Article
Engineering, Geological
Aali Pant, G. V. Ramana
Summary: This study proposes the prediction of pullout interaction coefficient of geogrids using data-driven machine learning regression algorithms, primarily focusing on extreme gradient boosting (XGBoost) method. The XGBoost model shows significantly superior and robust prediction compared to the random forest (RF) model, with an accuracy of 85% and 77% respectively. The importance analysis identifies normal stress as the most significant factor influencing the pullout interaction coefficients.
GEOTEXTILES AND GEOMEMBRANES
(2022)
Article
Environmental Sciences
M. N. M. Buthelezi, R. T. Lottering, S. T. Hlatshwayo, K. Peerbhay
Summary: This study explored the utilization of rotation forests and extreme gradient boosting machine learning algorithms to classify drought damage in commercial forests in KwaZulu-Natal. The results demonstrate that both algorithms are capable of accurately detecting trees with drought damage and those without, especially when using conditional drought indices.
GEOCARTO INTERNATIONAL
(2022)
Article
Computer Science, Information Systems
Debasmita GhoshRoy, Parvez Ahmad Alvi, K. C. Santosh
Summary: Infertility is a global issue, with male factors contributing to about 40% to 50% of cases. Existing AI systems lack interpretability, limiting clinicians' understanding of decision-making processes and their application in healthcare. This study introduces an explainable model for male fertility prediction, utilizing nine features related to lifestyle and environmental factors. Five AI tools (support vector machine, adaptive boosting, XGB, random forest, and extra tree algorithms) are deployed with balanced and imbalanced datasets, incorporating explainable AI techniques such as LIME, SHAP, and ELI5. XGB outperformed existing AI systems, achieving an optimal AUC of 0.98.
Article
Automation & Control Systems
Victor Henrique Alves Ribeiro, Roberto Santana, Gilberto Reynoso-Meza
Summary: This paper proposes two novel machine learning algorithms to improve the automatic target recognition system for unmanned aerial vehicles. These models make use of the stochastic procedure of Random Forests and employ the novel Random Vector Functional Link Tree or Extreme Learning Tree for decision split. Experimental results show that the proposed algorithms outperform other state-of-the-art ensemble learning techniques in terms of predictive performance and computational complexity.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Sinem Bozkurt Keser, Kemal Keskin
Summary: The aim of this study is to propose a gradient boosting-based model to predict the mortality of COVID-19 patients and to improve prediction accuracy through incorporating resampling strategies. Real COVID-19 data including patients' travel, health, geographical, and demographic information is used, and class imbalance problem in the dataset is solved using techniques like synthetic minority oversampling technique (SMOTE), random under-sampling, and clustering-based under-sampling. The experimental results reveal the influence of factors like age, Wuhan origin, and time difference between symptom onset and hospital visit on COVID-19 patient mortality, and compare the performance of XGBoost, LightGBM, and CatBoost algorithms. The study emphasizes the importance of addressing class imbalance problem and using resampling strategies to improve prediction accuracy for COVID-19 mortality.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Materials Science, Multidisciplinary
Seungro Lee, Joonhee Park, Naksoo Kim, Taeyong Lee, Luca Quagliato
Summary: This paper presents a machine learning methodology that can learn from simulation results, experimental data, or sensor signals, and is capable of predicting and optimizing specific user-defined process and design parameters. The methodology utilizes an enhanced Extreme Gradient Boosting (XGB) algorithm and a metaheuristic search algorithm based on Differential Evolution (DE) architecture for optimization.
MATERIALS & DESIGN
(2023)
Article
Computer Science, Artificial Intelligence
Elif Ceren Gok, Mehmet Onur Olgun
Summary: The serious Covid-19 pandemic has impacts on health, economy, society, with fast and accurate diagnosis being crucial. A study utilizing machine learning algorithms on blood samples from patients in Einstein Hospital in Brazil achieved high accuracy in predicting the severity of Covid-19.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Green & Sustainable Science & Technology
Odey Alshboul, Ali Shehadeh, Ghassan Almasabha, Ali Saeed Almuflih
Summary: Accurate prediction of green building costs is crucial for decision-making and management. This study presents machine learning-based algorithms for cost prediction and evaluates their accuracy.
