• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.304-311
• /
• 2022

Construction inspection is a crucial stage that ensures that all contractual requirements of a construction project are verified. The construction inspection capabilities among state highway agencies have been greatly affected due to budget reduction. As a result, efficient inspection practices such as risk-based inspection are required to optimize the use of limited resources without compromising inspection quality. Automated prioritization of textual requirements according to their criticality would be extremely helpful since contractual requirements are typically presented in an unstructured natural language in voluminous text documents. The current study introduces a novel model for predicting the risk level of requirements using machine learning (ML) algorithms. The ML algorithms tested in this study included naïve Bayes, support vector machines, logistic regression, and random forest. The training data includes sequences of requirement texts which were labeled with risk levels (such as very low, low, medium, high, very high) using the fuzzy logic systems. The fuzzy model treats the three risk factors (severity, probability, detectability) as fuzzy input variables, and implements the fuzzy inference rules to determine the labels of requirements. The performance of the model was examined on labeled dataset created by fuzzy inference rules and three different membership functions. The developed requirement risk prediction model yielded a precision, recall, and f-score of 78.18%, 77.75%, and 75.82%, respectively. The proposed model is expected to provide construction inspectors with a means for the automated prioritization of voluminous requirements by their importance, thus help to maximize the effectiveness of inspection activities under resource constraints.

• Geomechanics and Engineering
• /
• v.37 no.3
• /
• pp.223-241
• /
• 2024

Evaluating the performance of Tunnel Boring Machines (TBMs) stands as a pivotal juncture in the domain of hard rock mechanized tunneling, essential for achieving both a dependable construction timeline and utilization rate. In this investigation, three advanced artificial neural networks namely, gated recurrent unit (GRU), back propagation neural network (BPNN), and simple recurrent neural network (SRNN) were crafted to prognosticate TBM-rate of penetration (ROP). Drawing from a dataset comprising 1125 data points amassed during the construction of the Alborze Service Tunnel, the study commenced. Initially, five geomechanical parameters were scrutinized for their impact on TBM-ROP efficiency. Subsequent statistical analyses narrowed down the effective parameters to three, including uniaxial compressive strength (UCS), peak slope index (PSI), and Brazilian tensile strength (BTS). Among the methodologies employed, GRU emerged as the most robust model, demonstrating exceptional predictive prowess for TBM-ROP with staggering accuracy metrics on the testing subset (R² = 0.87, NRMSE = 6.76E-04, MAD = 2.85E-05). The proposed models present viable solutions for analogous ground and TBM tunneling scenarios, particularly beneficial in routes predominantly composed of volcanic and sedimentary rock formations. Leveraging forecasted parameters holds the promise of enhancing both machine efficiency and construction safety within TBM tunneling endeavors.

• Korean Journal of Construction Engineering and Management
• /
• v.6 no.4 s.26
• /
• pp.142-151
• /
• 2005

Several advanced countries have been continually developed PHC pile cutting automation machines for improving productivity, safety and quality of the conventional PHC pile cutting work. However, the target work of the previously developed PHC pile cutting automation machines is only crushing the head of PHC pile. Dangerous grinding work is still performed by workers with seven inch hand grinder. In domestic construction industry, the PHC pile cutting work is usually performed by a crusher and three to four skilled workers. Recent analysis results of the PHC pile cutting work reveal that it frequently makes a lot of cracks which significantly reduce the strength of the pile and is labor-intensive work. The primary objective of this study is to propose the end-effector which can effectively break PHC pile without any longitudinal cracks and to develop an automated pile cutting machine having unified grinder and crusher parts through a wide variety of laboratory and field tests. It is anticipated that the development of the automated pile cutting machine would be able to bring improvements in safety, productivity, quality as well as cost saving.

