The Design and Implementation of a Phased Antenna Array System for LEO Satellite Communications.

LEO satellite constellations can provide a viable alternative to expand connectivity to remote, isolated geographical areas and complement existing IoT terrestrial communication infrastructures. This paper aims to improve LEO satellite communications by implementing a new phased antenna array system that can significantly improve the radio communication link's performance. By adjusting the progressive phase shift to each element of the antenna array system, the direction of the main radiation lobe of the phased antenna array system can be controlled with accuracy. As far as we know, it is the first time that a four-element, three-quarter wavelength phased antenna array system has been successfully realized with the intention of being optimized for implementation in LEO IoT satellite reception systems. The proposed system's high level of performance is confirmed by the measurements, which indicate effective control of the main radiation lobe orientation. The numerical analysis shows a maximum gain close to 12 dBi for about 42° elevation, a Half Power Beamwidth (HPBW) of 32° in the vertical plane, and 80° in the azimuth plane. The experimental measurement results at various main lobe orientation angles revealed an HPBW ranging from 76° to 87° in the azimuth plane and a maximum Front-to-Back ratio (F/B) of 14.5 dB.

The Design and Development of a Microstrip Antenna for Internet of Things Applications.

The Internet of Things (IoT) has become a part of modern life where it is used for data acquisition and long-range wireless communications. Regardless of the IoT application profile, every wireless communication transmission is enabled by highly efficient antennas. The role of the antenna is thus very important and must not be neglected. Considering the high demand of IoT applications, there is a constant need to improve antenna technologies, including new antenna designs, in order to increase the performance level of WSNs (Wireless Sensor Networks) and enhance their efficiency by enabling a long range and a low error-rate communication link. This paper proposes a new antenna design that is able to increase the performance level of IoT applications by means of an original design. The antenna was designed, simulated, tested, and evaluated in a real operating scenario. From the obtained results, it ensured a high level of performance and can be used in IoT applications specific to the 868 MHz frequency band.By inserting two notches along x axis, we find an optimal structure of the microstrip patch antenna with a reflection coefficient of -34.3 dB and a bandwidth of 20 MHz. After testing the designed novel antenna in real IoT operating conditions, we concluded that the proposed antenna can increase the performance level of IoT wireless communications.

Massive Data Storage Solution for IoT Devices Using Blockchain Technologies.

The Internet of Things (IoT) concept involves connecting devices to the internet and forming a network of objects that can collect information from the environment without human intervention. Although the IoT concept offers some advantages, it also has some issues that are associated with cyber security risks, such as the lack of detection of malicious wireless sensor network (WSN) nodes, lack of fault tolerance, weak authorization, and authentication of nodes, and the insecure management of received data from IoT devices. Considering the cybersecurity issues of IoT devices, there is an urgent need of finding new solutions that can increase the security level of WSNs. One issue that needs attention is the secure management and data storage for IoT devices. Most of the current solutions are based on systems that operate in a centralized manner, ecosystems that are easy to tamper with and provide no records regarding the traceability of the data collected from the sensors. In this paper, we propose an architecture based on blockchain technology for securing and managing data collected from IoT devices. By implementing blockchain technology, we provide a distributed data storage architecture, thus eliminating the need for a centralized network topology using blockchain advantages such as immutability, decentralization, distributivity, enhanced security, transparency, instant traceability, and increased efficiency through automation. From the obtained results, the proposed architecture ensures a high level of performance and can be used as a scalable, massive data storage solution for IoT devices using blockchain technologies. New WSN communication protocols can be easily enrolled in our data storage blockchain architecture without the need for retrofitting, as our system does not depend on any specific communication protocol and can be applied to any IoT application.

Internet of Things Concept in the Context of the COVID-19 Pandemic: A Multi-Sensor Application Design.

