scholarly journals CNN for image-based sediment detection applied to a large terrestrial and airborne dataset

2021 ◽  
Author(s):  
Xingyu Chen ◽  
Marwan A. Hassan ◽  
Xudong Fu
Keyword(s):  
Grain Size ◽  
Predictive Accuracy ◽  
Predictive Ability ◽  
Field Measurements ◽  
Parameter Tuning ◽  
Image Resolution ◽  
Data Set ◽  
Diverse Range ◽  
Sandy Gravel ◽  
Organic Debris

Abstract. Image-based grain sizing has been used to measure grain size more efficiently compared to traditional methods (e.g. sieving and Wolman pebble count). However, current methods (e.g. BASEGRAIN) are largely based on detecting grain interstices from image intensity which not only require a significant level of expertise for parameter tuning but also underperform when they are applied to sub-optimal environments (e.g. dense organic debris, various sediment lithology). We proposed a model (GrainID) based on convolutional neural networks to measure grain size in a diverse range of fluvial environments. A data set of more than 125,000 grains from flume and field measurements were compiled to develop GrainID. Tests were performed to compare the predictive ability of GrainID with sieving, manual labeling, Wolman pebble counts and BASEGRAIN. When compared with the sieving results for a sandy-gravel bed, GrainID yielded high predictive accuracy (comparable to the performance of manual labeling) and outperformed BASEGRAIN and Wolman Pebble counts (especially for small grains). For the entire evaluation dataset, GrainID once again showed fewer predictive errors and significantly lower variation in results in comparison to BASEGRAIN and Wolman pebble counts and maintained this advantage even in uncalibrated rivers with drone images. Moreover, the existence of vegetation and noise have little influence on the performance of GrainID. Analysis indicated that GrainID performed optimally when the image resolution is higher than 1.8 mm/pixel, the image tile size is 512*512 pixel*pixel and the grain area truncation values (the area of smallest detectable grains) were equal to 18–25 pixels.

scholarly journals Analysis of genome-wide mutation profile and establishment of risk signature for prognosis of bladder cancer

2020 ◽  
Author(s):  
Yanyun Zhao ◽  
Rong Ma ◽  
Fangxiao Liu ◽  
Liwen Zhang ◽  
Xuemei Lv ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Cox Regression ◽  
Predictive Accuracy ◽  
Predictive Ability ◽  
Time Dependent ◽  
Net Benefit ◽  
Data Set ◽  
Clinical Prognosis ◽  
Cox Regression Analysis ◽  
Mutation Profile

Abstract Background: Emerging studies have shown that a variety of gene mutations occur in development and progression of cancer and highly mutation genes could play oncogenic or tumor suppressive roles in cancer. Therefore, our aim is to explore mutation genes which affect the prognosis of bladder.Methods: Mutation profile was obtained and analyzed from TCGA data set. A mutation-based signature was established by multivariable Cox regression analysis. Kaplan-Meier was performed to assess the prognostic power of signature. Time-dependent ROC was conducted to evaluate predictive accuracy of signature for bladder cancer patients.Results: There are 20177 genes have alteration in 403 bladder patients and 662 of them were frequently variation (mutation frequency > 5%). In this study, we assessed the prognostic predictive ability of 662 highly mutated genes and identified a mutation signature as an independent indicator for predicting the prognosis of bladder. The time-dependent ROC showed that AUC were 0.893, 0.896, 0.916 and 0.965 at 1, 3, 5 and 10 year, respectively. Stratified analysis and Multivariate Cox analysis showed that this mutation signature was reliable and independent biomarker. Furthermore, the nomogram predictive model can be used to effectively predict clinical prognosis of bladder patients. The decision analysis curve showed patients with risk threshold of 0.03-0.92 potentially yielded clinical net benefit. Finally, we identified several signaling pathways that associated with risk score by GSEA and KEGG analysis including PI3K-Akt signaling pathway and so on.Conclusions: In general, this study provide an optimal mutation signature as potential prognosis biomarker for bladder patients.

scholarly journals Risk prediction in multicentre studies when there is confounding by cluster or informative cluster size

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Menelaos Pavlou ◽  
Gareth Ambler ◽  
Rumana Z. Omar
Keyword(s):  
Risk Prediction ◽  
Cluster Size ◽  
Linear Models ◽  
Prediction Models ◽  
Predictive Accuracy ◽  
Clustered Data ◽  
Predictor Variable ◽  
Simulated Data ◽  
Predictive Ability ◽  
Informative Cluster Size

