scholarly journals New Autonomous Intelligent Sensor Design Approach for Multiple Parameter Inference

2021 ◽  
Vol 2 (1) ◽  
pp. 96
Author(s):  
Umberto Michelucci ◽  
Francesca Venturini
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Training Dataset ◽  
Network Architectures ◽  
Single Measurement ◽  
Intelligent Sensor ◽  
Multiple Parameters ◽  
Two Parameters ◽  
First Time

The determination of multiple parameters via luminescence sensing is of great interest for many applications in different fields, like biosensing and biological imaging, medicine, and diagnostics. The typical approach consists in measuring multiple quantities and in applying complex and frequently just approximated mathematical models to characterize the sensor response. The use of machine learning to extract information from measurements in sensors have been tried in several forms before. But one of the problems with the approaches so far, is the difficulty in getting a training dataset that is representative of the measurements done by the sensor. Additionally, extracting multiple parameters from a single measurement has been so far an impossible problem to solve efficiently in luminescence. In this work a new approach is described for building an autonomous intelligent sensor, which is able to produce the training dataset self-sufficiently, use it for training a neural network, and then use the trained model to do inference on measurements done on the same hardware. For the first time the use of machine learning additionally allows to extract two parameters from one single measurement using multitask learning neural network architectures. This is demonstrated here by a dual oxygen concentration and temperature sensor.

scholarly journals Studying the Potential of Graphcore® IPUs for Applications in Particle Physics

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Samuel Maddrell-Mander ◽  
Lakshan Ram Madhan Mohan ◽  
Alexander Marshall ◽  
Daniel O’Hanlon ◽  
Konstantinos Petridis ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Kalman Filter ◽  
Particle Physics ◽  
Processing Unit ◽  
Network Architectures ◽  
Track Reconstruction ◽  
Event Simulation ◽  
Scattering Correction ◽  
New Type

AbstractThis paper presents the first study of Graphcore’s Intelligence Processing Unit (IPU) in the context of particle physics applications. The IPU is a new type of processor optimised for machine learning. Comparisons are made for neural-network-based event simulation, multiple-scattering correction, and flavour tagging, implemented on IPUs, GPUs and CPUs, using a variety of neural network architectures and hyperparameters. Additionally, a Kálmán filter for track reconstruction is implemented on IPUs and GPUs. The results indicate that IPUs hold considerable promise in addressing the rapidly increasing compute needs in particle physics.

Determination of thermodynamic state variables of liquids from its microscopic structure using an artificial neural network

Soft Matter ◽  
2020 ◽  
Author(s):  
Ulices Que-Salinas ◽  
Pedro Ezequiel Ramirez-Gonzalez ◽  
Alexis Torres-Carbajal
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Distribution Function ◽  
Microscopic Structure ◽  
Machine Learning Method ◽  
Learning Method ◽  
State Variables ◽  
Thermodynamic State

In this work we implement a machine learning method to predict the thermodynamic state of a liquid using only its microscopic structure provided by the radial distribution function (RDF). The...

scholarly journals Encoding Health Records into Pathway Representations for Deep Learning

2021 ◽  
Author(s):  
Marco Luca Sbodio ◽  
Natasha Mulligan ◽  
Stefanie Speichert ◽  
Vanessa Lopez ◽  
Joao Bettencourt-Silva
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Source Code ◽  
Training Dataset ◽  
Health Records ◽  
Learning Tasks ◽  
Patient Pathways ◽  
Computational Resources ◽  
The Impact

There is a growing trend in building deep learning patient representations from health records to obtain a comprehensive view of a patient’s data for machine learning tasks. This paper proposes a reproducible approach to generate patient pathways from health records and to transform them into a machine-processable image-like structure useful for deep learning tasks. Based on this approach, we generated over a million pathways from FAIR synthetic health records and used them to train a convolutional neural network. Our initial experiments show the accuracy of the CNN on a prediction task is comparable or better than other autoencoders trained on the same data, while requiring significantly less computational resources for training. We also assess the impact of the size of the training dataset on autoencoders performances. The source code for generating pathways from health records is provided as open source.

