scholarly journals Machine Learning in KM3NeT

2019 ◽  
Vol 207 ◽  
pp. 05004 ◽  
Author(s):  
Chiara De Sio
Keyword(s):  
Machine Learning ◽  
Network Models ◽  
High Energy ◽  
Particle Identification ◽  
Machine Learning Techniques ◽  
Neutrino Interaction ◽  
Mass Hierarchy ◽  
Reconstruction Algorithms ◽  
Neural Network Models ◽  
Neutrino Mass Hierarchy

The KM3NeT Collaboration is building a network of underwater Cherenkov telescopes at two sites in the Mediterranean Sea, with the main goals of investigating astrophysical sources of high-energy neutrinos (ARCA) and of determining the neutrino mass hierarchy (ORCA). Various Machine Learning techniques, such as Random Forests, BDTs, Shallow and Deep Networks are being used for diverse tasks, such as event-type and particle identification, energy/direction estimation, source identification, signal/background discrimination and data analysis, with sound results as well as promising research paths. The main focus of this work is the application of Convolutional Neural Network models to the tasks of neutrino interaction classification, as well as the estimation of energy and direction of the propagating particles. The performances are also compared to those of the standard reconstruction algorithms used in the Collaboration.

scholarly journals Comparison of Implicit vs. Explicit Regime Identification in Machine Learning Methods for Solar Irradiance Prediction

Energies ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 689 ◽  
Author(s):  
Tyler McCandless ◽  
Susan Dettling ◽  
Sue Ellen Haupt
Keyword(s):  
Machine Learning ◽  
Solar Power ◽  
Network Models ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Validation Dataset ◽  
Prediction Errors ◽  
Learning Approaches ◽  
Power Prediction ◽  
Neural Network Models

This work compares the solar power forecasting performance of tree-based methods that include implicit regime-based models to explicit regime separation methods that utilize both unsupervised and supervised machine learning techniques. Previous studies have shown an improvement utilizing a regime-based machine learning approach in a climate with diverse cloud conditions. This study compares the machine learning approaches for solar power prediction at the Shagaya Renewable Energy Park in Kuwait, which is in an arid desert climate characterized by abundant sunshine. The regime-dependent artificial neural network models undergo a comprehensive parameter and hyperparameter tuning analysis to minimize the prediction errors on a test dataset. The final results that compare the different methods are computed on an independent validation dataset. The results show that the tree-based methods, the regression model tree approach, performs better than the explicit regime-dependent approach. These results appear to be a function of the predominantly sunny conditions that limit the ability of an unsupervised technique to separate regimes for which the relationship between the predictors and the predictand would differ for the supervised learning technique.

scholarly journals Revisiting the Contested Role of Natural Resources in Violent Conflict Risk through Machine Learning

2020 ◽  
Vol 12 (16) ◽  
pp. 6574
Author(s):  
Marie K. Schellens ◽  
Salim Belyazid
Keyword(s):  
Machine Learning ◽  
Natural Resources ◽  
Natural Resource ◽  
Network Models ◽  
Violent Conflict ◽  
Machine Learning Techniques ◽  
Economic Conditions ◽  
Neural Network Models ◽  
Logistic Regression Models ◽  
Conflict Risk

The integrated character of the sustainable development goals in Agenda 2030, as well as research in environmental security, flag that sustainable peace requires sustainable and conflict-sensitive natural resource use. The precise relationship between the risk for violent conflict and natural resources remains contested because of the interplay with socio-economic variables. This paper aims to improve the understanding of natural resources’ role in the risk of violent conflicts by accounting for complex interactions with socio-economic conditions. Conflict data was analysed with machine learning techniques, which can account for complex patterns, such as variable interactions. More commonly used logistic regression models are compared with neural network models and random forest models. The results indicate that a country’s natural resource features are important predictors of its risk for violent conflict and that they interact with socio-economic conditions. Based on these empirical results and the existing literature, we interpret that natural resources can be root causes of violent intrastate conflict, and that signals from natural resources leading to conflict risk are reflected in and influenced by interacting socio-economic conditions. More specifically, the results show that variables such as access to water and food security are important predictors of conflict, while resource rents and oil and ore exports are relatively less important than other natural resource variables, contrasting what prior research has suggested. Given the potential of natural resource features to act as an early warning for violent conflict, we argue that natural resources should be included in conflict risk models for conflict prevention.

scholarly journals Machine Learning in Agriculture Application: Algorithms and Techniques

2020 ◽  
Vol 9 (6) ◽  
pp. 1140-1146
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
High Performance ◽  
Network Models ◽  
Processing Technique ◽  
Machine Learning Techniques ◽  
Image Processing Technique ◽  
Neural Network Models ◽  
Survey Paper ◽  
Learning Techniques

