• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Journal of the Korean earth science society
• /
• v.37 no.7
• /
• pp.398-407
• /
• 2016

We cooperated with four domestic educational astronomical observatories to construct a baseline and perform simultaneous observations to determine the geocentric parallax, distance, and motion of 1036 Ganymed, an Amor asteroid near the Earth. Observations were made on the day when simultaneous observations were possible from September to November 2011. Measured distances of 1036 Ganymed were 0.394 AU on Sept. 26, 0.365 AU on Oct. 11, and 0.340 AU on Oct. 25, respectively, which were within the error range as compared with the measured distances proposed by the US Jet Propulsion Laboratory. The 1036 Ganymed showed a tilting motion during the observation period, and the tangential angular velocities were measured at $0.037-0.052^{{\prime {\prime}}\;sec^{-1}$. Through this study, it was shown that the simultaneous observations among educational astronomical observations can obtain distance measurements with an error range of about 5% for asteroids near 0.4 AU. And it expected to be used as a research & education program emphasizing collaborative observation activities based on a network between observatories.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.8
• /
• pp.72-78
• /
• 2009

We developed a line standards measurement system using an optical microscope and measured two kinds of line standards. It consists of three main parts: an optical microscope module including a CCD camera, a stage system with a linear encoder, and a measurement program for a microscopic image processing. The magnification of microscope part was calibrated using one-dimensional gratings and the angular motion of stage was measured to estimate the Abbe error. The threshold level in line width measurement was determined by comparing with certified values of a line width reference specimen, and its validity was proved through the measurement of another line width specimen. The expanded uncertainty (k=2) was about 100 nm in the measurements of $1{\mu}m{\sim}10{\mu}m$ line width. In the comparison results of line spacing measurement, two kinds of values were coincide within the expanded uncertainty, which were obtained by the one-dimensional measuring machine in KRISS and the line standards measurement system. The expanded uncertainty (k=2) in the line spacing measurement was estimated as $\sqrt{(0.098{\mu}m)^2+(1.8{\times}10^{-4}{\times}L)^2}$. Therefore, it will be applied effectively to the calibration of line standards, such as line width and line spacing, with the expanded uncertainty of several hundreds nanometer.

• Bulletin of the Korean Space Science Society
• /
• 2011.04a
• /
• pp.19.2-19.2
• /
• 2011

In 1861 Nam Byeong-Gil published a book called as "Seonggyeong" which contains a star catalogue (NBGC) with the positions, magnitudes, and star maps for 1449 stars. The NBGC lists only the traditional Chinese stars selected from "the sequel to the Qing Dynasty Star Catalogue and Star Map." To identify each star from the NBGC with modern counterpart, we correct the positions of the Hipparcos stars brighter than 6.5 mag for proper motion, then precess the coordinates to the epoch of the NBGC. For each star in the NBGC, we find the nearest counterpart in the Hipparcos Catalogue (HC). If a much brighter star is at a slightly larger angular distance, we select that star as the secure counterpart. As a result, 95.5% of the stars in the NBGC were identified. We find a very good overall agreement of our results with a previous analysis by Ahn et al. (1996, Journal of the Korean History of Science Society, vol. I). For securely identified stars, we analyse its accuracy on the basis of comparison with data from the HC. The correlation of the errors between right ascensions and declinations is significantly deviated from spherical distribution. The magnitudes recorded in the NBGC correlate well with modern values. The accuracy of position decreases slowly with magnitude. Right ascensions and declinations have error distributions with ${\sigma}$ = 2.0' for the former while the latter with ${\sigma}$ = 1.6', but with much more errors >5' than expected for a Gaussian distribution.