Search results

Experiments are the backbone of the development process of data-driven predictive models for scientific applications. The quality of the experiments directly impacts the model performance. Uncertainty inherently affects experiment measurements and is often missing in the available data sets due to its estimation cost. For similar reasons, experiments are very few compared to other data sources. Discarding experiments based on the missing uncertainty values would preclude the development of predictive models. Data profiling techniques are fundamental to assess data quality, but some data quality dimensions are challenging to evaluate without knowing the uncertainty. In this context, this paper aims to predict the missing uncertainty of the experiments.

This work presents a methodology to forecast the experiments’ missing uncertainty, given a data set and its ontological description. The approach is based on knowledge graph embeddings and leverages the task of link prediction over a knowledge graph representation of the experiments database. The validity of the methodology is first tested in multiple conditions using synthetic data and then applied to a large data set of experiments in the chemical kinetic domain as a case study.

The analysis results of different test case scenarios suggest that knowledge graph embedding can be used to predict the missing uncertainty of the experiments when there is a hidden relationship between the experiment metadata and the uncertainty values. The link prediction task is also resilient to random noise in the relationship. The knowledge graph embedding outperforms the baseline results if the uncertainty depends upon multiple metadata.

The employment of knowledge graph embedding to predict the missing experimental uncertainty is a novel alternative to the current and more costly techniques in the literature. Such contribution permits a better data quality profiling of scientific repositories and improves the development process of data-driven models based on scientific experiments.

Wireless sensor networks (WSNs) are periodically collecting data through randomly dispersed sensors (motes), which typically consume high energy in radio communication that mainly leans on data transmission within the network. Furthermore, dissemination mode in WSN usually produces noisy values, incorrect measurements or missing information that affect the behaviour of WSN. In this article, a Distributed Data Predictive Model (DDPM) was proposed to extend the network lifetime by decreasing the consumption in the energy of sensor nodes. It was built upon a distributive clustering model for predicting dissemination-faults in WSN. The proposed model was developed using Recursive least squares (RLS) adaptive filter integrated with a Finite Impulse Response (FIR) filter, for removing unwanted reflections and noise accompanying of the transferred signals among the sensors, aiming to minimize the size of transferred data for providing energy efficient. The experimental results demonstrated that DDPM reduced the rate of data transmission to ∼20%. Also, it decreased the energy consumption to 95% throughout the dataset sample and upgraded the performance of the sensory network by about 19.5%. Thus, it prolonged the lifetime of the network.

Occupational Safety and Health Administration (OSHA) of the U.S. government ensures that all health and safety regulations, protecting the workers, are enforced. OSHA officers conduct inspections and assess fines for non-compliance and regulatory violations. Literature discussion on the economic impact of OSHA inspections with COVID-19 related citations for the construction sector is lacking. This study aims to investigate the relationships between the number of COVID-19 cases, construction employment and OSHA citations and it further evaluates the total and monthly predicted cost impact of OSHA citations associated with COVID-19 violations.

An application of multiple regression analysis, a supervised machine learning linear regression model, based on K-fold cross validation sampling and a probabilistic risk-based cost estimate Monte Carlo simulation were utilized to evaluate the data. The data were collected from numerous websites including OSHA, Centers for Disease Control and the World Health Organization.

The results show that as the monthly construction employment increased, there was a decrease in OSHA citations. Conversely, the cost impact of OSHA citations had a positive relationship with the number of COVID-19 cases. In addition, the monthly cost impact of OSHA COVID-19 related citations along with the total cost impact of citations were predicted and analyzed.

The application of the two models on cost analysis provides a thorough comparison of predicted and overall cost impact, which can assist the contractors to better understand the possible cost ramifications. Based on the findings, it is suggested that the contractors include contingency fees within their contracts, hire safety managers to implement specific safety protocols related to COVID-19 and request a safety action plan when qualifying their subcontractors to avoid potential fines and citations.

This study aims at evaluating the effect of the COVID-19 pandemic on the export trade system for Mauritius during the first half of 2020 (January 2020–June 2020).

An initial analysis of the monthly export time series data proves that on the whole, the series have diverged from their actual trends after the outbreak of the COVID-19 pandemic: observed values are less than those predicted by the selected optimal forecast models. The authors subsequently employ the Bayesian structural time series (BSTS) framework for causal analysis to estimate the impact of the COVID-19 pandemic on the island's export system.

Overall, the findings show that the COVID-19 pandemic has a statistically significant and negative impact on the Mauritian export trade system, with the five main export trading partners and sectors the most affected. Despite that the impact in some cases is not apparent for the period of study, the results indicate that total exports will surely be affected by the pandemic in the long run. Nevertheless, this depends on the measures taken both locally and globally to mitigate the spread of the pandemic.

This study thus contributes to the growing literature on the economic impacts of the COVID-19 pandemic by focussing on a small island economy.

This article examines the accuracy and bias inherent in the wisdom of crowd effect. The purpose is to clarify what kind of bias crowds have when they make predictions. In the theoretical inquiry, the effect of the accumulated absolute deviation was simulated. In the empirical study, the observed biases were examined using data from forecasting foreign exchange rates.

In the theoretical inquiry, the effect of the accumulated absolute deviation was simulated based on mathematical propositions. In the empirical study, the data from 2004 to 2011 were provided by Nikkei, which holds the “Nikkei Yen Derby” competition. In total, 3,657 groups forecasted the foreign exchange rate, and the first prediction was done in early May to forecast the rate at the end of May. The second round took place in June in a similar manner.

The average absolute deviation in May was smaller than that in June. The first round of prediction was more accurate than the second round one. Predictors were affected by the observable real exchange rate, such that they modified their forecasts by referring to the actual data in early June. An actuality bias existed when the participants lost their diverse prospects. Since the standard deviations of the June forecasts were smaller than those of May, the fact-convergence effect was supported.

