Exploratory Study on Application of MALDI-TOF-MS to Detect SARS-CoV-2 Infection in Human Saliva

SARS-CoV-2 has caused a large outbreak since its emergence in December 2019. COVID-19 diagnosis became a priority so as to isolate and treat infected individuals in order to break the contamination chain. Currently, the reference test for COVID-19 diagnosis is the molecular detection (RT-qPCR) of the virus from nasopharyngeal swab (NPS) samples. Although this sensitive and specific test remains the gold standard, it has several limitations, such as the invasive collection method, the relative high cost and the duration of the test. Moreover, the material shortage to perform tests due to the discrepancy between the high demand for tests and the production capacities puts additional constraints on RT-qPCR. Here, we propose a PCR-free method for diagnosing SARS-CoV-2 based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) profiling and machine learning (ML) models from salivary samples. Kinetic saliva samples were collected at enrollment and ten and thirty days later (D0, D10 and D30), to assess the classification performance of the ML models compared to the molecular tests performed on NPS specimens. Spectra were generated using an optimized protocol of saliva collection and successive quality control steps were developed to ensure the reliability of spectra. A total of 360 averaged spectra were included in the study. At D0, the comparison of MS spectra from SARS-CoV-2 positive patients (n = 105) with healthy healthcare controls (n = 51) revealed nine peaks that significantly distinguished the two groups. Among the five ML models tested, support vector machine with linear kernel (SVM-LK) provided the best performance on the training dataset (accuracy = 85.2%, sensitivity = 85.1%, specificity = 85.3%, F1-Score = 85.1%). The application of the SVM-LK model on independent datasets confirmed its performances with 88.9% and 80.8% of correct classification for samples collected at D0 and D30, respectively. Conversely, at D10, the proportion of correct classification had fallen to 64.3%. The analysis of saliva samples by MALDI-TOF MS and ML appears as an interesting supplementary tool for COVID-19 diagnosis, despite the mitigated results obtained for convalescent patients (D10).

An Architectural Framework for Facebook Messenger Chatbot Enabled Home Appliance Control System

The need to remotely control home appliances is an important aspect of home automation and is now receiving lot of attentions in the literature. The works so far are still at a development level making further research necessary. This article presents a framework for chatbot-controlled home appliance control system and was implemented by programming a Raspberry Pi using the Python language while the chatbot server was also implemented using a Node.js on JavaScript. The Raspberry Pi was connected to the chatbot server via Wi-Fi using a websockets protocol. The chatbot server is linked to Facebook Messenger using the Messenger Application Protocol Interface. Messages received at the chatbot server are analyzed with RasaNLU to classify the user's intention and extract necessary information which are sent over websocket to the connected Raspberry pi. The system was evaluated using control precision and percentage correct classification with both producing a significant level of acceptance. This work produced a Facebook Messenger chatbot-based framework capable of controlling Home Appliances remotely.

Discrete Atomic Transform-Based Lossy Compression of Three-Channel Remote Sensing Images with Quality Control

Lossy compression of remote sensing data has found numerous applications. Several requirements are usually imposed on methods and algorithms to be used. A large compression ratio has to be provided, introduced distortions should not lead to sufficient reduction of classification accuracy, compression has to be realized quickly enough, etc. An additional requirement could be to provide privacy of compressed data. In this paper, we show that these requirements can be easily and effectively realized by compression based on discrete atomic transform (DAT). Three-channel remote sensing (RS) images that are part of multispectral data are used as examples. It is demonstrated that the quality of images compressed by DAT can be varied and controlled by setting maximal absolute deviation. This parameter also strictly relates to more traditional metrics as root mean square error (RMSE) and peak signal-to-noise ratio (PSNR) that can be controlled. It is also shown that there are several variants of DAT having different depths. Their performances are compared from different viewpoints, and the recommendations of transform depth are given. Effects of lossy compression on three-channel image classification using the maximum likelihood (ML) approach are studied. It is shown that the total probability of correct classification remains almost the same for a wide range of distortions introduced by lossy compression, although some variations of correct classification probabilities take place for particular classes depending on peculiarities of feature distributions. Experiments are carried out for multispectral Sentinel images of different complexities.