• Hwankyungkyoyuk
• /
• v.11 no.2
• /
• pp.130-143
• /
• 1998

This study was conducted as a preliminary step to establish a model for the practical application of environmental education related to food wastes collected from elementary school foodservices. Methods of treatment and present recycling status of food wastes in elementary schools in Kyonggido were surveyed. The consciousness of dieticians who have been serving for elementary school foodservices was also analyzed through the survey questions concerning environmental education for the reduction and recycling of food wastes. The results derived from this survey were as follows: The major portion of food wastes from elementary school foodservices was constituted with vegetables and soup, and an average amount of food wastes per day was highest in June and July. Therefore environmental education related to reduction of wastes was needed in the first semester of school terms, and the possible reduction of food wastes achieved through the proper planning of school foodservice menu was also needed. In most cases food wastes were collected and treated by animal growing farmers or composted by machines in school. In operating composting machines microorganism inoculant was mostly used but dieticians pointed out the problem of a nasty odor, insects, and high energy consumption. This situation means it has not been operated efficiently and suggests an efficiency problem of machine composting in elementary schools because composting itself is based on the aerobic digestion and high temperature fermentation which kills insects and harmful microorganisms. Elementary school dieticians in Kyonggido were aware that food wastes cause main pollution problem, and that food wastes are valuable resources which can be recycled, and recycling of food wastes is inevitable. But more than half of the schools surveyed have not been reused food wastes in school, so a proper model for recycling and reuse of food wastes in school grounds was thought to be needed. Environmental education programs related to food wastes have not been peformed in more than half of the schools surveyed. It was concluded that the following three plans will be helpful to reduce school food wastes. First, environmental education should be enforced, second, teachers' and dieticians' intensive teaching concerning food wastes should be needed, and finally establishment of a model for recycling and reuse of food wastes in school grounds and its application to environmental education would offer a valuable field experience to school students.

• Journal of Science and Technology Studies
• /
• v.19 no.3
• /
• pp.201-246
• /
• 2019

Information technology is sometimes considered as a cause that puts education in a big crisis, or it can be seen as a savior. In 2011, the Korean government announced that it would innovate education and build a talented nation by bringing IT into schools of public education system through the SMART education policy. The policy initiative aimed to establish a standard classroom models that can be diffused all over the country's schools so that teachers and students may become familiar of using devices such as tablet PCs and laptops. This paper analyzes how the smart classrooms caused friction in the actual education practices. To this end, I analyzed the direction and ideals of the SMART education policy by reading government policy document and design guidelines officially published, and visited three elementary schools that are actually building and operating a smart classroom environment to visit the facilities and have in-depth interviews with teachers and technicians. The ideal type of classroom proposed by the smart education policy was a package equipped with various functions at once in a neatly designed space like a "model house", but it was difficult to be used as a normal classroom in everyday life of school. Instead of copying and installing the model, each school decided to get "smart" in its own way, depending on how factors such as size, local characteristics, socioeconomic conditions of students and teachers, teacher experiences, and the level of existing infrastructure were combined. In Elementary School A, the machines tamed specific space of the school to create their own space, while following the rules of the school for being mobile. Although Elementary School B could not construct fully supported environment that encompassed the entire school, the system was organized with the help of well trained teacher's experiences in other schools. In Elementary School C, the machines are concentrated on specific classrooms and they promote teacher's professionalism. The components of the smart classroom were disassembled and recombined in context to make each school's classroom "smart".

• Investigative Magnetic Resonance Imaging
• /
• v.8 no.2
• /
• pp.79-85
• /
• 2004

Purpose : To evaluate the usefulness and reproducibility of $^1H$ MRS in different 1.5 T MR machines with different coils to compare the SNR, scan time and the spectral patterns in different brain regions in normal volunteers. Materials and Methods : Localized $^1H$ MR spectroscopy ($^1H$ MRS) was performed in a total of 10 normal volunteers (age; 20-45 years) with spectral parameters adjusted by the autoprescan routine (PROBE package). In all volunteers, MRS was performed in a three times using conventional MRS (Signa Horizon) with 1 channel coil and upgraded MRS (Echospeed plus with EXCITE) with both 1 channel and 8 channel coil. Using these three different machines and coils, SNRs of the spectra in both phantom and volunteers and (pre)scan time of MRS were compared. Two regions of the human brain (basal ganglia and deep white matter) were examined and relative metabolite ratios (NAA/Cr, Cho/Cr, and mI/Cr ratios) were measured in all volunteers. For all spectra, a STEAM localization sequence with three-pulse CHESS $H_2O$ suppression was used, with the following acquisition parameters: TR=3.0/2.0 sec, TE=30 msec, TM=13.7 msec, SW=2500 Hz, SI=2048 pts, AVG : 64/128, and NEX=2/8 (Signa/Echospeed). Results : The SNR was about over $30\%$ higher in Echospeed machine and time for prescan and scan was almost same in different machines and coils. Reliable spectra were obtained on both MRS systems and there were no significant differences in spectral patterns and relative metabolite ratios in two brain regions (p>0.05). Conclusion : Both conventional and new MRI systems are highly reliable and reproducible for $^1H$ MR spectroscopic examinations in human brains and there are no significant differences in applications for $^1H$ MRS between two different MRI systems.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.642-652
• /
• 2009

In order to improve the performance of the existing relation extraction approaches, we propose a method for combining two pivotal concepts which play an important role in classifying semantic relationships between entities in text. Having built a composite kernel-based relation extraction system, which incorporates both entity features and syntactic structured information of relation instances, we define nine classes of lexical features and synthetically apply them to the system. Evaluation on the ACE RDC corpus shows that our approach boosts the effectiveness of the existing composite kernels in relation extraction. It also confirms that by integrating the three important features (entity features, syntactic structures and contextual lexical features), we can improve the performance of a relation extraction process.