This article reports novel findings that affect the wisdom of crowd effect—referred to as actuality bias and fact-convergence effect. The former refers to a forecasting bias toward the observable rate near the forecasting date. The latter implies that predictors, as a whole, indicate smaller forecast deviations by observing the realized foreign exchange rate.

The purposes of this research are to study the theory and method of multi-attribute index system design and establish a set of systematic, standardized, scientific index systems for the design optimization and inspection process. The research may form the basis for a rational, comprehensive evaluation and provide the most effective way of improving the quality of management decision-making. It is of practical significance to improve the rationality and reliability of the index system and provide standardized, scientific reference standards and theoretical guidance for the design and construction of the index system.

Using modern methods such as complex networks and machine learning, a system for the quality diagnosis of index data and the classification and stratification of index systems is designed. This guarantees the quality of the index data, realizes the scientific classification and stratification of the index system, reduces the subjectivity and randomness of the design of the index system, enhances its objectivity and rationality and lays a solid foundation for the optimal design of the index system.

Based on the ideas of statistics, system theory, machine learning and data mining, the focus in the present research is on “data quality diagnosis” and “index classification and stratification” and clarifying the classification standards and data quality characteristics of index data; a data-quality diagnosis system of “data review – data cleaning – data conversion – data inspection” is established. Using a decision tree, explanatory structural model, cluster analysis, K-means clustering and other methods, classification and hierarchical method system of indicators is designed to reduce the redundancy of indicator data and improve the quality of the data used. Finally, the scientific and standardized classification and hierarchical design of the index system can be realized.

The innovative contributions and research value of the paper are reflected in three aspects. First, a method system for index data quality diagnosis is designed, and multi-source data fusion technology is adopted to ensure the quality of multi-source, heterogeneous and mixed-frequency data of the index system. The second is to design a systematic quality-inspection process for missing data based on the systematic thinking of the whole and the individual. Aiming at the accuracy, reliability, and feasibility of the patched data, a quality-inspection method of patched data based on inversion thought and a unified representation method of data fusion based on a tensor model are proposed. The third is to use the modern method of unsupervised learning to classify and stratify the index system, which reduces the subjectivity and randomness of the design of the index system and enhances its objectivity and rationality.

Inspired by the basic idea of gradient boosting, this study aims to design a novel multivariate regression ensemble algorithm RegBoost by using multivariate linear regression as a weak predictor.

To achieve nonlinearity after combining all linear regression predictors, the training data is divided into two branches according to the prediction results using the current weak predictor. The linear regression modeling is recursively executed in two branches. In the test phase, test data is distributed to a specific branch to continue with the next weak predictor. The final result is the sum of all weak predictors across the entire path.

Through comparison experiments, it is found that the algorithm RegBoost can achieve similar performance to the gradient boosted decision tree (GBDT). The algorithm is very effective compared to linear regression.

This paper attempts to design a novel regression algorithm RegBoost with reference to GBDT. To the best of the knowledge, for the first time, RegBoost uses linear regression as a weak predictor, and combine with gradient boosting to build an ensemble algorithm.

The purpose of this study is to show that closure-based classification and regression models provide both high accuracy and interpretability.

Pattern structures allow one to approach the knowledge extraction problem in case of partially ordered descriptions. They provide a way to apply techniques based on closed descriptions to non-binary data. To provide scalability of the approach, the author introduced a lazy (query-based) classification algorithm.

The experiments support the hypothesis that closure-based classification and regression allow one to both achieve higher accuracy in scoring models as compared to results obtained with classical banking models and retain interpretability of model results, whereas black-box methods grant better accuracy for the cost of losing interpretability.

This is an original research showing the advantage of closure-based classification and regression models in the banking sphere.

The purpose of this paper is to investigate and quantify the impact of product complexity, including architectural complexity, on operator learning, productivity and quality performance in both assembly and disassembly operations. This topic has not been extensively investigated in previous research.

An extensive experimental campaign involving 84 operators was conducted to repeatedly assemble and disassemble six different products of varying complexity to construct productivity and quality learning curves. Data from the experiment were analysed using statistical methods.

The human learning factor of productivity increases superlinearly with the increasing architectural complexity of products, i.e. from centralised to distributed architectures, both in assembly and disassembly, regardless of the level of overall product complexity. On the other hand, the human learning factor of quality performance decreases superlinearly as the architectural complexity of products increases. The intrinsic characteristics of product architecture are the reasons for this difference in learning factor.

The results of the study suggest that considering product complexity, particularly architectural complexity, in the design and planning of manufacturing processes can optimise operator learning, productivity and quality performance, and inform decisions about improving manufacturing operations.

While previous research has focussed on the effects of complexity on process time and defect generation, this study is amongst the first to investigate and quantify the effects of product complexity, including architectural complexity, on operator learning using an extensive experimental campaign.

In the literature there are numerous tests that compare the accuracy of automated valuation models (AVMs). These models first train themselves with price data and property characteristics, then they are tested by measuring their ability to predict prices. Most of them compare the effectiveness of traditional econometric models against the use of machine learning algorithms. Although the latter seem to offer better performance, there is not yet a complete survey of the literature to confirm the hypothesis.

All tests comparing regression analysis and AVMs machine learning on the same data set have been identified. The scores obtained in terms of accuracy were then compared with each other.

Machine learning models are more accurate than traditional regression analysis in their ability to predict value. Nevertheless, many authors point out as their limit their black box nature and their poor inferential abilities.

AVMs machine learning offers a huge advantage for all real estate operators who know and can use them. Their use in public policy or litigation can be critical.

According to the author, this is the first systematic review that collects all the articles produced on the subject done comparing the results obtained.