Machine learning techniques with high performance computing technologies can create various new opportunities in the agriculture domain. This paper does comprehensivereview of various papers which are concentrating on machine learning (ML) and deep learning application in agriculture. This paper is categorized into three sections a) Yield prediction using machine learning technique b) Price prediction c) Leaf disease detection using neural networks. In this paper we study the comparison of neural network models with existing models. The findings of this survey paper indicate Deep learning models give high accuracy and outperform traditional image processing technique and ML techniques outperforms various traditional techniques in prediction.

scholarly journals Disease Identification in Chilli Leaves using Machine Learning Techniques

2019 ◽  
Vol 9 (1S3) ◽  
pp. 325-329
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Detection System ◽  
Network Models ◽  
Detection Algorithm ◽  
Machine Learning Techniques ◽  
Neural Network Models ◽  
The Past ◽  
Learning Techniques ◽  
Proposed Model

Crop diseases reduce the yield of the crop or may even kill it. Over the past two years, as per the I.C.A.R, the production of chilies in the state of Goa has reduced drastically due to the presence of virus. Most of the plants flower very less or stop flowering completely. In rare cases when a plant manages to flower, the yield is substantially low. Proposed model detects the presence of disease in crops by examining the symptoms. The model uses an object detection algorithm and supervised image recognition and feature extraction using convolutional neural network to classify crops as infected or healthy. Google machine learning libraries, TensorFlow and Keras are used to build neural network models. An Android application is developed around the model for the ease of using the disease detection system.

scholarly journals Towards Robust Representations of Spatial Networks Using Graph Neural Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6918
Author(s):  
Chidubem Iddianozie ◽  
Gavin McArdle
Keyword(s):  
Machine Learning ◽  
Model Performance ◽  
Network Models ◽  
Data Representation ◽  
Spatial Networks ◽  
Neural Network Models ◽  
Improve Model ◽  
Graph Neural Networks ◽  
Spatial Entities ◽  
Improve Model Performance

The effectiveness of a machine learning model is impacted by the data representation used. Consequently, it is crucial to investigate robust representations for efficient machine learning methods. In this paper, we explore the link between data representations and model performance for inference tasks on spatial networks. We argue that representations which explicitly encode the relations between spatial entities would improve model performance. Specifically, we consider homogeneous and heterogeneous representations of spatial networks. We recognise that the expressive nature of the heterogeneous representation may benefit spatial networks and could improve model performance on certain tasks. Thus, we carry out an empirical study using Graph Neural Network models for two inference tasks on spatial networks. Our results demonstrate that heterogeneous representations improves model performance for down-stream inference tasks on spatial networks.

scholarly journals A novel reconstruction framework for an imaging calorimeter for HL-LHC

2021 ◽  
Vol 251 ◽  
pp. 03013
Author(s):  
Leonardo Cristella ◽  
Keyword(s):  
Clustering Algorithm ◽  
Particle Identification ◽  
Machine Learning Techniques ◽  
Radiation Tolerance ◽  
Reconstruction Algorithms ◽  
High Luminosity ◽  
Silicon Sensors ◽  
Learning Techniques ◽  
Recent Developments ◽  
Speed And Accuracy

To sustain the harsher conditions of the high-luminosity LHC, the CMS collaboration is designing a novel endcap calorimeter system. The new calorimeter will predominantly use silicon sensors to achieve sufficient radiation tolerance and will maintain highly-granular information in the readout to help mitigate the effects of pileup. In regions characterised by lower radiation levels, small scintillator tiles with individual on-tile SiPM readout are employed. A unique reconstruction framework (TICL: The Iterative CLustering) is being developed to fully exploit the granularity and other significant detector features, such as particle identification and precision timing, with a view to mitigate pileup in the very dense environment of HL-LHC. The inputs to the framework are clusters of energy deposited in individual calorimeter layers. Clusters are formed by a density-based algorithm. Recent developments and tunes of the clustering algorithm will be presented. To help reduce the expected pressure on the computing resources in the HL-LHC era, the algorithms and their data structures are designed to be executed on GPUs. Preliminary results will be presented on decreases in clustering time when using GPUs versus CPUs. Ideas for machine-learning techniques to further improve the speed and accuracy of reconstruction algorithms will be presented.

Artificial Metabolic Networks: enabling neural computation with metabolic networks

2022 ◽  
Author(s):  
Leon Faure ◽  
Bastien Mollet ◽  
Wolfram Liebermeister ◽  
Jean-Loup Faulon
Keyword(s):  
Machine Learning ◽  
Recurrent Neural Networks ◽  
Metabolic Networks ◽  
Cross Validation ◽  
Regression Coefficient ◽  
Network Models ◽  
Biotechnological Applications ◽  
Neural Network Models ◽  
Surrogate Constraint ◽  
Constraint Based Modeling

Metabolic networks have largely been exploited as mechanistic tools to predict the behavior of microorganisms with a defined genotype in different environments. However, flux predictions by constraint-based modeling approaches are limited in quality unless labor-intensive experiments including the measurement of media intake fluxes, are performed. Using machine learning instead of an optimization of biomass flux - on which most existing constraint-based methods are based - provides ways to improve flux and growth rate predictions. In this paper, we show how Recurrent Neural Networks can surrogate constraint-based modeling and make metabolic networks suitable for backpropagation and consequently be used as an architecture for machine learning. We refer to our hybrid - mechanistic and neural network - models as Artificial Metabolic Networks (AMN). We showcase AMN and illustrate its performance with an experimental dataset of Escherichia coli growth rates in 73 different media compositions. We reach a regression coefficient of R2=0.78 on cross-validation sets. We expect AMNs to provide easier discovery of metabolic insights and prompt new biotechnological applications.

