• Korean Journal of Construction Engineering and Management
• /
• v.19 no.4
• /
• pp.43-51
• /
• 2018

As the inventory of aged apartments is expected to increase explosively, the importance of maintenance to improve the durability of concrete facilities is increasing. Concrete compressive strength is a representative index of durability of concrete facilities, and is an important item in the precision safety diagnosis for facility maintenance. However, existing methods for measuring the concrete compressive strength and determining the maintenance of concrete facilities have limitations such as facility safety problem, high cost problem, and low reliability problem. In this study, we proposed a model that can predict the concrete compressive strength through images by using deep convolution neural network technique. Learning, validation and testing were conducted by applying the concrete compressive strength dataset constructed through the concrete specimen which is produced in the laboratory environment. As a result, it was found that the concrete compressive strength could be learned by using the images, and the validity of the proposed model was confirmed.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.26 no.1
• /
• pp.73-84
• /
• 2020

Purpose: Though Korean healthcare services have been upgraded, infection and fire had been broken out in general hospitals. And higher concerns about quality assessment made it to clinical laboratory design guideline studies. So, this study investigates the facilities, equipment and personnel of laboratory medicine focusing on more than five hundred fifty bed hospital, and contributes to make guidelines for safety and efficiency in lab. Methods: Questionnaires to supervisor technologist and field surveys to medical laboratories in korean hospitals have been conducted for the data collection. 16 answers have been analysed statistically by MS Excel program. Results: Most of the sample tests such as hematology, clinical chemistry, immunology, transfusion, urinalysis, microbiology and molecular diagnosis are performed by more than 80% in large sized general hospital laboratory. In the test methods, automatic analyzers are used up to 80%, total laboratory automation up to 43% in clinical chemistry and immunology, and manual tests in all sorts of the test. There are placed in single lab or two and three labs above the ground, which are all in semi-open lab. There is some correlation with the number of specimens and the number of lab people depending on the number of hospital beds. Laboratory environment shows that work distance is good, but evacuation path width, visibility, separation of staff area from automatic analyzer, and equipment installations are needed to have more spaces and gears. Most of the infection controls are equipped with mechanical ventilation, air-conditioning, washbasin and wastewater separation, BSC installation and negative pressure lab room. Implications: Although the laboratory space area is calculated considering the number of hospital beds, type of tests and number of staff, hospital's expertise and the samples numbers per year should be taken into account in the planning of the hospital.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1088-1097
• /
• 2021

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.27 no.4
• /
• pp.61-70
• /
• 2021

Purpose: The study aims at identifying patient-related and environmental factors associated with an increased risk of falling and, therefore, both caregivers and designers can be aware of fall risk factors and can contribute to prevent inpatient falls in their own areas of expertise. Methods: A case-control study has been conducted, utilizing patient data and physical environmental data in the unit of General Medicine in the United States. The case-control study investigated data about patients who had suffered falls as well as patients with similar characteristics (e.g., age, gender, and diagnosis) who did not suffer falls. Results: The study identified both patient-related and physical environmental factors associated with inpatient falls. Morse fall risk score, patient visibility, and patient accessibilityB were identified as significant predictors to inpatient falls, when controlling for other significant variables. Implications: The findings of the study can provide implications to both caregivers and healthcare and hospital environment designers. Caregivers should give special attention to patients with high Morse Fall Risk Scores to prevent inpatient falls. Designers also need to examine and to fine-tune the unit layout of inpatient care units to maximize each patient room's patient visibility from the rest of the unit and patient accessibilityB from working areas of nurses.

