Online Tensor-Based Learning Model for Structural Damage Detection

The online analysis of multi-way data stored in a tensor has become an essential tool for capturing the underlying structures and extracting the sensitive features that can be used to learn a predictive model. However, data distributions often evolve with time and a current predictive model may not be sufficiently representative in the future. Therefore, incrementally updating the tensor-based features and model coefficients are required in such situations. A new efficient tensor-based feature extraction, named Nesterov Stochastic Gradient Descent (NeSGD), is proposed for online (CP) decomposition. According to the new features obtained from the resultant matrices of NeSGD, a new criterion is triggered for the updated process of the online predictive model. Experimental evaluation in the field of structural health monitoring using laboratory-based and real-life structural datasets shows that our methods provide more accurate results compared with existing online tensor analysis and model learning. The results showed that the proposed methods significantly improved the classification error rates, were able to assimilate the changes in the positive data distribution over time, and maintained a high predictive accuracy in all case studies.

Download Full-text

Working with Industrial Cobots: The Influence of Reliability and Transparency on Perception and Trust

Proceedings of the Human Factors and Ergonomics Society Annual Meeting ◽

10.1177/1071181321651110 ◽

2021 ◽

Vol 65 (1) ◽

pp. 77-81

Author(s):

Lina Kluy ◽

Eileen Roesler

Keyword(s):

Study Design ◽

Real Life ◽

Error Rates ◽

Future Research ◽

Negative Effects ◽

Perceived Safety ◽

Fine Grained ◽

Online Study ◽

Human Robot Collaboration ◽

Positive Effect

Industrial human-robot collaboration (HRC) is not yet widely spread but on the rise. This development raises the question about properties collaborative robots (cobots) need, to enable a pleasant and smooth interaction. Therefore, this study investigated the influence of transparency and reliability on perception of and trust towards cobots. A video-enhanced online study with 124 participants was conducted. Transparency was provided through the presentation of differing information, and reliability was manipulated through differing error rates. The results showed a positive effect of transparency on perceived safety and intelligence. Reliability had a positive effect on perceived intelligence, likeability and trust. The effect of reliability on trust was more pronounced for low transparent robots. The results indicate the relevance of carefully selected information to counteract negative effects of failures. Future research should transfer the study design into a real-life experiment with more fine-grained levels of transparency and reliability.

Download Full-text

Is active sacroiliitis on MRI associated with radiographic damage in axial spondyloarthritis? Real-life data from the ASAS and DESIR cohorts

Rheumatology ◽

10.1093/rheumatology/key387 ◽

2018 ◽

Vol 58 (5) ◽

pp. 798-802 ◽

Cited By ~ 2

Author(s):

Alexandre Sepriano ◽

Sofia Ramiro ◽

Robert Landewé ◽

Maxime Dougados ◽

Désirée van der Heijde ◽

...

Keyword(s):

Bone Marrow ◽

Odds Ratio ◽

Structural Damage ◽

Axial Spondyloarthritis ◽

Multivariable Analysis ◽

Real Life ◽

Daily Practice ◽

Bone Marrow Oedema ◽

Number Of Patients ◽

Structural Progression

Abstract Objective To assess any association between bone marrow oedema on MRI of the sacroiliac joints (MRI-SIJ) according to local readings in daily practice and the development of structural damage on radiographs of the SIJ (X-SIJ) in axial spondyloarthritis (axSpA). Methods Patients with axSpA from the Assessment of the SpondyloArthritis international Society (ASAS) and DEvenir des Spondylarthopathies Indifférenciées Récentes (DESIR) multicentre cohorts were included. MRI-SIJ and X-SIJ were obtained at baseline, and X-SIJ at follow-up after a mean 4.6 years (ASAS) and 5.1 years (DESIR). All images were scored by local readers. Structural damage in the X-SIJ was defined according to the modified New York criteria. The percentage of structural net progression (number of ‘progressors’ minus the number of ‘regressors’ divided by the total number of patients) was assessed and the effect of bone marrow oedema on MRI-SIJ on X-SIJ damage evaluated by multivariable logistic regression. Results In total, 125 (ASAS-cohort) and 415 (DESIR-cohort) patients had baseline MRI-SIJ and complete X-SIJ data available. According to local readings, progression and ‘improvement’ in X-SIJ was seen in both the ASAS- and DESIR-cohort, yielding a net progression that was higher in the former than in the latter (19.2% and 6.3%). In multivariable analysis, baseline bone marrow oedema on MRI-SIJ was strongly associated with X-SIJ structural progression in both ASAS (odds ratio = 3.2 [95% CI: 1.3; 7.9]), and DESIR (odds ratio = 7.6 [95% CI: 4.3; 13.2]). Conclusion Inflammation on MRI-SIJ is associated with future radiographic progression according to local readings despite an expected increased imprecision invoked by local readings.