Global Position Prediction for Interactive Motion Capture

2021 ◽  
Vol 4 (3) ◽  
pp. 1-16
Author(s):  
Paul Schreiner ◽  
Maksym Perepichka ◽  
Hayden Lewis ◽  
Sune Darkner ◽  
Paul G. Kry ◽  
...  
Keyword(s):  
Neural Network ◽  
Motion Capture ◽  
Training Dataset ◽  
Good Representation ◽  
Network Architectures ◽  
Orientation Data ◽  
Position Sensing ◽  
Universal Network ◽  
Recorded Data ◽  
Training Examples

We present a method for reconstructing the global position of motion capture where position sensing is poor or unavailable. Capture systems, such as IMU suits, can provide excellent pose and orientation data of a capture subject, but otherwise need post processing to estimate global position. We propose a solution that trains a neural network to predict, in real-time, the height and body displacement given a short window of pose and orientation data. Our training dataset contains pre-recorded data with global positions from many different capture subjects, performing a wide variety of activities in order to broadly train a network to estimate on like and unseen activities. We compare training on two network architectures, a universal network (u-net) and a traditional convolutional neural network (CNN) - observing better error properties for the u-net in our results. We also evaluate our method for different classes of motion. We observe high quality results for motion examples with good representation in specialized datasets, while general performance appears better in a more broadly sampled dataset when input motions are far from training examples.

MACHINE LEARNING ALGORITHMS FOR IDENTIFICATION OF ABNORMAL GLOW CURVES AND ASSOCIATED ABNORMALITY IN CaSO4:DY-BASED PERSONNEL MONITORING DOSIMETERS

2020 ◽  
Vol 190 (3) ◽  
pp. 342-351
Author(s):  
Munir S Pathan ◽  
S M Pradhan ◽  
T Palani Selvam
Keyword(s):  
Machine Learning ◽  
Glow Curve ◽  
Good Accuracy ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Computationally Efficient ◽  
Artificial Neural Network Ann ◽  
First Time

Abstract In the present study, machine learning (ML) methods for the identification of abnormal glow curves (GC) of CaSO4:Dy-based thermoluminescence dosimeters in individual monitoring are presented. The classifier algorithms, random forest (RF), artificial neural network (ANN) and support vector machine (SVM) are employed for identifying not only the abnormal glow curve but also the type of abnormality. For the first time, the simplest and computationally efficient algorithm based on RF is presented for GC classifications. About 4000 GCs are used for the training and validation of ML algorithms. The performance of all algorithms is compared by using various parameters. Results show a fairly good accuracy of 99.05% for the classification of GCs by RF algorithm. Whereas 96.7% and 96.1% accuracy is achieved using ANN and SVM, respectively. The RF-based classifier is recommended for GC classification as well as in assisting the fault determination of the TLD reader system.

scholarly journals A Fortran-Keras Deep Learning Bridge for Scientific Computing

2020 ◽  
Vol 2020 ◽  
pp. 1-13 ◽  
Author(s):  
Jordan Ott ◽  
Mike Pritchard ◽  
Natalie Best ◽  
Erik Linstead ◽  
Milan Curcic ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Large Scale ◽  
Climate Model ◽  
Emergent Behavior ◽  
Training Dataset ◽  
Climate Simulation ◽  
Network Architectures ◽  
Efficient Computation ◽  
Radiation Physics

Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras. These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation. As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available. However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods. To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB). This two-way bridge connects environments where deep learning resources are plentiful with those where they are scarce. The paper describes several unique features offered by FKB, such as customizable layers, loss functions, and network ensembles. The paper concludes with a case study that applies FKB to address open questions about the robustness of an experimental approach to global climate simulation, in which subgrid physics are outsourced to deep neural network emulators. In this context, FKB enables a hyperparameter search of one hundred plus candidate models of subgrid cloud and radiation physics, initially implemented in Keras, to be transferred and used in Fortran. Such a process allows the model’s emergent behavior to be assessed, i.e., when fit imperfections are coupled to explicit planetary-scale fluid dynamics. The results reveal a previously unrecognized strong relationship between offline validation error and online performance, in which the choice of the optimizer proves unexpectedly critical. This in turn reveals many new neural network architectures that produce considerable improvements in climate model stability including some with reduced error, for an especially challenging training dataset.

scholarly journals Predicting Alert Source Device using Machine Learning Algorithms

2020 ◽  
Vol 9 (9) ◽  
pp. 1-10
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Model Building ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Research Work ◽  
Machine Learning Algorithms ◽  
Training Dataset ◽  
Imbalanced Dataset ◽  
Daunting Task