Abstract Background Clustered data arise in research when patients are clustered within larger units. Generalised Estimating Equations (GEE) and Generalised Linear Models (GLMM) can be used to provide marginal and cluster-specific inference and predictions, respectively. Methods Confounding by Cluster (CBC) and Informative cluster size (ICS) are two complications that may arise when modelling clustered data. CBC can arise when the distribution of a predictor variable (termed ‘exposure’), varies between clusters causing confounding of the exposure-outcome relationship. ICS means that the cluster size conditional on covariates is not independent of the outcome. In both situations, standard GEE and GLMM may provide biased or misleading inference, and modifications have been proposed. However, both CBC and ICS are routinely overlooked in the context of risk prediction, and their impact on the predictive ability of the models has been little explored. We study the effect of CBC and ICS on the predictive ability of risk models for binary outcomes when GEE and GLMM are used. We examine whether two simple approaches to handle CBC and ICS, which involve adjusting for the cluster mean of the exposure and the cluster size, respectively, can improve the accuracy of predictions. Results Both CBC and ICS can be viewed as violations of the assumptions in the standard GLMM; the random effects are correlated with exposure for CBC and cluster size for ICS. Based on these principles, we simulated data subject to CBC/ICS. The simulation studies suggested that the predictive ability of models derived from using standard GLMM and GEE ignoring CBC/ICS was affected. Marginal predictions were found to be mis-calibrated. Adjusting for the cluster-mean of the exposure or the cluster size improved calibration, discrimination and the overall predictive accuracy of marginal predictions, by explaining part of the between cluster variability. The presence of CBC/ICS did not affect the accuracy of conditional predictions. We illustrate these concepts using real data from a multicentre study with potential CBC. Conclusion Ignoring CBC and ICS when developing prediction models for clustered data can affect the accuracy of marginal predictions. Adjusting for the cluster mean of the exposure or the cluster size can improve the predictive accuracy of marginal predictions.

Predictive view of the value relevance of earnings in India

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hajam Abid Bashir ◽  
Manish Bansal ◽  
Dilip Kumar
Keyword(s):  
Capital Investment ◽  
Stock Return ◽  
Value Relevance ◽  
Stock Exchange ◽  
Predictive Ability ◽  
Cash Flows ◽  
Data Set ◽  
Content Type ◽  
Uniform Sample ◽  
Reported Earnings

Purpose This study aims to examine the value relevance of earnings in terms of predicting the value variables such as cash flow, capital investment (CI), dividend and stock return under the Indian institutional settings. Design/methodology/approach The study used panel Granger causality tests to examine causality relationships among variables and panel data regression models to check the statistical associations between earnings and value variables. Findings Based on a data set of 7,280 Bombay Stock Exchange-listed firm-years spanning over ten years from March 2009 to March 2018, the results show higher sensitivity of earnings toward cash flows, CI, divided and stock return and vice-versa. Further, the findings deduced from the empirical results demonstrate that earnings are positively related to value variables. Overall, the results established that earnings are value-relevant and have predictive ability to forecast the value variables that facilitate investors in portfolio valuation. The results are consistent with the predictive view of the value relevance of earnings. Several robustness checks confirm these results. Originality/value This study brings new empirical evidence from a distinct capital market, India, and provides a new facet to the value relevance debate in terms of its prediction view. The study is among earlier attempts that jointly measure the ability of earnings in forecasting different value variables by taking a uniform sample of firms at the same period. Hence, the study provides a comprehensive view of the predictive ability of reported earnings.

scholarly journals Factors determining generalization in deep learning models for scoring COVID-CT images

2021 ◽  
Vol 18 (6) ◽  
pp. 9264-9293
Author(s):  
Michael James Horry ◽  
◽  
Subrata Chakraborty ◽  
Biswajeet Pradhan ◽  
Maryam Fallahpoor ◽  
...  
Keyword(s):  
Deep Learning ◽  
Predictive Accuracy ◽  
Gabor Filter ◽  
Predictive Ability ◽  
Histogram Equalization ◽  
Data Sets ◽  
Lung Involvement ◽  
Learning Models ◽  
Key Factors ◽  
Independent Dataset

