Article
Construction & Building Technology
M. Z. Naser
Summary: The resistance towards adopting AI/ML in structural engineering stems from the lack of transparency in these technologies and the contrast with traditional methods favored by the industry and education. While engineers tend to chase good metrics when adopting AI/ML, forced goodness may lead to false inference.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Computer Science, Artificial Intelligence
Federico Cabitza, Andrea Campagner, Gianclaudio Malgieri, Chiara Natali, David Schneeberger, Karl Stoeger, Andreas Holzinger
Summary: This paper presents a framework for defining different types of explanations of AI systems and criteria for evaluating their quality. It proposes a structural view of constructing explanations and suggests a typology based on the explanandum, explanantia, and their relationship. The paper highlights the importance of epistemological and psychological perspectives in defining quality criteria and aims to support clear inventories, verification criteria, and validation methods for AI explainability.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Civil
Mohsen Zaker Esteghamati, Thomas Gernay, Srishti Banerji
Summary: This study develops explainable data-driven models to predict the fire resistance of timber columns, and compares their predictive capabilities to available prescriptive equations. The results show that the random forest-based model provides the best performance, with accurate and balanced predictions. Column capacity and cross-section dimension are the main factors influencing fire resistance.
ENGINEERING STRUCTURES
(2023)
Article
Computer Science, Information Systems
Angel Delgado-Panadero, Beatriz Hernandez-Lorca, Maria Teresa Garcia-Ordas, Jose Alberto Benitez-Andrades
Summary: This paper proposes a feature contribution method for GBDT, which can calculate the contribution of each feature to predictions. The method not only serves as a local explainability model for GBDT, but also reflects its internal behavior. It is significant for ethical analysis of AI and compliance with relevant regulations.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Emmanuel Doumard, Julien Aligon, Elodie Escriva, Jean -Baptiste Excoffier, Paul Monsarrat, Chantal Soule-Dupuy
Summary: This paper aims to evaluate the limitations of the widely used additive explanation methods, SHAP and LIME, on a wide range of datasets and propose coalitional-based methods to overcome their weaknesses. The results show that SHAP and LIME are efficient in generating intelligible global explanations in high dimension, but they lack precision in local explanations and may exhibit unwanted behavior when changing parameters. Coalitional-based methods are computationally expensive but offer higher quality local explanations. A roadmap is provided to guide the selection of the most appropriate method based on dataset dimensionality and user's objectives.
INFORMATION SYSTEMS
(2023)
Article
Medicine, General & Internal
Yiming Zhang, Ying Weng, Jonathan Lund
Summary: In recent years, artificial intelligence has shown promise in medicine, but lack of explainability limits its clinical applications. Explainable artificial intelligence (XAI) has been developed to overcome this limitation by providing both decision-making and explanations. This review surveys the recent trends in medical diagnosis and surgical applications using XAI and summarizes the methods, challenges, and future research directions.
Article
Computer Science, Artificial Intelligence
Richard Dazeley, Peter Vamplew, Cameron Foale, Charlotte Young, Sunil Aryal, Francisco Cruz
Summary: In recent years, research into eXplainable Artificial Intelligence (XAI) and Interpretable Machine Learning (IML) has rapidly grown, driven by legislative changes, increased industry and government investments, and growing concerns from the public. While most explanations in these fields focus on low-level explanations of individual decisions based on specific data, factors such as beliefs, motivations, and interpretations of external cultural expectations are essential for people to accept and trust AI decision-making.
ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Obumneme Nwafor, Emmanuel Okafor, Ahmed A. Aboushady, Chioma Nwafor, Chengke Zhou
Summary: There is a concern about non-technical losses in developing countries, especially in sub-Saharan Africa. Existing studies have focused only on customer data and ignored the contribution of electricity distribution staff. This study introduces a new approach by analyzing a combined dataset of staff operational processes and customer consumption data. The results suggest that staff-related variables are significant predictors of non-technical losses.
Article
Biochemical Research Methods
Natalia A. Szulc, Zuzanna Mackiewicz, Janusz M. Bujnicki, Filip Stefaniak
Summary: We developed a software called fingeRNAt for detecting non-covalent bonds formed within nucleic acid-ligand complexes. By using SIFts and machine learning methods, we were able to predict the binding of small molecules to RNA with higher accuracy compared to classic scoring functions. Additionally, we employed Explainable Artificial Intelligence (XAI) methods to better understand the decision-making process and quantitatively analyze the impact of interactions.
