• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.723-730
• /
• 2013

This paper presents the design of an arm gesture recognition system using Kinect sensor. A variety of methods have been proposed for gesture recognition, ranging from the use of Dynamic Time Warping(DTW) to Hidden Markov Models(HMM). Our system learns a unique HMM corresponding to each arm gesture from a set of sequential skeleton data. Whenever the same gesture is performed, the trajectory of each joint captured by Kinect sensor may much differ from the previous, depending on the length and/or the orientation of the subject's arm. In order to obtain the robust performance independent of these conditions, the proposed system executes the feature transformation, in which the feature vectors of joint positions are transformed into those of angles between joints. To improve the computational efficiency for learning and using HMMs, our system also performs the k-means clustering to get one-dimensional integer sequences as inputs for discrete HMMs from high-dimensional real-number observation vectors. The dimension reduction and discretization can help our system use HMMs efficiently to recognize gestures in real-time environments. Finally, we demonstrate the recognition performance of our system through some experiments using two different datasets.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.114-123
• /
• 2016

The effective feature extraction method for unmanned aerial vehicle (UAV) detection is proposed and verified in this paper. The UAV engine sound is harmonic complex tone whose frequency ratio is integer and its variation is continuous in time. Using these characteristic, we propose the feature vector composed of a mean and standard deviation of difference value between fundamental frequency with 1st overtone as well as mean variation of their frequency. It was revealed by simulation that the suggested feature vector has excellent discrimination in target signal identification from various interfering signals including frequency variation with time. By comparing Fisher scores, three features based on frequency show outstanding discrimination of measured UAV signals with low signal to noise ratio (SNR). Detection performance with simulated interference signal is compared by MFCC by using ELM classifier and the suggested feature vector shows 37.6% of performance improvement As the SNR increases with time, the proposed feature can detect the target signal ahead of MFCC that needs 4.5 dB higher signal power to detect the target.

• Review of Culture and Economy
• /
• v.19 no.2
• /
• pp.29-50
• /
• 2016

This paper is to apply an individual travel cost method(TCM) to estimate demand functions for cultural services enjoyed by visiting 3 branches of the National Museum of Modern and Contemporary Art located in the Seoul Metropolitan area. This paper extends the standard TCM by incorporating opportunity costs of leisure time and two different data generating process - 398 respondents from an on-site survey and 600 respondents from a general household survey. Negative binomial models reflecting the non-negative integer nature of visiting frequency with over-dispersed variance were best fitted for demand functions, in which residents of Seoul metropolitan area surveyed from on the site exhibited higher visitation demand for the national art museum. Price elasticity and income elasticity differed by respondents' residency. Price elasticity of long distance visitors (-0.21) was more inelastic from those of Seoul residents (-0.34 ~ -0.5). Moreover, regional residents outside of Seoul area seemed to consider that services from the national art museum is a normal good with income elasticity of 0.5, whereas the Seoul residents seemed to perceive it to be an inferior good with income elasticity of -0.05.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.10
• /
• pp.79-89
• /
• 2019

While most research focuses on the k-nearest neighbors (kNN) queries in the database community, an important type of proximity queries called k-farthest neighbors (kFN) queries has not received much attention. This paper addresses the problem of finding the k-farthest neighbors in road networks. Given a positive integer k, a query object q, and a set of data points P, a kFN query returns k data objects farthest from the query object q. Little attention has been paid to processing kFN queries in road networks. The challenge of processing kFN queries in road networks is reducing the number of network distance computations, which is the most prominent difference between a road network and a Euclidean space. In this study, we propose an efficient algorithm called FANS for k-FArthest Neighbor Search in road networks. We present a shared computation strategy to avoid redundant computation of the distances between a query object and data objects. We also present effective pruning techniques based on the maximum distance from a query object to data segments. Finally, we demonstrate the efficiency and scalability of our proposed solution with extensive experiments using real-world roadmaps.

