Article
Computer Science, Information Systems
Amgad Muneer, Suliman Mohamed Fati, Nur Arifin Akbar, David Agustriawan, Setyanto Tri Wahyudi
Summary: Messenger RNA (mRNA) has emerged as a critical global technology for COVID-19 vaccine development. However, the chemical properties of RNA present challenges in utilizing mRNA as a vaccine candidate. This study investigates the prediction of RNA degradation from RNA sequences using hybrid deep learning models. The GCN_GRU hybrid model outperforms the GCN_CNN model, demonstrating the importance of modeling RNA molecules using graphs in understanding degradation mechanisms.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Multidisciplinary Sciences
Pichatorn Suppakitjanusant, Somnuek Sungkanuparph, Thananya Wongsinin, Sirapong Virapongsiri, Nittaya Kasemkosin, Laor Chailurkit, Boonsong Ongphiphadhanakul
Summary: Recent breakthroughs in deep learning have allowed for the detection of subtle changes in voice features of COVID-19 patients post-recovery, with the model using polysyllabic sentences achieving the highest accuracy of 85%.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Interdisciplinary Applications
Rutwik Gulakala, Bernd Markert, Marcus Stoffel
Summary: In this study, an artificial intelligence-based method is proposed for the rapid diagnosis of Covid infections using Generative Adversarial Network (GAN) and Convolutional Neural Networks (CNN). Synthetic and augmented data are generated to supplement the dataset, and two novel CNN architectures are proposed for the multi-class classification of chest X-rays. The proposed models achieved extremely high classification metrics with 40% fewer training parameters compared to existing models.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Instruments & Instrumentation
Ahlam Fadhil Mahmood, Saja Waleed Mahmood
Summary: This paper introduced an accurate COVID-19 diagnostic system using deep learning models for x-ray and CT images, which achieved high accuracy and sensitivity. The proposed system outperformed previous deep learning algorithms and has the capability to automatically notify examination results.
REVIEW OF SCIENTIFIC INSTRUMENTS
(2021)
Article
Green & Sustainable Science & Technology
Sertan Serte, Mehmet Alp Dirik, Fadi Al-Turjman
Summary: Healthcare is enhanced through the Internet of things, with machine learning-based systems providing faster services and doctors utilizing artificial intelligence to analyze X-rays and CT scans. This paper proposes a data-efficient deep network that generates synthetic CT scans using a generative adversarial network (GAN) to increase the available data. The GAN-based deep learning model shows superior performance in COVID-19 detection compared to classic models, as evaluated on the COVID19-CT and Mosmed datasets.
Article
Biochemistry & Molecular Biology
Sandi Baressi Segota, Ivan Lorencin, Zoran Kovac, Zlatan Car
Summary: In the case of pandemics like COVID-19, the development of medicines to relieve pressure on the healthcare system is crucial. This study creates an AI-based model using a dataset of molecules and their pIC50 values to approximate pIC50 quickly. The hybrid neural network trained with molecular properties and SMILES representation shows the highest quality regression.
Article
Public, Environmental & Occupational Health
Abdolreza Marefat, Mahdieh Marefat, Javad Hassannataj Joloudari, Mohammad Ali Nematollahi, Reza Lashgari
Summary: COVID-19 is a novel virus that rapidly spreads and affects individuals' lives in various ways. Detecting the virus is crucial, and medical imaging such as CT and X-ray images are commonly used. However, the current procedures and high caseloads present challenges for medical practitioners. In this study, we propose a transformer-based method using Compact Convolutional Transformers (CCT) for automatically detecting COVID-19 from X-ray images. Our experiments demonstrate the effectiveness of the method with an accuracy of 99.22%, outperforming previous works.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Multidisciplinary Sciences
Thao Nguyen, Hieu H. Pham, Khiem H. Le, Anh-Tu Nguyen, Tien Thanh, Cuong Do
Summary: The vulnerability of healthcare systems during the COVID-19 pandemic has highlighted the need for rapid and cost-effective screening and diagnosis tools. This study proposes a novel method using electrocardiogram (ECG) signals to automatically detect COVID-19. By digitizing and analyzing the ECG signals using a 1D-CNN model, the study demonstrates accurate identification of COVID-19 cases, suggesting the potential of deep learning systems trained on digitized ECG signals as a diagnostic tool for COVID-19.