Article
Engineering, Civil
Hoang D. Nguyen, Gia Toai Truong, Myoungsu Shin
Summary: This paper presents the application of XGBoost in predicting the punching shear resistance of reinforced concrete interior slabs without shear reinforcement. The XGBoost model showed the best prediction performance compared to other machine learning models, with effective depth identified as the most important input variable in punching shear prediction.
ENGINEERING STRUCTURES
(2021)
Article
Chemistry, Multidisciplinary
Tao Ma, Lizhou Wu, Shuairun Zhu, Hongzhou Zhu
Summary: This study investigates the performance of extreme gradient boosting (XGBoost) in predicting multiclass clay sensitivity and the ability of synthetic minority over-sampling technique (SMOTE) in addressing imbalanced categories. The results show that XGBoost performs the best in the prediction of clay sensitivity, while SMOTE is useful in addressing imbalanced issues.
APPLIED SCIENCES-BASEL
(2022)
Article
Mathematical & Computational Biology
Jianfen Kong, Shuhong Zhang
Summary: In this paper, a novel regression model, named ELM-based BJ boosting model, is proposed to overcome the limitation of traditional BJ model in processing nonlinear problems. The model applies RSF for covariates imputation, develops an ensemble of ELMs for regression, and replaces the linear combination of covariates in BJ model. The ELM-based BJ boosting model outperforms traditional BJ model, two types of BJ boosting models, RSF, and Cox proportional hazards model in both simulation studies and real data applications in terms of concordance index and integrated Brier score.
BIOMETRICAL JOURNAL
(2023)
Article
Biochemistry & Molecular Biology
Omar Alghushairy, Farman Ali, Wajdi Alghamdi, Majdi Khalid, Raed Alsini, Othman Asiry
Summary: The identification of druggable proteins is crucial for drug development, personalized medicine, and understanding disease mechanisms. This study introduces a computational predictor called Drug-LXGB, which utilizes machine learning strategies to enhance the identification of druggable proteins. The predictor achieved high predictive accuracy through feature selection algorithms and learning methods.
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS
(2023)
Article
Computer Science, Artificial Intelligence
Jiaming Han, Kunxin Shu, Zhenyu Wang
Summary: Annual increases in global energy consumption are inevitable due to a growing global economy and population. Among sectors, the construction industry consumes 20.1% of the world's total energy, making it crucial to explore methods for estimating energy usage. Various computational approaches exist, including statistics-based, engineering-based, and machine learning-based methods. Machine learning-based frameworks outperform the others. In our study, we propose using the Extreme Gradient Boosting algorithm to predict energy consumption, achieving better results with combined historical and date features.
PEERJ COMPUTER SCIENCE
(2023)
Article
Computer Science, Information Systems
Liyan Jia, Zhiping Wang, Pengfei Sun, Zhaohui Xu, Sibo Yang
Summary: This paper proposes a novel approach based on XGBoost and TDMO to address the issue of data distribution. By training multiple balanced subsets, filtering noise, and combining multiple samples, the diversity of the minority class is expanded, resulting in superior classification results compared to other methods.
INFORMATION SCIENCES
(2023)
Article
Biology
Xue Wang, Yaqun Zhang, Bin Yu, Adil Salhi, Ruixin Chen, Lin Wang, Zengfeng Liu
Summary: The PPISP-XGBoost method proposed in the study uses XGBoost to predict PPI sites by extracting and optimizing features, achieving higher accuracy compared to existing methods on multiple datasets. The results demonstrate the effectiveness of PPISP-XGBoost in enhancing the prediction of PPI sites.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Remote Sensing
Carlos A. Puig-Mengual, Amy S. Woodget, Rafael Munoz-Mas, Francisco Martinez-Capel
Summary: Mapping streambed morphology is crucial for understanding river forms and processes, and recent advancements in using topobathymetric LiDAR and imagery from airborne platforms have provided a promising and effective surveying methodology. The use of RPAS combined with SfM photogrammetric processing offers a high-resolution approach to modeling fluvial morphology, with the possibility of correcting errors caused by water bodies in the data acquisition process. Results from this study showed that the novel refraction correction method presented smaller errors in modeling streambed morphology compared to traditional methods, especially in riffle habitats.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2021)
