• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.523-528
• /
• 2020

With a widespread of sensor-rich mobile devices, the analysis of human activities becomes more general and simpler than ever before. In this paper, we propose two deep neural networks that efficiently and accurately perform human activity recognition (HAR) using tri-axial accelerometers. In combination with powerful modern deep learning techniques like batch normalization and LSTM networks, our model outperforms baseline approaches and establishes state-of-the-art results on WISDM dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1104-1120
• /
• 2020

The chest X-rays are a common way to diagnose lung cancer or pneumonia. In particular, the finding of a lung nodule is the most important problem in the early detection of lung cancer. Recently, a lot of automatic diagnosis algorithms have been studied to find the lung nodules missed by doctors. The algorithms are typically based on segmentation network like U-Net. However, the occurrence of false positives that similar to lung nodules present outside the lungs can severely degrade performance. In this study, we propose a multi-task learning method that simultaneously learns the lung region and nodule-labeled data based on the prior knowledge that lung nodules exist only in the lung. The proposed method significantly reduces false positives outside the lung and improves the recognition rate of lung nodules to 83.8 F1 score compared to 66.6 F1 score of single task learning with U-net model. The experimental results on the JSRT public dataset demonstrate the effectiveness of the proposed method compared with other baseline methods.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.316-321
• /
• 2000

The role of fatigue on the surface damage of 5% chrome cold milling work roll is evaluated. Uniaxial and torsional fatigue tests are carried out, and the baseline data for fatigue life evaluation are established. An appropriate multiaxial fatigue parameter is developed from the fatigue data. Fatigue tests are also performed under compressive mean stresses, and a mean stress model is formulated. A computer program is developed to assess the interaction of fatigue and grinding of the roll. The fatigue damage is computed for selected servicing conditions. It is found that the fatigue damage can be an important issue when the effect of mean stress is ignored, however the fatigue damage is negligibly small when the effect of mean stress including the residual stresses currently used is fully accounted. The result indicates that spalling due to the growth of thermal shock cracks is more important than fatigue damage in roll surface failure.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.4
• /
• pp.277-284
• /
• 2012

Named entity recognition (NER) technique can play a crucial role in extracting information from the web. While NER systems with relatively high performances have been developed based on careful manipulation of terms with a statistical model, term mismatches often degrade the performance of such systems because the strings of all the candidate entities are not known a priori. Despite the importance of lexical-level term mismatches for NER systems, however, most NER approaches developed to date utilize only the term string itself and simple term-level features, and do not exploit the semantic features of terms which can handle the variations of terms effectively. As a solution to this problem, here we propose to match the semantic concepts of term units in restaurant named entities (NEs), where these units are automatically generated from multiple resolutions of a semantic tree. As a test experiment, we applied our restaurant NER scheme to 49,153 nouns in Korean restaurant web pages. Our scheme achieved an average accuracy of 87.89% when applied to test data, which was considerably better than the 78.70% accuracy obtained using the baseline system.

• The Korean Journal of Health Service Management
• /
• v.10 no.4
• /
• pp.37-50
• /
• 2016

Objectives : The aim of this meta-analysis was to draw overall conclusions on the correlation between the organizational effectiveness (OE) of healthcare employees and related factors by summarizing recent studies and to provide a baseline for future research. Methods : A literature search for original articles published from 2005 to 2014 including doctoral theses and KCI journal articles was done in KERIS' RISS, etc. in a systematic manner. From 77 studies which met the inclusion criteria 190 effect sizes (ESs) were calculated for the analysis. A meta-analysis was done with CMA 3 (Biostat company, USA). Results : The overall ES was moderate for all, positively and negatively related factors. For all related factors, job characteristics, group-leader relations, personal and organizational characteristics had a moderate ES. The ES for work experiences was small. Conclusions : Although the results of this study were meaningful it is necessary to perform follow-up analyses (1) based on a longer data period and more articles, (2) including moderating variables with higher explanatory power and (3) adopting a study model with more specific and simplified variables.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.9
• /
• pp.80-87
• /
• 2004

Active control of on-orbit spacecraft jitter is a significant problem for future spacecraft mission requiring stringent pointing performance. Jitter is major disturbance source degrading payload pointing performance. Both passive and active jitter isolation techniques have been studied during the last decade. We present active jitter isolation for a model device in this work. The device provides active control capability by 3 degree-of-freedom control of payload in feedback control strategy. Mathematical modeling of the device is pursued which is naturally used for a baseline controller design. Simulation results are used to validate the designed control law.