Emotional Intelligence and Academic Self-Efficacy in Relation to the Psychological Well-Being of University Students During COVID-19 in Venezuela

Due to the COVID-19 pandemic, educational centers and universities in Venezuela have closed their physical plants and are migrating to emergency remote education to continue with academic programs. This empirical study aimed to analyze the predictive capacity of academic self-efficacy and emotional intelligence skills on each of the dimensions of psychological well-being. We employed a cross-sectional predictive design. The sample comprised 277 university students, of which 252 were female (91.00%). Their ages ranged from 18 to 45 years, with a mean of 20.35 (SD = 2.29). Non-probabilistic chance sampling was used. For data collection, we used an anonymous online form, contacted students by mail, and invited them to participate in the study. Questionnaires were available between 217 and 227 days of decreed quarantine in Venezuela. The results indicated average levels of academic self-efficacy (Me = 4; IQR = 2), emotional intelligence: clarity (Me = 27; IQR = 10), attention (Me = 25; IQR = 10) y repair (Me = 25; IQR = 12), and psychological well-being (Me = 35; IQR = 5). We found differences according to sex and age, specifically in emotional regulation (z = 3.73, p < 0.001, d = 0.438) and in bonds of psychological well-being (z = 2.51, p = 0.012, d = 0.276) favoring men (Me = 33, IQR = 9; Me = 8, IQR = 1), respectively. Regarding age, statistically significant differences were found in the group of students older than 21 years with higher perception of psychological well-being (z = 3.69, p < 0.001, d = 0.43) and in each of its dimensions. Emotional intelligence and academic self-efficacy were found to be significant predictors of psychological well-being and its dimensions, specifically on control (R2-Cox = 0.25, R2-Nagelkerke = 0.34, 69.90% of total correct classification), links (R2-Cox = 0.09, R2-Nagelkerke = 0.12, 65.07% of total correct classification), projects (R2-Cox = 0.32, R2-Nagelkerke = 0.46, 78.40% of total correct classification), acceptance (R2-Cox = 0.17, R2-Nagelkerke = 0.23, 68.28% of total correct classification), and total well-being (R2-Cox = 0.52, R2-Nagelkerke = 0.71, 87.16% of total correct classification). It was concluded that emotional intelligence and academic self-efficacy are protective psychological resources of psychological well-being that should be promoted at university to mitigate the negative effects of the pandemic on the mental health of young people.

Selection of features system and network parameters for hyperspectral images classification using convolutional neural networks

A classification system for hyperspectral images using convolutional neural networks is described. A specific network was selected and analyzed. The network parameters, ensured the maximum classification accuracy: dimension of the input layer, number of the layers, size of the fragments into which the classified image is divided, number of learning epochs, are experimentally determined. High percentages of correct classification were obtained with a large-format hyperspectral image, and some of the classes into which the image is divided are very close to each other and, accordingly, are difficult to distinguish by hyperspectra.

Inheritance metrics feats in unsupervised learning to classify unlabeled datasets and clusters in fault prediction

Fault prediction is a necessity to deliver high-quality software. The absence of training data and mechanism to labeling a cluster faulty or fault-free is a topic of concern in software fault prediction (SFP). Inheritance is an important feature of object-oriented development, and its metrics measure the complexity, depth, and breadth of software. In this paper, we aim to experimentally validate how much inheritance metrics are helpful to classify unlabeled data sets besides conceiving a novel mechanism to label a cluster as faulty or fault-free. We have collected ten public data sets that have inheritance and C&K metrics. Then, these base datasets are further split into two datasets labeled as C&K with inheritance and the C&K dataset for evaluation. K-means clustering is applied, Euclidean formula to compute distances and then label clusters through the average mechanism. Finally, TPR, Recall, Precision, F1 measures, and ROC are computed to measure performance which showed an adequate impact of inheritance metrics in SFP specifically classifying unlabeled datasets and correct classification of instances. The experiment also reveals that the average mechanism is suitable to label clusters in SFP. The quality assurance practitioners can benefit from the utilization of metrics associated with inheritance for labeling datasets and clusters.