Download Full-text

Markovian analysis of cervical cell images.

Journal of Histochemistry & Cytochemistry ◽

10.1177/24.1.56387 ◽

1976 ◽

Vol 24 (1) ◽

pp. 138-144 ◽

Cited By ~ 74

Author(s):

N J Pressman

Keyword(s):

Transition Probabilities ◽

Classification Performance ◽

Error Rates ◽

Classification Error ◽

Correct Classification ◽

Cell Nuclei ◽

Step Size ◽

Cervical Cell ◽

Texture Parameters ◽

Markovian Analysis

Markovian analysis is a method to measure optical texture based on gray-level transition probabilities in digitized images. Experiments are described that investigate that classification performance of parameters generated by Markovian analysis. Results using Markov texture parameters show that the selection of a Markov step size strongly affects classification error rates and the number of parameters required to achieve the maximum correct classification rates. Markov texture parameters are shown to achieve high rates of correct classification in discriminating images of normal from abnormal cervical cell nuclei.

Download Full-text

From experiment to real-life data

The Mental Lexicon ◽

10.1075/ml.20006.sur ◽

2020 ◽

Vol 15 (3) ◽

Author(s):

Hanne Surkyn ◽

Reinhild Vandekerckhove ◽

Dominiek Sandra

Keyword(s):

Working Memory ◽

Social Factors ◽

Ecological Validity ◽

Real Life ◽

Error Rates ◽

Social Variables ◽

Online Chat ◽

Processing Level ◽

Automatic Retrieval ◽

The Social

Abstract We examine unintentional spelling errors on verb homophones in informal online chat conversations of Flemish adolescents. In experiments, these verb forms yielded an effect of homophone dominance, i.e., most errors occurred on the lower-frequency form (Sandra et al., 1999). Verb homophones are argued to require the conscious application of a spelling rule, which may cause a temporary overload of working memory resources and trigger automatic retrieval of the higher-frequency spelling from the mental lexicon. Unlike most previous research, we investigate homophone intrusions in a natural writing context. Thus, we test the ‘ecological validity’ of psycholinguistic experiments. Importantly, this study relates these psycholinguistic constructs to different social variables in social media writing to test a prediction that directly follows from Sandra et al.’s account. Whereas social factors likely affect the error rates, they should not affect the error pattern: the number of working memory failures occurs at another processing level than the homophone intrusions. Hence, the focus is on the interaction between homophone dominance and the social variables. The errors for two types of verb homophones reveal (a) an impact of all social variables, (b) an effect of homophone dominance, and (c) no interaction between this effect and the social factors.

Download Full-text

Predicting skilled delivery service use in Ethiopia: dual application of logistic regression and machine learning algorithms

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-019-0942-5 ◽

2019 ◽

Vol 19 (1) ◽

Cited By ~ 1

Author(s):

Brook Tesfaye ◽

Suleman Atique ◽

Tariq Azim ◽

Mihiretu M. Kebede

Keyword(s):

Logistic Regression ◽

Predictive Model ◽

Predictive Models ◽

Service Use ◽

Predictive Accuracy ◽

Maternal Deaths ◽

Skilled Delivery ◽

Skilled Assistance ◽

Delivery Assistance ◽

Delivery Services

Abstract Background Skilled assistance during childbirth is essential to reduce maternal deaths. However, in Ethiopia, which is among the six countries contributing to more than half of the global maternal deaths, the coverage of births attended by skilled health personnel remains very low. The aim of this study was to identify determinants and develop a predictive model for skilled delivery service use in Ethiopia by applying logistic regression and machine-learning techniques. Methods Data from the 2016 Ethiopian Demographic and Health Survey (EDHS) was used for this study. Statistical Package for Social Sciences (SPSS) and Waikato Environment for Knowledge Analysis (WEKA) tools were used for logistic regression and model building respectively. Classification algorithms namely J48, Naïve Bayes, Support Vector Machine (SVM), and Artificial Neural Network (ANN) were used for model development. The validation of the predictive models was assessed using accuracy, sensitivity, specificity, and area under Receiver Operating Characteristics (ROC) curve. Results Only 27.7% women received skilled delivery assistance in Ethiopia. First antenatal care (ANC) [AOR = 1.83, 95% CI (1.24–2.69)], birth order [AOR = 0.22, 95% CI (0.11–0.46)], television ownership [AOR = 6.83, 95% CI (2.52–18.52)], contraceptive use [AOR = 1.92, 95% CI (1.26–2.97)], cost needed for healthcare [AOR = 2.17, 95% CI (1.47–3.21)], age at first birth [AOR = 1.96, 95% CI (1.31–2.94)], and age at first sex [AOR = 2.72, 95% CI (1.55–4.76)] were determinants for utilizing skilled delivery services during the childbirth. Predictive models were developed and the J48 model had superior predictive accuracy (98%), sensitivity (96%), specificity (99%) and, the area under ROC (98%). Conclusions First ANC and contraceptive uses were among the determinants of utilization of skilled delivery services. A predictive model was developed to forecast the likelihood of a pregnant woman seeking skilled delivery assistance; therefore, the predictive model can help to decide targeted interventions for a pregnant woman to ensure skilled assistance at childbirth. The model developed through the J48 algorithm has better predictive accuracy. Web-based application can be build based on results of this study.

