• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.127-135
• /
• 2020

The purpose of this study is to develop a human activity recognition (HAR) system, which distinguishes 13 activities, including five activities commonly dealt with in conventional HAR researches and eight activities from the Eastern-Asian culture. The eight special activities include floor-sitting/standing, chair-sitting/standing, floor-lying/up, and bed-lying/up. We used a 3-axis accelerometer sensor on the wrist for data collection and designed a machine learning model for the activity classification. Data clustering through preprocessing and feature extraction/reduction is performed. We then tested six machine learning algorithms for recognition accuracy comparison. As a result, we have achieved an average accuracy of 99.7% for the 13 activities. This result is far better than the average accuracy of current HAR researches based on a smartwatch (89.4%). The superiority of the HAR system developed in this study is proven because we have achieved 98.7% accuracy with publically available 'pamap2' dataset of 12 activities, whose conventionally met the best accuracy is 96.6%.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.5
• /
• pp.788-797
• /
• 2011

This paper analyzes the accuracy on the approach and landing of aircraft to an airport through comparison with airbase Precision Approach Radar and aircraft track data of DGPS equipped in aircraft. The proposed analysis result could be a basis for verifying the possibility that DGPS can be utilized in Airbase precision approach and landing. Position identification capability of widely used commercial DGPS is fairly accurate on latitude and longitude, while there is a slight error for being used in an airbase accurate approach and landing of Category I precision when it comes to altitude. Thus, we tested accuracy by analyzing actual flight track data of high performance aircraft to verify the accuracy of the airbase approach and landing using DGPS. Through the research, we developed instrumentation to compare PAR track data with DGPS track data, which can be used in reducing the number of PAR verification Flight utilizing it as a system measuring PAR accuracy at PAR installation phase.

• Journal of Astronomy and Space Sciences
• /
• v.34 no.1
• /
• pp.19-30
• /
• 2017

The optical wide-field patrol network (OWL-Net) is a Korean optical surveillance system that tracks and monitors domestic satellites. In this study, a batch least squares algorithm was developed for optical measurements and verified by Monte Carlo simulation and covariance analysis. Potential error sources of OWL-Net, such as noise, bias, and clock errors, were analyzed. There is a linear relation between the estimation accuracy and the noise level, and the accuracy significantly depends on the declination bias. In addition, the time-tagging error significantly degrades the observation accuracy, while the time-synchronization offset corresponds to the orbital motion. The Cartesian state vector and measurement bias were determined using the OWL-Net tracking data of the KOMPSAT-1 and Cryosat-2 satellites. The comparison with known orbital information based on two-line elements (TLE) and the consolidated prediction format (CPF) shows that the orbit determination accuracy is similar to that of TLE. Furthermore, the precision and accuracy of OWL-Net observation data were determined to be tens of arcsec and sub-degree level, respectively.

• Journal of Industrial Technology
• /
• v.31 no.B
• /
• pp.9-15
• /
• 2011

Nowadays, the Surveying field is growing rapidly in terms of technology such as TS(Total Station) surveying, photographic surveying, digital aerial photogrammetry, utilization of GIS(Geographic Information System) using high-resolution satellite imagery, obtaining 3D Coordinate using GPS. But control point surveying, benchmark measuring, and field Surveying are still performed by the engineers in the field. So, 3D yerrestrial laser scanner comes to the fore recently. 3D terrestrial laser scanner can get 3D coordinate about a number of sites of the subject in a short period with high accuracy. This paper compared the accuracy of data from the performance using 3D terrestrial laser scanner with that of TS. It also obtained the geopositioning accuracy result equivalent to the surveying result of TS. With further researches in the future, it is expected to be used not only in LiDAR itself but also in various areas like reconnaissance Surveying and construction by combining with TS or other Surveying equipments.

• Journal of Welding and Joining
• /
• v.31 no.5
• /
• pp.15-19
• /
• 2013

In order to reduce a grand compute time in prediction of welding distortion and residual stress by 3D thermal elastic plastic analysis, idealization of welding that is methods to heat input simultaneously in all weld metal on the same welding direction is carried out on two weld joints(butt welding and fillet welding). Then, the accuracy of acquired results is investigated through the comparison of the high accuracy prediction results. The thermal conduction analysis results by idealization of welding, the temperature is raised accompany with beginning of heat input because all of weld metal is heated input at the same time. On the other side, the temperature witch predicted with high accuracy is raised at the moment heating source passes the measuring points. So, there is difference of time between idealization of welding and considering of moving heat source faithfully. However, temperature history by idealization of welding is well simulated a high accuracy prediction results.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.

