Search

With the rapid expansion of underground engineering, accurate settlement estimation during foundation excavation using monitoring data has gained prominence. Previous studies have typically overlooked data patterns, relying solely on time-series models, which yielded limited accuracy and short-term predictability. To address these issues, this paper performs a thorough pattern analysis covering both the temporal and spatial properties, and proposes a spatiotemporal modeling method grounded in explainable artificial intelligence technique. A real-world engineering case study is conducted to validate the effectiveness of the proposed method. Counterintuitively, the results reveal a weak temporal effect within the settlement data, with only the last step playing a dominant role, whereas the spatial correlation among measuring points is notably more significant. Compared to conventional models, the proposed method consistently outperforms, achieving significantly higher R2 scores and excelling in long-term estimation with reductions of at least 78% in RMSE, 80% in MAE, and 72% in MAPE. • Spatiotemporal pattern analysis and XAI modeling for estimation are performed. • Pattern analysis results shows weak temporal correlations of settlement. • Spatial correlations in measuring points persist across construction stages. • The method yields notably smaller RMSE, MAE, and MAPE than conventional models. • SHAP analysis results highly align with the patterns uncovered by data analysis. [ABSTRACT FROM AUTHOR]

At the beginning of a project, architects convey design ideas via quick 2D diagrams, front views, floor plans, and sketches. Consequently, many stakeholders have difficulty visualizing the 3D representation of the building mass, leading to varied interpretations thus inhibiting a shared understanding of the design. To alleviate the challenge, this paper proposes a deep learning-based method, Vitruvio, for creating a 3D model from a single perspective sketch. This method allows designers to automatically generate 3D representations in real-time based on their initial sketches and thus communicate effectively and intuitively to the client. Vitruvio adapts the Occupancy Network to perform single view reconstruction (SVR), a technique for creating 3D representations from a single image. Vitruvio achieves: (1) an 18% increase in the reconstruction accuracy and (2) a 26% reduction in the inference time compared to the Occupancy Network on one thousand buildings provided by the New York municipality. This research investigates the effect that the building orientation has on the reconstruction quality, discovering that Vitruvio can capture fine-grain details in complex buildings when their native orientation is preserved during training, as opposed to the SVR's standard practice that aligns every building to its canonical pose. The code is available here https://github.com/CDInstitute/Vitruvio. • We introduced a learning-based method for single perspective sketch-to-3D applications in the Architecture Engineering and Construction (AEC) industry. • We adapted a previous state-of-the-art Conditional Variational Autoencoder (Occupancy Network) to scalable datasets. • We showed qualitatively and quantitatively how the building orientation affects the reconstruction. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) plays a critical role in the prediction, planning, and control of autonomous vehicle. The original motion control methods are increasing in accuracy, but their control style markedly differs from that of human drivers. This not only degrades the passenger's ride experience but also brings unfamiliarity to other drivers, leading to safety hazards. Moreover, some of the methods are a direct application of AI techniques without any specific enhancements tailored for vehicle control. This both fails to fully utilize the potential of AI and reduces interpretability. To address these issues, in this paper, deep learning methods are integrated with driver control mechanisms to propose a human-like neural network for vehicle longitudinal dynamics estimation and control (HNN). First, the process of driver estimation and control of vehicle dynamics is proposed and described in mathematical language. Subsequently, the HNN composed of three sub-networks is presented. The three sub-networks correspond to the three sub-processes of the driver's mechanism, which makes the proposed HNN method more applicable to vehicle dynamics control and more interpretable in specific engineering domains. The effectiveness of the HNN method is verified on a real-world dataset. The results demonstrate that the HNN not only enhances vehicle human-like control but also surpasses baselines in terms of control style consistency and convergence rate. • The method is a deep integration of human control mechanisms and artificial intelligence in a specific engineering domain. • The proposed deep learning method has a unique structure derived from the driver control mechanism.The structure of the method makes it more applicable for vehicle motion control with active rule-based interpretability. • The tolerance control pattern is proposed and incorporated into the mechanism of driver control vehicle dynamics. • Compared to the baselines, the method proves to be more suitable for the engineering field of vehicle human-like control. [ABSTRACT FROM AUTHOR]

• Data-centric water engineering is emerging as a new paradigm for water research and practice. • The data pipeline is powered by AI for knowledge and insight extraction from data. • The new paradigm embraces three principles – data, integration and decision making. Artificial intelligence (AI) is expected to transform many scientific disciplines, with the potential to significantly accelerate scientific discovery. This perspective calls for the development of data-centric water engineering to tackle water challenges in a changing world. Building on the historical evolution of water engineering from empirical and theoretical paradigms to the current computational paradigm, we argue that a fourth paradigm, i.e., data-centric water engineering, is emerging driven by recent AI advances. Here we define a new framework for data-centric water engineering in which data are transformed into knowledge and insight through a data pipeline powered by AI technologies. It is proposed that data-centric water engineering embraces three principles – data-first, integration and decision making. We envision that the development of data-centric water engineering needs an interdisciplinary research community, a shift in mindset and culture in the academia and water industry, and an ethical and risk framework to guide the development and application of AI. We hope this paper could inspire research and development that will accelerate the paradigm shift towards data-centric water engineering in the water sector and fundamentally transform the planning and management of water infrastructure. [Display omitted] [ABSTRACT FROM AUTHOR]