Article
Ecology
Antica Culina, Frank Adriaensen, Liam D. Bailey, Malcolm D. Burgess, Anne Charmantier, Ella F. Cole, Tapio Eeva, Erik Matthysen, Chloe R. Nater, Ben C. Sheldon, Bernt-Erik Saether, Stefan J. G. Vriend, Zuzana Zajkova, Peter Adamik, Lucy M. Aplin, Elena Angulo, Alexandr Artemyev, Emilio Barba, Sanja Barisic, Eduardo Belda, Cemal Can Bilgin, Josefa Bleu, Christiaan Both, Sandra Bouwhuis, Claire J. Branston, Juli Broggi, Terry Burke, Andrey Bushuev, Carlos Camacho, Daniela Campobello, David Canal, Alejandro Cantarero, Samuel P. Caro, Maxime Cauchoix, Alexis Chaine, Mariusz Cichon, Davor Cikovic, Camillo A. Cusimano, Caroline Deimel, Andre A. Dhondt, Niels J. Dingemanse, Blandine Doligez, Davide M. Dominoni, Claire Doutrelant, Szymon M. Drobniak, Anna Dubiec, Marcel Eens, Kjell Einar Erikstad, Silvia Espin, Damien R. Farine, Jordi Figuerola, Pinar Kavak Gulbeyaz, Arnaud Gregoire, Ian R. Hartley, Michaela Hau, Gergely Hegyi, Sabine Hille, Camilla A. Hinde, Benedikt Holtmann, Tatyana Ilyina, Caroline Isaksson, Arne Iserbyt, Elena Ivankina, Wojciech Kania, Bart Kempenaers, Anvar Kerimov, Jan Komdeur, Peter Korsten, Miroslav Kral, Milos Krist, Marcel Lambrechts, Carlos E. Lara, Agu Leivits, Andras Liker, Jaanis Lodjak, Marko Magi, Mark C. Mainwaring, Raivo Mand, Bruno Massa, Sylvie Massemin, Jesus Martinez-Padilla, Tomasz D. Mazgajski, Adele Mennerat, Juan Moreno, Alexia Mouchet, Shinichi Nakagawa, Jan-Ake Nilsson, Johan F. Nilsson, Ana Claudia Norte, Kees van Oers, Markku Orell, Jaime Potti, John L. Quinn, Denis Reale, Tone Kristin Reiertsen, Balazs Rosivall, Andrew F. Russell, Seppo Rytkonen, Pablo Sanchez-Virosta, Eduardo S. A. Santos, Julia Schroeder, Juan Carlos Senar, Gabor Seress, Tore Slagsvold, Marta Szulkin, Celine Teplitsky, Vallo Tilgar, Andrey Tolstoguzov, Janos Torok, Mihai Valcu, Emma Vatka, Simon Verhulst, Hannah Watson, Teru Yuta, Jose M. Zamora-Marin, Marcel E. Visser
Summary: The lack of standards and networking programmes significantly hinders the integration and synthesis of data in various scientific fields. Long-term studies of individually marked animals play a crucial role in understanding evolutionary and ecological processes in the wild. The SPI-Birds Network and Database have been established to address data integration issues and enable a new scale of ecological and evolutionary research based on long-term studies of birds.
JOURNAL OF ANIMAL ECOLOGY
(2021)
Article
Environmental Sciences
Jose Manuel Zamora-Marin, Christiane Ilg, Eliane Demierre, Nelly Bonnet, Alexander Wezel, Joel Robin, Dominique Vallod, Jose Francisco Calvo, Francisco Jose Oliva-Paterna, Beat Oertli
Summary: The contribution of artificial ponds to regional biodiversity has not been quantified, but they have the potential to support freshwater biodiversity. Different types of artificial ponds are complementary in terms of supporting regional diversity for amphibians, water beetles, and freshwater snails. However, artificial ponds have lower α richness compared to natural ponds.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Marine & Freshwater Biology
Jose M. Zamora-Marin, Antonio Zamora-Lopez, Maria Jimenez-Franco, Jose F. Calvo, Francisco J. Oliva-Paterna
Summary: Ponds are among the world's most endangered freshwater ecosystems, and environmental heterogeneity has been found to positively influence bird species richness. The study suggests that in a semiarid region, drinking troughs outperformed other pond types in supporting bird species richness.
Article
Geography, Physical
Carmelo Conesa-Garcia, Carlos Puig-Mengual, Adrian Riquelme, Roberto Tomas, Francisco Martinez-Capel, Rafael Garcia-Lorenzo, Jose L. Pastor, Pedro Perez-Cutillas, Alberto Martinez-Salvador, Miguel Cano-Gonzalez
Summary: This study aimed to investigate the impact of stream power on morphological adjustments in a Mediterranean gravel-bed channel. Using high-resolution digital terrain models and a hydrodynamic model, the study found a certain correlation between stream power and sediment flux and bed changes.
