Search

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]

Smart manufacturing still remains critical challenges for pharmaceutical manufacturing. Here, an original data-driven engineering framework was proposed to tackle the challenges. Firstly, from sporadic indicators to five kinds of systematic quality characteristics, nearly 2,000,000 real-world data points were successively characterized from Ginkgo Folium tablet manufacturing. Then, from simplex to the multivariate system, the digital process capability diagnosis strategy was proposed by multivariate C pk integrated Bootstrap- t. The C pk of Ginkgo Folium extracts, granules, and tablets were discovered, which was 0.59, 0.42, and 0.78, respectively, indicating a relatively weak process capability, especially in granulating. Furthermore, the quality traceability was discovered from unit to end-to-end analysis, which decreased from 2.17 to 1.73. This further proved that attention should be paid to granulating to improve the quality characteristic. In conclusion, this paper provided a data-driven engineering strategy empowering industrial innovation to face the challenge of smart pharmaceutical manufacturing. The innovative data-driven engineering strategy integrated artificial intelligence (Al) algorithms was proposed for process capability and end-to-end quality traceability of intelligent pharmaceutical manufacturing. [Display omitted] [ABSTRACT FROM AUTHOR]

Product variety is a growing trend of offering highly configurable products at the cost of inducing complexity in manufacturing. Joining is a key manufacturing process and historically was a paper-based process with incomplete variety documentation. Nowadays, digital joining element design is a substitution of paper for 3D space. Nonetheless, it remains an ambiguous manual task with limited automation, resulting in time-consuming iterative error-prone development trajectories and costly reworks. This contribution addresses the state of the art in joining element design in both research and industry practice. It reviews product variety and its impact on joining processes. The paper identifies a need for integrating product variety into joining element design and it proposes a solution pathway using artificial intelligence methods. [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]

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]

Product variety and its induced manufacturing complexity remains to increase and therefore greatens challenges for design of joining elements. Historically, joining element design was a paper-based process with incomplete variety documentation and is digitalized only by replacing paper for 3D space. Currently, joining element design remains an ambiguous manual task with limited automation, resulting in long iterative, error prone development trajectories and costly reworks. Thus, processes in practice conflict with required capabilities. Artificial intelligence helps to solve such conflicts by taking over repetitive tasks, preventing human errors, optimizing designs and enabling designers to focus on their core competencies. This paper proposes a novel artificial intelligence method toolbox as a foundation to automate joining element design in manufacturing industries. The methodology aims to incorporate multiple lifecycle requirements including large product variety. [ABSTRACT FROM AUTHOR]

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]

• 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]

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]

Machine learning and Artificial Intelligence have grown significant attention from industry and academia during the past decade. The key reason behind interest is such technologies capabilities to revolutionize human life since they seamlessly integrate classical networks, networked objects and people to create more efficient environments. In this paper, the Knowledge Representation technique of Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA) is applied to facilitate Machine Learning. For effective and efficient decision-making in Machine Learning, the environment's own experience is captured, stored and reused using the DDNA technique. The proposed approach is implemented on practical test cases like a Chatbot. Decisional DNA gathers explicit experiential knowledge based on formal decision events and uses this knowledge to support decision-making processes. The experimental test and results of the presented implementation of Decisional DNA Chatbot case studies support it as a technology that can improve and be applied to the technology, enhancing intelligence by predicting capabilities and facilitating knowledge engineering processes. [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]

Engineering Artificial Intelligence (AI) software is a relatively new area with many challenges, unknowns, and limited proven best practices. Big companies such as Google, Microsoft, and Apple have provided a suite of recent guidelines to assist engineering teams in building human-centered AI systems. The practices currently adopted by practitioners for developing such systems, especially during Requirements Engineering (RE), are little studied and reported to date. This paper presents the results of a survey conducted to understand current industry practices in RE for AI (RE4AI) and to determine which key human-centered AI guidelines should be followed. Our survey is based on mapping existing industrial guidelines, best practices, and efforts in the literature. We surveyed 29 professionals and found most participants agreed that all the human-centered aspects we mapped should be addressed in RE. Further, we found that most participants were using UML or Microsoft Office to present requirements. We identify that most of the tools currently used are not equipped to manage AI-based software, and the use of UML and Office may pose issues with the quality of requirements captured for AI. Also, all human-centered practices mapped from the guidelines should be included in RE. • Human-centered AI guidelines be included in Requirements Engineering. • Industry practices use tools that do not enforce Requirements Engineering for AI. • Practices use modeling that are not suited for modeling requirements for AI. • There are gaps between research and practices in Requirements Engineering for AI. • No evident studies focus on feedback or errors in Requirements Engineering for AI. [ABSTRACT FROM AUTHOR]

Imagineering is a portmanteau combining the words imagination and engineering. The term, imagineering, was coined during the early 1940s. Since the new Millennium, imagineering has grown to the scale of a mass paradigm, because of the increasing scope and availability of automated engineering. Automated engineering is enabled by sophisticated software and artificial intelligence (AI) across the virtual-social-physical convergence (VSP) of consumer devices, desktop machines, and Web platforms. The combining of human imagination with automated engineering is enabling millions of vloggers, self-publishers and makers to imagineer at high speed and low cost. This mass imagineering can range from early education to digital afterlife. It involves makerspaces, fab labs, hackerspaces, as well as use of disparate devices, machines, and platforms “in the wild”. In this paper, three principal contributions to the literature are provided. First, mass imagineering is described from early education to digital afterlife. Second, analysis of structure and agency in mass imagineering is provided. This reveals that individual agency varies in different settings for mass imagineering, but is always more than in mass production and mass customization settings. Third, division of labour analysis of mass imagineering is provided. This reveals that mass imagineering extends labour outside of paid employment, such as in the home, towards greater self-expression and increased entrepreneurship. This is possible because of increasing automated engineering across VSP enabled by devices, machines, and platforms. [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]