In this paper, we present the design, development and implementation of an integrated system for the management of COVID-19 patient, using the LoRaWAN communication infrastructure. Our system offers certain advantages when compared to other similar solutions, allowing remote symptom and health monitoring that can be applied to isolated or quarantined people, without any external interaction with the patient. The IoT wearable device can monitor parameters of health condition like pulse, blood oxygen saturation, and body temperature, as well as the current location. To test the performance of the proposed system, two persons under quarantine were monitored, for a complete 14-day standard quarantine time interval. Based on the data transmitted to the monitoring center, the medical staff decided, after several days of monitoring, when the measured values were outside of the normal parameters, to do an RT-PCR test for one of the two persons, confirming the SARS-CoV2 virus infection. We have to emphasize the high degree of scalability of the proposed solution that can oversee a large number of patients at the same time, thanks to the LoRaWAN communication protocol used. This solution can be successfully implemented by local authorities to increase monitoring capabilities, also saving lives.

Large-Scale Internet of Things Multi-Sensor Measurement Node for Smart Grid Enhancement.

Electric power infrastructure has revolutionized our world and our way of living has completely changed. The necessary amount of energy is increasing faster than we realize. In these conditions, the grid is forced to run against its limitations, resulting in more frequent blackouts. Thus, urgent solutions need to be found to meet this greater and greater energy demand. By using the internet of things infrastructure, we can remotely manage distribution points, receiving data that can predict any future failure points on the grid. In this work, we present the design of a fully reconfigurable wireless sensor node that can sense the smart grid environment. The proposed prototype uses a modular developed hardware platform that can be easily integrated into the smart grid concept in a scalable manner and collects data using the LoRaWAN communication protocol. The designed architecture was tested for a period of 6 months, revealing the feasibility and scalability of the system, and opening new directions in the remote failure prediction of low voltage/medium voltage switchgears on the electric grid.

LoRa Traffic Generator Based on Software Defined Radio Technology for LoRa Modulation Orthogonality Analysis: Empirical and Experimental Evaluation.

The digital revolution has changed the way we implement and use connected devices and systems by offering Internet communication capabilities to simple objects around us. The growth of information technologies, together with the concept of the Internet of Things (IoT), exponentially amplified the connectivity capabilities of devices. Up to this moment, the Long Range (LoRa) communication technology has been regarded as the perfect candidate, created to solve the issues of the IoT concept, such as scalability and the possibility of integrating a large number of sensors. The goal of this paper is to present an analysis of the communication collisions that occur through the evaluation of performance level in various scenarios for the LoRa technology. The first part addresses an empirical evaluation and the second part presents the development and validation of a LoRa traffic generator. The findings suggest that even if the packet payload increases, the communication resistance to interferences is not drastically affected, as one may expect. These results are analyzed by using a novel Software Defined Radio (SDR) technology LoRa traffic generator, that ensures a high-performance level in terms of generating a large LoRa traffic volume. Despite the use of orthogonal variable spreading factor technique, within the same communication channel, the collisions between LoRa packets may dramatically decrease the communication performance level.

Detecting dry eye from ocular surface videos based on deep learning.

OBJECTIVE: To assess the performance of convolutional neural networks (CNNs) for automated diagnosis of dry eye (DE) in patients undergoing video keratoscopy based on single ocular surface video frames. DESIGN: This retrospective cohort study included 244 ocular surface videos from 244 eyes of 244 subjects based on corneal topography. A total of 116 eyes were normal while 128 eyes had DE based on clinical evaluations. METHODS: We developed a deep transfer learning model to directly identify DE from ocular surface videos. We evaluated the performance of the CNN model based on objective accuracy metrics. We assessed the clinical relevance of the findings by evaluating class activations maps. MAIN OUTCOME MEASURE: Area under the receiver operating characteristics curve (AUC), accuracy, specificity, and sensitivity. RESULTS: The AUC of the model for discriminating normal eyes from eyes with DE was 0.98. Network activation maps suggested that the lower paracentral cornea was the most important region for detection of DE by the CNN model. CONCLUSIONS: Deep transfer learning achieved a high diagnostic accuracy in detecting DE based on non-invasive ocular surface videos at levels that may prove useful in clinical practice.