BRIEFINGS IN BIOINFORMATICS
(2023)
Review
Computer Science, Artificial Intelligence
Johannes Allgaier, Lena Mulansky, Rachel Lea Draelos, Ruediger Pryss
Summary: Background: The use of machine learning in medical applications is growing rapidly, but most ML systems are still opaque in their decision-making process. In this paper, the authors provide an overview of explainability methods in ML and review popular methods. They also conduct a literature search on PubMed to investigate the use of explainable artificial intelligence (XAI) methods in specific medical supervised ML use cases and the evolution of ML pipeline descriptions.
Results: Many publications on ML use cases do not employ XAI methods to explain predictions. However, when XAI methods are used, open-source and model-agnostic explanation methods, such as SHAP and Grad-CAM, are commonly utilized for tabular and image data. The level of detail and uniformity in describing ML pipelines has improved in recent years, but the willingness to share data and code remains limited.
Conclusions: XAI methods are mainly used in simpler applications. Standardized reporting in ML use cases can enhance comparability and should be promoted further. With the increasing complexity of the domain, experts who bridge the gap between informatics and medicine will be in high demand when using ML systems.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Computer Science, Information Systems
Eun-Hun Lee, Hyeoncheol Kim
Summary: Deep neural networks capture high-level features of data by stacking layers deeply; various studies aim to interpret the knowledge learned by neural networks; a proposed method provides global explanations for deep neural network models through model features.
Article
Chemistry, Multidisciplinary
Suk-Young Lim, Dong-Kyu Chae, Sang-Chul Lee
Summary: This paper presents a human perception level interpretability method for deepfake audio detection and proposes a novel concept of providing fresh interpretation using attribution scores.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Hafsa Binte Kibria, Md Nahiduzzaman, Md Omaer Faruq Goni, Mominul Ahsan, Julfikar Haider
Summary: Diabetes is a worldwide health concern, and current machine learning algorithms lack reliability and trust from physicians. This study proposes an efficient and interpretable method that uses explainable AI and different types of graphs to help physicians understand and trust model predictions.
Review
Computer Science, Theory & Methods
Meike Nauta, Jan Trienes, Shreyasi Pathak, Elisa Nguyen, Michelle Peters, Yasmin Schmitt, Joerg Schloetterer, Maurice Van Keulen, Christin Seifert
Summary: The evaluation of explanations for machine learning models is a complex concept that should not be solely based on subjective validation. This study identifies 12 conceptual properties that should be considered for a comprehensive assessment of explanation quality. The evaluation practices of over 300 papers introducing explainable artificial intelligence (XAI) methods in the past 7 years were systematically reviewed, finding that one-third of the papers exclusively relied on anecdotal evidence and one-fifth evaluated with users. The study also provides an extensive overview of quantitative XAI evaluation methods, offering researchers and practitioners concrete tools for validation and benchmarking.
ACM COMPUTING SURVEYS
(2023)
Article
Information Science & Library Science
Marina Johnson, Abdullah Albizri, Antoine Harfouche, Samuel Fosso-Wamba
Summary: Artificial intelligence (AI) has gained attention for its potential to reduce costs, increase revenue, and improve customer satisfaction. However, the lack of labeled datasets and the opaque nature of AI algorithms hinder effective decision-making. In this study, the authors propose an approach called informed AI (IAI) that integrates human domain knowledge to develop reliable data labeling and model explainability processes.
INTERNATIONAL JOURNAL OF INFORMATION MANAGEMENT
(2022)
Review
Computer Science, Interdisciplinary Applications
Arash Teymori Gharah Tapeh, M. Z. Naser
Summary: This review aims to promote the integration of artificial intelligence techniques into the field of structural engineering. It provides a comprehensive analysis and review of commonly used algorithms, techniques, and best practices, with a focus on applications in earthquake, wind, fire engineering, etc.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Materials Science, Multidisciplinary
Aditya Daware, Abdul Basit Peerzada, M. Z. Naser, Prasada Rangaraju, Brad Butman
Summary: Investigated the fire-induced degradation of compressive strength in masonry and found a lower level of degradation, as well as higher retention of strength under post-fire conditions.
FIRE AND MATERIALS
(2023)
Article
Engineering, Civil
Huanting Zhou, Huaidong Li, Han Qin, Tianfu Liang, M. Z. Naser
Summary: Prestressed steel-concrete composite beams can improve their fire resistance by reinforcing the webs with concrete, preventing buckling and horizontal deflection. Finite element models further revealed the mechanisms of fire response.
ENGINEERING STRUCTURES
(2023)
Article
Materials Science, Multidisciplinary
Ghada Karaki, Mohannad Z. Naser
Summary: Probabilistic approaches provide a realistic assessment of structures under fire conditions and overcome limitations of traditional methods. This paper presents a methodology to develop temperature-dependent probabilistic models for commonly used construction materials. The newly derived models are compared against fire codes and machine learning models.
