The impact of using biased performance metrics on software defect prediction research

J Yao, M Shepperd - Information and Software Technology, 2021 - Elsevier
Context: Software engineering researchers have undertaken many experiments
investigating the potential of software defect prediction algorithms. Unfortunately some …

Use and misuse of the term “experiment” in mining software repositories research

C Ayala, B Turhan, X Franch… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The significant momentum and importance of Mining Software Repositories (MSR) in
Software Engineering (SE) has fostered new opportunities and challenges for extensive …

Impact of digitalization on the way of working and skills development in hydrocarbon production forecasting and project decision analysis

T Clemens, M Viechtbauer-Gruber - SPE Reservoir Evaluation & …, 2020 - onepetro.org
Hydrocarbon (re‐) development projects need to be evaluated under uncertainty.
Forecasting oil and gas production needs to capture the ranges of the multitude of uncertain …

Visual digital data, ethical challenges, and psychological science.

M Levine, R Philpot, SJ Nightingale… - American …, 2024 - psycnet.apa.org
Digital visual data afford psychologists with exciting research possibilities. It becomes
possible to see real-life interactions in real time and to be able to analyze this behavior in a …

Testing the Consistency of Performance Scores Reported for Binary Classification Problems

A Fazekas, G Kovács - arXiv preprint arXiv:2310.12527, 2023 - arxiv.org
Binary classification is a fundamental task in machine learning, with applications spanning
various scientific domains. Whether scientists are conducting fundamental research or …

mlscorecheck: Testing the consistency of reported performance scores and experiments in machine learning

G Kovács, A Fazekas - Neurocomputing, 2024 - Elsevier
Addressing the reproducibility crisis in artificial intelligence through the validation of reported
experimental results is a challenging task. It necessitates either the reimplementation of …

Pitfalls in Experiments with DNN4SE: An Analysis of the State of the Practice

S Vegas, S Elbaum - Proceedings of the 31st ACM Joint European …, 2023 - dl.acm.org
Software engineering (SE) techniques are increasingly relying on deep learning
approaches to support many SE tasks, from bug triaging to code generation. To assess the …

Remaining useful life estimation of bearings: Meta-analysis of experimental procedure

HM Ferreira, AC de Sousa - International Journal of …, 2020 - papers.phmsociety.org
In the domain of predictive maintenance, when trying to repli-cate and compare research in
remaining useful life estimation (RUL), several inconsistencies and errors were identified in …

Extracting biological insights from genomics data using machine learning approaches

LD Hentges - 2021 - ora.ox.ac.uk
ATAC-seq, ChIP-seq, and DNase-seq have revolutionised molecular biology by allowing
researchers to identify important DNA-encoded elements genome-wide. Regions where …

[PDF][PDF] Scoring assessment of three machine learning models based on molecular docking at multiple conformations of two kinase targets

A Diaz - 2020 - erepo.uef.fi
The drug discovery pipeline is time consuming and expensive for both industry and
academia. Molecular docking, is an efficient method which succeeds when generating …