Bias-aware degradation models for reinforced concrete bridges based on XAI by Francesca Marsili, Filippo Landi, Rade Hajdin, Sylvia Kessler

“…The analysis comprises four steps: (1) cluster analysis of damage transition times using the k-means algorithm to identify damage patterns with similar damage evolution rates (fast, normal, slow, corresponding to bridge components with a fragile, normal, and robust deterioration behavior); (2) Random Forest classification to predict the cluster based on bridge inventory data; (3) SHAP analysis to explain the predictions of the Random Forest classifier; (4) application of the gamma process to the grouped damage transition times to assess damage evolution. …”
Get full text

Structure, short-range order, and phase stability of the Al x CrFeCoNi high-entropy alloy: insights from a perturbative, DFT-based analysis by Christopher D. Woodgate, George A. Marchant, Livia B. Pártay, Julie B. Staunton

“…In addition, we recover a pairwise form of the alloy internal energy suitable for study via atomistic simulations, which in this work are performed using the nested sampling algorithm, which is well-suited for studying complex potential energy surfaces. …”
Get full text

Travel route recommendation with a trajectory learning model by Xiangping Wu, Zheng Zhang, Wangjun Wan

“…Then, it integrates this information through neural networks to predict the next intersection. Finally, a beam search algorithm is applied to generate and recommend multiple candidate routes. …”
Get full text

Identification of differentially expressed genes associated with ferroptosis in ulcerative colitis. by Fang Zhang, Xin Jiang, Xuyu Chen, Zheng Wang, Jianlei Xia, Bingcheng Wang, Mei Wang, Yanbing Ding

“…<h4>Results</h4>Eleven ferroptosis-related DEGs were identified (nine upregulated and two downregulated genes) in UC, with eight genes chosen from the PPI network. MCC algorithm demonstrated that SLC7A11, PSAT1, SLC7A5, ACSF2, and ACSL4 were hub genes, predicting TFs, miRNAs and drugs. …”
Get full text

Mathematical reconstruction of the metabolic network in an in-vitro multiple myeloma model. by Elias Vera-Siguenza, Cristina Escribano-Gonzalez, Irene Serrano-Gonzalo, Kattri-Liis Eskla, Fabian Spill, Daniel Tennant

“…To procure this model, we devised a bespoke human genome constraint-based reconstruction workflow that combines aspects from the legacy mCADRE & Metabotools algorithms, the novel redHuman algorithm, along with 13C-metabolic flux analysis. …”
Get full text

Classifying the Mortality of People with Underlying Health Conditions Affected by COVID-19 Using Machine Learning Techniques by Rami Mustafa A. Mohammad, Malak Aljabri, Menna Aboulnour, Samiha Mirza, Ahmad Alshobaiki

“…The best performance was demonstrated by the Bagging algorithm with an accuracy of 83.55% when using all the dataset features. …”
Get full text

Potential natural vegetation pattern based on major tree distribution modeling in the western Rif of Morocco by Ghallab A, Boubekraoui H, Laaribya S, Ben-Said M

“…In a fragile ecological environment, understanding the potential spatial distribution of species and the underlying environmental conditions is crucial for resolving ecosystem management issues and predicting impacts of global change. This study aimed to determine the potential distribution of fourteen major Mediterranean taxa (seven conifers and seven broadleaves) native to northwestern Morocco using the Maximum Entropy Algorithm (MaxEnt). …”
Get full text

Constructing a web recommender system using web usage mining and user’s profiles by T. Mombeini, A. Harounabadi, J. Rezaeian Sheshdeh

“…Following the creation of user profiles, users are categorized in clusters using the Fuzzy C-means clustering algorithm and S(c) criterion based on their similarities. …”
Get full text

Incorporation of Sub‐Resolution Porosity Into Two‐Phase Flow Models With a Multiscale Pore Network for Complex Microporous Rocks by Sajjad Foroughi, Branko Bijeljic, Ying Gao, Martin J. Blunt

“…Each grain voxel with sub‐resolution porosity is assigned to the two nearest resolved pores using an automatic dilation algorithm. By including these microlinks with empirical models in flow modeling, we simulate single‐phase and multiphase flow. …”
Get full text

