Search results for "machine learning"

showing 10 items of 1464 documents

Thompson Sampling Based Active Learning in Probabilistic Programs with Application to Travel Time Estimation

2019

The pertinent problem of Traveling Time Estimation (TTE) is to estimate the travel time, given a start location and a destination, solely based on the coordinates of the points under consideration. This is typically solved by fitting a function based on a sequence of observations. However, it can be expensive or slow to obtain labeled data or measurements to calibrate the estimation function. Active Learning tries to alleviate this problem by actively selecting samples that minimize the total number of samples needed to do accurate inference. Probabilistic Programming Languages (PPL) give us the opportunities to apply powerful Bayesian inference to model problems that involve uncertainties.…

0106 biological sciencesEstimation0303 health sciencesSequenceActive learning (machine learning)business.industryComputer scienceProbabilistic logicInferenceFunction (mathematics)Bayesian inferenceMachine learningcomputer.software_genre010603 evolutionary biology01 natural sciences03 medical and health sciencesArtificial intelligencebusinesscomputerThompson sampling030304 developmental biology
researchProduct

A Methodology to Derive Global Maps of Leaf Traits Using Remote Sensing and Climate Data

2018

This paper introduces a modular processing chain to derive global high-resolution maps of leaf traits. In particular, we present global maps at 500 m resolution of specific leaf area, leaf dry matter content, leaf nitrogen and phosphorus content per dry mass, and leaf nitrogen/phosphorus ratio. The processing chain exploits machine learning techniques along with optical remote sensing data (MODIS/Landsat) and climate data for gap filling and up-scaling of in-situ measured leaf traits. The chain first uses random forests regression with surrogates to fill gaps in the database (> 45% of missing entries) and maximizes the global representativeness of the trait dataset. Plant species are then a…

0106 biological sciencesFOS: Computer and information sciences010504 meteorology & atmospheric sciencesSpecific leaf areaClimateBos- en LandschapsecologieSoil ScienceFOS: Physical sciencesApplied Physics (physics.app-ph)010603 evolutionary biology01 natural sciencesStatistics - ApplicationsGoodness of fitAbundance (ecology)Machine learningForest and Landscape EcologyApplications (stat.AP)Computers in Earth SciencesPlant ecologyVegetatie0105 earth and related environmental sciencesRemote sensingMathematics2. Zero hungerPlant traitsVegetationData stream miningClimate; Landsat; Machine learning; MODIS; Plant ecology; Plant traits; Random forests; Remote sensing; Soil Science; Geology; Computers in Earth SciencesGlobal MapRegression analysisGeologyPhysics - Applied Physics15. Life on landRandom forestsRemote sensingPE&RCRandom forestMODISTraitVegetatie Bos- en LandschapsecologieVegetation Forest and Landscape EcologyLandsat
researchProduct

Temperate Fish Detection and Classification: a Deep Learning based Approach

2021

A wide range of applications in marine ecology extensively uses underwater cameras. Still, to efficiently process the vast amount of data generated, we need to develop tools that can automatically detect and recognize species captured on film. Classifying fish species from videos and images in natural environments can be challenging because of noise and variation in illumination and the surrounding habitat. In this paper, we propose a two-step deep learning approach for the detection and classification of temperate fishes without pre-filtering. The first step is to detect each single fish in an image, independent of species and sex. For this purpose, we employ the You Only Look Once (YOLO) …

0106 biological sciencesFOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognition010603 evolutionary biology01 natural sciencesConvolutional neural networkVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420Machine Learning (cs.LG)Artificial IntelligenceClassifier (linguistics)FOS: Electrical engineering electronic engineering information engineeringbusiness.industry010604 marine biology & hydrobiologyDeep learningImage and Video Processing (eess.IV)Process (computing)Pattern recognitionElectrical Engineering and Systems Science - Image and Video ProcessingObject detectionA priori and a posterioriNoise (video)Artificial intelligenceTransfer of learningbusiness
researchProduct

Machine learning predictions of trophic status indicators and plankton dynamic in coastal lagoons