Download Full-text

Applying Machine-Learning to Human Gastrointestinal Microbial Species to Predict Dietary Intake (P20-040-19)

Current Developments in Nutrition ◽

10.1093/cdn/nzz040.p20-040-19 ◽

2019 ◽

Vol 3 (Supplement_1) ◽

Cited By ~ 1

Author(s):

Leila Shinn ◽

Yutong Li ◽

Ruoqing Zhu ◽

Aditya Mansharamani ◽

Loretta Auvil ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Dietary Intake ◽

Predictive Accuracy ◽

Bacterial Species ◽

Whole Grains ◽

Classification Error ◽

Whole Grain ◽

Model Accuracy ◽

Food And Agriculture

Abstract Objectives To better understand host-microbe interactions, a more computationally intensive, multivariate, machine learning approach must be utilized. Accordingly, we aimed to identify biomarkers with high predictive accuracy for dietary intake. Methods Data were aggregated from five randomized, controlled, feeding studies in adults (n = 199) that provided avocados, almonds, broccoli, walnuts, or whole grain oats and whole grain barley. Fecal samples were collected during treatment and control periods for each study for DNA extraction. Subsequently, the 16S rRNA gene (V4 region) was amplified and sequenced. Sequence data were analyzed using DADA2 and QIIME2. Marginal screening using the Kruskal-Wallis test was performed on all species-level taxa to examine the differences between each of the 6 treatment groups and respective control groups. The top 20 species from each diet were selected and pooled together for multiclass classification using random forest. The resultant bacterial species were further decreased in a stepwise fashion and iteratively analyzed with the variable importance generated from random forest to determine a compact feature set with a minor loss of accuracy in the prediction of food consumed. Result When all six foods were analyzed together using the top 20 species of each diet, oats and barley were frequently confused for each other, with 44% and 47% classification error, respectively, and the overall model accuracy was 66%. Collapsing oats and barley into one category, whole grains, reduced the classification error of the whole grain category to 6% and improved the overall model accuracy to 73%. Refitting the random forest with the top 30, 20, and 10 important species resulted in correct identification of the 5 foods (avocados, almonds, broccoli, walnuts, and whole grains) 75%, 74%, and 70% of the time, respectively. Conclusions These results reveal promise in accurately predicting foods consumed using bacterial species as biomarkers. Ongoing analyses include incorporation of metagenomic and metabolomic data into the models to improve predictive accuracy and utilize the multi-omics dataset to predict health status. Long-term, these approaches may inform diet-microbiota-tailored recommendations. Funding Sources This research was funded by The Foundation for Food and Agriculture Research, USDA, Hass Avocado Board, and USDA National Institute of Food and Agriculture, Hatch project 1009249.

Download Full-text

A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R

Applied Sciences ◽

10.3390/app9102048 ◽

2019 ◽

Vol 9 (10) ◽

pp. 2048 ◽

Cited By ~ 4

Author(s):

Jin Li

Keyword(s):

Predictive Model ◽

Predictive Modeling ◽

Predictive Models ◽

Predictive Accuracy ◽

Hybrid Methods ◽

R Package ◽

Environmental Sciences ◽

Modeling Process ◽

Predictive Methods ◽

Management And Conservation

Spatial predictive methods are increasingly being used to generate predictions across various disciplines in environmental sciences. Accuracy of the predictions is critical as they form the basis for environmental management and conservation. Therefore, improving the accuracy by selecting an appropriate method and then developing the most accurate predictive model(s) is essential. However, it is challenging to select an appropriate method and find the most accurate predictive model for a given dataset due to many aspects and multiple factors involved in the modeling process. Many previous studies considered only a portion of these aspects and factors, often leading to sub-optimal or even misleading predictive models. This study evaluates a spatial predictive modeling process, and identifies nine major components for spatial predictive modeling. Each of these nine components is then reviewed, and guidelines for selecting and applying relevant components and developing accurate predictive models are provided. Finally, reproducible examples using spm, an R package, are provided to demonstrate how to select and develop predictive models using machine learning, geostatistics, and their hybrid methods according to predictive accuracy for spatial predictive modeling; reproducible examples are also provided to generate and visualize spatial predictions in environmental sciences.

