Machine learning (ML) has evolved rapidly over recent years with the promise to substantially alter and enhance the role of data science in a variety of disciplines. Compared with traditional approaches, ML offers advantages to handle complex problems, provide computational efficiency, propagate and treat uncertainties, and facilitate decision making. Also, the maturing of ML has led to significant advances in not only the main-stream artificial intelligence (AI) research but also other science and engineering fields, such as material science, bioengineering, construction management, and transportation engineering. This study conducts a comprehensive review of the progress and challenges of implementing ML in the earthquake engineering domain. A hierarchical attribute matrix is adopted to categorize the existing literature based on four traits identified in the field, such as ML method, topic area, data resource, and scale of analysis. The state-of-the-art review indicates to what extent ML has been applied in four topic areas of earthquake engineering, including seismic hazard analysis, system identification and damage detection, seismic fragility assessment, and structural control for earthquake mitigation. Moreover, research challenges and the associated future research needs are discussed, which include embracing the next generation of data sharing and sensor technologies, implementing more advanced ML techniques, and developing physics-guided ML models.
Saif Z. S. Al Ghafri, S. Munro, U. Cardella
et al.
Hydrogen is emerging as one of the most promising energy carriers for a decarbonised global energy system. Transportation and storage of hydrogen are critical to its large-scale adoption and to...
Bubble behaviors play crucial roles in mass transfer and energy efficiency in gas evolution reactions. Combining multiscale structures and surface chemical compositions, micro-/nanostructured electrodes have drawn increasing attention. With the aim to identify the exciting opportunities and rationalize the electrode designs, in this review, we present our current comprehension of bubble engineering on micro-/nanostructured electrodes, focusing on water splitting. We first provide a brief introduction of gas wettability on micro-/nanostructured electrodes. Then we discuss the advantages of micro-/nanostructured electrodes for mass transfer (detailing the lowered overpotential, promoted supply of electrolyte, and faster bubble growth kinetics), localized electric field intensity, and electrode stability. Following that, we outline strategies for promoting bubble detachment and directional transportation. Finally, we offer our perspectives on this emerging field for future research directions.
The performance of Organic Solar Cells (OSCs) is intrinsically linked to the molecular, electronic, and structural properties of donor and acceptor materials. This study employs various machine learning techniques, namely the Generalized Regression Neural Network (GRNN), Support Vector Machine (SVM), and Tree Boost, to predict key performance metrics of OSCs, including power conversion efficiency (PCE), short-circuit current density (JSC), open-circuit voltage (VOC), and fill factor (FF). The models are trained and evaluated using an experimentally reported dataset compiled by Sahu et al. Correlation analysis demonstrates that material characteristics such as polarizability, bandgap, dipole moment, and charge transfer are statistically associated with OSC performance. The predictive performance of the GRNN model is compared with that of the SVM and Tree Boost models, showing consistently lower prediction errors within the considered dataset. In addition, sensitivity analysis is performed to assess the relative importance of the predictor variables and to examine the influence of kernel functions on GRNN performance. The results indicate that machine learning models, particularly GRNN, can serve as effective data-driven tools for predicting the performance of organic solar cells and for supporting computational screening studies.
Pengfei Zheng, Wilson Byiringiro, Weiwei Xie
et al.
Structural defects and cell irregularity significantly impact the performance and safety of honeycomb structures. Thus, various image processing techniques have been employed to evaluate the cell shape and detect structural defects within these structures. This paper proposes an improved Harris vertex extraction method for detecting honeycomb structures. Initially, the influence of parameters on Harris detection results is examined, and an empirical equation is derived to directly determine the optimal parameter values. Subsequently, a thinning process is applied to generate a honeycomb skeleton with single-pixel lines, ensuring consistent parameter settings across different cellular images and eliminating scale discrepancies. A Gaussian filter is then incorporated to smooth the noise and create a controllable multilevel grayscale transition, allowing the Harris corner detector to accurately identify corners. Comparative experiments demonstrate that the proposed method outperforms conventional algorithms, achieving an accuracy of 99.5%. In addition, a cell reconstruction approach is introduced to form a measurable honeycomb Y-shaped structure, accompanied by a regularity evaluation method based on the consistency of the side lengths and internal angles. Test results confirm that the proposed method accurately determines the side lengths and angles with an error margin of less than ±2% compared with manual measurements, effectively evaluating the regularity of the honeycomb. This methodology enhances the applicability and reliability of the structural performance evaluation through image processing.
Timo Kehrer, Robert Haines, Guido Juckeland
et al.