• Ocean and Polar Research
• /
• v.38 no.3
• /
• pp.247-257
• /
• 2016

The inter-comparison project for seawater salinity measurements, in which 25 laboratories from 16 countries took part, was conducted by JCOMM (Joint WMO/IOC Technical Commission for Oceanography and Marine Meteorology) for the first time in 2014. Two seawater samples of different salinity values ranging from 30-35 and 20-25 for Sample A and Sample B respectively and which had sufficient homogeneity and stability were distributed to all participants. Participants measured the salinity in their own laboratories at least 3 times and reported the results. Statistical treatments were applied to the results to assess discrepancies among laboratories. 20 out of the 25 laboratories used laboratory salinometers and statistics for this group were denoted as belonging to group ${\alpha}$; while 5 out of the 25 laboratories used hand-held measuring instruments and statistics for this group were denoted as belonging to group ${\beta}$. Bias described as discrepancy among laboratories in group ${\alpha}$ was within ${\pm}0.001$ and expanded uncertainty (k = 2) was in the vicinity of 0.002. The bias and the uncertainty of Korea Institute of Ocean Science and Technology (KIOST), in group ${\alpha}$, were 0.000 and 0.002, respectively. The biases of group ${\beta}$ were greater than group ${\alpha}$ because of constraints related to instrument accuracy. Biases from 3 laboratories in group ${\beta}$ exceed the accuracy specification of the corresponding instruments. Considering that the uncertainty of Standard Seawater (SSW) is of the order 0.001 to 0.002, the inter-comparison results show that 16 laboratories among the 25 laboratories made high quality measurements, largely indistinguishable from one another.

• Journal of the Society of Naval Architects of Korea
• /
• v.39 no.2
• /
• pp.28-33
• /
• 2002

The characteristics of hull-pieces are large quantity, comparatively large piece-size, and different each shape. For the more, in the forming process(including Line-Heating Process) of curved hull pieces, shape checking processes including initial shape measurement and forming shape measurement of the each pieces are needed to achieve a given accuracy. So, the forming process of large curved hull pieces needs efficient measurement and comparison technique to check the shape and ensure the forming-accuracy In this paper, we try to construct integrated S/W, H/W system for efficient measurement and comparison of large curved hull pieces, which can apply to above forming environment.

• Journal of Navigation and Port Research
• /
• v.41 no.5
• /
• pp.269-276
• /
• 2017

"Tracking" here refers to the estimation of a moving object with some degree of accuracy where at least one measurement is given. The measurement, which is the sensor-obtained output, contains systemic errors and errors that are due to the surrounding environment. Tracking filters play the key role of the target-state estimation after the updating of the tracking system; therefore, the type of filter that is used for the conduction of the estimations is crucial in the determining of the reliability of the updated value, and this is especially true since the performances of different filters vary when they are subjected to different environmental and initial conditions. The purpose of this paper is the conduction of a comparison between the performances of the ${\alpha}-{\beta}-{\gamma}$ filter and the Kalman filter regarding an ARPA-system tracking module that is used on board high-dynamic warships. The comparison is based on the capability of each filter to reduce noise and maintain a stable response. The residual error is computed from the difference between the true and predicted positions and the true and estimated positions for the given sample. The results indicate that the tracking accuracy of the Kalman filter is higher compared with that of the optimal ${\alpha}-{\beta}-{\gamma}$ filter; however, the response of the optimal ${\alpha}-{\beta}-{\gamma}$ filter is more stable.

• Korean Journal of Remote Sensing
• /
• v.25 no.4
• /
• pp.359-366
• /
• 2009

Research of accurate DEM generation using images of Kompsat-2 is not enough. This paper focused on generation of accurate Kompsat-2 DEM and comparison with DEM from common software like PCI Geomatica and ENVI. For Kompsat-2 DEM generation, we applied orbit-attitude sensor modeling technique and matching method based on epipolarity and image geometry. The comparison of performance with each commercial programs made a qualitative experiment through naked eyes and a quantitative experiment with USGS DTED. The accuracy was judged by the average absolute error and RMS error with DIED. The result of comparison experiment, we could confirm that the method used in the experiment showed much better performance than DEM made from other commercial programs in most of images.