ORCID Profile
0000-0002-3395-1772
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: Elsevier BV
Date: 12-2017
Publisher: IEEE
Date: 12-2010
Publisher: IEEE
Date: 11-2010
DOI: 10.1109/EMS.2010.33
Publisher: IEEE
Date: 12-2010
Publisher: IEEE
Date: 11-2010
DOI: 10.1109/EMS.2010.34
Publisher: Emerald
Date: 29-05-2020
DOI: 10.1108/ECAM-08-2019-0406
Abstract: This study aims to propose the adoption of artificial neural network (ANN)-based prediction intervals (PIs) to give more reliable prediction of labour productivity using historical data. Using the proposed PI method, various sources of uncertainty affecting predictions can be accounted for, and a PI is proposed instead of a less reliable single-point estimate. The proposed PI consists of a lower and upper bound in which the realization of the predicted variable, namely, labour productivity, is anticipated to fall with a defined probability and represented in terms of a confidence level (CL). The proposed PI method is implemented on a case study project to predict labour productivity. The quality of the generated PIs for the labour productivity is investigated at three confidence levels. The results show that the proposed method can predict the value of labour productivity efficiently. This study is the first attempt in construction management to undertake a shift from deterministic point predictions to interval forecasts to improve the reliability of predictions. The proposed PI method will help project managers obtain accurate and credible predictions of labour productivity using historical data. With a better understanding of future outcomes, project managers can adopt appropriate improvement strategies to enhance labour productivity before commencing a project. Point predictions provided by traditional deterministic ANN-based forecasting methodologies may be unreliable due to the different sources of uncertainty affecting predictions. The current study proposes ANN-based PIs as an alternative and robust tool to give a more reliable prediction of labour productivity using historical data. Using the proposed method, various sources of uncertainty affecting the predictions are accounted for, and a PI is proposed instead of a less reliable single point estimate.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Publisher: IEEE
Date: 12-2010
Publisher: IEEE
Date: 11-2010
Publisher: IEEE
Date: 12-2010
Publisher: IEEE
Date: 11-2010
Publisher: IEEE
Date: 04-2017
Publisher: IEEE
Date: 11-2010
Publisher: The Hong Kong Institution of Engineers
Date: 02-01-2015
Publisher: IEEE
Date: 11-2010
Publisher: Elsevier BV
Date: 04-2022
DOI: 10.1016/J.COMPBIOMED.2022.105246
Abstract: The user does not have any idea about the credibility of outcomes from deep neural networks (DNN) when uncertainty quantification (UQ) is not employed. However, current Deep UQ classification models capture mostly epistemic uncertainty. Therefore, this paper aims to propose an aleatory-aware Deep UQ method for classification problems. First, we train DNNs through transfer learning and collect numeric output posteriors for all training s les instead of logical outputs. Then we determine the probability of happening a certain class from K-nearest output posteriors of the same DNN in training s les. We name this probability as opacity score, as the paper focuses on the detection of opacity on X-ray images. This score reflects the level of aleatory on the s le. When the NN is certain on the classification of the s le, the probability of happening a class becomes much higher than the probabilities of others. Probabilities for different classes become close to each other for a highly uncertain classification outcome. To capture the epistemic uncertainty, we train multiple DNNs with different random initializations, model selection, and augmentations to observe the effect of these training parameters on prediction and uncertainty. To reduce execution time, we first obtain features from the pre-trained NN. Then we apply features to the ensemble of fully connected layers to get the distribution of opacity score during the test. We also train several ResNet and DenseNet DNNs to observe the effect of model selection on prediction and uncertainty. The paper also demonstrates a patient referral framework based on the proposed uncertainty quantification. The scripts of the proposed method are available at the following link: ipuk0506/Aleatory-aware-UQ.
Publisher: IEEE
Date: 12-2010
Location: Australia
Location: Bangladesh
No related grants have been discovered for Hussain Mohammed Dipu Kabir.