Chatbots are becoming a common component of many types of software systems. But they are typically developed as a side feature using ad-hoc tools and custom integrations. Moreover, current frameworks are efficient only when designing simple chatbot applications while they still require advanced technical knowledge to define complex interactions and are difficult to evolve along with the company needs. In addition, the deployment of a chatbot application usually requires a deep understanding of the targeted platforms, especially back-end connections, increasing the development and maintenance costs. In this paper, we discuss our experiences building, evolving and distributing the Xatkit framework. Xatkit is a model-based framework built around a Domain-Specific Language to define chatbots (and voicebots and bots in general) in a platform-independent way. Xatkit also comes with a runtime engine that automatically deploys the chatbot application and manages the defined conversation logic over the platforms of choice. Xatkit has significantly evolved since its initial release. This paper focuses on describing the evolution and the reasons (technical and non-technical) that triggered them. We believe our lessons learned can be useful to any other initiative trying to build a successful industrial-level chatbot platform, and in general, any type of model-based solution. • Model-driven engineering can be successfully applied to new domains such as AI-based software. • Model-driven tools have limitations when it comes to developing industrial-strength solutions. • Commercial success of model-driven based approaches depends on numerous factors beyond technical ones. [ABSTRACT FROM AUTHOR]

Graph Neural Networks (GNNs) have emerged as a promising solution for effectively handling non-Euclidean data in construction, including building information models (BIM) and scanned point clouds. However, despite their potential, there is a lack of comprehensive scholarly work providing a holistic understanding of the application of GNNs in the construction domain. This paper addresses this gap by conducting a thorough review of 34 publications on GNNs in construction, presenting a comprehensive overview of the current research landscape. By analyzing the existing literature, this paper aims to identify opportunities and challenges for further advancing the application of GNNs in construction. The findings from this review shed light on diverse approaches for constructing graph data from common construction data types and demonstrate the significant potential of GNNs for the industry. Moreover, this paper contributes to the existing body of knowledge by increasing awareness of the current state of GNNs in the construction industry and offering practical recommendations to overcome challenges in real-world practice. [Display omitted] • A systematic review of GNNs research and applications in the construction industry • Identification of GNNs potential in handling the non-Euclidean data commonly found in construction activities. • Various approaches to developing graph data from common data types in construction • Discussion of current applications and potential of GNNs in construction, as well as its challenges and opportunities. [ABSTRACT FROM AUTHOR]

Optical network performance monitoring technology, which can effectively identify physical impairment in the network, is of great significance to ensure network stability and prevent accidents. In order to establish a high-precision performance monitoring framework for optical networks, a three-step feature engineering and deep attention mechanism approach is proposed in the paper. The main modeling process consists of the following three steps: In Step I, the AAH (Asynchronous Amplitude Histogram) method is used to initially extract features from the original data. In Step II, the KPCA (Kernel Principal Component Analysis) method and the Q-learning method are utilized to reduce the feature dimension and transmit the optimized feature to the downstream predictor. In step III, the downstream predictor based on the LSTM (long short-term memory network) and attention mechanism can effectively construct the mapping between features and labels and realize data prediction. After several groups of comparative experiments, the following conclusions can be obtained: (a) Ablation experiments and component comparisons demonstrate that the proposed framework is able to effectively combine feature engineering and predictors, which can get excellent results. (b) The optical network performance detection framework proposed in the paper achieves better results than three SOTA (state-of-the-art) models and fifteen alternative frameworks. • LSTM-attention is used to establish the mapping between inputs and targets. • A new three-step feature engineering technique is proposed. • The proposed model is compared with eighteen mainstream models. [ABSTRACT FROM AUTHOR]

Fully combining the emerging intelligent technologies, such as big data and artificial intelligence, to realize the effective data fusion of bridge management with multi-source, autonomous, massive, heterogeneous features, and to further improve the capability of domain knowledge sharing and services have become the urgent demand and future development trend in the field of bridge engineering. This paper summarizes the business background and big data characteristics of bridge management, and represents a brief review of related work. According to the big data knowledge engineering paradigm, this paper proposes a novel BigKE-based intelligent bridge management and maintenance framework consisting of the layers of data-sources, storage and computing, knowledge representation, knowledge computing, and knowledge services. The corresponding main research contents involved in each layer are discussed as well. Finally, we point out some possible application scenarios and main challenges of the proposed framework, which elaborate on areas for future research. • This paper provides the state-of-the-art survey of data-driven manners related to bridge management and maintenance. • A novel framework driven by big data knowledge engineering is proposed for intelligent bridge management and maintenance. • The typical application scenarios are used to illustrate the effect. The main challenges are discussed to elaborate on future research. [ABSTRACT FROM AUTHOR]

• A bibliometric analysis on machine learning research in all engineering fields. • VOSviewer is employed to this study based on retrieved 3057 articles. • Research distributions of this topic are identified. • A detailed discussion on the knowledge bases, research hotspots and frontiers. In this work, we conducted a visualized bibliometric analysis to map the research trends of machine learning in engineering (MLE) based on articles indexed in the Web of Science Core Collection published between 2000 and 2019. The research distributions, knowledge bases, research hotspots, and research frontiers for MLE studies are revealed by using VOSviewer software and visualization technology. The growth of the literature related to MLE averaged 24.3% in the past two decades. A total of 3057 peer-reviewed papers from 96 countries published in 1299 different journals were identified. The USA was the most productive country, with 23.73% of the overall articles and 32.25% of the overall citations. The most active research organization was MIT, with 41 publications and 1079 citations, and the Journal of Machine Learning Research had the largest number of citations in the field of MLE. In particular, our findings indicate that the research issues of "random forests", "support vector machine", "extreme learning machine", "deep learning", "statistical learning theory", and "Python machine learning" formed the knowledge bases of MLE from 2000 to 2019, while the research hotspots focused on applications of machine learning benchmark algorithms. Burst detection analysis results showed that more burst keywords emerged and had a higher frequency of change after 2010. This study provides an insight view of the overall research trends of MLE and may help researchers better understand this research field and predict its dynamic directions. [ABSTRACT FROM AUTHOR]