Anecdotal evidence suggests that Research Software Engineers (RSEs) and Software Engineering Researchers (SERs) often use different terminologies for similar concepts, creating communication challenges. To better understand these divergences, we have started investigating how SE fundamentals from the SER community are interpreted within the RSE community, identifying aligned concepts, knowledge gaps, and areas for potential adaptation. Our preliminary findings reveal opportunities for mutual learning and collaboration, and our systematic methodology for terminology mapping provides a foundation for a crowd-sourced extension and validation in the future.
Lekshmi Murali Rani, Richard Berntsson Svensson, Robert Feldt
The integration of AI for Requirements Engineering (RE) presents significant benefits but also poses real challenges. Although RE is fundamental to software engineering, limited research has examined AI adoption in RE. We surveyed 55 software practitioners to map AI usage across four RE phases: Elicitation, Analysis, Specification, and Validation, and four approaches for decision making: human-only decisions, AI validation, Human AI Collaboration (HAIC), and full AI automation. Participants also shared their perceptions, challenges, and opportunities when applying AI for RE tasks. Our data show that 58.2% of respondents already use AI in RE, and 69.1% view its impact as positive or very positive. HAIC dominates practice, accounting for 54.4% of all RE techniques, while full AI automation remains minimal at 5.4%. Passive AI validation (4.4 to 6.2%) lags even further behind, indicating that practitioners value AI's active support over passive oversight. These findings suggest that AI is most effective when positioned as a collaborative partner rather than a replacement for human expertise. It also highlights the need for RE-specific HAIC frameworks along with robust and responsible AI governance as AI adoption in RE grows.
Daniel Mendez, Paris Avgeriou, Marcos Kalinowski
et al.
Empirical Software Engineering has received much attention in recent years and became a de-facto standard for scientific practice in Software Engineering. However, while extensive guidelines are nowadays available for designing, conducting, reporting, and reviewing empirical studies, similar attention has not yet been paid to teaching empirical software engineering. Closing this gap is the scope of this edited book. In the following editorial introduction, we, the editors, set the foundation by laying out the larger context of the discipline for a positioning of the remainder of this book.
Kevin Hermann, Sven Peldszus, Jan-Philipp Steghöfer
et al.
Software security is of utmost importance for most software systems. Developers must systematically select, plan, design, implement, and especially, maintain and evolve security features -- functionalities to mitigate attacks or protect personal data such as cryptography or access control -- to ensure the security of their software. Although security features are usually available in libraries, integrating security features requires writing and maintaining additional security-critical code. While there have been studies on the use of such libraries, surprisingly little is known about how developers engineer security features, how they select what security features to implement and which ones may require custom implementation, and the implications for maintenance. As a result, we currently rely on assumptions that are largely based on common sense or individual examples. However, to provide them with effective solutions, researchers need hard empirical data to understand what practitioners need and how they view security -- data that we currently lack. To fill this gap, we contribute an exploratory study with 26 knowledgeable industrial participants. We study how security features of software systems are selected and engineered in practice, what their code-level characteristics are, and what challenges practitioners face. Based on the empirical data gathered, we provide insights into engineering practices and validate four common assumptions.
Engineering complex systems (aircraft, buildings, vehicles) requires accounting for geometric and performance couplings across subsystems. As generative models proliferate for specialized domains (wings, structures, engines), a key research gap is how to coordinate frozen, pre-trained submodels to generate full-system designs that are feasible, diverse, and high-performing. We introduce Generative Latent Unification of Expertise-Informed Engineering Models (GLUE), which orchestrates pre-trained, frozen subsystem generators while enforcing system-level feasibility, optimality, and diversity. We propose and benchmark (i) data-driven GLUE models trained on pre-generated system-level designs and (ii) a data-free GLUE model trained online on a differentiable geometry layer. On a UAV design problem with five coupling constraints, we find that data-driven approaches yield diverse, high-performing designs but require large datasets to satisfy constraints reliably. The data-free approach is competitive with Bayesian optimization and gradient-based optimization in performance and feasibility while training a full generative model in only 10 min on a RTX 4090 GPU, requiring more than two orders of magnitude fewer geometry evaluations and FLOPs than the data-driven method. Ablations focused on data-free training show that subsystem output continuity affects coordination, and equality constraints can trigger mode collapse unless mitigated. By integrating unmodified, domain-informed submodels into a modular generative workflow, this work provides a viable path for scaling generative design to complex, real-world engineering systems.
Transportation infrastructure is essential to a nation's everyday life and economic activity. Accordingly, pavement design and engineering are imperative to ensure safe, comfortable, and efficient transportation of goods, services, and people across countries. Pavements should be designed to be adaptable to changing traffic inputs and environmental conditions and always strive to fulfill the requirements of the end-users, including safety, durability, comfort, efficiency, sustainability, and cost. This review highlights innovations in paving technologies with a focus on sustainability from a socio-technical perspective; the scope is meant to be comprehensive but not exhaustive. The discussion categorizes paving design and technology innovations into two high-level sections: 1) high-volume urban pavement innovations and 2) low-volume rural pavement innovations.
