scholarly journals Improving Accelerometry-Based Measurement of Functional Use of the Upper Extremity After Stroke: Machine Learning Versus Counts Threshold Method

2020 ◽  
Vol 34 (12) ◽  
pp. 1078-1087
Author(s):  
Peter S. Lum ◽  
Liqi Shu ◽  
Elaine M. Bochniewicz ◽  
Tan Tran ◽  
Lin-Ching Chang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Upper Extremity ◽  
Functional Activity ◽  
Learning Algorithms ◽  
Ground Truth ◽  
Machine Learning Algorithms ◽  
Average Error ◽  
Test Duration ◽  
Accelerometer Data ◽  
Paretic Limb

Background Wrist-worn accelerometry provides objective monitoring of upper-extremity functional use, such as reaching tasks, but also detects nonfunctional movements, leading to ambiguity in monitoring results. Objective Compare machine learning algorithms with standard methods (counts ratio) to improve accuracy in detecting functional activity. Methods Healthy controls and individuals with stroke performed unstructured tasks in a simulated community environment (Test duration = 26 ± 8 minutes) while accelerometry and video were synchronously recorded. Human annotators scored each frame of the video as being functional or nonfunctional activity, providing ground truth. Several machine learning algorithms were developed to separate functional from nonfunctional activity in the accelerometer data. We also calculated the counts ratio, which uses a thresholding scheme to calculate the duration of activity in the paretic limb normalized by the less-affected limb. Results The counts ratio was not significantly correlated with ground truth and had large errors ( r = 0.48; P = .16; average error = 52.7%) because of high levels of nonfunctional movement in the paretic limb. Counts did not increase with increased functional movement. The best-performing intrasubject machine learning algorithm had an accuracy of 92.6% in the paretic limb of stroke patients, and the correlation with ground truth was r = 0.99 ( P < .001; average error = 3.9%). The best intersubject model had an accuracy of 74.2% and a correlation of r =0.81 ( P = .005; average error = 5.2%) with ground truth. Conclusions In our sample, the counts ratio did not accurately reflect functional activity. Machine learning algorithms were more accurate, and future work should focus on the development of a clinical tool.

scholarly journals Assessing biases, relaxing moralism: On ground-truthing practices in machine learning design and application

2021 ◽  
Vol 8 (1) ◽  
pp. 205395172110135
Author(s):  
Florian Jaton
Keyword(s):  
Machine Learning ◽  
William James ◽  
A Priori ◽  
Learning Algorithms ◽  
Three Dimensional ◽  
Ground Truth ◽  
Machine Learning Algorithms ◽  
Ground Truthing ◽  
Set Up ◽  
The Moment

This theoretical paper considers the morality of machine learning algorithms and systems in the light of the biases that ground their correctness. It begins by presenting biases not as a priori negative entities but as contingent external referents—often gathered in benchmarked repositories called ground-truth datasets—that define what needs to be learned and allow for performance measures. I then argue that ground-truth datasets and their concomitant practices—that fundamentally involve establishing biases to enable learning procedures—can be described by their respective morality, here defined as the more or less accounted experience of hesitation when faced with what pragmatist philosopher William James called “genuine options”—that is, choices to be made in the heat of the moment that engage different possible futures. I then stress three constitutive dimensions of this pragmatist morality, as far as ground-truthing practices are concerned: (I) the definition of the problem to be solved (problematization), (II) the identification of the data to be collected and set up (databasing), and (III) the qualification of the targets to be learned (labeling). I finally suggest that this three-dimensional conceptual space can be used to map machine learning algorithmic projects in terms of the morality of their respective and constitutive ground-truthing practices. Such techno-moral graphs may, in turn, serve as equipment for greater governance of machine learning algorithms and systems.

scholarly journals Integrating hierarchical statistical models and machine-learning algorithms for ground-truthing drone images of the vegetation: taxonomy, abundance and population ecological models

2018 ◽  
Author(s):  
Christian Damgaard
Keyword(s):  
Machine Learning ◽  
Statistical Models ◽  
Learning Algorithms ◽  
Plant Competition ◽  
Image Data ◽  
Ground Truth ◽  
Ecological Models ◽  
Machine Learning Algorithms ◽  
Ground Truth Data ◽  
Ground Truthing

