Extensive application of clustering and classification algorithms shows the potential of a CNT-based sensor array in breathomics.
In many application settings, labeling data examples is a costly endeavor, while unlabeled examples are abundant and cheap to produce. Labeling examples can be particularly problematic in an online setting, where there can be arbitrarily many examples that arrive at high frequencies. It is also problematic when we need to predict complex values (e.g., multiple real values), a task that has started receiving considerable attention, but mostly in the batch setting. In this paper, we propose a method for online semi-supervised multi-target regression. It is based on incremental trees for multi-target regression and the predictive clustering framework. Furthermore, it utilizes unlabeled examples to improve its predictive performance as compared to using just the labeled examples. We compare the proposed iSOUP-PCT method with supervised tree methods, which do not use unlabeled examples, and to an oracle method, which uses unlabeled examples as though they were labeled. Additionally, we compare the proposed method to the available state-of-the-art methods. The method achieves good predictive performance on account of increased consumption of computational resources as compared to its supervised variant. The proposed method also beats the state-of-the-art in the case of very few labeled examples in terms of performance, while achieving comparable performance when the labeled examples are more common./=3 for Cd and Cu, and 1-4 for Pb and Zn), the Ramallosa marsh is highly polluted with Cd and moderately to highly polluted with Cu, Pb and Zn. The enrichment factors obtained confirm that the salt marsh is highly polluted (especially with Cd) as the primary result of anthropic activity.", "keywords": ["Industrial Waste", "Reproducibility of Results", "Agriculture", "Pentetic Acid", "15. Life on land", "Waste Disposal", " Fluid", "01 natural sciences", "6. Clean water", "Ion Exchange", "13. Climate action", "Metals", " Heavy", "Wetlands", "Linear Models", "Potentiometry", "Water Pollution", " Chemical", "Soil Pollutants", "Oxidation-Reduction", "Algorithms", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1016/j.jhazmat.2009.05.074"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Hazardous%20Materials", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.jhazmat.2009.05.074", "name": "item", "description": "10.1016/j.jhazmat.2009.05.074", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.jhazmat.2009.05.074"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2009-10-01T00:00:00Z"}}, {"id": "10.1038/s41598-021-02302-2", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:17:52Z", "type": "Journal Article", "created": "2021-11-30", "title": "Predicting sensitivity of recently harvested tomatoes and tomato sepals to future fungal infections", "description": "Abstract
Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.The advent of novel sequencing techniques has unraveled a tremendous diversity on Earth. Genomic data allow us to understand ecology and function of organisms that we would not otherwise know existed. However, major methodological challenges remain, in particular for multicellular organisms with large genomes. Arbuscular mycorrhizal (AM) fungi are important plant symbionts with cryptic and complex multicellular life cycles, thus representing a suitable model system for method development. Here, we report a novel method for large scale, unbiased nuclear sorting, sequencing, and de novo assembling of AM fungal genomes. After comparative analyses of three assembly workflows we discuss how sequence data from single nuclei can best be used for different downstream analyses such as phylogenomics and comparative genomics of single nuclei. Based on analysis of completeness, we conclude that comprehensive de novo genome assemblies can be produced from six to seven nuclei. The method is highly applicable for a broad range of taxa, and will greatly improve our ability to study multicellular eukaryotes with complex life cycles.
", "keywords": ["0301 basic medicine", "Evolutionary Biology", "0303 health sciences", "Genome", "Fungi", "Computational Biology", "Eukaryota", "Genomics", "Article", "Workflow", "Evolutionsbiologi", "03 medical and health sciences", "13. Climate action", "Algorithms"]}, "links": [{"href": "https://www.nature.com/articles/s41598-020-58025-3.pdf"}, {"href": "https://doi.org/10.1038/s41598-020-58025-3"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Scientific%20Reports", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1038/s41598-020-58025-3", "name": "item", "description": "10.1038/s41598-020-58025-3", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1038/s41598-020-58025-3"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-01-28T00:00:00Z"}}, {"id": "10.1039/d1ra03337a", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:17:56Z", "type": "Journal Article", "created": "2021-09-10", "title": "Exploring the performance of a functionalized CNT-based sensor array for breathomics through clustering and classification algorithms: from gas sensing of selective biomarkers to discrimination of chronic obstructive pulmonary disease", "description": "Extensive application of clustering and classification algorithms shows the potential of a CNT-based sensor array in breathomics.
Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, the prediction capacity of new samples is also subject to the number and diversity of soil types and conditions represented in the SSLs. To help bridge this gap and enable hundreds of stakeholders to collect more affordable soil data by leveraging a centralized open resource, the Soil Spectroscopy for Global Good has created the Open Soil Spectral Library (OSSL). In this paper, we describe the procedures for collecting and harmonizing several SSLs that are incorporated into the OSSL, followed by exploratory analysis and predictive modeling. The results of 10-fold cross-validation with refitting show that, in general, mid-infrared (MIR)-based models are significantly more accurate than visible and near-infrared (VisNIR) or near-infrared (NIR) models. From independent model evaluation, we found that Cubist comes out as the best-performing ML algorithm for the calibration and delivery of reliable outputs (prediction uncertainty and representation flag). Although many soil properties are well predicted, total sulfur, extractable sodium, and electrical conductivity performed poorly in all spectral regions, with some other extractable nutrients and physical soil properties also performing poorly in one or two spectral regions (VisNIR or Neospectra NIR). Hence, the use of predictive models based solely on spectral variations has limitations. This study also presents and discusses several other open resources that were developed from the OSSL, aspects of opening data, current limitations, and future development. With this genuinely open science project, we hope that OSSL becomes the driver of the soil spectroscopy community to accelerate the pace of scientific discovery and innovation.Analysis of differential expression of genes is often performed to understand how the metabolic activity of an organism is impacted by a perturbation. However, because the system of metabolic regulation is complex and all changes are not directly reflected in the expression levels, interpreting these data can be difficult.
ResultsIn this work, we present a new algorithm and computational tool that uses a genome-scale metabolic reconstruction to infer metabolic changes from differential expression data. Using the framework of constraint-based analysis, our method produces a qualitative hypothesis of a change in metabolic activity. In other words, each reaction of the network is inferred to have increased, decreased, or remained unchanged in flux. In contrast to similar previous approaches, our method does not require a biological objective function and does not assign on/off activity states to genes. An implementation is provided and it is available online. We apply the method to three published datasets to show that it successfully accomplishes its two main goals: confirming or rejecting metabolic changes suggested by differentially expressed genes based on how well they fit in as parts of a coordinated metabolic change, as well as inferring changes in reactions whose genes did not undergo differential expression.
Availability and implementationgithub.com/htpusa/moomin.
Supplementary informationSupplementary data are available at Bioinformatics online.
", "keywords": ["0301 basic medicine", "570", "[SDV.BIBS] Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]", "Metabolic networks; omics data", "Genome", "[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]", "0206 medical engineering", "610", "Computational Biology", "[INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS]", "02 engineering and technology", "[SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]", "Original Papers", "Models", " Biological", "03 medical and health sciences", "[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]", "Algorithms", "Metabolic Networks and Pathways", "[INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM]"]}, "links": [{"href": "https://iris.uniroma1.it/bitstream/11573/1321358/5/Pusa_MOOMIN_2020.pdf"}, {"href": "https://academic.oup.com/bioinformatics/article-pdf/36/2/514/48991611/btz584.pdf"}, {"href": "https://doi.org/10.1093/bioinformatics/btz584"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Bioinformatics", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1093/bioinformatics/btz584", "name": "item", "description": "10.1093/bioinformatics/btz584", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1093/bioinformatics/btz584"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-08-22T00:00:00Z"}}, {"id": "10.1093/nar/gkz378", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:18:27Z", "type": "Journal Article", "created": "2019-05-06", "title": "Caver Web 1.0: identification of tunnels and channels in proteins and analysis of ligand transport", "description": "AbstractCaver Web 1.0 is a web server for comprehensive analysis of protein tunnels and channels, and study of the ligands\uffe2\uff80\uff99 transport through these transport pathways. Caver Web is the first interactive tool allowing both the analyses within a single graphical user interface. The server is built on top of the abundantly used tunnel detection tool Caver 3.02 and CaverDock 1.0 enabling the study of the ligand transport. The program is easy-to-use as the only required inputs are a protein structure for a tunnel identification and a list of ligands for the transport analysis. The automated guidance procedures assist the users to set up the calculation in a way to obtain biologically relevant results. The identified tunnels, their properties, energy profiles and trajectories for ligands\uffe2\uff80\uff99 passages can be calculated and visualized. The tool is very fast (2\uffe2\uff80\uff9320 min per job) and is applicable even for virtual screening purposes. Its simple setup and comprehensive graphical user interface make the tool accessible for a broad scientific community. The server is freely available at https://loschmidt.chemi.muni.cz/caverweb.