A Deep Feature Fusion of Improved Suspected Keratoconus Detection with Deep Learning.

Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97-100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with 213 eyes examined in Iraq and obtained AUCs of 0.91-0.92 and an accuracy range of 88-92%. The proposed model is a step toward improving the detection of clinical and subclinical forms of KCN.

Association between visual field damage and corneal structural parameters.

The main goal of this study is to identify the association between corneal shape, elevation, and thickness parameters and visual field damage using machine learning. A total of 676 eyes from 568 patients from the Jichi Medical University in Japan were included in this study. Corneal topography, pachymetry, and elevation images were obtained using anterior segment optical coherence tomography (OCT) and visual field tests were collected using standard automated perimetry with 24-2 Swedish Interactive Threshold Algorithm. The association between corneal structural parameters and visual field damage was investigated using machine learning and evaluated through tenfold cross-validation of the area under the receiver operating characteristic curves (AUC). The average mean deviation was - 8.0 dB and the average central corneal thickness (CCT) was 513.1 µm. Using ensemble machine learning bagged trees classifiers, we detected visual field abnormality from corneal parameters with an AUC of 0.83. Using a tree-based machine learning classifier, we detected four visual field severity levels from corneal parameters with an AUC of 0.74. Although CCT and corneal hysteresis have long been accepted as predictors of glaucoma development and future visual field loss, corneal shape and elevation parameters may also predict glaucoma-induced visual functional loss.

A Hybrid Deep Learning Construct for Detecting Keratoconus From Corneal Maps.

Purpose: To develop and assess the accuracy of a hybrid deep learning construct for detecting keratoconus (KCN) based on corneal topographic maps. Methods: We collected 3794 corneal images from 542 eyes of 280 subjects and developed seven deep learning models based on anterior and posterior eccentricity, anterior and posterior elevation, anterior and posterior sagittal curvature, and corneal thickness maps to extract deep corneal features. An independent subset with 1050 images collected from 150 eyes of 85 subjects from a separate center was used to validate models. We developed a hybrid deep learning model to detect KCN. We visualized deep features of corneal parameters to assess the quality of learning subjectively and computed area under the receiver operating characteristic curve (AUC), confusion matrices, accuracy, and F1 score to evaluate models objectively. Results: In the development dataset, 204 eyes were normal, 123 eyes were suspected KCN, and 215 eyes had KCN. In the independent validation dataset, 50 eyes were normal, 50 eyes were suspected KCN, and 50 eyes were KCN. Images were annotated by three corneal specialists. The AUC of the models for the two-class and three-class problems based on the development set were 0.99 and 0.93, respectively. Conclusions: The hybrid deep learning model achieved high accuracy in identifying KCN based on corneal maps and provided a time-efficient framework with low computational complexity. Translational Relevance: Deep learning can detect KCN from non-invasive corneal images with high accuracy, suggesting potential application in research and clinical practice to identify KCN.

KeratoDetect: Keratoconus Detection Algorithm Using Convolutional Neural Networks.

Keratoconus (KTC) is a noninflammatory disorder characterized by progressive thinning, corneal deformation, and scarring of the cornea. The pathological mechanisms of this condition have been investigated for a long time. In recent years, this disease has come to the attention of many research centers because the number of people diagnosed with keratoconus is on the rise. In this context, solutions that facilitate both the diagnostic and treatment options are quickly needed. The main contribution of this paper is the implementation of an algorithm that is able to determine whether an eye is affected or not by keratoconus. The KeratoDetect algorithm analyzes the corneal topography of the eye using a convolutional neural network (CNN) that is able to extract and learn the features of a keratoconus eye. The results show that the KeratoDetect algorithm ensures a high level of performance, obtaining an accuracy of 99.33% on the data test set. KeratoDetect can assist the ophthalmologist in rapid screening of its patients, thus reducing diagnostic errors and facilitating treatment.