2018

Abstract Multivariate trophic indices provide an efficient way to assess and classify the eutrophication level and ecological status of a given water body, but their computation requires the availability of experimental information on many parameters, including biological data, that might not always be available. Here we show that machine learning techniques – once trained against a full data set – can be used to infer plankton biomass information from chemical and physical parameter only, so that trophic index can then be computed without using additional biological data. More specifically, we reconstruct plankton information from chemical and physical data, and this information together w…

0106 biological sciencesGeneral Decision Sciences010501 environmental sciencesMachine learningcomputer.software_genre01 natural sciencesZooplanktonPhytoplankton14. Life underwaterEcology Evolution Behavior and SystematicsComputingMilieux_MISCELLANEOUS0105 earth and related environmental sciencesTrophic levelBiological dataEcologybusiness.industry010604 marine biology & hydrobiologyPlanktonEcological indicator[SDE]Environmental SciencesEnvironmental scienceArtificial intelligenceTrixbusinessEutrophicationcomputer
researchProduct

Unsupervised Classification of Acoustic Echoes from Two Krill Species in the Southern Ocean (Ross Sea)

2021

This work presents a computational methodology able to automatically classify the echoes of two krill species recorded in the Ross sea employing scientific echo-sounder at three different frequencies (38, 120 and 200 kHz). The goal of classifying the gregarious species represents a time-consuming task and is accomplished by using differences and/or thresholds estimated on the energy features of the insonified targets. Conversely, our methodology takes into account energy, morphological and depth features of echo data, acquired at different frequencies. Internal validation indices of clustering were used to verify the ability of the clustering in recognizing the correct number of species. Th…

0106 biological sciencesKrillbiologybusiness.industry010604 marine biology & hydrobiologyEuphausiaSettore MAT/01 - Logica MatematicaEuphausia crystallorophiasbiology.organism_classificationSpatial distributionMachine learning for pelagic species classification01 natural sciencesKrill identification010104 statistics & probabilityRoss SeaAcoustic dataArtificial intelligence0101 mathematicsCluster analysisbusinessRelative species abundanceGeologyEnergy (signal processing)Global biodiversityRemote sensing
researchProduct

Gene flow relates to evolutionary divergence among populations at the range margin

2020

Background Morphological differentiation between populations resulting from local adaptations to environmental conditions is likely to be more pronounced in populations with increasing genetic isolation. In a previous study a positive clinal variation in body size was observed in isolated Roesel’s bush-cricket, Metrioptera roeselii, populations, but were absent from populations within a continuous distribution at the same latitudinal range. This observational study inferred that there was a phenotypic effect of gene flow on climate-induced selection in this species. Methods To disentangle genetic versus environmental drivers of population differences in morphology, we measured the size of …

0106 biological sciencesRange (biology)Climatelcsh:MedicineBody sizeBiology010603 evolutionary biology01 natural sciencesGeneral Biochemistry Genetics and Molecular BiologyGene flowEvolutionsbiologi03 medical and health sciencesAdaptive divergenceMargin (machine learning)GeneticsGenetikGenetic isolation030304 developmental biologyEvolutionary Biology0303 health sciencesEcologyMorphological differentiationGeneral Neurosciencelcsh:RVDP::Matematikk og Naturvitenskap: 400Body sizeGeneral MedicineEvolutionary StudiesEvolutionary biologyOrthopteraEvolutionary divergenceGeneral Agricultural and Biological SciencesEntomologyZoologyGenetic isolatePeerJ
researchProduct

Monitoring internet trade to inform species conservation actions

2017

Specimens, parts and products of threatened species are now commonly traded on the internet. This could threaten the survival of some wild populations if inadequately regulated. We outline two methods to monitor internet sales of threatened species in order to assess potential threats and inform conservation actions. Our first method combines systematic monitoring of online offers of plants for sale over the internet with consultation by experts experienced in identifying plants collected from the wild based on images of the specimens, species identity and details of the trade. Our second method utilises a computational model, trained using Bayesian techniques to records that have been clas…

