Requirements engineering for machine learning: A review and reflection

Z Pei, L Liu, C Wang, J Wang - 2022 IEEE 30th International …, 2022 - ieeexplore.ieee.org
Today, many industrial processes are undergoing digital transformation, which often
requires the integration of well-understood domain models and state-of-the-art machine …

Causality in configurable software systems

C Dubslaff, K Weis, C Baier, S Apel - Proceedings of the 44th …, 2022 - dl.acm.org
Detecting and understanding reasons for defects and inadvertent behavior in software is
challenging due to their increasing complexity. In configurable software systems, the …

[HTML][HTML] Modeling of H2S solubility in ionic liquids: comparison of white-box machine learning, deep learning and ensemble learning approaches

SP Mousavi, R Nakhaei-Kohani, S Atashrouz… - Scientific Reports, 2023 - nature.com
In the context of gas processing and carbon sequestration, an adequate understanding of
the solubility of acid gases in ionic liquids (ILs) under various thermodynamic circumstances …

Unicorn: reasoning about configurable system performance through the lens of causality

MS Iqbal, R Krishna, MA Javidian, B Ray… - Proceedings of the …, 2022 - dl.acm.org
Modern computer systems are highly configurable, with the total variability space sometimes
larger than the number of atoms in the universe. Understanding and reasoning about the …

Adaptive Façades Strategy: An architect-friendly computational approach based on co-simulation and white-box models for the early design stage

Z Nie, S Chen, S Zhang, H Wu, T Weiss, L Zhao - Energy and Buildings, 2023 - Elsevier
Adaptive façades (AFs) are technologies with great potential to reduce energy consumption
by changing their properties to adapt to variable climatic conditions. This paper proposes an …

On debugging the performance of configurable software systems: Developer needs and tailored tool support

M Velez, P Jamshidi, N Siegmund, S Apel… - Proceedings of the 44th …, 2022 - dl.acm.org
Determining whether a configurable software system has a performance bug or it was
misconfigured is often challenging. While there are numerous debugging techniques that …

Transfer learning across variants and versions: The case of linux kernel size

H Martin, M Acher, JA Pereira, L Lesoil… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
With large scale and complex configurable systems, it is hard for users to choose the right
combination of options (ie, configurations) in order to obtain the wanted trade-off between …

[HTML][HTML] Adaptive thermal load prediction in residential buildings using artificial neural networks

MH Fouladfar, A Soppelsa, H Nagpal, R Fedrizzi… - Journal of Building …, 2023 - Elsevier
Accurate prediction of thermal load in buildings is essential for efficient energy planning. In
this study, we investigate the application of Artificial Neural Networks (ANNs) to predict …

White-box performance-influence models: A profiling and learning approach

M Weber, S Apel, N Siegmund - 2021 IEEE/ACM 43rd …, 2021 - ieeexplore.ieee.org
Many modern software systems are highly configurable, allowing the user to tune them for
performance and more. Current performance modeling approaches aim at finding …

Generalizable and interpretable learning for configuration extrapolation

Y Ding, A Pervaiz, M Carbin, H Hoffmann - … of the 29th ACM joint meeting …, 2021 - dl.acm.org
Modern software applications are increasingly configurable, which puts a burden on users to
tune these configurations for their target hardware and workloads. To help users, machine …