Search results

The purpose of this paper is to present a method and results of evaluating damaged building extraction using an object recognition task in pre‐ and post‐tsunami event. The advantage of remote sensing and its applications made it possible to extract damaged building images and vulnerability easement of wide urban areas due to natural disasters.

The proposed approach involves several advanced morphological operators, among which are adaptive transforms with varying size, shape and grey level of the structuring elements. IKONOS‐2 satellite images consisting of pre‐ and post‐2004 Indian Ocean Tsunami site of the Kalmunai area on the East coast of Sri Lanka were used. Morphological operation using structural element are applied for segmented images, then extracted remaining building foot print using random forest classification method. This work extended further the road lines extraction using Hough transform.

The result was investigated using geographic information system (GIS) data and global positioning system (GPS) ground survey in the field and it appeared to have high accuracy: the confidence measures produced of a completely destroyed structure give 86 percent by object‐based, respectively, after the tsunami in one segment of Maruthamune GN Division.

This study has also identified significant limitations, due to the resolution and clearness of satellite images and vegetation canopy over the building footprint.

The authors develop an automated method to detect damaged buildings and compare the results with GIS‐based ground survey.

Light Detection and Ranging (LiDAR) offers a fast and effective way to acquire DSM and extract ground objects such as building, trees and so on. However, it is difficult to extract sharp and precise building boundary from LiDAR data, because its ground sample distance (GSD) is often worse than that of high resolution image. Recently, fusion of LiDAR and high resolution image becomes a promising approach to extract precise boundary. To find the correct and precise boundary, the aim of this paper is to present a series of novel algorithms to improve the quality.

To find the correct and precise boundary, this paper presents a series of novel algorithms to improve the quality. At first, a progressive algorithm is presented to register LiDAR data and images; second, a modified adaptive TIN algorithm is presented to filter ground point, where a region growth method is applied in the adaptive TIN algorithm; third, a novel criterion based on the density, connectivity and distribution of point cluster is developed to distinguish trees point; fourth, a novel method based on the height difference between neighbor points is employed to extract coarse boundaries; at last, a knowledge based rule is put forward to identify correct building boundary from parallel edges.

Thorough experiments, it is conducted that: the registration results are accurate and reliable; filtered ground points has good quality, without missing or redundancy; all tree clusters bigger than one grid are detected, and points of walls and edges are eliminated with the new criterion; detected edges exactly locate at real building boundaries, and statistics show the detection correctness is 98 percent, and the detection completeness is 95 percent.

All results prove that precise boundary can be extracted with fusion of LiDAR and high resolution image.

In the last decades, various building information modeling–life cycle assessment (BIM-LCA) integration approaches have been developed to assess the environmental impact of the built asset. However, there is a lack of consensus on the optimal BIM-LCA integration approach that provides the most accurate and efficient assessment outcomes. To compare and determine their accuracy and efficiency, this study aimed to investigate four typical BIM-LCA integration solutions, namely, conventional, parametric modeling, plug-in and industry foundation classes (IFC)-based integration.

The four integration approaches were developed and applied using the same building project. A quantitative technique for evaluating the accuracy and efficiency of BIM-LCA integration solutions was used. Four indicators for assessing the performance of BIM-LCA integration were (1) validity of LCA results, (2) accuracy of bill-of-quantity (BOQ) extraction, (3) time for developing life cycle inventories (i.e. developing time) and (4) time for calculating LCA results (i.e. calculation time).

The results show that the plug-in-based approach outperforms others in developing and calculation time, while the conventional one could derive the most accuracy in BOQ extraction and result validity. The parametric modeling approach outperforms the IFC-based method regarding BOQ extraction, developing time and calculation time. Despite this, the IFC-based approach produces LCA outcomes with approximately 1% error, proving its validity.

This paper forms one of the first studies that employ a quantitative and objective method to determine the performance of four typical BIM-LCA integration solutions and reveal the trade-offs between the accuracy and efficiency of the integration approaches. The findings provide practical references for LCA practitioners to select appropriate BIM-LCA integration approaches for evaluating the environmental impact of the built asset during the design phase.

This study is a follow‐up to the previous studies undertaken by the authors. The paper aims to develop a set of valid and reliable performance indicators to evaluate the environmental quality of a project in order to minimise the adverse impacts of urban renewal projects on the environment.

First, a brief introduction to the most critical environmentally sustainable factors that should be considered when planning an urban renewal project is provided. Then this study identifies criteria for the selection of indicators, and develops appropriate indicators and a corresponding points‐scoring system for six major environmental design criteria through a comprehensive literature review and with the help of a number of experts from industry and academia.

This study proposes a set of environmental performance indicators and a corresponding points‐scoring system for the assessment model derived in a previous study. A total of 12 indicators have been developed for six design criteria (i.e. two indicators per criterion) in which both quantitative and qualitative indicators are derived, and five different scales are adopted to score individual assessment indicators.

By developing relevant indicators, the parties concerned can easily identify whether a renewal project meets pre‐determined planning initiatives and environmental objectives. Once deficiencies are noted, the relevant parties can take immediate action to rectify and refine the design accordingly. It is expected that the environmental performance of a renewal project can be evaluated effectively against the benchmarks through the assessment process.

The purpose of this article is to examine the effectiveness of the unified medical language system (UMLS) semantic network as a seed ontology for building a medical field ontology.

The information extraction process known as the knowledge engineering approach was used to extract concepts and their semantic relations from documents on “colon cancer treatment”. The UMLS semantic network was used as a seed ontology, and was extended and enriched with the extracted concepts and semantic relations using Protégé.

