sensors to measure medical parameters anywhere and anytime. The information collected by IoT devices can then be sent to the health care professionals, and physicians allow having a real-time access to patients’ data. However, besides limited batteries lifetime and computational power, there is spatio-temporal correlation, where unnecessary transmission of these redundant data has a significant impact on reducing energy consumption and reducing battery lifetime. Thus, this paper aims to propose a routing protocol to enhance energy-efficiency, which in turn prolongs the sensor lifetime. The proposed work is based on Energy Efficient Routing Protocol using Dual Prediction Model (EERP-DPM) for Healthcare using IoT, where Dual-Prediction Mechanism is used to reduce data transmission between sensor nodes and medical server if predictions match the readings or if the data are considered critical if it goes beyond the upper/lower limits of defined thresholds. The proposed system was developed and tested using MATLAB software and a hardware platform called “MySignals HW V2.” Both simulation and experimental results confirm that the proposed EERP-DPM protocol has been observed to be extremely successful compared to other existing routing protocols not only in terms of energy consumption and network lifetime but also in terms of guaranteeing reliability, throughput, and end-to-end delay.