", "keywords": ["0301 basic medicine", "Internet", "0303 health sciences", "Binding Sites", "BINDING; STABILITY; MECHANISM; MYOGLOBIN; MIGRATION; DYNAMICS; KINETICS; PATHWAY; ENZYMES; SERVER", "Computational Biology", "Ligands", "Protein Structure", " Tertiary", "3. Good health", "Molecular Docking Simulation", "Benchmarking", "User-Computer Interface", "03 medical and health sciences", "Web Server Issue", "Animals", "Humans", "Protein Interaction Domains and Motifs", "Amino Acid Sequence", "Carrier Proteins", "Protein Structure", " Quaternary", "Algorithms", "Protein Binding"]}, "links": [{"href": "http://academic.oup.com/nar/article-pdf/47/W1/W414/28880050/gkz378.pdf"}, {"href": "https://doi.org/10.1093/nar/gkz378"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Nucleic%20Acids%20Research", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1093/nar/gkz378", "name": "item", "description": "10.1093/nar/gkz378", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1093/nar/gkz378"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-05-22T00:00:00Z"}}, {"id": "10.1093/toxsci/kfae051", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:18:27Z", "type": "Journal Article", "created": "2024-04-18", "title": "Parameter grouping and co-estimation in physiologically based kinetic models using genetic algorithms", "description": "AbstractPhysiologically based kinetic (PBK) models are widely used in pharmacology and toxicology for predicting the internal disposition of substances upon exposure, voluntarily or not. Due to their complexity, a large number of model parameters need to be estimated, either through in silico tools, in vitro experiments, or by fitting the model to in vivo data. In the latter case, fitting complex structural models on in vivo data can result in overparameterization and produce unrealistic parameter estimates. To address these issues, we propose a novel parameter grouping approach, which reduces the parametric space by co-estimating groups of parameters across compartments. Grouping of parameters is performed using genetic algorithms and is fully automated, based on a novel goodness-of-fit metric. To illustrate the practical application of the proposed methodology, two case studies were conducted. The first case study demonstrates the development of a new PBK model, while the second focuses on model refinement. In the first case study, a PBK model was developed to elucidate the biodistribution of titanium dioxide (TiO2) nanoparticles in rats following intravenous injection. A variety of parameter estimation schemes were employed. Comparative analysis based on goodness-of-fit metrics demonstrated that the proposed methodology yields models that outperform standard estimation approaches, while utilizing a reduced number of parameters. In the second case study, an existing PBK model for perfluorooctanoic acid (PFOA) in rats was extended to incorporate additional tissues, providing a more comprehensive portrayal of PFOA biodistribution. Both models were validated through independent in vivo studies to ensure their reliability.
We lack strong empirical evidence for links between plant attributes (plant community attributes and functional traits) and the distribution of soil microbial communities at large spatial scales.
Using datasets from two contrasting regions and ecosystem types in Australia and England, we report that aboveground plant community attributes, such as diversity (species richness) and cover, and functional traits can predict a unique portion of the variation in the diversity (number of phylotypes) and community composition of soil bacteria and fungi that cannot be explained by soil abiotic properties and climate. We further identify the relative importance and evaluate the potential direct and indirect effects of climate, soil properties and plant attributes in regulating the diversity and community composition of soil microbial communities.
