Search results

The building commissioning (BCx) phase is a critical stage in a building's lifecycle. It is also a complex process that involves a large number of actors and activities. While the use of building information modeling (BIM) in the commissioning phase of building equipment and systems could be beneficial, few studies have investigated the processes behind its implementation. The research presented in this paper aims to investigate the implementation of BIM for the commissioning phase within a general contracting company through action-research.

Through direct involvement with the research partner, a large general contractor, a diagnosis on the current limitations of the commissioning process was conducted. An action plan to implement BIM for commissioning was developed and implemented in two pilot projects. Evaluation was performed through on-site observations and informal discussions with field staff. Learning was specified through the development of a formal protocol for BIM-enabled BCx.

This action-research project helped the partner organization identify the challenges and a way forward to formalize its BIM-enabled BCx process. The action plan aimed at countering the lack of knowledge about the status of equipment and system commissioning as well as the lack of standardization. The research team co-developed and tested a formal protocol, including BIM-enabled processes and technologies to address these observed problems. A complete implementation ecosystem was structured and deployed. Preliminary feedback indicated that improvements were obtained using a BIM-enabled approach over a traditional approach.

While past studies have investigated the BCx process, this study identified current challenges considering recent advances in BIM and focused on a large general contractor. This work provides an in-depth account of a large general contractor attempting to streamline its BCx process. The results of the study could help guide practitioners in implementing more streamlined BIM-enabled BCx processes.

The purpose of this study is, first, to determine which developments have shaped official hotel classification systems over recent years (including the impact of guest-review platforms) and second to establish the future of those systems through the eyes of the people who are actually in charge of operating them.

Semi-structured interviews were chosen as the most suitable method for approaching hotel classification system administrators. This method is in line with previous research on approaching key informants in their respective fields. Sixteen people representing 12 different official national hotel classification systems from across the world as well as one commercial hotel star rating system participated in the online interviews.

The first main conclusion is that hotel classification systems – especially voluntary ones – would not have survived the enormous impact of guest-review platforms without quickly adjusting to the ever-changing hotel industry landscape. The frequent review of classification criteria and procedures has become the main survival strategy of classification systems. The second conclusion is that system operators are strongly optimistic about the future outlook of hotel classification based on their proven flexibility to swiftly adapt to new market conditions.

Research about hotel classification systems is usually based on the views of the systems' users, i.e. hotels or hotel guests, whereas the present paper reflects the perspective of the systems' operators, an angle rarely analyzed in the literature.

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

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.

In the context of promoting sustainable development in SMEs, the present study aims to investigate the relationship among solution dimensions based on the Industry 4.0 (I4.0) concept.

The study employs a comprehensive methodology that includes a systematic literature review, workshop, grounded theory and interpretive structural modeling. Various dimensions concerning I4.0 sustainability are tested and evaluated using a questionnaire design followed by hypothesis formulation. Further, grounded theory is used to extract the key solution dimensions that capture the essence of I4.0 implementation in SMEs. Finally, the solution dimensions for I4.0 sustainability are modeled using the ISM approach to understand the structural interdependencies among them, and Matrice d'Impacts Croisés Multiplication Applied to a Classification (MICMAC) analysis is done to understand the driving and dependence power among these dimensions.

The study identified 14 solution dimensions for the implementation of I4.0 in SMEs for sustainable development. Out of the 14 solution dimensions, human resource training programs (D4) appear at level 11, followed by top management commitment (D1), strategic collaborations (D3) and coordination among key stakeholders (D5) at level 2 in the hierarchical interpretive structural modeling (ISM) model. Also, these dimensions have an effect size of more than 0.50 which indicates a substantial correlation between the sustainability dimensions and Industry 4.0 implementation in SMEs.

The study contributes to the overall goal of fostering sustainability within the SME sector, which can pave the way for various stakeholders for the successful implementation of I4.0 sustainable solution dimensions.

Automatic anatomical therapeutic chemical (ATC) classification is progressing at a rapid pace because of its potential in drug development. Predicting an unknown compound's therapeutic and chemical characteristics in terms of how it affects multiple organs and physiological systems makes automatic ATC classification a vital yet challenging multilabel problem. The aim of this paper is to experimentally derive an ensemble of different feature descriptors and classifiers for ATC classification that outperforms the state-of-the-art.

The proposed method is an ensemble generated by the fusion of neural networks (i.e. a tabular model and long short-term memory networks (LSTM)) and multilabel classifiers based on multiple linear regression (hMuLab). All classifiers are trained on three sets of descriptors. Features extracted from the trained LSTMs are also fed into hMuLab. Evaluations of ensembles are compared on a benchmark data set of 3883 ATC-coded pharmaceuticals taken from KEGG, a publicly available drug databank.

Experiments demonstrate the power of the authors’ best ensemble, EnsATC, which is shown to outperform the best methods reported in the literature, including the state-of-the-art developed by the fast.ai research group. The MATLAB source code of the authors’ system is freely available to the public at https://github.com/LorisNanni/Neural-networks-for-anatomical-therapeutic-chemical-ATC-classification.

This study demonstrates the power of extracting LSTM features and combining them with ATC descriptors in ensembles for ATC classification.

The purpose of this paper is to explore the emergence of innovation in smart service systems to conceptualize how actor’s relationships through technology-enabled interactions can give birth to novel technologies, processes, strategies and value. The objectives of the study are: to detect the different enablers that activate innovation in smart service systems; and to explore how these can lead dynamically to the emergence of different innovation patterns.

