• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.284-291
• /
• 2022

Historical data from comparable projects can serve as benchmarking data for an ongoing project's planning during the project scoping phase. As project owners typically store substantial amounts of data generated throughout project life cycles in digitized databases, they can capture appropriate data to support various project planning activities by accessing digital databases. One of the most important work tasks in this process is identifying one or more past projects comparable to a new project. The uniqueness and complexity of construction projects along with unorganized data, impede the reliable identification of comparable past projects. A project scope document provides the preliminary overview of a project in terms of the extent of the project and project requirements. However, narratives and free-formatted descriptions of project scopes are a significant and time-consuming barrier if a human needs to review them and determine similar projects. This study proposes an Artificial Intelligence-driven model for analyzing project scope descriptions and evaluating project similarity using natural language processing (NLP) techniques. The proposed algorithm can intelligently a) extract major work activities from unstructured descriptions held in a database and b) quantify similarities by considering the semantic features of texts representing work activities. The proposed model enhances historical comparable project identification by systematically analyzing project scopes.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.6
• /
• pp.205-220
• /
• 2018

Software defect prediction is helpful for allocating valuable project resources effectively for software quality assurance activities thanks to focusing on the identified fault-prone modules. If historical data collected within a company is sufficient, a Within-Project Defect Prediction (WPDP) can be utilized for accurate fault-prone module prediction. In case a company does not maintain historical data, it may be helpful to build a classifier towards predicting comprehensible fault prediction based on Cross-Project Defect Prediction (CPDP). Since CPDP employs different project data collected from other organization to build a classifier, the main obstacle to build an accurate classifier is that distributions between source and target projects are not similar. To address the problem, because it is crucial to identify effective similarity measure techniques to obtain high performance for CPDP, In this paper, we aim to identify them. We compare various similarity measure techniques. The effectiveness of similarity weights calculated by those similarity measure techniques are evaluated. The results are verified using the statistical significance test and the effect size test. The results show k-Nearest Neighbor (k-NN), LOcal Correlation Integral (LOCI), and Range methods are the top three performers. The experimental results show that predictive performances using the three methods are comparable to those of WPDP.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.4_2
• /
• pp.991-999
• /
• 2024

This study is based on research on a magnetic induction amplification power generation system using quantum fluctuations, and aims to confirm the similarity to the meissner effect through quantum analysis using magnets and suggest the possibility of utilizing alternative energy. Research was conducted on increasing the efficiency of motors based on the similarity between magnetic quantum array experimental devices and the superconductor phenomenon. It was confirmed that the experimental device that arranged the quantum of magnetism rotated by canceling out the magnetism by having a resistance value of "0", which is not a general characteristic of magnetism that generates attractive force. This is an observation of the similarity between the superconductor phenomenon and the meissner effect, and it was confirmed that material synthesis or temperature had little effect. This study confirmed that the efficiency is more than 20 times that of existing power on average. Therefore, this study suggests that there is a possibility of commercialization of an Energy Harvesting System (EHS) that can produce and store energy.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2010.05a
• /
• pp.143-147
• /
• 2010

Due to the diversification and complication of construction projects, controlling risks from the early design-planning phase gives huge impact on success of the construction project. As a part of managing uncertainties it is also important to estimate the project cost several times. Especially, estimating project cost in the early stage gives effects on making a budget for projects. This study estimated the apartment project cost using case-based reasoning(CBR), which is the process of solving new problems based on the past problems. For this, we deduced the apartment cost influence factors which can be gathered in the early stage of project. Based on the factors we established the database for apartment project and calculated the attribute value, attribute similarity and case similarity. Although we retrieve the most similar case from the database, it is very hard to utilize it directly due to the uniqueness of each project. So, Genetic Algorithm(GA) was applied in revising the cost of the retrieved-case. Therefore, the accuracy of the prediction was improved by GA optimization.