Finally, we deliver a list of examples of common taxa from Australia and England that are strongly related to specific plant traits, such as specific leaf area index, leaf nitrogen and nitrogen fixation.
Together, our work provides new evidence that plant attributes, especially plant functional traits, can predict the distribution of soil microbial communities at the regional scale and across two hemispheres.
In precision agriculture (PA) practices, the accurate delineation of management zones (MZs), with each zone having similar characteristics, is essential for map-based variable rate application of farming inputs. However, there is no consensus on an optimal clustering algorithm and the input data format. In this paper, we evaluated the performances of five clustering algorithms including k-means, fuzzy C-means (FCM), hierarchical, mean shift, and density-based spatial clustering of applications with noise (DBSCAN) in different scenarios and assessed the impacts of input data format and feature selection on MZ delineation quality. We used key soil fertility attributes (moisture content (MC), organic carbon (OC), calcium (Ca), cation exchange capacity (CEC), exchangeable potassium (K), magnesium (Mg), sodium (Na), exchangeable phosphorous (P), and pH) collected with an online visible and near-infrared (vis-NIR) spectrometer along with Sentinel2 and yield data of five commercial fields in Belgium. We demonstrated that k-means is the optimal clustering method for MZ delineation, and the input data should be normalized (range normalization). Feature selection was also shown to be positively effective. Furthermore, we proposed an algorithm based on DBSCAN for smoothing the MZs maps to allow smooth actuating during variable rate application by agricultural machinery. Finally, the whole process of MZ delineation was integrated in a clustering and smoothing pipeline (CaSP), which automatically performs the following steps sequentially: (1) range normalization, (2) feature selection based on cross-correlation analysis, (3) k-means clustering, and (4) smoothing. It is recommended to adopt the developed platform for automatic MZ delineation for variable rate applications of farming inputs.
This technical note presents the experimental validation of a hybrid fire testing coordination algorithm recently developed by some of the authors. For the first time, the algorithm is applied to solve the static response of a multiple-degrees-of-freedom hybrid model.
", "keywords": ["Coordination algorithms", "Fire test", "Dynamic relaxation", "Computer science", "bepress|Engineering", "General Physics and Astronomy", "02 engineering and technology", "0201 civil engineering", "Control theory", "engrXiv|Engineering|Civil and Environmental Engineering", "0202 electrical engineering", " electronic engineering", " information engineering", "General Materials Science", "Safety", " Risk", " Reliability and Quality", "Partitioned time integration", "Hybrid fire testing", "engrXiv|Engineering|Civil and Environmental Engineering|Structural Engineering", "Technical note", "General Chemistry", "Experimental validation", "Hybrid fire testing; Dynamic relaxation; Partitioned time integration", "engrXiv|Engineering", "bepress|Engineering|Civil and Environmental Engineering", "Static response", "bepress|Engineering|Civil and Environmental Engineering|Structural Engineering", "Multi axial", "Hybrid model"]}, "links": [{"href": "https://doi.org/10.31224/osf.io/r8xau"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Fire%20Safety%20Journal", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.31224/osf.io/r8xau", "name": "item", "description": "10.31224/osf.io/r8xau", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.31224/osf.io/r8xau"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-09-02T00:00:00Z"}}, {"id": "10.3390/ijms24076573", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:21:00Z", "type": "Journal Article", "created": "2023-04-03", "title": "A Systematic Review of Deep Learning Methodologies Used in the Drug Discovery Process with Emphasis on In Vivo Validation", "description": "The discovery and development of new drugs are extremely long and costly processes. Recent progress in artificial intelligence has made a positive impact on the drug development pipeline. Numerous challenges have been addressed with the growing exploitation of drug-related data and the advancement of deep learning technology. Several model frameworks have been proposed to enhance the performance of deep learning algorithms in molecular design. However, only a few have had an immediate impact on drug development since computational results may not be confirmed experimentally. This systematic review aims to summarize the different deep learning architectures used in the drug discovery process and are validated with further in vivo experiments. For each presented study, the proposed molecule or peptide that has been generated or identified by the deep learning model has been biologically evaluated in animal models. These state-of-the-art studies highlight that even if artificial intelligence in drug discovery is still in its infancy, it has great potential to accelerate the drug discovery cycle, reduce the required costs, and contribute to the integration of the 3R (Replacement, Reduction, Refinement) principles. Out of all the reviewed scientific articles, seven algorithms were identified: recurrent neural networks, specifically, long short-term memory (LSTM-RNNs), Autoencoders (AEs) and their Wasserstein Autoencoders (WAEs) and Variational Autoencoders (VAEs) variants; Convolutional Neural Networks (CNNs); Direct Message Passing Neural Networks (D-MPNNs); and Multitask Deep Neural Networks (MTDNNs). LSTM-RNNs were the most used architectures with molecules or peptide sequences as inputs.