• Journal of Positioning, Navigation, and Timing
• /
• v.7 no.4
• /
• pp.295-305
• /
• 2018

Network RTK is a highly practical technology that can provide high positioning accuracy at levels between cm~dm regardless of user location in the network by extending the available range of RTK using reference station network. In particular, unlike other carrier-based positioning techniques such as PPP, users are able to acquire high-accuracy positions within a short initialization time of a few or tens of seconds, which increases its value as a future navigation system. However, corrections must be continuously received to maintain a high level of positioning accuracy, and when a time delay of more than 30 seconds occurs, the accuracy may be reduced to the code-based positioning level of meters. In case of SSR, which is currently in the process of standardization for PPP service, the corrections by each error source are transmitted in different transmission intervals, and the rate of change of each correction is transmitted together to compensate the time delay. Using these features of SSR correction is expected to reduce the performance degradation even if users do not receive the network RTK corrections for more than 30 seconds. In this paper, the simulation data were generated from 5 domestic reference stations in Gunwi, Yeongdoek, Daegu, Gimcheon, and Yecheon, and the network RTK and SSR corrections were generated for the corresponding data and applied to the simulation data from Cheongsong reference station, assumed as the user. As a result of the experiment assuming 30 seconds of missing data, the positioning performance compensating for time delay by SSR was analyzed to be horizontal RMS (about 5 cm) and vertical RMS (about 8 cm), and the 95% error was 8.7 cm horizontal and 1cm vertical. This is a significant amount when compared to the horizontal and vertical RMS of 0.3 cm and 0.6 cm, respectively, for Network RTK without time delay for the same data, but is considerably smaller compared to the 0.5 ~ 1 m accuracy level of DGPS or SBAS. Therefore, maintaining Network RTK mode using SSR rather than switching to code-based DGPS or SBAS mode due to failure to receive the network RTK corrections for 30 seconds is considered to be favorable in terms of maintaining position accuracy and recovering performance by quickly resolving the integer ambiguity when the communication channel is recovered.

• Korean Journal of Ichthyology
• /
• v.31 no.3
• /
• pp.131-140
• /
• 2019

This study is to observe species identification and early life history of Gnathopogon strigatus and to use it as a basis for taxonomic studies and conservation of species. For the experiments, the mature adults were collected at the Wang-suk Stream located in Namyang-ju city, Gyeong-gi Province and eggs were artificially fertilized by the wet method in the laboratory. The shape of the fertilized egg was globular, adhesive, opaque white in color and had no oil globules. The fertilized egg was 1.66~1.88 mm (average 1.76 mm, n=30) in diameter. The blastular stage occurred at 3 hours 05 minutes after fertilization and the gastrular stage was detected at 8 hours 30 minutes after fertilization. The embryo began to hatch about 54 hrs after fertilization under water temperature of $23{\pm}1^{\circ}C$ and the newly hatched larva (yolksac larva) were 4.1~4.7 mm (mean 4.4 mm, n=20) in total length (TL). The fourth day after hatching, the postlarva were 5.4~5.9 mm (mean 5.6 mm, n=20) in total length, their york sacs were completely absorbed and Start eating Artemia sp. Ten days after hatching, flexion larva were begins Notochord flexion were 7.5~8.6 mm (mean 8.1 mm, n=20) in total length. Sixteenth day after hatching, postflexion larva were complete Notochord flexion were 8.2~9.7 mm (mean 9.1 mm, n=20) in total length. At thirty-eight days after hatching, Juvenile were arrive integer all fin rays and similar to those of adults were 11.3~15.5 mm (mean 13.3 mm, n=20) in total length.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.5
• /
• pp.467-474
• /
• 2019

In this paper, we propose a novel method to improve FPS while maintaining the accuracy of YOLO v2 model in NVIDIA Jetson TX1. In general, in order to reduce the amount of computation, a conversion to an integer operation or reducing the depth of a network have been used. However, the accuracy of recognition can be deteriorated. So, we use methods to reduce computation and memory consumption through adjustment of the filter size and integrated computation of the network The first method is to replace the $3{\times}3$ filter with a $1{\times}1$ filter, which reduces the number of parameters to one-ninth. The second method is to reduce the amount of computation through CBR (Convolution-Add Bias-Relu) among the inference acceleration functions of TensorRT, and the last method is to reduce memory consumption by integrating repeated layers using TensorRT. For the simulation results, although the accuracy is decreased by 1% compared to the existing YOLO v2 model, the FPS has been improved from the existing 3.9 FPS to 11 FPS.