CONVOLUTIONAL NEURAL NETWORKS AS AN AID TO BIOSTRATIGRAPHY AND MICROPALEONTOLOGY: A TEST ON LATE PALEOZOIC MICROFOSSILS

Palaios ◽  
2020 ◽  
Vol 35 (9) ◽  
pp. 391-402 ◽  
Author(s):  
RAFAEL PIRES DE LIMA ◽  
KATIE F. WELCH ◽  
JAMES E. BARRICK ◽  
KURT J. MARFURT ◽  
ROGER BURKHALTER ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cross Validation ◽  
Network Models ◽  
Late Paleozoic ◽  
Neural Network Models ◽  
Thin Sections ◽  
Machine Learning Approach ◽  
Taxonomic Groups ◽  
And Training

ABSTRACT Accurate taxonomic classification of microfossils in thin-sections is an important biostratigraphic procedure. As paleontological expertise is typically restricted to specific taxonomic groups and experts are not present in all institutions, geoscience researchers often suffer from lack of quick access to critical taxonomic knowledge for biostratigraphic analyses. Moreover, diminishing emphasis on education and training in systematics poses a major challenge for the future of biostratigraphy, and on associated endeavors reliant on systematics. Here we present a machine learning approach to classify and organize fusulinids—microscopic index fossils for the late Paleozoic. The technique we employ has the potential to use such important taxonomic knowledge in models that can be applied to recognize and categorize fossil specimens. Our results demonstrate that, given adequate images and training, convolutional neural network models can correctly identify fusulinids with high levels of accuracy. Continued efforts in digitization of biological and paleontological collections at numerous museums and adoption of machine learning by paleontologists can enable the development of highly accurate and easy-to-use classification tools and, thus, facilitate biostratigraphic analyses by non-experts as well as allow for cross-validation of disparate collections around the world. Automation of classification work would also enable expert paleontologists and others to focus efforts on exploration of more complex interpretations and concepts.

scholarly journals Comparison of rule-based and neural network models for negation detection in radiology reports

2020 ◽  
pp. 1-22 ◽  
Author(s):  
D. Sykes ◽  
A. Grivas ◽  
C. Grover ◽  
R. Tobin ◽  
C. Sudlow ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Language Processing ◽  
Network Models ◽  
Neural Network Models ◽  
Test Set ◽  
Rule Based ◽  
Radiology Reports ◽  
The Neural Network ◽  
Negation Detection

Abstract Using natural language processing, it is possible to extract structured information from raw text in the electronic health record (EHR) at reasonably high accuracy. However, the accurate distinction between negated and non-negated mentions of clinical terms remains a challenge. EHR text includes cases where diseases are stated not to be present or only hypothesised, meaning a disease can be mentioned in a report when it is not being reported as present. This makes tasks such as document classification and summarisation more difficult. We have developed the rule-based EdIE-R-Neg, part of an existing text mining pipeline called EdIE-R (Edinburgh Information Extraction for Radiology reports), developed to process brain imaging reports, (https://www.ltg.ed.ac.uk/software/edie-r/) and two machine learning approaches; one using a bidirectional long short-term memory network and another using a feedforward neural network. These were developed on data from the Edinburgh Stroke Study (ESS) and tested on data from routine reports from NHS Tayside (Tayside). Both datasets consist of written reports from medical scans. These models are compared with two existing rule-based models: pyConText (Harkema et al. 2009. Journal of Biomedical Informatics42(5), 839–851), a python implementation of a generalisation of NegEx, and NegBio (Peng et al. 2017. NegBio: A high-performance tool for negation and uncertainty detection in radiology reports. arXiv e-prints, p. arXiv:1712.05898), which identifies negation scopes through patterns applied to a syntactic representation of the sentence. On both the test set of the dataset from which our models were developed, as well as the largely similar Tayside test set, the neural network models and our custom-built rule-based system outperformed the existing methods. EdIE-R-Neg scored highest on F1 score, particularly on the test set of the Tayside dataset, from which no development data were used in these experiments, showing the power of custom-built rule-based systems for negation detection on datasets of this size. The performance gap of the machine learning models to EdIE-R-Neg on the Tayside test set was reduced through adding development Tayside data into the ESS training set, demonstrating the adaptability of the neural network models.

Sign in / Sign up

Export Citation Format

Share Document