Search results

This work aims to develop a web platform for inspecting roof structures for technical assistance supported by drones and artificial intelligence. The tools used were HTML, CSS and JavaScript languages; Firebase software for infrastructure; and Custom Vision for image processing.

This study adopted the design science research approach, and the main stages for the development of the web platform include (1) creation and validation of the roof inspection checklist, (2) validation of the use of Custom Vision as an image recognition tool, and (3) development of the web platform.

The results of automatic recognition showed a percentage of 77.08% accuracy in identifying pathologies in roof images obtained by drones for technical assistance.

This study contributed to developing a drone-integrated roof platform for visual data collection and artificial intelligence for automatic recognition of pathologies, enabling greater efficiency and agility in the collection, processing and analysis of results to guarantee the durability of the building.

Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance.

This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity.

In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability.

The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme.

This paper investigates the semantic association mechanisms of weak demand signals that facilitate innovative product development in terms of conceptual and temporal precedence, despite their inherent ambiguity and uncertainty.

To address this challenge, a domain ontology approach is proposed to construct a customer demand scenario-based framework that eliminates the blind spots in weak demand signal identification. The framework provides a basis for identifying such signals and introduces evaluation indices, such as depth, novelty and association, which are integrated to propose a three-dimensional weak signal recognition model based on domain ontology that outperforms existing research.

Empirical analysis is carried out based on customer comments of new energy vehicles on car platform such as “Auto Home” and “Bitauto”. Results demonstrate that in terms of recognition quantity, the three-dimensional weak demand signal recognition model, based on domain ontology, can accurately identify six demand weak signals. Conversely, the keyword analysis method exhibits a recognition quantity of four weak signals; in terms of recognition quality, the three-dimensional weak demand signal recognition model based on domain ontology can exclude non-demand signals such as “charging technology”, while keyword analysis methods cannot. Overall, the model proposed in this paper has higher sensitivity.

This paper proposes a novel method for identifying weak demand signals that considers the frequency of the signal's novelty, depth and relevance to the target demand. To verify its effectiveness, customer review data for new energy vehicles is used. The results provide a theoretical reference for formulating government policies and identifying weak demand signals for businesses.

Automatic modulation recognition (AMR) is a challenging problem in intelligent communication systems and has wide application prospects. At present, although many AMR methods based on deep learning have been proposed, the methods proposed by these works cannot be directly applied to the actual wireless communication scenario, because there are usually two kinds of dilemmas when recognizing the real modulated signal, namely, long sequence and noise. This paper aims to effectively process in-phase quadrature (IQ) sequences of very long signals interfered by noise.

This paper proposes a general model for a modulation classifier based on a two-layer nested structure of long short-term memory (LSTM) networks, called a two-layer nested structure (TLN)-LSTM, which exploits the time sensitivity of LSTM and the ability of the nested network structure to extract more features, and can achieve effective processing of ultra-long signal IQ sequences collected from real wireless communication scenarios that are interfered by noise.

Experimental results show that our proposed model has higher recognition accuracy for five types of modulation signals, including amplitude modulation, frequency modulation, gaussian minimum shift keying, quadrature phase shift keying and differential quadrature phase shift keying, collected from real wireless communication scenarios. The overall classification accuracy of the proposed model for these signals can reach 73.11%, compared with 40.84% for the baseline model. Moreover, this model can also achieve high classification performance for analog signals with the same modulation method in the public data set HKDD_AMC36.

At present, although many AMR methods based on deep learning have been proposed, these works are based on the model’s classification results of various modulated signals in the AMR public data set to evaluate the signal recognition performance of the proposed method rather than collecting real modulated signals for identification in actual wireless communication scenarios. The methods proposed in these works cannot be directly applied to actual wireless communication scenarios. Therefore, this paper proposes a new AMR method, dedicated to the effective processing of the collected ultra-long signal IQ sequences that are interfered by noise.

Contractors must check the provisions that may cause disputes in the specifications to manage project risks when bidding for a construction project. However, since the specification is mainly written regarding many national standards, determining which standard each section of the specification is derived from and whether the content is appropriate for the local site is a labor-intensive task. To develop an automatic reference section identification model that helps complete the specification review process in short bidding steps, the authors proposed a framework that integrates rules and machine learning algorithms.

The study begins by collecting 7,795 sections from construction specifications and the national standards from different countries. Then, the collected sections were retrieved for similar section pairs with syntactic rules generated by the construction domain knowledge. Finally, to improve the reliability and expandability of the section paring, the authors built a deep structured semantic model that increases the cosine similarity between documents dealing with the same topic by learning human-labeled similarity information.

The integrated model developed in this study showed 0.812, 0.898, and 0.923 levels of performance in NDCG@1, NDCG@5, and NDCG@10, respectively, confirming that the model can adequately select document candidates that require comparative analysis of clauses for practitioners.

The results contribute to more efficient and objective identification of potential disputes within the specifications by automatically providing practitioners with the reference section most relevant to the analysis target section.

This study aims to identify leather type and authenticity through optical coherence tomography.

Optical coherence tomography images taken from genuine and faux leather samples were used to create an image dataset, and automated machine learning algorithms were also used to distinguish leather types.

The optical coherence tomography scan results in a different image based on leather type. This information was used to determine the leather type correctly by optical coherence tomography and automatic machine learning algorithms. Please note that this system also recognized whether the leather was genuine or synthetic. Hence, this demonstrates that optical coherence tomography and automatic machine learning can be used to distinguish leather type and determine whether it is genuine.

For the first time to the best of the authors' knowledge, spectral-domain optical coherence tomography and automated machine learning algorithms were applied to identify leather authenticity in a noncontact and non-invasive manner. Since this model runs online, it can readily be employed in automated quality monitoring systems in the leather industry. With recent technological progress, optical coherence tomography combined with automated machine learning algorithms will be used more frequently in automatic authentication and identification systems.