Article
Limnology
Adrian Guerrero-Gomez, Antonio Zamora-Lopez, Antonio Guillen-Beltran, Jose M. Zamora-Marin, Ana Sanchez-Perez, Mar Torralva, Francisco J. Oliva-Paterna
Summary: This study presents an updated checklist of young of the year fish species inhabiting the shallow areas of Mar Menor in the Western Mediterranean from 2018 to 2019. A total of 43 taxa in 19 families were identified. This information is valuable for establishing environmental monitoring programs and implementing management actions.
Article
Environmental Sciences
Francisco N. Godinho, Carlos Alexandre, Pedro R. Almeida, Francisco Martinez-Capel, Rui M. Cortes, Bernardo R. Quintella, Javier Sanz-Ronda, Jose M. Santos, Antoni Palau, Antonio N. Pinheiro, Isabel Boavida
Summary: Hydropeaking negatively affects fish assemblages, and there is a lack of research on its impacts on Iberian Cypriniformes and Mediterranean rivers. This study adapted a tool developed for salmonids to assess hydropeaking impacts on Iberian Cypriniformes, incorporating factors related to hydromorphological effects and fish vulnerability. Experts ranked the timing and distribution of peaking events higher in effect factors, and the population size of barbel and smaller native Cypriniformes, as well as the degree of limitations in recruitment, higher in vulnerability factors. The study provided a comprehensive and systematic assessment tool for evaluating hydropeaking impacts on Iberian Cypriniformes.
RIVER RESEARCH AND APPLICATIONS
(2023)
Article
Environmental Sciences
Ana Sanchez-Perez, Mar Torralva, Jose Manuel Zamora-Marin, Francisco Javier Bravo-Cordoba, Francisco Javier Sanz-Ronda, Francisco Jose Oliva-Paterna
Summary: River connectivity is crucial for the resilience of fish assemblages and populations, and is a top priority for achieving good ecological status in river systems. The assessment of different types of multispecies fishways in a Mediterranean-type river showed clear ecological contributions, including their use as migration corridors and compensatory habitats for small and juvenile fish.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Environmental Sciences
Enrique Gonzalez-Ortegon, Selina Berger, Joao Encarnacao, Hicham Chairi, Pedro Morais, Maria Alexandra Teodosio, Francisco J. Oliva-Paterna, Christoph D. Schubart, Jose A. Cuesta
Summary: The Atlantic blue crab has extended its distribution along the Gulf of Cadiz and Moroccan coasts, and our study reveals low genetic variability in the study region. We also observed an inversion of haplotype predominance between regions. Further research on additional populations is needed to better understand the history of this invasive species in the Gulf of Cadiz.
FRONTIERS IN MARINE SCIENCE
(2022)
Article
Multidisciplinary Sciences
Sara Abalo-Morla, Eduardo J. Belda, Jesus Tomas, Jose Luis Crespo-Picazo, Adolfo Marco, Ohiana Revuelta
Summary: This study provides satellite-tracking data of 44 loggerhead sea turtles collected between 2016 and 2018, including post-hatchlings, nesting females, and juvenile and adult turtles. The data contribute to understanding the spatial use and dispersal of loggerhead sea turtles in the Mediterranean Sea.
Article
Biodiversity Conservation
Sara Abalo-Morla, Eduardo J. Belda, David March, Ohiana Revuelta, Luis Cardona, Silvia Giralt, Jose Luis Crespo-Picazo, Sandra Hochscheid, Adolfo Marco, Manuel Merchan, Ricardo Sagarminaga, Yonat Swimmer, Jesus Tomas
Summary: There are 264 Marine Protected Areas (MPAs) in the western Mediterranean Sea, with 25 of them prioritizing the protection of loggerhead sea turtles. However, it is uncertain whether these MPAs are actually utilized by the turtles. Satellite tracking data of 103 loggerhead turtles over a 15-year period were analyzed, and it was found that the turtles visited several MPAs but rarely used them. Most of the core areas and high-density areas of the turtles were not included within any MPAs. These findings suggest that the existing MPAs may not contribute enough to loggerhead turtle conservation.