<abstract> <p>The COVID-19 pandemic has inspired unprecedented data collection and computer vision modelling efforts worldwide, focused on the diagnosis of COVID-19 from medical images. However, these models have found limited, if any, clinical application due in part to unproven generalization to data sets beyond their source training corpus. This study investigates the generalizability of deep learning models using publicly available COVID-19 Computed Tomography data through cross dataset validation. The predictive ability of these models for COVID-19 severity is assessed using an independent dataset that is stratified for COVID-19 lung involvement. Each inter-dataset study is performed using histogram equalization, and contrast limited adaptive histogram equalization with and without a learning Gabor filter. We show that under certain conditions, deep learning models can generalize well to an external dataset with F1 scores up to 86%. The best performing model shows predictive accuracy of between 75% and 96% for lung involvement scoring against an external expertly stratified dataset. From these results we identify key factors promoting deep learning generalization, being primarily the uniform acquisition of training images, and secondly diversity in CT slice position.</p> </abstract>

scholarly journals Predicting Anxiety in Routine Palliative Care Using Bayesian-Inspired Association Rule Mining

2021 ◽  
Vol 3 ◽  
Author(s):  
Oliver Haas ◽  
Luis Ignacio Lopera Gonzalez ◽  
Sonja Hofmann ◽  
Christoph Ostgathe ◽  
Andreas Maier ◽  
...  
Keyword(s):  
Palliative Care ◽  
Association Rule ◽  
Association Rule Mining ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Rule Mining ◽  
Data Set ◽  
Routinely Collected Data ◽  
Previous State ◽  
Insight Into

We propose a novel knowledge extraction method based on Bayesian-inspired association rule mining to classify anxiety in heterogeneous, routinely collected data from 9,924 palliative patients. The method extracts association rules mined using lift and local support as selection criteria. The extracted rules are used to assess the maximum evidence supporting and rejecting anxiety for each patient in the test set. We evaluated the predictive accuracy by calculating the area under the receiver operating characteristic curve (AUC). The evaluation produced an AUC of 0.89 and a set of 55 atomic rules with one item in the premise and the conclusion, respectively. The selected rules include variables like pain, nausea, and various medications. Our method outperforms the previous state of the art (AUC = 0.72). We analyzed the relevance and novelty of the mined rules. Palliative experts were asked about the correlation between variables in the data set and anxiety. By comparing expert answers with the retrieved rules, we grouped rules into expected and unexpected ones and found several rules for which experts' opinions and the data-backed rules differ, most notably with the patients' sex. The proposed method offers a novel way to predict anxiety in palliative settings using routinely collected data with an explainable and effective model based on Bayesian-inspired association rule mining. The extracted rules give further insight into potential knowledge gaps in the palliative care field.

scholarly journals River ice flux and water velocities along a 600 km long reach of Lena River, Siberia, from satellite stereo

2013 ◽  
Vol 10 (7) ◽  
pp. 9967-9997 ◽  
Author(s):  
A. Kääb ◽  
M. Lamare ◽  
M. Abrams
Keyword(s):  
River Flow ◽  
Thermal Emission ◽  
Time Lag ◽  
Open Water ◽  
Image Resolution ◽  
Surface Velocity ◽  
River Ice ◽  
Data Set ◽  
Hazard Management ◽  
Lena River

Abstract. Knowledge of water-surface velocities in rivers is useful for understanding a range of river processes. In cold regions, river-ice break up and the related downstream transport of ice debris is often the most important hydrological event of the year, leading to flood levels that typically exceed those for the open-water period and to strong consequences for river infrastructure and ecology. Accurate and complete surface-velocity fields on rivers have rarely been produced. Here, we track river ice debris over a time period of about one minute, which is the typical time lag between the two or more images that form a stereo data set in spaceborne, along-track optical stereo-mapping. Using a series of 9 stereo scenes from the US/Japanese Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) onboard the NASA Terra spacecraft with 15 m image resolution, we measure the ice and water velocity field over a 620 km long reach of the lower Lena River, Siberia, just above its entry into the Lena delta. Careful analysis and correction of higher-order image and sensor errors enables an accuracy of ice-debris velocities of up to 0.04 m s−1 from the ASTER data. Maximum ice or water speeds, respectively, reach up to 2.5 m s−1 at the time of data acquisition, 27 May 2011 (03:30 UTC). Speeds show clear along-stream undulations with a wavelength of about 21 km that agree well with variations in channel width and with the location of sand bars along the river reach studied. The methodology and results of this study could be valuable to a number of disciplines requiring detailed information about river flow, such as hydraulics, hydrology, river ecology and natural-hazard management.