• Journal of architectural history
• /
• v.28 no.5
• /
• pp.43-58
• /
• 2019

After the study of Fujishima Gaijiro(1930), although it is common to see that the Tang-ruler(唐尺) was used in the construction of the Silla Sacheonwangsa temple(679), the basis of the discrimination of the construction measure and the detection of the unit length is not actually sufficient since conventional research was done before the excavation. The study was based on archaeological results, which was secured through the excavation research(2006~2012) of the temple site in recent years, to determine the construction measure and try to detect the unit length. In the analysis of the measured value of the ruins, the numerical data were obtained through measurements on drawings of the ruins, the tendency of conversion measure's number appearing by dividing each unit length of the Goguryeo-ruler(高句麗尺) and Tang-ruler within a certain range was compared from the Wansu-je(完數制) viewpoint. The research results are summarized as follows : 1)As a result of the analysis of the distance between the site's center, the case that conversion Cheok's(尺) number is converged to the unit of Jang(丈) within the range of unit length expresses three times more in Tang-ruler, and it is confirmed that a simple multiple relationship based on the unit of Jang is established between conversion Cheok's number. 2)As a result of analysis of Bokan(梁間) of the each Corridor site and the measured value of the stonework ruins, it could be confirmed that appears overwhelmingly in the Tang-ruler when conversion Cheok's number becomes an integer within the range of unit length. The results of the analysis are judged to be a clear basis for viewing the Tang-ruler as the construction measure of the Sacheonwangsa temple. 3)The estimated unit lengths of the construction measure that were obtained from the analysis of the distance between the site'scenter, the foundation stone center distance of the building site and the measured value of the stonework ruins are slightly different. There is a limit to the verification of the construction error about this, however it is difficult to specify, it is mentioned 294.37mm which is obtained from the analysis of the distance between the site's center.

• Journal of Korea Trade
• /
• v.24 no.7
• /
• pp.1-28
• /
• 2020

Purpose - This paper empirically investigates the predictors and main determinants of consumers' ratings of mobile applications in the Google Play Store. Using a linear and nonlinear model comparison to identify the function of users' review, in determining application rating across countries, this study estimates the direct effects of users' reviews on the application rating. In addition, extending our modelling into a sentimental analysis, this paper also aims to explore the effects of review polarity and subjectivity on the application rating, followed by an examination of the moderating effect of user reviews on the polarity-rating and subjectivity-rating relationships. Design/methodology - Our empirical model considers nonlinear association as well as linear causality between features and targets. This study employs competing theoretical frameworks - multiple regression, decision-tree and neural network models - to identify the predictors and main determinants of app ratings, using data from the Google Play Store. Using a cross-validation method, our analysis investigates the direct and moderating effects of predictors and main determinants of application ratings in a global app market. Findings - The main findings of this study can be summarized as follows: the number of user's review is positively associated with the ratings of a given app and it positively moderates the polarity-rating relationship. Applying the review polarity measured by a sentimental analysis to the modelling, it was found that the polarity is not significantly associated with the rating. This result best applies to the function of both positive and negative reviews in playing a word-of-mouth role, as well as serving as a channel for communication, leading to product innovation. Originality/value - Applying a proxy measured by binomial figures, previous studies have predominantly focused on positive and negative sentiment in examining the determinants of app ratings, assuming that they are significantly associated. Given the constraints to measurement of sentiment in current research, this paper employs sentimental analysis to measure the real integer for users' polarity and subjectivity. This paper also seeks to compare the suitability of three distinct models - linear regression, decision-tree and neural network models. Although a comparison between methodologies has long been considered important to the empirical approach, it has hitherto been underexplored in studies on the app market.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.28 no.3
• /
• pp.183-192
• /
• 2022

With the growth of the packaging industry, demand on the packaging printing comes in various forms. Customers' orders are diversifying and the standards for quality are increasing. Offset printing is mainly used in the packaging printing since it is easy to print in large quantities. However, productivity of the offset printing decreases when printing various order. This is because it takes time to change colors for each printing unit. Therefore, scheduling that minimizes the color replacement time and shortens the overall makespan is required. By the existing manual method based on workers' experience or intuition, scheduling results may vary for workers and this uncertainty increase the production cost. In this study, we propose an automated scheduling method of parallel offset printing process for packaging printing. We decompose the original problem into assigning and sequencing orders, and ink arrangement for printing problems. Vehicle routing problem and assignment problem are applied to each part. Mixed integer programming is used to model the problem mathematically. But it needs a lot of computational time to solve as the size of the problem grows. So guided local search algorithm is used to solve the problem. Through actual data experiments, we reviewed our method's applicability and role in the field.