Structural health monitoring (SHM) allows the acquisition of information on the structural integrity of any mechanical system by processing data, measured through a set of sensors, in order to estimate relevant mechanical parameters and indicators of performance. Herein we present a method to perform the cost\uffe2\uff80\uff93benefit optimization of a sensor network by defining the density, type, and positioning of the sensors to be deployed. The effectiveness (benefit) of an SHM system may be quantified by means of information theory, namely through the expected Shannon information gain provided by the measured data, which allows the inherent uncertainties of the experimental process (i.e., those associated with the prediction error and the parameters to be estimated) to be accounted for. In order to evaluate the computationally expensive Monte Carlo estimator of the objective function, a framework comprising surrogate models (polynomial chaos expansion), model order reduction methods (principal component analysis), and stochastic optimization methods is introduced. Two optimization strategies are proposed: the maximization of the information provided by the measured data, given the technological, identifiability, and budgetary constraints; and the maximization of the information\uffe2\uff80\uff93cost ratio. The application of the framework to a large-scale structural problem, the Pirelli tower in Milan, is presented, and the two comprehensive optimization methods are compared.
", "keywords": ["Stochastic Processes", "structural health monitoring", "structural health monitoring; Bayesian inference; cost\u2013benefit analysis; stochastic optimization; information theory; Bayesian experimental design; surrogate modeling; model order reduction", "Chemical technology", "Cost-Benefit Analysis", "Bayesian inference", "Bayesian experimental design", "Uncertainty", "Bayes Theorem", "TP1-1185", "02 engineering and technology", "stochastic optimization", "Bayesian experimental design; Bayesian inference; Benefit analysis; Cost; Information theory; Model order reduction; Stochastic optimization; Structural health monitoring; Surrogate modeling; Algorithms; Monte Carlo Method; Nonlinear Dynamics; Stochastic Processes; Uncertainty; Bayes Theorem; Cost-Benefit Analysis; Analytical Chemistry; Atomic and Molecular Physics", " and Optics; Biochemistry; Instrumentation; Electrical and Electronic Engineering", "Article", "surrogate modeling", "0201 civil engineering", "Nonlinear Dynamics", "model order reduction", "cost\u2013benefit analysis", "Monte Carlo Method", "Algorithms", "information theory"]}, "links": [{"href": "http://www.mdpi.com/1424-8220/18/7/2174/pdf"}, {"href": "https://re.public.polimi.it/bitstream/11311/1085132/1/Sensors_2018b.pdf"}, {"href": "https://doi.org/10.3929/ethz-b-000278733"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Sensors", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3929/ethz-b-000278733", "name": "item", "description": "10.3929/ethz-b-000278733", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3929/ethz-b-000278733"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2018-07-06T00:00:00Z"}}, {"id": "2954562561", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-07-25T16:26:04Z", "type": "Report", "title": "Decision-Support System for Optimisation of Crop Configuration based on Artificial Intelligence", "description": "The work is the first official outcome of the collaboration between MSU and BS. Here we analysed the potential of multi-objective evolutionary algorithms in smart seed selection.", "keywords": ["Portfolio Optimisation", "Data analytics", "Evolutionary algorithms", "DSS"], "contacts": [{"organization": "Dejan Pavlovic, Oskar Marko, Vladimir Crnojevic, Kalyanmoy Deb,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/2954562561"}, {"rel": "self", "type": "application/geo+json", "title": "2954562561", "name": "item", "description": "2954562561", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2954562561"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-06-29T00:00:00Z"}}, {"id": "10.5281/zenodo.3268521", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-07-25T16:23:22Z", "type": "Report", "title": "Decision-Support