Download Full-text

Global diffusion tensor imaging derived metrics differentiate glioblastoma multiforme vs. normal brains by using discriminant analysis: introduction of a novel whole-brain approach

Radiology and Oncology ◽

10.2478/raon-2014-0004 ◽

2014 ◽

Vol 48 (2) ◽

pp. 127-136 ◽

Cited By ~ 9

Author(s):

Ernesto Roldan-Valadez ◽

Camilo Rios ◽

David Cortez-Conradis ◽

Rafael Favila ◽

Sergio Moreno-Jimenez

Keyword(s):

Diffusion Tensor Imaging ◽

Discriminant Analysis ◽

Glioblastoma Multiforme ◽

Predictive Model ◽

Predictive Accuracy ◽

Diffusion Tensor ◽

Mean Diffusivity ◽

Continuous Variables ◽

Whole Brain ◽

Axial Diffusivity

Abstract Background. Histological behavior of glioblastoma multiforme suggests it would benefit more from a global rather than regional evaluation. A global (whole-brain) calculation of diffusion tensor imaging (DTI) derived tensor metrics offers a valid method to detect the integrity of white matter structures without missing infiltrated brain areas not seen in conventional sequences. In this study we calculated a predictive model of brain infiltration in patients with glioblastoma using global tensor metrics. Methods. Retrospective, case and control study; 11 global DTI-derived tensor metrics were calculated in 27 patients with glioblastoma multiforme and 34 controls: mean diffusivity, fractional anisotropy, pure isotropic diffusion, pure anisotropic diffusion, the total magnitude of the diffusion tensor, linear tensor, planar tensor, spherical tensor, relative anisotropy, axial diffusivity and radial diffusivity. The multivariate discriminant analysis of these variables (including age) with a diagnostic test evaluation was performed. Results. The simultaneous analysis of 732 measures from 12 continuous variables in 61 subjects revealed one discriminant model that significantly differentiated normal brains and brains with glioblastoma: Wilks’ λ = 0.324, χ2 (3) = 38.907, p < .001. The overall predictive accuracy was 92.7%. Conclusions. We present a phase II study introducing a novel global approach using DTI-derived biomarkers of brain impairment. The final predictive model selected only three metrics: axial diffusivity, spherical tensor and linear tensor. These metrics might be clinically applied for diagnosis, follow-up, and the study of other neurological diseases.

Download Full-text

Bayesian Structural Time Series

Nanoscience and Nanotechnology Letters ◽

10.1166/nnl.2020.3083 ◽

2020 ◽

Vol 12 (1) ◽

pp. 54-61

Author(s):

Abdullah M. Almarashi ◽

Khushnoor Khan

Keyword(s):

Time Series ◽

Stock Prices ◽

Predictive Accuracy ◽

Local Level ◽

Real Life ◽

Secondary Data ◽

Real Data ◽

Data Set ◽

Structural Time Series ◽

Structural Time

The current study focused on modeling times series using Bayesian Structural Time Series technique (BSTS) on a univariate data-set. Real-life secondary data from stock prices for flying cement covering a period of one year was used for analysis. Statistical results were based on simulation procedures using Kalman filter and Monte Carlo Markov Chain (MCMC). Though the current study involved stock prices data, the same approach can be applied to complex engineering process involving lead times. Results from the current study were compared with classical Autoregressive Integrated Moving Average (ARIMA) technique. For working out the Bayesian posterior sampling distributions BSTS package run with R software was used. Four BSTS models were used on a real data set to demonstrate the working of BSTS technique. The predictive accuracy for competing models was assessed using Forecasts plots and Mean Absolute Percent Error (MAPE). An easyto-follow approach was adopted so that both academicians and practitioners can easily replicate the mechanism. Findings from the study revealed that, for short-term forecasting, both ARIMA and BSTS are equally good but for long term forecasting, BSTS with local level is the most plausible option.

Download Full-text