Managing building defects in the residential environment is an important social issue in South Korea. Therefore, most South Korean construction companies devote a large amount of human resources and economic costs in managing such defects. This paper proposes a machine learning approach for investigating whether a specific defect can be autonomously categorized into one of the categories of repair tasks. To this end, we employed a dataset of 310,044 defect cases (from 656,266 validated cases of 717,550 total collected cases). Three machine learning classifiers (support vector machine, random forest, and logistic regression) with three word embedding methods (bag-of-words, term frequency-inverse document frequency, and Word2Vec) were employed for the classification tasks. The highest yielded results showed more than 99% accuracy, precision, recall, and F1-scores for the random forest classifier with the Word2Vec embedding. Finally, based on these findings, the implications and limitations of this study are discussed. Representatively, the findings of this research can improve the defect management effectiveness of the apartment construction industry in South Korea. Moreover, to contribute to future research, we have made the dataset publicly available.
31 October 2023 in Journal of Korean Society of Water Science and Technology
In this study, we investigated the actual situation of sewage facilities in the Myon area in order to obtain the basic information necessary for establishing a sewerage development plan in areas where the population is decreasing. The phenomenon of population decline was found to be more pronounced in the Myon area than in the Eup area. Although the average operation rate of sewage treatment facilities in these areas has increased slightly, there are many places where the operation rate is increasing even though there are no factors that will increase the inflow. Hence, the possibility of an inflow of unknown water is high. In addition, the population density in the sewage treatment area in the Myon area has been continuously decreasing, and the length of sewer pipes per person is also increasing. Therefore, it is predicted that maintenance of the facility will be difficult in the future. Additionally, 74% of the sewage generated in the Myon area is treated at private sewage treatment facilities. Moreover, as a result of analyzing the efficiency of public sewage treatment facilities using data envelopment analysis, approximately 50% were found to be inefficient in terms of facility capacity and operation. Considering the situation in the Myon area, it is believed that a change in perception of public and private sewage treatment facilities is necessary when establishing a sewerage maintenance plan for areas with a declining population.
Environmental Health Perspectives is an Open Access journal published by the National Institute of Environmental Health Sciences. Environmental Health Perspectives is an Open Access journal published by the National Institute of Environmental Health Sciences.
Environmental Health Perspectives is an Open Access journal published by the National Institute of Environmental Health Sciences. Environmental Health Perspectives is an Open Access journal published by the National Institute of Environmental Health Sciences.
2005년 아이치 엑스포는 국제박람회기구(BIE)에 의한 21세기 최초의 세계 엑스포였다. 아이치 엑스포 구상은 88년 올림픽 유치에 실패했던 나고야시와 아이치현이 엑스포 유치로 개발 방향을 전환하면서 1980년대 초반에 시작되었다. 개발과정에서 제기된 토지 및 환경 문제를 둘러싼 갈등도 있었지만, 정부-지자체-시민(환경)단체들은 검토회의(라운드테이블)를 형성함으로써 개발 계획을 재검토하고 실질적 수준의 합의를 형성해갔다. 아이치 엑스포는 지역적인 것이 국가적인 테두리를 넘어 글로벌한 것으로 수렴되면서, 다중스케일적인 행위자들이 교차했던 포스트 개발주의의 전형적 사례였다. 1990년대 이후 장기불황 가운데 아이치 엑스포는 환경을 내걸면서도 산업과 오락을 전면에 내세운 도요타가 주도권을 갖게 되었다. 이 연구는 1980년대부터 시작된 아이치 엑스포의 개발과정에 대한 시민사회의 참가, 환경・지속가능성을 고찰하고, 최근 사후 활용으로서 지브리 파크 유치와 주부권 중장기 경제 활성화를 분석했다. 이러한 과정을 통해 본 연구는 최근 한국의 엑스포 유치 과정에 포함된 대도시권 발전과 공항 건설 계획 등에 대한 시사점을 전망해 보았다.