Objective To address the challenges associated with the manual layout and point selection of S+T (standard rings+turning rings (double-sided wedges)) in shield tunnel segments, including high subjectivity, complex calculations, and heavy repetitive workload, a research is carried out focusing on algorithm development to resolve practical engineering issues. Method An automatic layout, assembly selection, prediction algorithm and software are developed for S+T in tunnel segments. Referring to mature construction experience, segment layout plan is calculated based on tunnel alignment and segment turning angles, and segment layout calculation automation is achieved. The calculation and decision-making methods of S+T segment types are proposed with comprehensive consideration of tunnel alignment, shield tail clearance, hydraulic cylinder stroke, and shield machine trends, enabling the automatic selection and assembly of segment points. Furthermore, by establishing a relationship between shield posture changes and variations in shield tail clearance and cylinder stroke, the algorithm can predict the S+T assembly points and segment types for the two future rings. Result & Conclusion The research results are successfully applied to Guangzhou Metro Line 12, significantly improving the efficiency of on-site S+T layout and selection, reducing labor costs, and optimizing the shield tunnel construction process.
Participatory citizen platforms are innovative solutions to digitally better engage citizens in policy-making and deliberative democracy in general. Although these platforms have been used also in an engineering context, thus far, there is no existing work for connecting the platforms to requirements engineering. The present paper fills this notable gap. In addition to discussing the platforms in conjunction with requirements engineering, the paper elaborates potential advantages and disadvantages, thus paving the way for a future pilot study in a software engineering context. With these engineering tenets, the paper also contributes to the research of large socio-technical software systems in a public sector context, including their implementation and governance.
Mehil B Shah, Mohammad Masudur Rahman, Foutse Khomh
Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). However, DL systems are prone to bugs from many sources, including training data. Existing literature suggests that bugs in training data are highly prevalent, but little research has focused on understanding their impacts on the models used in software engineering tasks. In this paper, we address this research gap through a comprehensive empirical investigation focused on three types of data prevalent in software engineering tasks: code-based, text-based, and metric-based. Using state-of-the-art baselines, we compare the models trained on clean datasets with those trained on datasets with quality issues and without proper preprocessing. By analysing the gradients, weights, and biases from neural networks under training, we identify the symptoms of data quality and preprocessing issues. Our analysis reveals that quality issues in code data cause biased learning and gradient instability, whereas problems in text data lead to overfitting and poor generalisation of models. On the other hand, quality issues in metric data result in exploding gradients and model overfitting, and inadequate preprocessing exacerbates these effects across all three data types. Finally, we demonstrate the validity and generalizability of our findings using six new datasets. Our research provides a better understanding of the impact and symptoms of data bugs in software engineering datasets. Practitioners and researchers can leverage these findings to develop better monitoring systems and data-cleaning methods to help detect and resolve data bugs in deep learning systems.
In this paper we address the following question: How can we use Large Language Models (LLMs) to improve code independently of a human, while ensuring that the improved code - does not regress the properties of the original code? - improves the original in a verifiable and measurable way? To address this question, we advocate Assured LLM-Based Software Engineering; a generate-and-test approach, inspired by Genetic Improvement. Assured LLMSE applies a series of semantic filters that discard code that fails to meet these twin guarantees. This overcomes the potential problem of LLM's propensity to hallucinate. It allows us to generate code using LLMs, independently of any human. The human plays the role only of final code reviewer, as they would do with code generated by other human engineers. This paper is an outline of the content of the keynote by Mark Harman at the International Workshop on Interpretability, Robustness, and Benchmarking in Neural Software Engineering, Monday 15th April 2024, Lisbon, Portugal.
During past few decades, fuzzy decision is an important attention in the areas of science, engineering, economic system, business, etc. To solve day-to-day problem, researchers use fuzzy data in transportation problem for presenting the uncontrollable factors; and most of multi-objective transportation problems are solved using goal programming. However, when the problem contains interval-valued data, then the obtained solution was provided by goal programming may not satisfy by all decision-makers. In such condition, we consider a fixed-charge solid transportation problem in multi-objective environment where all the data are intuitionistic fuzzy numbers with membership and non-membership function. The intuitionistic fuzzy transportation problem transforms into interval-valued problem using (α,β)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\alpha ,\beta )$$\end{document}-cut, and thereafter, it reduces into a deterministic problem using accuracy function. Also the optimum value of alternative corresponds to the optimum value of accuracy function. A numerical example is included to illustrate the usefulness of our proposed model. Finally, conclusions and future works with the study are described.