• Journal of Acupuncture Research
• /
• v.28 no.3
• /
• pp.85-100
• /
• 2011

Objectives : The purpose of this thesis is to help the preparation of oriental medicine clinical guidelines for drawing up the standards of oriental medicine demonstration and diagnosis classification about the neck pain. Methods : Statistical analysis about Gyeonghangtong(頸項痛), Nakchim(落枕), Sagyeong(斜頸), Hanggang (項强) classified experts' opinions about neck pain patients by Delphi method is conducted by using oriental medicine diagnosis questionnaire. The result was classified by using linear discriminant analysis (LDA), diagonal linear discriminant analysis (DLDA), diagonal quadratic discriminant analysis (DQDA), K-nearest neighbor classification (KNN), classification and regression trees (CART), support vector machines (SVM). Results : The results are summarized as follows. 1. The result analyzed by using LDA has a hit rate of 84.47% in comparison with the original diagnosis. 2. High hit rate was shown when the test for three categories such as Gyeonghangtong and Hanggang category, Sagyeong caterogy and Nakchim caterogy was conducted. 3. The result analyzed by using DLDA has a hit rate of 58.25% in comparison with the original diagnosis. The result analyzed by using DQDA has a accuracy of 57.28% in comparison with the original diagnosis. 4. The result analyzed by using KNN has a hit rate of 69.90% in comparison with the original diagnosis. 5. The result analyzed by using CART has a hit rate of 69.60% in comparison with the original diagnosis. There was a hit rate of 70.87% When the test of selected 8 significant questions based on analysis of variance was performed. 6. The result analyzed by using SVM has a hit rate of 80.58% in comparison with the original diagnosis. Conclusions : Statistical analysis using oriental medicine diagnosis questionnaire on neck pain generally turned out to have a significant result.

• The Journal of Advanced Prosthodontics
• /
• v.12 no.3
• /
• pp.114-123
• /
• 2020

PURPOSE. The aim of this study was to evaluate the corrosion resistance of the specimens produced by five different commercial metal laser sintering (MLS) systems with their recommended Co-Cr alloy powders. MATERIALS AND METHODS. The MLS machines and the alloy powders used were, ProX 100-ST2724G (St-Pro), Mysint 100-EOS SP2 (SP2-Mys), EOSINT 270-EOS SP2 (SP2-EOS), SLM 100-Starbond CoS (SB-SLM), and MLab Cusing-Remanium^® Star (RS-MLab), respectively. Eight specimens from each group were prepared. Open circuit potential (E_ocp) and electrochemical impedance spectroscopy (EIS) measurements of polished surfaces of the specimens were conducted in a three-electrode cell using a potentiostat-galvanostat in Fusayama-Meyer artificial saliva (AS). Specimens from each group were immersed in AS and de-ionized water for seven days. E_ocp, charge transfer resistance (R_ct) values, and released ions (㎍/㎠ × 7d) in different solutions were determined. The specimen surfaces were observed with SEM/EDS. Results were analyzed statistically. RESULTS. E_ocp values have shifted to potentials that are more positive over time. Steady-state E_ocp values were from high to low as follows, SB-SLM, SP2-Mys, SP2-EOS, RS-MLab, and ST-Pro, respectively. After 60 mins, RS-MLab specimens had the highest R_ct value, followed by SP2-Mys, SB-SLM, SP2-EOS, and ST-Pro. In all groups, ion release was higher in AS than that in de-ionized water. CONCLUSION. There were small differences among the corrosion resistances of the Co-Cr alloy specimens produced with MLS systems; meanwhile, the corrosion resistances were quite high for all specimens.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.109-118
• /
• 2020

In recent years, the needs of consumers for personality and personalized clothing are increasing. Knitting machines, which produce clothing by the user at low cost, are a good way to meet consumer demand. However, the user is having difficulty in using the knitting machine pattern program, which is a software program, independently of the operation of the knitting machine. Therefore, this study conducted a literature review prior to the empirical research and evaluated the usability by selecting three kinds of frequently used knitting machine pattern programs as research subjects. Based on the nine usability evaluation principles derived from expert group discussions, the study found that the needs of users for nine evaluation principles: visibility, conciseness, operability, consistency, accuracy, flexibility, intuition, error recognition, and supplementary explanation (The purpose of this study is to identify the direction and alternatives of usability improvement for the interface of the knitting machine pattern program.