A - 24 Exploring Vestibular/Ocular and Cognitive Dysfunction as Prognostic Factors for Protracted Recovery in Sports-Related Concussion Patients Aged 8–12 Years

2021 ◽  
Vol 36 (4) ◽  
pp. 664-664
Author(s):  
Price AM ◽  
Knell G ◽  
Caze TJ ◽  
Abt JP ◽  
Loveland D ◽  
...  
Keyword(s):  
Prognostic Factors ◽  
Cognitive Dysfunction ◽  
Recovery Time ◽  
Predictive Accuracy ◽  
Test Validity ◽  
Predictive Ability ◽  
Ocular Motor ◽  
Youth Athletes ◽  
Prognostic Accuracy

Abstract Objective To explore the prognostic ability of the Vestibular/Ocular Motor Screening (VOMS) tool, the King-Devick Test (KD), and the C3 Logix Trails A and B (C3), individually and in combination, for identifying protracted recovery from sports-related concussion (SRC) in patients aged 8–12 years. Methods 114 youth athletes aged 8–12 years diagnosed with a SRC within 7-days of injury participated in this study. The prognostic ability of the VOMS, KD, and C3 to classify patients as normal versus protracted recovery, defined as recovery time greater than 30-days, was evaluated using measures of test validity and predictive ability. Results After adjustment for age and days since injury, a positive VOMS was associated with 1.31 greater days to recover (p = 0.02) than a negative VOMS. The KD, and the C3 were not significantly associated with recovery time (all p &gt; 0.05), nor were any combinations of tests (any 2 or 3 positive tests, all 4 positive tests). The VOMS prognostic ability to predict normal recovery (NPV = 80.78% [95%CI = 63.73–90.95]) was moderate. Overall predictive accuracy of normal versus protracted recovery was strongest when a participant screened positive on 3 out of 4 possible measures (Acc = 66.67% [95%CI = 57.23–75.22]). Conclusions The VOMS was the most useful test for identifying patients who will experience a normal SRC recovery time, however, combining the VOMS with KD and C3 improved prognostic accuracy. These findings suggest that combining multiple, varied assessments of cognition and vestibular/ocular functions may be useful for understanding factors contributing to protracted recovery from SRC.

Advanced Processing of a Blade Vibratory Response Obtained With Tip Timing Method Using Hyperparameter-Free Sparse Estimation Method

2021 ◽  
Author(s):  
Vsevolod Kharyton ◽  
Dave Zachariah
Keyword(s):  
Estimation Method ◽  
Field Measurements ◽  
Parameter Tuning ◽  
Test Cases ◽  
Time Data ◽  
Sparse Estimation ◽  
Vibratory Response ◽  
Blade Tip ◽  
Data Adaptive ◽  
Real Time Data Processing

Abstract The study presents the application of a sparse estimation method which enables explicit identification of spectrum components of a vibratory signal of a blade obtained by means of blade tip timing measurement. The method exploits the sparse frequency content of the blade vibratory response and uses a data-adaptive weighting to achieve sparsity. In contrast to other approaches, this method obviates the need for any parameter tuning during the identification process and admits an online formulation that renders it capable of real-time data processing. In the study only experimentally acquired data from either prototype testing or field measurements are used to evoke the method applicability. For some considered test cases there were no strain gauges available, therefore proposed method was the only means to study blades vibratory response.

Early prediction of chronic disease using an efficient machine learning algorithm through adaptive probabilistic divergence based feature selection approach

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sandeepkumar Hegde ◽  
Monica R. Mundada
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Chronic Disease ◽  
Learning Algorithm ◽  
Predictive Ability ◽  
Experimental Result ◽  
Data Set ◽  
Content Type ◽  
Learning Classifier ◽  
Feature Selection Approach