• Imaging Science in Dentistry
• /
• v.53 no.4
• /
• pp.271-281
• /
• 2023

Purpose: The objective of this scoping review was to investigate the applicability and performance of various convolutional neural network (CNN) models in tooth numbering on panoramic radiographs, achieved through classification, detection, and segmentation tasks. Materials and Methods: An online search was performed of the PubMed, Science Direct, and Scopus databases. Based on the selection process, 12 studies were included in this review. Results: Eleven studies utilized a CNN model for detection tasks, 5 for classification tasks, and 3 for segmentation tasks in the context of tooth numbering on panoramic radiographs. Most of these studies revealed high performance of various CNN models in automating tooth numbering. However, several studies also highlighted limitations of CNNs, such as the presence of false positives and false negatives in identifying decayed teeth, teeth with crown prosthetics, teeth adjacent to edentulous areas, dental implants, root remnants, wisdom teeth, and root canal-treated teeth. These limitations can be overcome by ensuring both the quality and quantity of datasets, as well as optimizing the CNN architecture. Conclusion: CNNs have demonstrated high performance in automated tooth numbering on panoramic radiographs. Future development of CNN-based models for this purpose should also consider different stages of dentition, such as the primary and mixed dentition stages, as well as the presence of various tooth conditions. Ultimately, an optimized CNN architecture can serve as the foundation for an automated tooth numbering system and for further artificial intelligence research on panoramic radiographs for a variety of purposes.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.292-297
• /
• 2001

In writing learning as a second/foreign language, a learner has to acquire not only lexical and syntactical knowledge but also the skills to choose suitable words for content which s/he is interested in. A learning system should extrapolate learner\\`s intention and give example phrases that concern with the content in order to support this on the system. However, a learner cannot always represent a content of his/her desired phrase as inputs to the system. Therefore, the system should be equipped with a diagnosis function for learner\\`s intention. Additionally, a system also should be equipped with an analysis function to score similarity between learner\\`s intention and phrases which is stored in the system on both syntactic and idiomatic level in order to present appropriate example phrases to a learner. In this paper, we propose architecture of an interactive support method for English writing learning which is based an analogical search technique of sample phrases from corpora. Our system can show a candidate of variation/next phrases to write and an analogous sentence that a learner wants to represents from corpora.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.73-76
• /
• 2005

The advanced information and communication technology gives vehicles another role of the third digital space, merging a physical space with a virtual space in a ubiquitous society. In the ubiquitous environment, the vehicle becomes a sensor node, which has a computing and communication capability in the digital space of wired and wireless network. An intelligent vehicle information system with a remote control and diagnosis is one of the future vehicle systems that we can expect in the ubiquitous environment. However, for the intelligent vehicle system, many issues such as vehicle mobility, in-vehicle communication, service platform and network convergence should be resolved. In this paper, an in-vehicle gateway is presented for an intelligent vehicle information system to make an access to heterogeneous networks. It gives an access to the server systems on the internet via CDMA-based hierarchical module architecture. Some experiments was made to find out how long it takes to communicate between a vehicle's intelligent information system and an external server in the various environment. The results show that the average response time amounts to 776ms at fixec place, 707ms at rural area and 910ms at urban area.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.233-238
• /
• 2017

Automatic identification of disease in plants from their leaves is one of the most challenging task to researchers. Diseases among plants degrade their performance and results into a huge reduction of agricultural products. Therefore, early and accurate diagnosis of such disease is of the utmost importance. The advancement in deep Convolutional Neural Network (CNN) has change the way of processing images as compared to traditional image processing techniques. Deep learning architectures are composed of multiple processing layers that learn the representations of data with multiple levels of abstraction. Therefore, proved highly effective in comparison to many state-of-the-art works. In this paper, we present a plant disease identification methodology from their leaves using deep CNNs. For this, we have adopted GoogLeNet that is considered a powerful architecture of deep learning to identify the disease types. Transfer learning has been used to fine tune the pre-trained model. An accuracy of 85.04% has been recorded in the identification of four disease class in Apple plant leaves. Finally, a comparison with other models has been performed to show the effectiveness of the approach.

• KIEAE Journal
• /
• v.11 no.1
• /
• pp.21-28
• /
• 2011

The objective of this study is to analysis the properties for reclassifying green roofs into three types by cluster analysis after investigating the present condition in thirty green roofs which were created from 2002 to 2004 by Seoul Metropolitan Government. The previous classification was resulted in structure safety diagnosis in the type of green roofs and visible judgment by experts in sites. However, it should have been corrected. Therefore, it needed a reestablished concept and a reclassification in green roofs. The results of this study are as follows : the concept of a rooftop garden and a green roof is different from previous studies. The rooftop gardens named by intensive green roofs are closed to integrated management, whereas the green roofs are closed to low management. The reclassification of green type was also conducted to use the statistic analysis of categorical regression by previous studies, and the factors extracted by the categorical regression were influenced by greening type. The figure of R-square representing explanation in regression analysis is 95.2%. As this result was analyzed, it was proved into rooftop gardens demanded for high activity by people.