The empirical research adopts an approach based on constructivist grounded theory, performed through observation and semi-structured interviews to investigate the development of innovation in the Italian CTNA (Italian acronym of National Cluster for Aerospace Technology).

The identification and re-elaboration of the novelties that emerged from the analysis of the Cluster allow the elaboration of a diagram that classifies five different shades of innovation, introduced through some related theoretical propositions: technological; process; business model and data-driven; social and eco-sustainable; and practice-based.

The paper embraces a synthesis view that detects the enabling structural and systems dimensions for innovation (the “what”) and the way in which these can be combined to create new technologies, resources, values and social rules (the “how” dimension). The classification of five different kinds of innovation can contribute to enrich extant research on value co-creation and innovation and can shed light on how given technologies and relational strategies can produce varied innovation outcomes according to the diverse stakeholders engaged.

The purpose of this paper is to identify the historical trends and status of the national development of artificial intelligence (AI) from a nationwide perspective and to enable governments at different administrative levels to promote AI development through policymaking.

This paper analyzed 248 Chinese AI policies (36 issued by the state agencies and 212 by the regional agencies). Policy bibliometrics, policy instruments and network analysis were used to reveal the AI policy patterns. Three aspects were analyzed: the spatiotemporal distribution of issued policies, the policy foci and instruments of policy contents and the cooperation and citation among policy-issuing agencies.

Results indicate that Chinese AI development is still in the initial phase. During the policymaking processes, the state and regional policy foci have strong consistency; however, the coordination among state and regional agencies is supposed to be strengthened. According to the issuing time of AI policies, Chinese AI development is in accordance with the global situation and has witnessed unprecedented growth in the last five years. And the coastal provinces have issued more targeted policies than the middle and western provinces. Governments at the state and regional levels have emphasized familiar policy foci and played the role of policymakers, along with regional governments that also functioned as policy executors as well. According to the three-dimension instruments coding, the authors found an uneven structure of policy instruments at both levels. Furthermore, weak cooperation appears at the state level, while little cooperation is found among regional agencies. Regional governments cite state policies, thus leading to the formation of top-down diffusion, lacking bottom-up diffusion.

The paper contributes to the literature by characterizing policy patterns from both external attributes and semantic contents, thus revealing features of policy distribution, contents and agencies. What is more, this research analyzes Chinese AI policies from a nationwide perspective, which contributes to clarifying the overall status and multi-level relationships of policies. The findings also benefit the coordinated development of governments during further policymaking processes.

High-efficiency video coding (HEVC) is the latest video coding standard that has better coding efficiency than the H.264/advanced video coding (AVC) standard. The purpose of this paper is to design and develop an effective block search mechanism for the video compression-HEVC standard such that the developed compression standard is applied for the communication applications.

In the proposed method, an rate-distortion (RD) trade-off, named regressive RD trade-off is used based on the conditional autoregressive value at risk (CaViar) model. The motion estimation (ME) is based on the new block search mechanism, which is developed with the modification in the Ordered Tree-based Hex-Octagon (OrTHO)-search algorithm along with the chronological Salp swarm algorithm (SSA) based on deep recurrent neural network (deepRNN) for optimally deciding the shape of search, search length of the tree and dimension. The chronological SSA is developed by integrating the chronological concept in SSA, which is used for training the deep RNN for ME.

The competing methods used for the comparative analysis of the proposed OrTHO-search based RD + chronological-salp swarm algorithm (RD + C-SSA) based deep RNN are support vector machine (SVM), fast encoding framework, wavefront-based high parallel (WHP) and OrTHO-search based RD method. The proposed video compression method obtained a maximum peak signal-to-noise ratio (PSNR) of 42.9180 dB and a maximum structural similarity index measure (SSIM) of 0.9827.

In this research, an effective block search mechanism was developed with the modification in the OrTHO-search algorithm along with the chronological SSA based on deepRNN for the video compression-HEVC standard.

An abundance of techniques has been presented so forth for waste classification but, they deliver inefficient results with low accuracy. Their achievement on various repositories is different and also, there is insufficiency of high-scale databases for training. The purpose of the study is to provide high security.

In this research, optimization-assisted federated learning (FL) is introduced for thermoplastic waste segregation and classification. The deep learning (DL) network trained by Archimedes Henry gas solubility optimization (AHGSO) is used for the classification of plastic and resin types. The deep quantum neural networks (DQNN) is used for first-level classification and the deep max-out network (DMN) is employed for second-level classification. This developed AHGSO is obtained by blending the features of Archimedes optimization algorithm (AOA) and Henry gas solubility optimization (HGSO). The entities included in this approach are nodes and servers. Local training is carried out depending on local data and updations to the server are performed. Then, the model is aggregated at the server. Thereafter, each node downloads the global model and the update training is executed depending on the downloaded global and the local model till it achieves the satisfied condition. Finally, local update and aggregation at the server is altered based on the average method. The Data tag suite (DATS_2022) dataset is used for multilevel thermoplastic waste segregation and classification.

By using the DQNN in first-level classification the designed optimization-assisted FL has gained an accuracy of 0.930, mean average precision (MAP) of 0.933, false positive rate (FPR) of 0.213, loss function of 0.211, mean square error (MSE) of 0.328 and root mean square error (RMSE) of 0.572. In the second level classification, by using DMN the accuracy, MAP, FPR, loss function, MSE and RMSE are 0.932, 0.935, 0.093, 0.068, 0.303 and 0.551.

The multilevel thermoplastic waste segregation and classification using the proposed model is accurate and improves the effectiveness of the classification.