AbstractIn order to fit population ecological models, e.g. plant competition models, to new drone-aided image data, we need to develop statistical models that may take the new type of measurement uncertainty when applying machine-learning algorithms into account and quantify its importance for statistical inferences and ecological predictions. Here, it is proposed to quantify the uncertainty and bias of image predicted plant taxonomy and abundance in a hierarchical statistical model that is linked to ground-truth data obtained by the pin-point method. It is critical that the error rate in the species identification process is minimized when the image data are fitted to the population ecological models, and several avenues for reaching this objective are discussed. The outlined method to statistically model known sources of uncertainty when applying machine-learning algorithms may be relevant for other applied scientific disciplines.

scholarly journals Integrating Hierarchical Statistical Models and Machine-Learning Algorithms for Ground-Truthing Drone Images of the Vegetation: Taxonomy, Abundance and Population Ecological Models

2021 ◽  
Vol 13 (6) ◽  
pp. 1161
Author(s):  
Christian Damgaard
Keyword(s):  
Machine Learning ◽  
Statistical Models ◽  
Learning Algorithms ◽  
Plant Competition ◽  
Image Data ◽  
Ground Truth ◽  
Ecological Models ◽  
Machine Learning Algorithms ◽  
Ground Truth Data ◽  
Ground Truthing

In order to fit population ecological models, e.g., plant competition models, to new drone-aided image data, we need to develop statistical models that may take the new type of measurement uncertainty when applying machine-learning algorithms into account and quantify its importance for statistical inferences and ecological predictions. Here, it is proposed to quantify the uncertainty and bias of image predicted plant taxonomy and abundance in a hierarchical statistical model that is linked to ground-truth data obtained by the pin-point method. It is critical that the error rate in the species identification process is minimized when the image data are fitted to the population ecological models, and several avenues for reaching this objective are discussed. The outlined method to statistically model known sources of uncertainty when applying machine-learning algorithms may be relevant for other applied scientific disciplines.

scholarly journals Detection of Unilateral Arm Paresis after Stroke by Wearable Accelerometers and Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7784
Author(s):  
Johan Wasselius ◽  
Eric Lyckegård Finn ◽  
Emma Persson ◽  
Petter Ericson ◽  
Christina Brogårdh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Accelerometer Data ◽  
Learning Models ◽  
Stroke Patients ◽  
Convolutional Network ◽  
Stroke Treatment ◽  
Data Windows

Recent advances in stroke treatment have provided effective tools to successfully treat ischemic stroke, but still a majority of patients are not treated due to late arrival to hospital. With modern stroke treatment, earlier arrival would greatly improve the overall treatment results. This prospective study was performed to asses the capability of bilateral accelerometers worn in bracelets 24/7 to detect unilateral arm paralysis, a hallmark symptom of stroke, early enough to receive treatment. Classical machine learning algorithms as well as state-of-the-art deep neural networks were evaluated on detection times between 15 min and 120 min. Motion data were collected using triaxial accelerometer bracelets worn on both arms for 24 h. Eighty-four stroke patients with unilateral arm motor impairment and 101 healthy subjects participated in the study. Accelerometer data were divided into data windows of different lengths and analyzed using multiple machine learning algorithms. The results show that all algorithms performed well in separating the two groups early enough to be clinically relevant, based on wrist-worn accelerometers. The two evaluated deep learning models, fully convolutional network and InceptionTime, performed better than the classical machine learning models with an AUC score between 0.947–0.957 on 15 min data windows and up to 0.993–0.994 on 120 min data windows. Window lengths longer than 90 min only marginally improved performance. The difference in performance between the deep learning models and the classical models was statistically significant according to a non-parametric Friedman test followed by a post-hoc Nemenyi test. Introduction of wearable stroke detection devices may dramatically increase the portion of stroke patients eligible for revascularization and shorten the time to treatment. Since the treatment effect is highly time-dependent, early stroke detection may dramatically improve stroke outcomes.

scholarly journals G-PARE: A visual analytic tool for comparative analysis of uncertain graphs

2020 ◽  
Author(s):  
awalin sopan
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Ground Truth ◽  
Citation Network ◽  
Viral Marketing ◽  
Machine Learning Algorithms ◽  
Analytic Tool ◽  
Uncertain Graphs ◽  
Exploration Environment