GLOBAL ECOLOGY AND CONSERVATION
(2022)
Article
Biodiversity Conservation
Jose M. Zamora-Marin, Antonio Zamora-Lopez, David Sanchez-Fernandez, Jose F. Calvo
Summary: Farmland bird populations are declining worldwide due to agricultural intensification and the loss of unique landscape elements. In arid and semiarid regions, traditional small waterbodies are disappearing rapidly, exacerbating the simplification of agroecosystems. This study confirms that any type of traditional man-made waterbody, such as cattle ponds, drinking troughs, or traditional artificial pools, can play a crucial role in supporting farmland bird communities at landscape scale if properly designed and managed. However, these traditional waterbodies are often overlooked and their importance for farmland biodiversity is rarely considered in agri-environment schemes.
GLOBAL ECOLOGY AND CONSERVATION
(2022)
Article
Environmental Sciences
Fanny Girard, Alexandre Girard, Jonathan Monsinjon, Antonella Arcangeli, Eduardo Belda, Luis Cardona, Paolo Casale, Sidonie Catteau, Lea David, Florence Dell'Amico, Delphine Gambaiani, Marc Girondot, Imed Jribi, Giancarlo Lauriano, Paolo Luschi, David March, Antonios D. Mazaris, Claude Miaud, Andreas Palialexis, Jacques Sacchi, Ricardo Sagarminaga, Paola Tepsich, Jesus Tomas, Frederic Vandeperre, Francoise Claro
Summary: This study aims to provide indicators and assessment methods for European Union Member States to evaluate the status of marine turtle populations under the Marine Strategy Framework Directive. It highlights the importance of international collaboration for the conservation of vulnerable species.
FRONTIERS IN MARINE SCIENCE
(2022)
Article
Environmental Sciences
Francisco J. Oficialdegui, Jose M. Zamora-Marin, Simone Guareschi, Pedro M. Anastacio, Pablo Garcia-Murillo, Filipe Ribeiro, Rafael Miranda, Fernando Cobo, Belinda Gallardo, Emili Garcia-Berthou, Dani Boix, Andres Arias, Jose A. Cuesta, Leopoldo Medina, David Almeida, Filipe Banha, Sandra Barca, Idoia Biurrun, M. Pilar Cabezas, Sara Calero, Juan A. Campos, Laura Capdevila-Arguelles, Cesar Capinha, Frederic Casals, Miguel Clavero, Joao Encarnacao, Carlos Fernandez-Delgado, Javier Franco, Antonio Guillen, Virgilio Hermoso, Annie Machordom, Joana Martelo, Andres Mellado-Diaz, Felipe Morcilloy, Javier Oscoz, Anabel Perdices, Quim Pou-Rovira, Argantonio Rodriguez-Merino, Macarena Ros, Ana Ruiz-Navarro, Marta I. Sanchez, David Sanchez-Fernandez, Jorge R. Sanchez-Gonzalez, Enrique Sanchez-Gullon, M. Alexandra Teodosio, Mar Torralva, Rufino Vieira-Lanero, Francisco J. Oliva-Paterna
Summary: As the number of introduced species continues to rise, it is crucial to identify and prioritize current and potential invasive alien species (IAS) for effective management. Using a combination of scientific knowledge and expert opinion, this study identified the most relevant aquatic IAS in the Iberian Peninsula and classified them into a concern list and an alert list. This approach provides a robust assessment and cost-effective strategy for prioritizing resources in IAS prevention and management.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Marine & Freshwater Biology
Sara Abalo-Morla, Rafael Munoz-Mas, Jesus Tomas, Eduardo J. Belda
Summary: Nesting events of loggerhead sea turtles (Caretta caretta) are increasing in the Western Mediterranean Sea, far from their usual nesting areas. A study was conducted to understand the dispersal behavior and habitat use of loggerhead post-hatchlings from this new nesting area. Satellite-tracking data of 19 head-started loggerhead post-hatchlings released from the Spanish Mediterranean coast between 2016 and 2018 were analyzed. The turtles dispersed over large areas, swimming actively against sea currents. While the dispersal routes varied for each individual, they consistently dispersed southeastwards, especially during colder periods. Some post-hatchlings traveled through the Sicilian Channel to reach deep and warmer areas in the eastern Mediterranean basin. Conservation measures should focus on protecting these developmental areas.