Purpose According to the World Health Organization, by 2025, the contribution of chronic disease is expected to rise by 73% compared to all deaths and it is considered as global burden of disease with a rate of 60%. These diseases persist for a longer duration of time, which are almost incurable and can only be controlled. Cardiovascular disease, chronic kidney disease (CKD) and diabetes mellitus are considered as three major chronic diseases that will increase the risk among the adults, as they get older. CKD is considered a major disease among all these chronic diseases, which will increase the risk among the adults as they get older. Overall 10% of the population of the world is affected by CKD and it is likely to double in the year 2030. The paper aims to propose novel feature selection approach in combination with the machine-learning algorithm which can early predict the chronic disease with utmost accuracy. Hence, a novel feature selection adaptive probabilistic divergence-based feature selection (APDFS) algorithm is proposed in combination with the hyper-parameterized logistic regression model (HLRM) for the early prediction of chronic disease. Design/methodology/approach A novel feature selection APDFS algorithm is proposed which explicitly handles the feature associated with the class label by relevance and redundancy analysis. The algorithm applies the statistical divergence-based information theory to identify the relationship between the distant features of the chronic disease data set. The data set required to experiment is obtained from several medical labs and hospitals in India. The HLRM is used as a machine-learning classifier. The predictive ability of the framework is compared with the various algorithm and also with the various chronic disease data set. The experimental result illustrates that the proposed framework is efficient and achieved competitive results compared to the existing work in most of the cases. Findings The performance of the proposed framework is validated by using the metric such as recall, precision, F1 measure and ROC. The predictive performance of the proposed framework is analyzed by passing the data set belongs to various chronic disease such as CKD, diabetes and heart disease. The diagnostic ability of the proposed approach is demonstrated by comparing its result with existing algorithms. The experimental figures illustrated that the proposed framework performed exceptionally well in prior prediction of CKD disease with an accuracy of 91.6. Originality/value The capability of the machine learning algorithms depends on feature selection (FS) algorithms in identifying the relevant traits from the data set, which impact the predictive result. It is considered as a process of choosing the relevant features from the data set by removing redundant and irrelevant features. Although there are many approaches that have been already proposed toward this objective, they are computationally complex because of the strategy of following a one-step scheme in selecting the features. In this paper, a novel feature selection APDFS algorithm is proposed which explicitly handles the feature associated with the class label by relevance and redundancy analysis. The proposed algorithm handles the process of feature selection in two separate indices. Hence, the computational complexity of the algorithm is reduced to O(nk+1). The algorithm applies the statistical divergence-based information theory to identify the relationship between the distant features of the chronic disease data set. The data set required to experiment is obtained from several medical labs and hospitals of karkala taluk ,India. The HLRM is used as a machine learning classifier. The predictive ability of the framework is compared with the various algorithm and also with the various chronic disease data set. The experimental result illustrates that the proposed framework is efficient and achieved competitive results are compared to the existing work in most of the cases.

Evaluating the quality of investment products: can expert judgment outsmart the market?

foresight ◽  
2019 ◽  
Vol 21 (4) ◽  
pp. 497-507
Author(s):  
Jiří Šindelář ◽  
Martin Svoboda
Keyword(s):  
Domain Knowledge ◽  
Predictive Accuracy ◽  
Value Added ◽  
Predictive Ability ◽  
Expert Judgment ◽  
Financial Advisors ◽  
Large Set ◽  
Investment Funds ◽  
Content Type ◽  
Ex Post

Purpose This paper aims to deal with expert judgment and its predictive ability in the context of investment funds. The judgmental ratings awarder with a large set of experts was compared to a sample of the dynamic investment funds operating in Central and Eastern Europe with their objective performance, both past and future, relatively to the time of the forecast. Design/methodology/approach Data on the survey sample enabled the authors to evaluate both ex post judgmental validity, i.e. how the experts reflected the previous performance of funds, and ex ante predictive accuracy, i.e. how well their judgments estimated the future performance of the fund. For this purpose, logistic regression for past values estimations and linear model for future values estimations was used. Findings It was found that the experts (independent academicians, senior bank specialists and senior financial advisors) were only able to successfully reflect past annual returns of a five-year period, failing to reflect costs and annual volatility and, mainly, failing to predict any of the indicators on the same five-year horizon. Practical implications The outcomes of this paper confirm that expert judgment should be used with caution in the context of financial markets and mainly in situations when domain knowledge is applicable. Procedures incorporating judgmental evaluations, such as individual investment advice, should be thoroughly reviewed in terms of client value-added, to eliminate potential anchoring bias. Originality/value This paper sheds new light on the quality and nature of individual judgment produced by financial experts. These are prevalent in many situations influencing clients’ decision-making, be it financial advice or multiple product contests. As such, our findings underline the need of scepticism when these judgments are taken into account.

Sign in / Sign up

Export Citation Format

Share Document