scholarly journals DeepSatData: Building large scale datasets of satellite images for training machine learning models

2021 ◽  
Author(s):  
Michael Tarasiou
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Point Of View ◽  
Learning Models ◽  
Ground Truth Data ◽  
Machine Learning Models ◽  
Sentinel 2

This paper presents DeepSatData a pipeline for automatically generating satellite imagery datasets for training machine learning models. We also discuss design considerations with emphasis on dense classification tasks, e.g. semantic segmentation. The implementation presented makes use of freely available Sentinel-2 data which allows the generation of large scale datasets required for training deep neural networks (DNN). We discuss issues faced from the point of view of DNN training and evaluation such as checking the quality of ground truth data and comment on the scalability of the approach.

scholarly journals DeepSatData: Building large scale datasets of satellite images for training machine learning models

2021 ◽  
Author(s):  
Michael Tarasiou
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Point Of View ◽  
Learning Models ◽  
Ground Truth Data ◽  
Machine Learning Models ◽  
Sentinel 2

This paper presents DeepSatData a pipeline for automatically generating satellite imagery datasets for training machine learning models. We also discuss design considerations with emphasis on dense classification tasks, e.g. semantic segmentation. The implementation presented makes use of freely available Sentinel-2 data which allows the generation of large scale datasets required for training deep neural networks (DNN). We discuss issues faced from the point of view of DNN training and evaluation such as checking the quality of ground truth data and comment on the scalability of the approach.

Collective annotation patterns in learning from crowds

2020 ◽  
Vol 24 ◽  
pp. 63-86
Author(s):  
Francisco Mena ◽  
Ricardo Ñanculef ◽  
Carlos Valle
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Ground Truth ◽  
Experimental Results ◽  
Ground Truth Data ◽  
Satisfactory Performance ◽  
Machine Learning Applications ◽  
Data Points ◽  
Confusion Matrices

The lack of annotated data is one of the major barriers facing machine learning applications today. Learning from crowds, i.e. collecting ground-truth data from multiple inexpensive annotators, has become a common method to cope with this issue. It has been recently shown that modeling the varying quality of the annotations obtained in this way, is fundamental to obtain satisfactory performance in tasks where inexpert annotators may represent the majority but not the most trusted group. Unfortunately, existing techniques represent annotation patterns for each annotator individually, making the models difficult to estimate in large-scale scenarios. In this paper, we present two models to address these problems. Both methods are based on the hypothesis that it is possible to learn collective annotation patterns by introducing confusion matrices that involve groups of data point annotations or annotators. The first approach clusters data points with a common annotation pattern, regardless the annotators from which the labels have been obtained. Implicitly, this method attributes annotation mistakes to the complexity of the data itself and not to the variable behavior of the annotators. The second approach explicitly maps annotators to latent groups that are collectively parametrized to learn a common annotation pattern. Our experimental results show that, compared with other methods for learning from crowds, both methods have advantages in scenarios with a large number of annotators and a small number of annotations per annotator.

scholarly journals Survey of Public Assay Data: Opportunities and Challenges to Understanding Antimicrobial Resistance

2019 ◽  
Author(s):  
Akshay Agarwal ◽  
Gowri Nayar ◽  
James Kaufman
Keyword(s):  
Machine Learning ◽  
Antimicrobial Resistance ◽  
Pathogen Detection ◽  
Ground Truth ◽  
Training Data ◽  
Learning Models ◽  
Learning Methods ◽  
Ground Truth Data ◽  
Specificity And Sensitivity ◽  
Machine Learning Models

ABSTRACTComputational learning methods allow researchers to make predictions, draw inferences, and automate generation of mathematical models. These models are crucial to solving real world problems, such as antimicrobial resistance, pathogen detection, and protein evolution. Machine learning methods depend upon ground truth data to achieve specificity and sensitivity. Since the data is limited in this case, as we will show during the course of this paper, and as the size of available data increases super-linearly, it is of paramount importance to understand the distribution of ground truth data and the analyses it is suited and where it may have limitations that bias downstream learning methods. In this paper, we focus on training data required to model antimicrobial resistance (AR). We report an analysis of bacterial biochemical assay data associated with whole genome sequencing (WGS) from the National Center for Biotechnology Information (NCBI), and discuss important implications when making use of assay data, utilizing genetic features as training data for machine learning models. Complete discussion of machine learning model implementation is outside the scope of this paper and the subject to a later publication.The antimicrobial assay data was obtained from NCBI BioSample, which contains descriptive information about the physical biological specimen from which experimental data is obtained and the results of those experiments themselves.[1] Assay data includes minimum inhibitory concentrations (MIC) of antibiotics, links to associated microbial WGS data, and treatment of a particular microorganism with antibiotics.We observe that there is minimal microbial data available for many antibiotics and for targeted taxonomic groups. The antibiotics with the highest number of assays have less than 1500 measurements each. Corresponding bias in available assays makes machine learning problematic for some important microbes and for building more advanced models that can work across microbial genera. In this study we focus, therefore, on the antibiotic with most assay data (tetracycline) and the corresponding genus with the most available sequence (Acinetobacter with 14000 measurements across 49 antibiotic compounds). Using this data for training and testing, we observed contradictions in the distribution of assay outcomes and report methods to identify and resolve such conflicts. Per antibiotic, we find that there can be up to 30% of (resolvable) conflicting measurements. As more data becomes available, automated training data curation will be an important part of creating useful machine learning models to predict antibiotic resistance.CCS CONCEPTS• Applied computing → Computational biology; Computational genomics; Bioinformatics;