• Journal of Digital Contents Society
• /
• v.13 no.3
• /
• pp.317-324
• /
• 2012

Recently, coordination task of similarity between national R&D programs is emphasized on view from the R&D investment efficiency. But the previous similarity search method like text-based similarity search which using keyword of R&D projects has reached the limit due to deviation of document's quality. For the solve the limitations of text-based similarity search using the keyword extraction, in this study, utilization of R&D project's technical classification will be discussed as a new similarity search method when analyzed of similarity between national R&D programs. To this end, extracts the Science and Technology Standard Classification of R & D projects which are collected when national R&D Survey & analysis, and creates peculiar vector model of each R&D programs. Verify a reliability of this study by calculate the cosine-based and Euclidean distance-based similarity and compare with calculated the text-based similarity.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2014.05a
• /
• pp.162-163
• /
• 2014

Operation and maintenance stage consists the largest portion of project life cycle cost. Appropriate management and analysis of such stages have massive effect on the total project cost. The effective prediction of optimized repair period is one of main factors in ㅌ management. However, it has been analyzed that the prediction of appropriate repair period revealed limitations in reliability. Therefore, this study suggests a methodology of repair period prediction by dividing finished projects into similar groups with same properties to be compared with the target project using quantitative variables.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2014.05a
• /
• pp.32-33
• /
• 2014

The appropriate selection of a construction material is important considering the effect on the total project cost and quality. However, the methodologies of the existing systems and databases to suggest search results have been analyzed to lack reliability. Therefore, this study suggests a material searching methodology that results in quantitative results using similarity.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.883-889
• /
• 2009

The importance of cost estimate in early stage such has been increasing due to market change and severe competition in construction industry. Because the adjustable budget is only 20% after design stage, most of the crucial decisions to influence cost is made in the early stage. However, in the early stage, the project scope is not defined completely so that estimator has inaccurate information to make critical decision. Therefore, this research suggests the cost estimate method using case-based reasoning. Case-based reasoning is appropriate for the early cost estimating, as it has the strength of rapidity and convenience in cost estimation. This research analyzes 84 actual data of public apartment on the scale of 11~15 stories. In order to extract the most similar case, at the first step this research identifies influence factors and calculates attribute similarity. In case-based reasoning, the most challenging task is determining attribute weight. At the third step, this research calculates case similarity which is aggregated attribute similarity multipled by attribute weight. Finally, extracts the most similar case which has the highest score of case similarity.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.329-331
• /
• 2014

The analysis of the similarities and redundancies among R&D projects is important for the efficient investment of government budgets. When government R&D projects are planned, the redundancies of research tasks are examined by institutions specializing in research management, relevant offices and departments, and the government to prevent redundant funding. However, as existing similarity analyses depend on methods wherein new task proposals and existing R&D project proposals are compared and looked up based on keywords. This results in vulnerability wherein similarity cannot be accurately measured in the event of partial modifications of the task name or technical substitutions. This study aims to use patent information as characteristics by which R&D project documents can be identified. The patent data used is based on materials officially published by the government's R&D patent trend survey project (http://ipas.rndip.re.kr). The study aims to propose a method by which patent information can be used to analyze the similarity and redundancy among R&D projects when new projects are entered. For this purpose, a similarity measurement model based on set theory and probability theory is presented. The presented measurement model is implemented into an actual system to identify redundant documents, and calculate and show their similarity.

• Korean Journal of Environment and Ecology
• /
• v.35 no.3
• /
• pp.294-304
• /
• 2021

This study aims to obtain basic data for systematic restoration by analyzing the monitoring results of the Shimwon Valley Ecological Landscape Restoration Project area in Jirisan National Park. In 2017, when the restoration project was completed, 12 monitoring plots and 4 control plots were installed for vegetation monitoring, and changes in the relative dominance, species diversity index and similarity between 2017 and 2020 were analyzed. The species diversity index of the surveyed areas where trees were planted during the restoration project was 0-1.4552, and the similarity index with the control group was 0% except for one survey area at 1.32%. The very low species diversity index and similarity index in the survey areas were attributed to the loss of trees planted during the restoration project due to death, damage by wild boars, or erosion by running water. On the other hand, the species diversity index was 0.9538-2.3222 in the monitoring plot where no tree was planted, and the similarity index was analyzed to be as high as 8.33%. It is necessary to continue the long-term monitoring for the development of ecological landscape restoration methods in the national park and analysis of the succession in monitoring plots where no trees were planted.