Only half of the semantic relations extracted manually were defined (or inferable) in the UMLS semantic network. The remaining half could be added to the network to extend its coverage. In addition, two semantic types in the network were found to be too general and four new sublevel semantic types were proposed to make them more specific.

Since only 109 research paper abstracts in the “colon cancer treatment” domain were analyzed in this study, more abstracts from the colon cancer treatment domain as well as from other cancer treatment domains (such as breast cancer treatment) can be analyzed to give a better generalization of our findings.

This study shares our findings on the effectiveness of the UMLS semantic network as a seed ontology for building a medical domain ontology, and also provides the basic guidelines for building or extending a medical domain ontology using the UMLS.

The largest share of a building maintenance budget goes towards preventing or repairing building defects. Also, building defects shorten a building’s lifetime, impact the user’s safety and health, prevent the buildings from performing their functions well and repairing building defects generates waste. Therefore, this study aims to specify the factors that affecting the number of building defects and how to reduce their negative impacts.

A case study was used as a research strategy and convergent parallel mixed methods were used as research design. Quantitative and qualitative data were collected concurrently, followed by independent analyses of the quantitative and qualitative data, and then merged the two sets of results according to the procedure of using the convergent parallel design. Descriptive statistics analysed quantitative data, whilst qualitative data was analysed by the content analysis technique.

The findings of this study explored the factors that affect the number of defects in buildings, the significant factors were related to the building’s life cycle in terms of design, construction, operation and maintenance phase; relevant attributes were construction teams, building users and maintenance teams. The study also addressed the approaches to minimise the negative impacts of those factors. Their negative impacts mainly contributed to increased building defects that increase maintenance costs, affect users’ safety and health, reduce buildings’ lifespan and cause environmental impact due to resource extraction.

The existing studies have not adequately addressed the significant factors that affect the number of building defects. Also, emerging technologies and environmental sustainability considerations related to building defects have not been linked in previous related work. Therefore, the present study has contributed to filling this gap.

The purpose of this paper is to develop a building information modelling (BIM)-based multi-objective optimization (MOO) framework for volumetric analysis of buildings during early design stages. The objective is to optimize volumetric spaces (3D) instead of 2D spaces to enhance space utilization, thermal comfort, constructability and rental value of buildings

The integration of two fundamental concepts – BIM and MOO, forms the basis of proposed framework. In the early design phases of a project, BIM is used to generate precise building volume data. The non-sorting genetic algorithm-II, a MOO algorithm, is then used to optimize extracted volume data from 3D BIM models, considering four objectives: space utilization, thermal comfort, rental value and construction cost. The framework is implemented in context of a school of architecture building project.

The findings of case study demonstrate significant improvements resulting from MOO of building volumes. Space utilization increased by 30%, while thermal comfort improved by 20%, and construction costs were reduced by 10%. Furthermore, rental value of the case study building increased by 33%.

The proposed framework offers practical implications by enabling project teams to generate optimal building floor layouts during early design stages, thereby avoiding late costly changes during construction phase of project.

The integration of BIM and MOO in this study provides a unique approach to optimize building volumes considering multiple factors during early design stages of a project

Aiming to simplify the extraction of embodied carbon data using a building information modeling (BIM) software, the purpose of this paper is to present a framework that integrates BIM and life cycle assessment (LCA), which are useful to the architecture, engineer and construction (AEC) industry. As a further purpose, this study also tests four different wall systems.

The study applies design science research and it presents a framework that integrates BIM and LCA. For analysis and validation, a case study features four different wall systems costs based on the Brazilian context. In the proposed framework, SimaPro8 accomplishes the LCA, while ArchiCAD 19 the modeling.

The first analysis covers embodied carbon and the second covers the total cost of each m² of wall. The proposed framework performs well, and it is effective in the Brazilian context. Concerning the walls, the wood frame system is the most sustainable option within this analysis and the most financially feasible option in Brazil.

The present study contributes to embodied carbon data analysis, ensuring that the best choice of elements and components is being used in the building project. This BIM–LCA integrated solution is valuable not only to the AEC industry and to professionals, but also to future researchers. This analysis is of great value to new ventures, since the society shows a great concern about reducing GHGs emissions.

Owing to the uneven distribution of annotated corpus among different languages, it is necessary to bridge the gap between low resource languages and high resource languages. From the perspective of entity relation extraction, this paper aims to extend the knowledge acquisition task from a single language context to a cross-lingual context, and to improve the relation extraction performance for low resource languages.

This paper proposes a cross-lingual adversarial relation extraction (CLARE) framework, which decomposes cross-lingual relation extraction into parallel corpus acquisition and adversarial adaptation relation extraction. Based on the proposed framework, this paper conducts extensive experiments in two tasks, i.e. the English-to-Chinese and the English-to-Arabic cross-lingual entity relation extraction.

The Macro-F1 values of the optimal models in the two tasks are 0.880 1 and 0.789 9, respectively, indicating that the proposed CLARE framework for CLARE can significantly improve the effect of low resource language entity relation extraction. The experimental results suggest that the proposed framework can effectively transfer the corpus as well as the annotated tags from English to Chinese and Arabic. This study reveals that the proposed approach is less human labour intensive and more effective in the cross-lingual entity relation extraction than the manual method. It shows that this approach has high generalizability among different languages.

The research results are of great significance for improving the performance of the cross-lingual knowledge acquisition. The cross-lingual transfer may greatly reduce the time and cost of the manual construction of the multi-lingual corpus. It sheds light on the knowledge acquisition and organization from the unstructured text in the era of big data.