In a large distributed virtualized environment, predicting the alerting source from its text seems to be daunting task. This paper explores the option of using machine learning algorithm to solve this problem. Unfortunately, our training dataset is highly imbalanced. Where 96% of alerting data is reported by 24% of alerting sources. This is the expected dataset in any live distributed virtualized environment, where new version of device will have relatively less alert compared to older devices. Any classification effort with such imbalanced dataset present different set of challenges compared to binary classification. This type of skewed data distribution makes conventional machine learning less effective, especially while predicting the minority device type alerts. Our challenge is to build a robust model which can cope with this imbalanced dataset and achieves relative high level of prediction accuracy. This research work stared with traditional regression and classification algorithms using bag of words model. Then word2vec and doc2vec models are used to represent the words in vector formats, which preserve the sematic meaning of the sentence. With this alerting text with similar message will have same vector form representation. This vectorized alerting text is used with Logistic Regression for model building. This yields better accuracy, but the model is relatively complex and demand more computational resources. Finally, simple neural network is used for this multi-class text classification problem domain by using keras and tensorflow libraries. A simple two layered neural network yielded 99 % accuracy, even though our training dataset was not balanced. This paper goes through the qualitative evaluation of the different machine learning algorithms and their respective result. Finally, two layered deep learning algorithms is selected as final solution, since it takes relatively less resource and time with better accuracy values.

scholarly journals Evaluating structural safety of trusses using Machine Learning

2021 ◽  
Vol 15 (58) ◽  
pp. 308-318
Author(s):  
Tran-Hieu Nguyen ◽  
Anh-Tuan Vu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Roc Curve ◽  
Deep Neural Network ◽  
Structural Safety ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Model ◽  
Adaptive Boosting

In this paper, a machine learning-based framework is developed to quickly evaluate the structural safety of trusses. Three numerical examples of a 10-bar truss, a 25-bar truss, and a 47-bar truss are used to illustrate the proposed framework. Firstly, several truss cases with different cross-sectional areas are generated by employing the Latin Hypercube Sampling method. Stresses inside truss members as well as displacements of nodes are determined through finite element analyses and obtained values are compared with design constraints. According to the constraint verification, the safety state is assigned as safe or unsafe. Members’ sectional areas and the safety state are stored as the inputs and outputs of the training dataset, respectively. Three popular machine learning classifiers including Support Vector Machine, Deep Neural Network, and Adaptive Boosting are used for evaluating the safety of structures. The comparison is conducted based on two metrics: the accuracy and the area under the ROC curve. For the two first examples, three classifiers get more than 90% of accuracy. For the 47-bar truss, the accuracies of the Support Vector Machine model and the Deep Neural Network model are lower than 70% but the Adaptive Boosting model still retains the high accuracy of approximately 98%. In terms of the area under the ROC curve, the comparative results are similar. Overall, the Adaptive Boosting model outperforms the remaining models. In addition, an investigation is carried out to show the influence of the parameters on the performance of the Adaptive Boosting model.

scholarly journals AutoSmarTrace: Automated Chain Tracing and Flexibility Analysis of Biological Filaments

2021 ◽  
Author(s):  
Mathew Schneider ◽  
Alaa Al-Shaer ◽  
Nancy R. Forde
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Single Molecule ◽  
Persistence Length ◽  
Large Data ◽  
Ground Truth ◽  
Biological Macromolecules ◽  
Single Molecule Imaging ◽  
Chain Flexibility

AbstractSingle-molecule imaging is widely used to determine statistical distributions of molecular properties. One such characteristic is the bending flexibility of biological filaments, which can be parameterized via the persistence length. Quantitative extraction of persistence length from images of individual filaments requires both the ability to trace the backbone of the chains in the images and sufficient chain statistics to accurately assess the persistence length. Chain tracing can be a tedious task, performed manually or using algorithms that require user input and/or supervision. Such interventions have the potential to introduce user-dependent bias into the chain selection and tracing. Here, we introduce a fully automated algorithm for chain tracing and determination of persistence lengths. Dubbed “AutoSmarTrace”, the algorithm is built off a neural network, trained via machine learning to identify filaments within images recorded using atomic force microscopy (AFM). We validate the performance of AutoSmarTrace on simulated images with widely varying levels of noise, demonstrating its ability to return persistence lengths in agreement with the ground truth. Persistence lengths returned from analysis of experimental images of collagen and DNA agree with previous values obtained from these images with different chain-tracing approaches. While trained on AFM-like images, the algorithm also shows promise to identify chains in other single-molecule imaging approaches, such as rotary shadowing electron microscopy and fluorescence imaging.Statement of SignificanceMachine learning presents powerful capabilities to the analysis of large data sets. Here, we apply this approach to the determination of bending flexibility – described through persistence length – from single-molecule images of biological filaments. We present AutoSmarTrace, a tool for automated tracing and analysis of chain flexibility. Built on a neural network trained via machine learning, we show that AutoSmarTrace can determine persistence lengths from AFM images of a variety of biological macromolecules including collagen and DNA. While trained on AFM-like images, the algorithm works well to identify filaments in other types of images. This technique can free researchers from tedious tracing of chains in images, removing user bias and standardizing determination of chain mechanical parameters from single-molecule conformational images.

Sign in / Sign up

Export Citation Format

Share Document