Non-Destructive Detection of Fillet Fish Quality Using MQ135 Gas Sensor and Neutrosophic Logic-Enhanced System by M. Y. Shams, M. R. Darwesh, Roheet Bhatnagar, N. S. A. Al-Sattary, A. A. Salama, M. S. Ghoname

“…Artificial intelligence algorithms were employed to predict quality and calculate regression coefficients. …”
Get full text

Quantitative structure-activity relationship study of some angiotensin-converting enzyme inhibitor drugs in the treatment of hypertension based on Monte Carlo optimization method by Shahram Lotfi, Shahin Ahmadi, Ali Azimi

“…Materials & Methods: In this study, quantitative structure-activity relationship to predict the inhibitory activity of the data set containing 255 angiotensin-converting enzyme inhibitor compounds based on the algorithm Monte Carlo was studied. …”
Get full text

Mechanisms and optimization for simultaneous removal of Cd(II) and Sb(V) from aqueous solutions using birnessite and fulvic acid composite by Changsheng Jin, Jingjing Lu, Yin Gao, Baowei Hu, Yuxi Liu

“…The RF model demonstrated superior predictive accuracy (R² = 0.8037, RMSE = 0.0625) compared to the RSM and GABP models. …”
Get full text

Spatial transcriptomics and scRNA-seq: decoding tumor complexity and constructing prognostic models in colorectal cancer by Wei Song, Yatao Wang, Min Zhou, Fengqin Guo, Yanliang Liu

“…We developed a 13-gene prognostic signature (PS) using machine learning algorithm (StepCox backward), which predicts the prognosis of CRC patients. …”
Get full text

Variance exchange process: overcoming the problem of singular information matrices in quadratic three−variable response designs by Okim Ikpan, Felix Nwobi

“…For such matrices, the variances of predicted responses at variance points cannot be evaluated, and the variance exchange process, not possible. …”
Get full text

Development of a mathematical model of dependence of specific volumetric electrical resistance of SIW-4 insulation on factors affecting its reliability by Denisov I. V.

“…It also opens up the possibility of developing the second stage of the study, associated with the construction of an algorithm for the method of predictive assessment of the residual life of the insulation material of the conductor under study.…”
Get full text

Comprehensive analysis of cuproptosis-related genes in immune infiltration and development of a novel diagnostic model for acute kidney injury by Yajing Li, Yingxue Ding

“…The six-gene cuproptosis-related signature exhibited remarkable predictive efficiency for AKI.…”
Get full text

Methodological levels of research the post-industrial development of the city by Olha Suptelo

“…A detailed study of these processes makes it possible to predict the possible paths of developed countries and individual territories. …”
Get full text

Bioinformatics analysis of potential targets influencing the prognosis of OSCC by ZOU Xian, SONG Tao

“…The Timer website was used to analyze the relationship between hub genes and immune cell infiltration and immune checkpoints. Based on Lasso-Cox algorithm, a prognostic risk model of related genes was constructed. …”
Get full text

The J-PLUS collaboration. Additive versus multiplicative systematics in surveys of the large scale structure of the Universe by Carlos Hernández-Monteagudo, G. Aricò, J. Chaves-Montero, L. R. Abramo, P. Arnalte-Mur, A. Hernán-Caballero, Francisco José Galindo-Guil, C. López-Sanjuan, V. Marra, R. von Marttens, E. Tempel, J. Cenarro, D. Cristóbal-Hornillos, A. Marín-Franch, M. Moles, J. Varela, H. Vázquez Ramió, J. Alcaniz, R. Dupke, A. Ederoclite, L. Sodré Jr., R. E. Angulo

“…This model allows us devising a novel algorithm that addresses the identification and correction for either additive and/or multiplicative contaminants. …”
Get full text

Forecasting dengue in Bangladesh using meteorological variables with a novel feature selection approach by Mahadee Al Mobin

“…A novel wrapper feature selection algorithm employing a custom objective function is proposed in this study, which significantly improves model accuracy by 12.63% and reduces the mean absolute percentage error by 70.82%. …”
Get full text