FIRE AND MATERIALS
(2023)
Article
Green & Sustainable Science & Technology
M. Z. Naser
Summary: Machine learning presents attractive opportunities in engineering by bypassing the limitations of traditional methods, but also brings unique challenges such as heavy reliance on large datasets and computing facilities. This paper emphasizes the importance of energy consumption and carbon emissions in ML modeling and proposes the concept of Green ML. By examining different ML algorithms on a large dataset, it is found that adopting simple models can significantly reduce energy consumption and carbon emissions while maintaining comparable accuracy.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Construction & Building Technology
M. Z. Naser, Aybike Ozyuksel Ciftcioglu
Summary: Experiments are the most reliable way to understand fire-related phenomena. The goal of tests is to uncover the process behind the data we observe and determine the causes of these observations. This paper introduces an approach that combines causal discovery and causal inference to evaluate the fire resistance of structural members.
STRUCTURAL CONCRETE
(2023)
Article
Engineering, Multidisciplinary
M. Z. Naser, Aybike Ozyuksel Ciftcioglu
Summary: The expensive and unique facilities required for fire testing make it difficult to conduct comprehensive experimental campaigns, resulting in limited testing of specimens. Addressing causal and hypothetical questions about fire response becomes challenging for statistical and machine learning methods. To overcome this, this paper presents a causal approach to answer such questions by adopting principles of causal inference to reconstruct the deformation-time history of reinforced concrete (RC) columns and propose an idealized fire response. The findings highlight the significant influence of loading level, aggregate type, and longitudinal steel ratio on the deformation history of fire-exposed RC columns.
Review
Construction & Building Technology
Balamurali Kanagaraj, N. Anand, Diana Andrushia, M. Z. Naser
Summary: This article provides a detailed study of different RSC materials suitable for radiation shielding and evaluates their shielding performance, hardening characteristics, and serviceability. It also comprehensively reviews the potential of RSC as an innovative building material for radiation protection and highlights current knowledge gaps and future research directions in this field.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Mohammad Khaled al-Bashiti, M. Z. Naser
Summary: This paper presents a comprehensive statistical investigation of the largest database on fire-induced spalling of concrete collected to date, examining 43 factors and proposing future research directions.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Engineering, Civil
Ahmad Tarawneh, Eman Saleh, Abdullah Alghossoon, M. Z. Naser
Summary: Existing shear design models for reinforced concrete are not accurate and conservative. A modified shear design model consistent with the current ACI 318-19 model is proposed, which accounts for FRP axial stiffness and has higher accuracy. The proposed model outperformed the ACI 318-19 model in statistical measures when applied to steel-RC concrete beams.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Industrial
Zhiyuan Qin, M. Z. Naser
Summary: This paper presents a novel framework for quantifying the uncertainty in the inverse problems of suspended nonstructural systems. The framework combines machine learning and model-driven stochastic Gaussian process model calibration to account for geometric complexity through Bayesian inference. The proposed framework is validated using a large-scale shaking table test and simulated data, showing computational soundness, scalability, and optimal generalizability.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Civil
Alireza Ghasemi, M. Z. Naser
Summary: This paper presents a study on 3D printed concrete, which includes the establishment of a large database with over 300 experiments. The data is analyzed using multilinear regression and explainable artificial intelligence algorithms, resulting in a working model capable of predicting the compressive strength of 3D concrete mixtures.
Review
Construction & Building Technology
Deanna Craig, M. Z. Naser
Summary: This paper discusses the unique nature of structural fire engineering and highlights the reliance on expensive fire tests and outdated procedures. It compares global efforts in performance-based fire design and finds that European and Oceanian efforts are more advanced. Most performance-based fire designs are related to steel and composite structures.
JOURNAL OF STRUCTURAL FIRE ENGINEERING
(2023)
Article
Construction & Building Technology
Maha Assad, Rami Hawileh, Ghada Karaki, Jamal Abdalla, M. Z. Naser
Summary: This research investigates the behavior of reinforced concrete walls under fire conditions and identifies the thermal and mechanical factors that affect their performance. A 3D finite element model is developed to predict the response of the walls and is validated through experimental tests. The study finds that the fire resistance of the walls is compromised under hydrocarbon fire, and the minimum wall thickness specified by current regulations may not be sufficient.
JOURNAL OF STRUCTURAL FIRE ENGINEERING
(2023)
Article
Construction & Building Technology
Haley Hostetter, M. Z. Naser
Summary: This paper examines the architectural engineering features of psychiatric hospitals from the perspective of fire hazards, and analyzes the common causes and mitigation strategies of structural fires in these hospitals. By studying the shortcomings of past designs, it aims to enhance the understanding of current and future professionals in mitigating fire risks for vulnerable populations in healthcare facilities.
JOURNAL OF ARCHITECTURAL ENGINEERING
(2023)