System for Optimisation of Crop Configuration based on Artificial Intelligence", "description": "The work is the first official outcome of the collaboration between MSU and BS. Here we analysed the potential of multi-objective evolutionary algorithms in smart seed selection.", "keywords": ["Portfolio Optimisation", "Data analytics", "Evolutionary algorithms", "DSS"], "contacts": [{"organization": "Marko, Oskar, Pavlovi\u0107, Dejan, Crnojevi\u0107, Vladimir, Kalyanmoy Deb,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.3268521"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.3268521", "name": "item", "description": "10.5281/zenodo.3268521", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.3268521"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-06-29T00:00:00Z"}}, {"id": "10.5281/zenodo.3268522", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-07-25T16:23:22Z", "type": "Report", "title": "Decision-Support System for Optimisation of Crop Configuration based on Artificial Intelligence", "description": "The work is the first official outcome of the collaboration between MSU and BS. Here we analysed the potential of multi-objective evolutionary algorithms in smart seed selection.", "keywords": ["Portfolio Optimisation", "Data analytics", "Evolutionary algorithms", "DSS"], "contacts": [{"organization": "Dejan Pavlovic, Oskar Marko, Vladimir Crnojevic, Kalyanmoy Deb,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.3268522"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.3268522", "name": "item", "description": "10.5281/zenodo.3268522", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.3268522"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-06-29T00:00:00Z"}}, {"id": "10807/190102", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:24:54Z", "type": "Journal Article", "created": "2021-09-10", "title": "Exploring the performance of a functionalized CNT-based sensor array for breathomics through clustering and classification algorithms: from gas sensing of selective biomarkers to discrimination of chronic obstructive pulmonary disease", "description": "Extensive application of clustering and classification algorithms shows the potential of a CNT-based sensor array in breathomics.
In precision agriculture (PA) practices, the accurate delineation of management zones (MZs), with each zone having similar characteristics, is essential for map-based variable rate application of farming inputs. However, there is no consensus on an optimal clustering algorithm and the input data format. In this paper, we evaluated the performances of five clustering algorithms including k-means, fuzzy C-means (FCM), hierarchical, mean shift, and density-based spatial clustering of applications with noise (DBSCAN) in different scenarios and assessed the impacts of input data format and feature selection on MZ delineation quality. We used key soil fertility attributes (moisture content (MC), organic carbon (OC), calcium (Ca), cation exchange capacity (CEC), exchangeable potassium (K), magnesium (Mg), sodium (Na), exchangeable phosphorous (P), and pH) collected with an online visible and near-infrared (vis-NIR) spectrometer along with Sentinel2 and yield data of five commercial fields in Belgium. We demonstrated that k-means is the optimal clustering method for MZ delineation, and the input data should be normalized (range normalization). Feature selection was also shown to be positively effective. Furthermore, we proposed an algorithm based on DBSCAN for smoothing the MZs maps to allow smooth actuating during variable rate application by agricultural machinery. Finally, the whole process of MZ delineation was integrated in a clustering and smoothing pipeline (CaSP), which automatically performs the following steps sequentially: (1) range normalization, (2) feature selection based on cross-correlation analysis, (3) k-means clustering, and (4) smoothing. It is recommended to adopt the developed platform for automatic MZ delineation for variable rate applications of farming inputs.
We lack strong empirical evidence for links between plant attributes (plant community attributes and functional traits) and the distribution of soil microbial communities at large spatial scales.