Article
Computer Science, Information Systems
Monia Hamdi, Amel Ksibi, Manel Ayadi, Hela Elmannai, Abdullah I. A. Alzahrani
Summary: This paper presents a method for using chest X-ray images to diagnose and detect COVID-19 disease. The study employs a generative adversarial network to generate balanced samples and utilizes the VGG16 model for classification. With various preprocessing and hyperparameter settings, the experimental results demonstrate an accuracy of 99.76% for both the GAN and the VGG16 models.
Article
Computer Science, Artificial Intelligence
Fabricio Aparecido Breve
Summary: This paper investigates the use of convolutional neural networks (CNNs) for identifying COVID-19 in chest X-ray images. By testing 21 different CNN architectures and employing ensemble methods, the study achieves superior results compared to previous research.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Automation & Control Systems
Elene Firmeza Ohata, Gabriel Maia Bezerra, Joao Victor Souza das Chagas, Aloisio Vieira Lira Neto, Adriano Bessa Albuquerque, Victor Hugo C. de Albuquerque, Pedro Pedrosa Reboucas Filho
Summary: The new coronavirus has become a global pandemic, infecting over 1 million people and causing more than 50 thousand deaths. A new method for automatically detecting COVID-19 infection based on chest X-ray images has been proposed and shown to be efficient in detecting COVID-19 in X-ray images.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2021)
Article
Computer Science, Artificial Intelligence
Aksh Garg, Sana Salehi, Marianna La Rocca, Rachael Garner, Dominique Duncan
Summary: This paper utilizes 20 convolutional neural networks to classify patients as COVID-19 positive, healthy, or suffering from other pulmonary infections based on chest CT scans. The study finds that the EfficientNet-B5 model performs the best, offering a rapid and accurate diagnostic for COVID-19.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Energy & Fuels
Weiqi Hua, Jing Jiang, Hongjian Sun, Andrea M. Tonello, Meysam Qadrdan, Jianzhong Wu
Summary: This study proposes a novel data-driven energy scheduling model to address the challenges faced by individual energy prosumers in terms of pricing patterns, power profile prediction, and scheduling. By using convolutional neural networks and real-time scenarios selection approach, the model is able to accurately predict scheduling decisions in microseconds.
Article
Physics, Fluids & Plasmas
Elham Kiyani, Steven Silber, Mahdi Kooshkbaghi, Mikko Karttunen
Summary: This paper presents data-driven architectures based on machine learning algorithms for discovering nonlinear equations of motion for phase-field models. The experimental results show that we can effectively learn the time derivatives of the field and use the data-driven partial differential equations (PDEs) to propagate the field in time, achieving results in good agreement with the original PDEs.
Article
Biology
Muhammet Fatih Aslan, Kadir Sabanci, Akif Durdu, Muhammed Fahri Unlersen
Summary: This paper presents a method for classifying COVID-19 using computed tomography chest images. By extracting features using convolutional neural network models and determining hyperparameters using Bayesian optimization, a classification accuracy of 96.29% was achieved.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Engineering, Electrical & Electronic
Andres J. Sanchez-Fernandez, Luis F. Romero, Gerardo Bandera, Siham Tabik
Summary: This article introduces a visibility-based path planning algorithm (VPP) that generates paths with maximum visual coverage by identifying hidden areas in the target territory. Simulation results and a real flight test confirm the high visibility achieved using VPP in monitoring large outdoor areas.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
German Gonzalez-Almagro, Juan Luis Suarez, Julian Luengo, Jose-Ramon Cano, Salvador Garcia
Summary: This paper proposes a method of incorporating constraints into the clustering process, including quantifying constraint relevance, learning a metric matrix, computing instance similarities, and performing clustering merges. Experimental results demonstrate a significant improvement of this method in the constrained clustering problem.
Article
Ecology
Jorge Castro, Fernando Morales-Rueda, Domingo Alcaraz-Segura, Siham Tabik
Summary: Despite the increasing news coverage promoting drone seeding as a promising solution for large-scale forest restoration, there is currently no evidence or peer-reviewed studies supporting these claims. The challenges of biotic and abiotic hazards faced by the seeds and seedlings make it clear that simply dropping seeds from the air will not lead to successful forest restoration. Before considering drone seeding as an efficient and widely applicable technology, it is crucial to improve the precision of seeding and reduce the number of seeds and cost required for the operation.