• Journal of Construction Engineering and Project Management
• /
• v.1 no.1
• /
• pp.37-43
• /
• 2011

Labor productivity is a significant factor associated with controlling time, cost, and quality. Many researchers have developed models to define methods of measuring the relationship between productivity and various parameters such as the size of working area, maximum working hours, and the crew composition. Most of the previous research has focused on estimating productivity; however, this research concentrates on estimating labor productivity and developing time and cost data for repetitive concrete pouring activity. In Korea, "Standard Estimating" only entails the average productivity data of the construction industry, and it is difficult to predict the time and cost spent on any particular project. As a result, errors occur in estimating duration and cost for individual activities or projects. To address these issues, this research sought to collect data, measure productivity, and develop time and cost data using labor productivity based on field conditions from the collected data. A probabilistic approach is also proposed to develop data. A case study is performed to validate this process using actual data collected from construction sites. It is possible that the result will be used as the EVMS baseline of cost management and schedule management.

• Journal of Periodontal and Implant Science
• /
• v.32 no.4
• /
• pp.847-855
• /
• 2002

It has been reported that Magnoliae cortex extract has antibacterial and antimicrobial activity against pathogenic microbes and Zea Mays L. extract is effective for improving gingival tissue health. The purpose of this study was to examine the anti-inflammatory and antimicrobial effects of Zea Mays L. and Magnoliac cortex extract mixtures through experimental peridontitis induced beagle dog model. Nine beagle dogs with experimentally induced periodontitis were selected. Baseline clinical indices which includes plaque index, gingival index, probing pocket depth, clinical attachment level, gingival fluid flow rate were recorded and microbial assays were done. Magnoliac cortex and Zea Mays L., mixed at 2:l ratio in 105mg capsular dosage, were taken by 3 capsule (Group I) or 6 capsule dosages (Group II) three times a day. After 4,8,12 weeks, clinical indices were recorded. All data of clinical indices were compared through one-way ANOVA with 95% confidence level. Clinical indices of group I and II showed significantly better results than those of control group. There were no significant differences between group I and II. In conclusion, it was confirmed that mixture of Magnoliae cortex and Zea May L. (mix ratio 2:1) possessed clinical improving effects to periodontitis.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.4
• /
• pp.368-374
• /
• 2011

This paper proposes a robot control human interface using Markov model (HMM) based hand signal recognizer. The command receiving humanoid robot sends webcam images to a client computer. The client computer then extracts the intended commanding hum n's hand motion descriptors. Upon the feature acquisition, the hand signal recognizer carries out the recognition procedure. The recognition result is then sent back to the robot for responsive actions. The system performance is evaluated by measuring the recognition of '48 hand signal set' which is created randomly using fundamental hand motion set. For isolated motion recognition, '48 hand signal set' shows 97.07% recognition rate while the 'baseline hand signal set' shows 92.4%. This result validates the proposed hand signal recognizer is indeed highly discernable. For the '48 hand signal set' connected motions, it shows 97.37% recognition rate. The relevant experiments demonstrate that the proposed system is promising for real world human-robot interface application.

• Journal of Ocean Engineering and Technology
• /
• v.17 no.3 s.52
• /
• pp.13-20
• /
• 2003

This research aims at investigation of accuracy potential of RTK(Real-Time Kinematic) GPS in combination with Echo Sounder(E/S) for the coastal mapping. Apart from this purpose, the accuracy of ambiguity resolution with the OTF(On The Fly) method was tested with respect to the initialization time. The result shows that the accuracy is better than 1cm with 5-minute initialization in the distance of 10km baseline. The seaside topography was measured by the RTK GPS only, on the other hand the seafloor topography was surveyed in combination of RTK GPS and E/S. Comparing to the volume of seaside measured by RTK GPS and digital topographical map, the difference of only $2\%$ was achieved. This indicates that the coastal mapping. As a result, it has been revealed that every possible noise in surveying could be corrected and the accuracy could be improved. The accuracy of GPS data acquired in real time was as good as that acquired by post processing. It is expected that it will be useful for the analysis of coastal geographic characteristics because DTM(Digital Terrain Model) can be also constructed for the harbor reclamation, the dredging, and the variation of soil movement in a river.