There are a growing number of machine learning algorithms which operate on graphs. Example applications for these algorithms include predicting which customers will recommend products to their friends in a viral marketing campaign using a customer network, predicting the topics of publications in a citation network, or predicting the political affiliations of people in a social network. It is important for an analyst to have tools to help compare the output of these machine learning algorithms. In this work, we present G-PARE, a visual analytic tool for comparing two uncertain graphs, where each uncertain graph is produced by a machine learning algorithm which outputs probabilities over node labels. G-PARE provides several different views which allow users to obtain a global overview of the algorithms output, as well as focused views that show subsets of nodes of interest. By providing an adaptive exploration environment, G-PARE guides the users to places in the graph where two algorithms predictions agree and places where they disagree. This enables the user to follow cascades of misclassifications by comparing the algorithms outcome with the ground truth. After describing the features of G-PARE, we illustrate its utility through several use cases based on networks from different domains.

Intelligent Predictor for Polymer Viscosity to Enhance Support for EOR Processes

2021 ◽  
Author(s):  
Mohammad Rasheed Khan ◽  
Shams Kalam ◽  
Abdul Asad ◽  
Rizwan Ahmed Khan ◽  
Muhammad Shahzad Kamal
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Learning Algorithms ◽  
Polymer Concentration ◽  
Machine Learning Algorithms ◽  
Rheological Parameters ◽  
Average Error ◽  
Back Propagation Algorithm ◽  
Molecular Weight Polymer ◽  
Eor Processes

Abstract Research into the use of polymers for enhanced oil recovery (EOR) processes has been going on for more than 6 decades and is now classified as a techno-commercially viable option. A comprehensive evaluation of the polymer's rheology is pivotal to the success of any polymer EOR process. Laboratory-based evaluation is critical to EOR success; however, it is also a time/capital consuming process. Consequently, any tool which can aid in optimizing lab tests design can bring in great value. Accordingly, in this study a novel predictive correlation for viscosity estimation of commonly used "FP 3330S" EOR polymer is presented through use of cutting-edge machine learning neural networks. Mathematical equation for polymer viscosity is developed using machine learning algorithms as a function of polymer concentration, NaCl concentration, and Ca2+ concentration. The measured input data was collected from the literature and sub-divided into training and test sets. A wide-ranging optimization was performed to select the best parameters for the neural network which includes the number of neurons, neuron layers, activation functions between multiple layers, weights, and bias. Furthermore, the Levenberg-Marquardt back-propagation algorithm was utilized to train the model. Finally, measured and estimated viscosities were compared based on error-analysis. Novel correlation is developed for the polymer that can be used in predictive mode. This established correlation can predict polymer viscosity when applied to the test dataset and outperforms other published models with average error in the range of 3-5% and coefficient of determination in excess of 0.95. Moreover, it is shown that neural networks are faster and relatively better than other machine learning algorithms explored in this study. The proposed correlation can map non-linear relationships between polymer viscosity and other rheological parameters such as molecular weight, polymer concentration, and cation concentration of polymer solution. Lastly, through machine learning validation approach, it was possible to examine feasibility of the proposed models which is not done by traditional empirical equations.

scholarly journals Applying Machine Learning Techniques in Older People Activity Recognition usingWearable and Mobile Devices

2019 ◽  
Author(s):  
Flavio Vinicius Vieira Santana ◽  
Bruno Henrique Rasteiro ◽  
Larissa Cardoso Zimmermann ◽  
Luciana De Nardin ◽  
Maria da Graça Campos Pimentel
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Accelerometer Data ◽  
Smartphone Apps ◽  
Online Recognition ◽  
Learning Techniques ◽  
Combined Use ◽  
Future Work

We investigate the potential of the combined use of smartwatch accelerometer data and smartphone apps for online older adultsactivity recognition.We selected machine learning algorithms which resulted in a posteriori recognition accuracy of 98.92%. Our smartphone app, with the selected machine learning algorithms, carried out online recognition from data captured on the smartwatch. These results allow us, as future work, assess the accuracy of online recognition when the system is used by older adults.

Sign in / Sign up

Export Citation Format

Share Document