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

scholarly journals Statistical and machine learning models for optimizing energy in parallel applications

2019 ◽  
Vol 33 (6) ◽  
pp. 1079-1097 ◽  
Author(s):  
Mark Endrei ◽  
Chao Jin ◽  
Minh Ngoc Dinh ◽  
David Abramson ◽  
Heidi Poxon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
High Performance ◽  
Large Scale ◽  
Energy Use ◽  
Parallel Applications ◽  
Learning Models ◽  
Trade Off ◽  
Time Required ◽  
Machine Learning Models

Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.

scholarly journals Development of Machine Learning Models to Predict Compressed Sward Height in Walloon Pastures Based on Sentinel-1, Sentinel-2 and Meteorological Data Using Multiple Data Transformations

2021 ◽  
Vol 13 (3) ◽  
pp. 408
Author(s):  
Charles Nickmilder ◽  
Anthony Tedde ◽  
Isabelle Dufrasne ◽  
Françoise Lessire ◽  
Bernard Tychon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Support System ◽  
Cross Validation ◽  
Learning Models ◽  
Data Transformations ◽  
Independent Validation ◽  
Sward Height ◽  
Machine Learning Models ◽  
Sentinel 2

Accurate information about the available standing biomass on pastures is critical for the adequate management of grazing and its promotion to farmers. In this paper, machine learning models are developed to predict available biomass expressed as compressed sward height (CSH) from readily accessible meteorological, optical (Sentinel-2) and radar satellite data (Sentinel-1). This study assumed that combining heterogeneous data sources, data transformations and machine learning methods would improve the robustness and the accuracy of the developed models. A total of 72,795 records of CSH with a spatial positioning, collected in 2018 and 2019, were used and aggregated according to a pixel-like pattern. The resulting dataset was split into a training one with 11,625 pixellated records and an independent validation one with 4952 pixellated records. The models were trained with a 19-fold cross-validation. A wide range of performances was observed (with mean root mean square error (RMSE) of cross-validation ranging from 22.84 mm of CSH to infinite-like values), and the four best-performing models were a cubist, a glmnet, a neural network and a random forest. These models had an RMSE of independent validation lower than 20 mm of CSH at the pixel-level. To simulate the behavior of the model in a decision support system, performances at the paddock level were also studied. These were computed according to two scenarios: either the predictions were made at a sub-parcel level and then aggregated, or the data were aggregated at the parcel level and the predictions were made for these aggregated data. The results obtained in this study were more accurate than those found in the literature concerning pasture budgeting and grassland biomass evaluation. The training of the 124 models resulting from the described framework was part of the realization of a decision support system to help farmers in their daily decision making.

scholarly journals QUBO formulations for training machine learning models

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Prasanna Date ◽  
Davis Arthur ◽  
Lauren Pusey-Nazzaro
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Large Scale ◽  
Support Vector ◽  
Quantum Computers ◽  
Np Hard ◽  
Learning Models ◽  
Moore’S Law ◽  
Moore's Law ◽  
Machine Learning Models

AbstractTraining machine learning models on classical computers is usually a time and compute intensive process. With Moore’s law nearing its inevitable end and an ever-increasing demand for large-scale data analysis using machine learning, we must leverage non-conventional computing paradigms like quantum computing to train machine learning models efficiently. Adiabatic quantum computers can approximately solve NP-hard problems, such as the quadratic unconstrained binary optimization (QUBO), faster than classical computers. Since many machine learning problems are also NP-hard, we believe adiabatic quantum computers might be instrumental in training machine learning models efficiently in the post Moore’s law era. In order to solve problems on adiabatic quantum computers, they must be formulated as QUBO problems, which is very challenging. In this paper, we formulate the training problems of three machine learning models—linear regression, support vector machine (SVM) and balanced k-means clustering—as QUBO problems, making them conducive to be trained on adiabatic quantum computers. We also analyze the computational complexities of our formulations and compare them to corresponding state-of-the-art classical approaches. We show that the time and space complexities of our formulations are better (in case of SVM and balanced k-means clustering) or equivalent (in case of linear regression) to their classical counterparts.

scholarly journals A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

2019 ◽  
Author(s):  
Mojtaba Haghighatlari ◽  
Gaurav Vishwakarma ◽  
Mohammad Atif Faiz Afzal ◽  
Johannes Hachmann
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Organic Molecules ◽  
Learning Model ◽  
Training Data ◽  
Refractive Indices ◽  
Learning Models ◽  
Deep Learning Model ◽  
Machine Learning Models

<div><div><div><p>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</p></div></div></div>

scholarly journals Application of Bioactivity Profile Based Fingerprints for Building Machine Learning Models

2018 ◽  
Author(s):  
Noé Sturm ◽  
Jiangming Sun ◽  
Yves Vandriessche ◽  
Andreas Mayr ◽  
Günter Klambauer ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
High Throughput ◽  
Scaffold Hopping ◽  
Learning Models ◽  
Industrial Data ◽  
Structural Descriptors ◽  
Bioactivity Profile ◽  
Machine Learning Models

<div>This article describes an application of high-throughput fingerprints (HTSFP) built upon industrial data accumulated over the years. </div><div>The fingerprint was used to build machine learning models (multi-task deep learning + SVM) for compound activity predictions towards a panel of 131 targets. </div><div>Quality of the predictions and the scaffold hopping potential of the HTSFP were systematically compared to traditional structural descriptors ECFP. </div><div><br></div>

Sign in / Sign up

Export Citation Format

Share Document