RESTORATION ECOLOGY
(2023)
Article
History & Philosophy Of Science
Jaime Martinez-Valderrama, Emilio Guirado, Fernando T. Maestre
Summary: Drylands cover 40% of the Earth and their unique hydrological system, limited by water, combined with characteristics such as rainfall variability and ecological heterogeneity, make them significant biomes. Despite their perception as economically and ecologically poor areas, they have high biodiversity and support 40% of the world's population. With global warming increasing atmospheric aridity, the millennia-old strategies developed by inhabitants of these regions serve as a valuable model. Understanding and preserving these areas are crucial in combating climate change.
METODE SCIENCE STUDIES JOURNAL
(2023)
Article
Biodiversity Conservation
Eduardo Moreno-Jimenez, Fernando T. Maestre, Maren Flagmeier, Emilio Guirado, Miguel Berdugo, Felipe Bastida, Marina Dacal, Paloma Diaz-Martinez, Raul Ochoa-Hueso, Cesar Plaza, Matthias C. Rillig, Thomas W. Crowther, Manuel Delgado-Baquerizo
Summary: By analyzing over 1300 topsoil samples, we found that warmer arid and tropical ecosystems, particularly in less developed countries, have the lowest contents of multiple soil micronutrients. We also provide evidence that temperature increases may result in abrupt reductions in soil micronutrient content when a temperature threshold of 12-14 degrees Celsius is crossed, potentially affecting 3% of the planet over the next century. Our findings have important implications for understanding the global distribution of soil micronutrients and their impact on ecosystem functioning, rangeland management, and food production in the warmest and poorest regions of the planet.
GLOBAL CHANGE BIOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Ignacio Aguilera-Martos, Angel M. Garcia-Vico, Julian Luengo, Sergio Damas, Francisco J. Melero, Jose Javier Valle-Alonso, Francisco Herrera
Summary: The combination of convolutional and recurrent neural networks is a promising framework for time series prediction problems. This paper introduces the TSFEDL library, which compiles 22 state-of-the-art methods for time series feature extraction and prediction using convolutional and recurrent deep neural networks.
Article
Ecology
Eleonora Egidi, Manuel Delgado-Baquerizo, Miguel Berdugo, Emilio Guirado, Davide Albanese, Brajesh K. Singh, Claudia Coleine
Summary: Increases in aridity negatively impact fungal community composition. The most important environmental factors driving community shifts are UV index, climate seasonality, and sand content. Increases in UV and temperature seasonality are associated with higher probability of plant pathogen and saprotroph occurrence, while these factors have a negative relationship with litter and soil saprotroph richness. These findings highlight the sensitivity of fungal groups in drylands to shifts in UV radiation and climate seasonality.
GLOBAL ECOLOGY AND BIOGEOGRAPHY
(2023)
Article
Ecology
Javier Blanco-Sacristan, Emilio Guirado, Jose Luis Molina-Pardo, Javier Cabello, Esther Gimenez-Luque, Domingo Alcaraz-Segura
Summary: Wildfires have significant impacts on ecosystems, and long-term monitoring of plant species is essential for understanding their responses to disturbances. This study used object-based image analysis to assess changes in the number of individuals and canopy cover extent of a Juniperus communis population following a wildfire. The results showed a partial recovery of the population and canopy cover over a four-decade period.
Article
Computer Science, Artificial Intelligence
Ivan Sevillano-Garcia, Julian Luengo, Francisco Herrera
Summary: Explainable artificial intelligence aims to provide explanations for AI reasoning. However, there is no consensus on how to evaluate the quality of explanations, and the definition of explanation itself is unclear. Local linear explanations face challenges in evaluation, and visual explanations for images may not truly explain decision-making. Previous attempts at developing evaluation measures have lacked objectivity and mathematical consistency. In this paper, the REVEL procedure is proposed to evaluate the quality of explanations in a theoretically coherent manner, addressing previous issues. Experimental results on image datasets demonstrate the descriptive and analytical power of REVEL.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Geosciences, Multidisciplinary
David J. Eldridge, Emilio Guirado, Peter B. Reich, Raul Ochoa-Hueso, Miguel Berdugo, Tadeo Saez-Sandino, Jose L. Blanco-Pastor, Leho Tedersoo, Cesar Plaza, Jingyi Ding, Wei Sun, Steven Mamet, Haiying Cui, Ji-Zheng He, Hang-Wei Hu, Blessing Sokoya, Sebastian Abades, Fernando Alfaro, Adebola R. Bamigboye, Felipe Bastida, Asuncion de los Rios, Jorge Duran, Juan J. Gaitan, Carlos A. Guerra, Tine Grebenc, Javier G. Illan, Yu-Rong Liu, Thulani P. Makhalanyane, Max Mallen-Cooper, Marco A. Molina-Montenegro, Jose L. Moreno, Tina U. Nahberger, Gabriel F. Penaloza-Bojaca, Sergio Pico, Ana Rey, Alexandra Rodriguez, Christina Siebe, Alberto L. Teixido, Cristian Torres-Diaz, Pankaj Trivedi, Juntao Wang, Ling Wang, Jianyong Wang, Tianxue Yang, Eli Zaady, Xiaobing Zhou, Xin-Quan Zhou, Guiyao Zhou, Shengen Liu, Manuel Delgado-Baquerizo
Summary: A global survey of soil attributes reveals that mosses play a crucial role in carbon sequestration, nutrient cycling, organic matter decomposition, and plant pathogen control. This comprehensive field study demonstrates that soil mosses contribute to soil biodiversity and function across different environments worldwide.