Using datasets from two contrasting regions and ecosystem types in Australia and England, we report that aboveground plant community attributes, such as diversity (species richness) and cover, and functional traits can predict a unique portion of the variation in the diversity (number of phylotypes) and community composition of soil bacteria and fungi that cannot be explained by soil abiotic properties and climate. We further identify the relative importance and evaluate the potential direct and indirect effects of climate, soil properties and plant attributes in regulating the diversity and community composition of soil microbial communities.
Finally, we deliver a list of examples of common taxa from Australia and England that are strongly related to specific plant traits, such as specific leaf area index, leaf nitrogen and nitrogen fixation.
Together, our work provides new evidence that plant attributes, especially plant functional traits, can predict the distribution of soil microbial communities at the regional scale and across two hemispheres.
This technical note presents the experimental validation of a hybrid fire testing coordination algorithm recently developed by some of the authors. For the first time, the algorithm is applied to solve the static response of a multiple-degrees-of-freedom hybrid model.", "keywords": ["Coordination algorithms", "Fire test", "Dynamic relaxation", "Computer science", "bepress|Engineering", "General Physics and Astronomy", "02 engineering and technology", "0201 civil engineering", "Control theory", "engrXiv|Engineering|Civil and Environmental Engineering", "0202 electrical engineering", " electronic engineering", " information engineering", "General Materials Science", "Safety", " Risk", " Reliability and Quality", "Partitioned time integration", "Hybrid fire testing", "engrXiv|Engineering|Civil and Environmental Engineering|Structural Engineering", "Technical note", "General Chemistry", "Experimental validation", "Hybrid fire testing; Dynamic relaxation; Partitioned time integration", "engrXiv|Engineering", "bepress|Engineering|Civil and Environmental Engineering", "Static response", "bepress|Engineering|Civil and Environmental Engineering|Structural Engineering", "Multi axial", "Hybrid model"]}, "links": [{"href": "https://doi.org/20.500.11850/510230"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Fire%20Safety%20Journal", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "20.500.11850/510230", "name": "item", "description": "20.500.11850/510230", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/20.500.11850/510230"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-09-02T00:00:00Z"}}, {"id": "20.500.14243/532031", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:25:34Z", "type": "Journal Article", "created": "2022-10-03", "title": "Mathematical techniques to remove moisture effects from visible\u2013near-infrared\u2013shortwave-infrared soil spectra\u2014review", "description": "This is an Accepted Manuscript of an article published by Taylor & Francis in Applied Spectroscopy Reviews on 03 October 2022, available at: https://doi.org/10.1080/05704928.2022.2128365", "keywords": ["EJP Soil", "Proximal Sensing", "ProbeField", "Soil Moisture", "04 agricultural and veterinary sciences", "algorithms", "01 natural sciences", "diffuse reflectance spectroscopy", "field-moist conditions", "EJPSOIL", "0401 agriculture", " forestry", " and fisheries", "indices", "Soil moisture", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://www.tandfonline.com/doi/pdf/10.1080/05704928.2022.2128365"}, {"href": "https://doi.org/20.500.14243/532031"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Applied%20Spectroscopy%20Reviews", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "20.500.14243/532031", "name": "item", "description": "20.500.14243/532031", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/20.500.14243/532031"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-10-03T00:00:00Z"}}, {"id": "2117/83996", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-07-25T16:25:41Z", "type": "Report", "title": "Sistemas TCM-8PSK en canales con interferencia intersimbolica", "description": "Peer Reviewed", "keywords": ["Algorismes", ":Enginyeria de la telecomunicaci\u00f3 [\u00c0rees tem\u00e0tiques de la UPC]", "\u00c0rees tem\u00e0tiques de la UPC::Enginyeria de la telecomunicaci\u00f3", "Algorithms"], "contacts": [{"organization": "Femenias Nadal, Guillem", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/2117/83996"}, {"rel": "self", "type": "application/geo+json", "title": "2117/83996", "name": "item", "description": "2117/83996", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2117/83996"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "1991-01-01T00:00:00Z"}}, {"id": "3215851315", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:26:26Z", "type": "Journal Article", "created": "2021-11-30", "title": "Predicting sensitivity of recently harvested tomatoes and tomato sepals to future fungal infections", "description": "AbstractTomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.Physiologically based kinetic (PBK) models are widely used in