0106 biological sciencesSettore BIO/07 - EcologiaEcologybusiness.industry010604 marine biology & hydrobiologyInternet privacyfood and beverages010603 evolutionary biology01 natural scienceslcsh:QK1-989Geographylcsh:Botanylcsh:ZoologySettore BIO/03 - Botanica Ambientale E ApplicataThe InternetAdenia Commiphora Operculicarya Uncarina Machine learning Infer.NET Naive Bayes classifierlcsh:QL1-991businessNature and Landscape Conservation
researchProduct

Partitioning net carbon dioxide fluxes into photosynthesis and respiration using neural networks

2020

Abstract The eddy covariance (EC) technique is used to measure the net ecosystem exchange (NEE) of CO2 between ecosystems and the atmosphere, offering a unique opportunity to study ecosystem responses to climate change. NEE is the difference between the total CO2 release due to all respiration processes (RECO), and the gross carbon uptake by photosynthesis (GPP). These two gross CO2 fluxes are derived from EC measurements by applying partitioning methods that rely on physiologically based functional relationships with a limited number of environmental drivers. However, the partitioning methods applied in the global FLUXNET network of EC observations do not account for the multiple co‐acting…

0106 biological sciencesecosystem respiration010504 meteorology & atmospheric sciencesnet ecosystem exchangeneural networkEddy covarianceClimate changeAtmospheric sciencesPhotosynthesis01 natural sciences7. Clean energyCarbon CycleAtmosphereFlux (metallurgy)FluxNetRespirationeddy covarianceEnvironmental ChemistryEcosystemPrimary Research ArticlePhotosynthesisEcosystem0105 earth and related environmental sciencesGeneral Environmental ScienceGlobal and Planetary ChangeEcologycarbon dioxide fluxes partitioningRespirationgross primary production (GPP)Carbon DioxideBiological Sciences15. Life on landgross primary productionmachine learning13. Climate action[SDE]Environmental SciencesEnvironmental scienceNeural Networks ComputerSeasonsecosystem respiration (RECO)Environmental Sciences010606 plant biology & botanyGlobal Change Biology
researchProduct

Which traits allow weed species to persist in grass margin strips ?

2017

EASPEGESTADINRA; Sown-grass margin strips, historically established to limit pesticide drift and soil erosion, are now also promoted for enhancing floral diversity and associated ecosystem services. To better understand weed community assembly in grass margin strips, we performed floral surveys in 75 sown-grass margin strips in two regions in France and characterized each species using information from trait databases. We hypothesized that traits of dominant species would differ between newly sown-grass margin strips and older strips. Weed species were separated into functional groups based on their traits using multiple correspondence analysis and hierarchical ascendant classification. Fun…

0106 biological sciencesfunctional group[SDV]Life Sciences [q-bio]Plant ScienceBiology010603 evolutionary biology01 natural sciencesMonocotyledonEcosystem servicesagri-environmental schemesMargin (machine learning)field marginRuderal species2. Zero hunger[ SDV ] Life Sciences [q-bio]traitEcologyfungiDicotyledonfood and beverages04 agricultural and veterinary sciences15. Life on landbiology.organism_classificationfield edgeDisturbance (ecology)040103 agronomy & agricultureTrait0401 agriculture forestry and fisheriescommunity assemblyWeedAgronomy and Crop Science
researchProduct

Ant Colony Optimisation-Based Classification Using Two-Dimensional Polygons

2016

The application of Ant Colony Optimization to the field of classification has mostly been limited to hybrid approaches which attempt at boosting the performance of existing classifiers (such as Decision Trees and Support Vector Machines (SVM)) — often through guided feature reductions or parameter optimizations.

0209 industrial biotechnologyBoosting (machine learning)business.industryComputer scienceAnt colony optimization algorithmsDecision treePattern recognition02 engineering and technologyAnt colonycomputer.software_genreSwarm intelligenceSupport vector machineComputingMethodologies_PATTERNRECOGNITION020901 industrial engineering & automationKernel method0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligenceData miningbusinesscomputer
researchProduct