Review
Microbiology
Brajesh K. Singh, Manuel Delgado-Baquerizo, Eleonora Egidi, Emilio Guirado, Jan E. Leach, Hongwei Liu, Pankaj Trivedi
Summary: This review explores the impact of future climate scenarios on plant pathogen burden and biogeography, as well as their interaction with the plant microbiome and the consequences on plant disease and productivity. Climate change increases the risk of disease outbreaks by altering pathogen evolution and host-pathogen interactions, and facilitating the emergence of new pathogenic strains. The spread of plant diseases can also be increased as pathogen range shifts to new areas.
NATURE REVIEWS MICROBIOLOGY
(2023)
Article
Engineering, Civil
Jaime Martinez-Valderrama, Jorge Olcina, Gonzalo Delacamara, Emilio Guirado, Fernando T. Maestre
Summary: The divergence between agricultural water use and the annual supply of water resources has been increasing for decades, which poses a threat to global water security. The increase in demand is attributed to population growth and a high-water consumption lifestyle, while climate change exacerbates the problem. The water gap is particularly severe in drylands, where development and food security heavily rely on water exploitation. This article analyzes the underlying mechanisms of the water gap and suggests suitable solutions to close it, emphasizing the need for integrated water resource management under future climatic conditions.
WATER RESOURCES MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
Ignacio Aguilera-Martos, Marta Garcia-Barzana, Diego Garcia-Gil, Jacinto Carrasco, David Lopez, Julian Luengo, Francisco Herrera
Summary: Anomaly detection is the identification of samples that deviate from normal behavior or contain abnormal values. Unsupervised anomaly detection is the most common scenario where algorithms cannot train using labeled data and are unaware of anomaly behavior. Histogram-based methods are commonly used in unsupervised anomaly detection due to their good performance and low runtime. However, they are unable to process data streams and handle large amounts of samples. This paper proposes a new histogram-based approach called Multi-step Histogram Based Outlier Scores (MHBOS) that addresses these limitations by introducing update mechanisms for the histogram. Experimental results demonstrate the effectiveness and efficiency of MHBOS and the proposed strategies.
Article
Computer Science, Artificial Intelligence
David Lopez, Ignacio Aguilera-Martos, Marta Garcia-Barzana, Francisco Herrera, Diego Garcia-Gil, Julian Luengo
Summary: Anomaly detection aims to identify observations that differ significantly from the majority of the data. Time series is often used for this purpose. False positive mitigation is the task of reducing the number of false positives tagged by the anomaly detector. This paper proposes a two-stage methodology for multivariate anomaly detection and false positive mitigation, which has shown good performance in experiments.
INFORMATION FUSION
(2023)
Article
Geosciences, Multidisciplinary
Beatriz P. Cazorla, Javier Cabello, Andres Reyes, Emilio Guirado, Julio Penas, Antonio J. Perez-Luque, Domingo Alcaraz-Segura
Summary: This article introduces the study of ecosystem functions through satellite remote sensing imagery, providing a multitemporal database that analyzes the spatial and temporal dynamics of ecosystem functioning. It characterizes the types, richness, and rarity of ecosystem functional traits. This dataset is valuable for scientists and environmental managers.
EARTH SYSTEM SCIENCE DATA
(2023)