pharmacology and toxicology for predicting the internal disposition of substances upon exposure, voluntarily or not. Due to their complexity, a large number of model parameters need to be estimated, either through in silico tools, in vitro experiments, or by fitting the model to in vivo data. In the latter case, fitting complex structural models on in vivo data can result in overparameterization and produce unrealistic parameter estimates. To address these issues, we propose a novel parameter grouping approach, which reduces the parametric space by co-estimating groups of parameters across compartments. Grouping of parameters is performed using genetic algorithms and is fully automated, based on a novel goodness-of-fit metric. To illustrate the practical application of the proposed methodology, two case studies were conducted. The first case study demonstrates the development of a new PBK model, while the second focuses on model refinement. In the first case study, a PBK model was developed to elucidate the biodistribution of titanium dioxide (TiO2) nanoparticles in rats following intravenous injection. A variety of parameter estimation schemes were employed. Comparative analysis based on goodness-of-fit metrics demonstrated that the proposed methodology yields models that outperform standard estimation approaches, while utilizing a reduced number of parameters. In the second case study, an existing PBK model for perfluorooctanoic acid (PFOA) in rats was extended to incorporate additional tissues, providing a more comprehensive portrayal of PFOA biodistribution. Both models were validated through independent in vivo studies to ensure their reliability. The discovery and development of new drugs are extremely long and costly processes. Recent progress in artificial intelligence has made a positive impact on the drug development pipeline. Numerous challenges have been addressed with the growing exploitation of drug-related data and the advancement of deep learning technology. Several model frameworks have been proposed to enhance the performance of deep learning algorithms in molecular design. However, only a few have had an immediate impact on drug development since computational results may not be confirmed experimentally. This systematic review aims to summarize the different deep learning architectures used in the drug discovery process and are validated with further in vivo experiments. For each presented study, the proposed molecule or peptide that has been generated or identified by the deep learning model has been biologically evaluated in animal models. These state-of-the-art studies highlight that even if artificial intelligence in drug discovery is still in its infancy, it has great potential to accelerate the drug discovery cycle, reduce the required costs, and contribute to the integration of the 3R (Replacement, Reduction, Refinement) principles. Out of all the reviewed scientific articles, seven algorithms were identified: recurrent neural networks, specifically, long short-term memory (LSTM-RNNs), Autoencoders (AEs) and their Wasserstein Autoencoders (WAEs) and Variational Autoencoders (VAEs) variants; Convolutional Neural Networks (CNNs); Direct Message Passing Neural Networks (D-MPNNs); and Multitask Deep Neural Networks (MTDNNs). LSTM-RNNs were the most used architectures with molecules or peptide sequences as inputs.
Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, the prediction capacity of new samples is also subject to the number and diversity of soil types and conditions represented in the SSLs. To help bridge this gap and enable hundreds of stakeholders to collect more affordable soil data by leveraging a centralized open resource, the Soil Spectroscopy for Global Good has created the Open Soil Spectral Library (OSSL). In this paper, we describe the procedures for collecting and harmonizing several SSLs that are incorporated into the OSSL, followed by exploratory analysis and predictive modeling. The results of 10-fold cross-validation with refitting show that, in general, mid-infrared (MIR)-based models are significantly more accurate than visible and near-infrared (VisNIR) or near-infrared (NIR) models. From independent model evaluation, we found that Cubist comes out as the best-performing ML algorithm for the calibration and delivery of reliable outputs (prediction uncertainty and representation flag). Although many soil properties are well predicted, total sulfur, extractable sodium, and electrical conductivity performed poorly in all spectral regions, with some other extractable nutrients and physical soil properties also performing poorly in one or two spectral regions (VisNIR or Neospectra NIR). Hence, the use of predictive models based solely on spectral variations has limitations. This study also presents and discusses several other open resources that were developed from the OSSL, aspects of opening data, current limitations, and future development. With this genuinely open science project, we hope that OSSL becomes the driver of the soil spectroscopy community to accelerate the pace of scientific discovery and innovation.Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.