An Analysis of Image Features Extracted by CNNs to Design Classification Models for COVID-19 and Non-COVID-19.

The SARS-CoV-2 virus causes a respiratory disease in humans, known as COVID-19. The confirmatory diagnostic of this disease occurs through the real-time reverse transcription and polymerase chain reaction test (RT-qPCR). However, the period of obtaining the results limits the application of the mass test. Thus, chest X-ray computed tomography (CT) images are analyzed to help diagnose the disease. However, during an outbreak of a disease that causes respiratory problems, radiologists may be overwhelmed with analyzing medical images. In the literature, some studies used feature extraction techniques based on CNNs, with classification models to identify COVID-19 and non-COVID-19. This work compare the performance of applying pre-trained CNNs in conjunction with classification methods based on machine learning algorithms. The main objective is to analyze the impact of the features extracted by CNNs, in the construction of models to classify COVID-19 and non-COVID-19. A SARS-CoV-2 CT data-set is used in experimental tests. The CNNs implemented are visual geometry group (VGG-16 and VGG-19), inception V3 (IV3), and EfficientNet-B0 (EB0). The classification methods were k-nearest neighbor (KNN), support vector machine (SVM), and explainable deep neural networks (xDNN). In the experiments, the best results were obtained by the EfficientNet model used to extract data and the SVM with an RBF kernel. This approach achieved an average performance of 0.9856 in the precision macro, 0.9853 in the sensitivity macro, 0.9853 in the specificity macro, and 0.9853 in the F1 score macro.

BoostedEnML: Efficient Technique for Detecting Cyberattacks in IoT Systems Using Boosted Ensemble Machine Learning.

Following the recent advances in wireless communication leading to increased Internet of Things (IoT) systems, many security threats are currently ravaging IoT systems, causing harm to information. Considering the vast application areas of IoT systems, ensuring that cyberattacks are holistically detected to avoid harm is paramount. Machine learning (ML) algorithms have demonstrated high capacity in helping to mitigate attacks on IoT devices and other edge systems with reasonable accuracy. However, the dynamics of operation of intruders in IoT networks require more improved IDS models capable of detecting multiple attacks with a higher detection rate and lower computational resource requirement, which is one of the challenges of IoT systems. Many ensemble methods have been used with different ML classifiers, including decision trees and random forests, to propose IDS models for IoT environments. The boosting method is one of the approaches used to design an ensemble classifier. This paper proposes an efficient method for detecting cyberattacks and network intrusions based on boosted ML classifiers. Our proposed model is named BoostedEnML. First, we train six different ML classifiers (DT, RF, ET, LGBM, AD, and XGB) and obtain an ensemble using the stacking method and another with a majority voting approach. Two different datasets containing high-profile attacks, including distributed denial of service (DDoS), denial of service (DoS), botnets, infiltration, web attacks, heartbleed, portscan, and botnets, were used to train, evaluate, and test the IDS model. To ensure that we obtained a holistic and efficient model, we performed data balancing with synthetic minority oversampling technique (SMOTE) and adaptive synthetic (ADASYN) techniques; after that, we used stratified K-fold to split the data into training, validation, and testing sets. Based on the best two models, we construct our proposed BoostedEnsML model using LightGBM and XGBoost, as the combination of the two classifiers gives a lightweight yet efficient model, which is part of the target of this research. Experimental results show that BoostedEnsML outperformed existing ensemble models in terms of accuracy, precision, recall, F-score, and area under the curve (AUC), reaching 100% in each case on the selected datasets for multiclass classification.

Digital Twin for a Collaborative Painting Robot.

A collaborative painting robot that can be used as an alternative to workers has been developed using a digital twin framework and its performance was demonstrated experimentally. The digital twin of the automatic painting robot simulates the entire process and estimates the paint result before the real execution. An operator can view the simulated process and result with an option to either confirm or cancel the task. If the task is accepted, the digital twin generates all the parameters, including the end effector trajectory of the robot, the material flow to the collaborative robot, and a spray mechanism. This ability means that the painting process can be practiced in a virtual environment to decrease set costs, waste, and time, all of which are highly demanded in single-item production. In this study, the screen was fixtureless and, thus, a camera was used to capture it in a physical environment, which was further analyzed to determine its pose. The digital twin then builds the screen in real-time in a virtual environment. The communication between the physical and digital twins is bidirectional in this scenario. An operator can design a painting pattern, such as a basic shape and/or letter, along with its size and paint location, in the resulting procedure. The digital twin then generates the simulation and expected painting result using the physical twin's screen pose. The painting results show that the root mean square error (RMSE) of the painting is less than 1.5 mm and the standard deviation of RMSE is less than 0.85 mm. Additionally, the initial benefits of the technique include lower setup costs, waste, and time, as well as an easy-to-use operating procedure. More benefits are expected from the digital twin framework, such as the ability of the digital twin to (1) find a solution when a fault arises, (2) refine the control or optimize the operation, and (3) plan using historic data.

Coherent detection-based photonic radar for autonomous vehicles under diverse weather conditions.

Autonomous vehicles are regarded as future transport mechanisms that drive the vehicles without the need of drivers. The photonic-based radar technology is a promising candidate for delivering attractive applications to autonomous vehicles such as self-parking assistance, navigation, recognition of traffic environment, etc. Alternatively, microwave radars are not able to meet the demand of next-generation autonomous vehicles due to its limited bandwidth availability. Moreover, the performance of microwave radars is limited by atmospheric fluctuation which causes severe attenuation at higher frequencies. In this work, we have developed coherent-based frequency-modulated photonic radar to detect target locations with longer distance. Furthermore, the performance of the proposed photonic radar is investigated under the impact of various atmospheric weather conditions, particularly fog and rain. The reported results show the achievement of significant signal to noise ratio (SNR) and received power of reflected echoes from the target for the proposed photonic radar under the influence of bad weather conditions. Moreover, a conventional radar is designed to establish the effectiveness of the proposed photonic radar by considering similar parameters such as frequency and sweep time.

Q-Meter: Quality Monitoring System for Telecommunication Services Based on Sentiment Analysis Using Deep Learning.

A quality monitoring system for telecommunication services is relevant for network operators because it can help to improve users' quality-of-experience (QoE). In this context, this article proposes a quality monitoring system, named Q-Meter, whose main objective is to improve subscriber complaint detection about telecommunication services using online-social-networks (OSNs). The complaint is detected by sentiment analysis performed by a deep learning algorithm, and the subscriber's geographical location is extracted to evaluate the signal strength. The regions in which users posted a complaint in OSN are analyzed using a freeware application, which uses the radio base station (RBS) information provided by an open database. Experimental results demonstrated that sentiment analysis based on a convolutional neural network (CNN) and a bidirectional long short-term memory (BLSTM)-recurrent neural network (RNN) with the soft-root-sign (SRS) activation function presented a precision of 97% for weak signal topic classification. Additionally, the results showed that 78.3% of the total number of complaints are related to weak coverage, and 92% of these regions were proved that have coverage problems considering a specific cellular operator. Moreover, a Q-Meter is low cost and easy to integrate into current and next-generation cellular networks, and it will be useful in sensing and monitoring tasks.