The compliance checking of Building Information Modeling (BIM) models is crucial throughout the lifecycle of construction. The increasing amount and complexity of information carried by BIM models have made compliance checking more challenging, and manual methods are prone to errors. Therefore, this study aims to propose an integrative conceptual framework for automated compliance checking of BIM models, allowing for the identification of errors within BIM models.

This study first analyzed the typical building standards in the field of architecture and fire protection, and then the ontology of these elements is developed. Based on this, a building standard corpus is built, and deep learning models are trained to automatically label the building standard texts. The Neo4j is utilized for knowledge graph construction and storage, and a data extraction method based on the Dynamo is designed to obtain checking data files. After that, a matching algorithm is devised to express the logical rules of knowledge graph triples, resulting in automated compliance checking for BIM models.

Case validation results showed that this theoretical framework can achieve the automatic construction of domain knowledge graphs and automatic checking of BIM model compliance. Compared with traditional methods, this method has a higher degree of automation and portability.

This study introduces knowledge graphs and natural language processing technology into the field of BIM model checking and completes the automated process of constructing domain knowledge graphs and checking BIM model data. The validation of its functionality and usability through two case studies on a self-developed BIM checking platform.

Successful implementation of a building information modeling (BIM) for building operation and maintenance (O&M) requires purposeful, early-design identification of end-user-specific model exchange requirements. This paper aims to provide a semantic data-rich classification system for model objects to convey facilities management (FM) requirements in BIM guidelines in support of efficient FM-BIM data workflows.

A modularized, repeatable and technical solution for semantic requirements of BIM exchange objects was developed through ontology-based data mapping of the industry foundation classes. The proposed solution further contextualizes syntax per the buildingSMART Data Dictionary schema and provides an implementation agreement to address the quality issues of discipline BIMs and establish consistent modeling and naming conventions to facilitate automated BIM data workflow.

The level of semantics (LOS) development framework and the results of LOS implementation focusing on a building mechanical system case project are presented and discussed to showcase the increased efficiency resulting from its implementation throughout the BIM data management workflows.

This study represents a pioneering effort to create and implement the LOS schema as a modularized solution in support of automatic BIM data creation, adjustment, verification and transition across the design, construction and O&M workflows of a large owner organization in the Midwest USA.

Identifying the flow regime is a prerequisite for accurately modeling two-phase flow. This paper aims to introduce a comprehensive data-driven workflow for flow regime identification.

A numerical two-phase flow model was validated against experimental data and was used to generate dynamic pressure signals for three different flow regimes. First, four distinct methods were used for feature extraction: discrete wavelet transform (DWT), empirical mode decomposition, power spectral density and the time series analysis method. Kernel Fisher discriminant analysis (KFDA) was used to simultaneously perform dimensionality reduction and machine learning (ML) classification for each set of features. Finally, the Shapley additive explanations (SHAP) method was applied to make the workflow explainable.

The results highlighted that the DWT + KFDA method exhibited the highest testing and training accuracy at 95.2% and 88.8%, respectively. Results also include a virtual flow regime map to facilitate the visualization of features in two dimension. Finally, SHAP analysis showed that minimum and maximum values extracted at the fourth and second signal decomposition levels of DWT are the best flow-distinguishing features.

This workflow can be applied to opaque pipes fitted with pressure sensors to achieve flow assurance and automatic monitoring of two-phase flow occurring in many process industries.

This paper presents a novel flow regime identification method by fusing dynamic pressure measurements with ML techniques. The authors’ novel DWT + KFDA method demonstrates superior performance for flow regime identification with explainability.

The number of construction dispute cases has maintained a high growth trend in recent years. The effective exploration and management of construction contract risk can directly promote the overall performance of the project life cycle. The miss of clauses may result in a failure to match with standard contracts. If the contract, modified by the owner, omits key clauses, potential disputes may lead to contractors paying substantial compensation. Therefore, the identification of construction project contract missing clauses has heavily relied on the manual review technique, which is inefficient and highly restricted by personnel experience. The existing intelligent means only work for the contract query and storage. It is urgent to raise the level of intelligence for contract clause management. Therefore, this paper aims to propose an intelligent method to detect construction project contract missing clauses based on Natural Language Processing (NLP) and deep learning technology.

A complete classification scheme of contract clauses is designed based on NLP. First, construction contract texts are pre-processed and converted from unstructured natural language into structured digital vector form. Following the initial categorization, a multi-label classification of long text construction contract clauses is designed to preliminary identify whether the clause labels are missing. After the multi-label clause missing detection, the authors implement a clause similarity algorithm by creatively integrating the image detection thought, MatchPyramid model, with BERT to identify missing substantial content in the contract clauses.

1,322 construction project contracts were tested. Results showed that the accuracy of multi-label classification could reach 93%, the accuracy of similarity matching can reach 83%, and the recall rate and F1 mean of both can reach more than 0.7. The experimental results verify the feasibility of intelligently detecting contract risk through the NLP-based method to some extent.

NLP is adept at recognizing textual content and has shown promising results in some contract processing applications. However, the mostly used approaches of its utilization for risk detection in construction contract clauses predominantly are rule-based, which encounter challenges when handling intricate and lengthy engineering contracts. This paper introduces an NLP technique based on deep learning which reduces manual intervention and can autonomously identify and tag types of contractual deficiencies, aligning with the evolving complexities anticipated in future construction contracts. Moreover, this method achieves the recognition of extended contract clause texts. Ultimately, this approach boasts versatility; users simply need to adjust parameters such as segmentation based on language categories to detect omissions in contract clauses of diverse languages.