Sensing Performance of Thermal Electronic Noses: A Comparison between ZnO and SnO2 Nanowires

In recent times, an increasing number of applications in different fields need gas sensors that are miniaturized but also capable of distinguishing different gases and volatiles. Thermal electronic noses are new devices that meet this need, but their performance is still under study. In this work, we compare the performance of two thermal electronic noses based on SnO2 and ZnO nanowires. Using five different target gases (acetone, ammonia, ethanol, hydrogen and nitrogen dioxide), we investigated the ability of the systems to distinguish individual gases and estimate their concentration. SnO2 nanowires proved to be more suitable for this purpose with a detection limit of 32 parts per billion, an always correct classification (100%) and a mean absolute error of 7 parts per million.

Signal Modulation Identification Based on Deep Learning in FBMC/OQAM Systems

Signal modulation identification (SMI) has always been one of hot issues in filter-bank multicarrier with offset quadrature amplitude modulation (FBMC/OQAM), which is usually implemented by the machine learning-based feature extraction. However, it is difficult for conventional methods to extract the signal feature, resulting in a limited probability of correct classification (PCC). To tackle this problem, we put forward a novel SMI method based on deep learning to identify FBMC/OQAM signals in this paper. It is noted that the block repetition is employed in the FBMC/OQAM system to achieve the imaginary interference cancelation. In the proposed deep learning-based SMI technique, the in-phase and quadrature samples of FBMC/OQAM signals are trained by the convolutional neural network. Subsequently, the dropout layer is designed to prevent overfilling and improve the identification accuracy. To evaluate the proposed scheme, extensive experiments are conducted by employing datasets with different modulations. The results show that the proposed method can achieve better accuracy than conventional methods.

Ontology-Based Reasoning for Educational Assistance in Noncommunicable Chronic Diseases

Noncommunicable chronic diseases (NCDs) affect a large part of the population. With the emergence of COVID-19, its most severe cases impact people with NCDs, increasing the mortality rate. For this reason, it is necessary to develop personalized solutions to support healthcare considering the specific characteristics of individuals. This paper proposes an ontology to represent the knowledge of educational assistance in NCDs. The purpose of ontology is to support educational practices and systems oriented towards preventing and monitoring these diseases. The ontology is implemented under Protégé 5.5.0 in Ontology Web Language (OWL) format, and defined competency questions, SWRL rules, and SPARQL queries. The current version of ontology includes 138 classes, 31 relations, 6 semantic rules, and 575 axioms. The ontology serves as a NCDs knowledge base and supports automatic reasoning. Evaluations performed through a demo dataset demonstrated the effectiveness of the ontology. SWRL rules were used to define accurate axioms, improving the correct classification and inference of six instantiated individuals. As a scientific contribution, this study presents the first ontology for educational assistance in NCDs.

Discrimination of Geographical Origin of Unroasted Kernels Argan Oil (Argania spinosa (L.) Skeels) Using Tocopherols and Chemometrics

Valorisation of Argan oil requires the precise identification of different provenances markers. The concentration of tocopherol is regarded as one of the essential parameters that certifies the quality and purity of Argan oil. In this study, 39 Argan samples from six different geographical origins (Safi, Essaouira, Agadir, Taroudant, Tiznit, and Sidi Ifni) from the central west of Morocco were collected and extracted using cold pressing. The total tocopherol amount was found to range from 783.23 to 1,271.68 mg/kg. Generally, γ-tocopherol has the highest concentration in Argan oil. It should also be noted that the geographical origin was found to have a strong effect on the amounts of all tocopherol homologues studied. Principal component analysis of tocopherol concentrations highlighted a significant difference between the different provenances. The content of tocopherol has also been found to be strongly influenced by the distance from the coast and altitude, whereas no significant effect was found regarding other ecological parameters. The prediction ability of the LDA models was 87.2%. The highest correct classification was revealed in coastal provenances (100%), and the lowest values were from the continental ones (71.4%). These results provide the basis for determining the geographical origins of Argan oil production with well-defined characteristics to increase the product’s value and the income of local populations. In addition, this study provides a very promising basis for developing Argan varieties with a high content of tocopherol homologues, as well as contributing to the traceability and protection of Argan oil’s geographical indication.