• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.55-58
• /
• 2024

In this paper, we propose a design and implementation of big data-based fine dust anomaly detection machine learning system. The proposed is system that classifies the fine dust air quality index through meteorological information composed of fine dust and big data. This system classifies fine dust through the design of an anomaly detection algorithm according to the outliers for each air quality index classification categories based on machine learning. Depth data of the image collected from the camera collects images according to the level of fine dust, and then creates a fine dust visibility mask. And, with a learning-based fingerprinting technique through a mono depth estimation algorithm, the fine dust level is derived by inferring the visibility distance of fine dust collected from the monoscope camera. For experimentation and analysis of this method, after creating learning data by matching the fine dust level data and CCTV image data by region and time, a model is created and tested in a real environment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.9
• /
• pp.1027-1032
• /
• 2015

Using the radio wave, RFID(: Radio Frequency IDentification) wirelessly transmits the unique information saved in a tag attached on the specific object. In the construction area, the trend in using RFID for managing the input and inventory of the construction materials is upward. General management systems for the construction materials have only a function of identifying the tag attached on the construction materials, but the management system with a function of identifying and managing the location information of the construction materials employing RFID, for reusing it, is not actively developed. For the efficient reuse of the construction materials, in this paper, we propose the RFID system with a function of estimating and saving the location information of the specific construction materials, based on the estimated distances between the particular subs and reader. The proposed system consists of RFID reader, distance estimate, communication, and memory units.

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.564-573
• /
• 2015

GPS is the representative positioning technology for providing the location information. This technique has the disadvantage that does not operate in the shadow areas, such as urban or dense forest and the interior. This paper proposes a hybrid indoor positioning algorithm, which estimates a more accurate location of the terminal using strength of the Wi-Fi signal from the indoor AP. To determine the location of the user, we establish the most appropriate path loss model for the measurement environment. by using the RSSI value measured in a variety of environment such as building structure, person, distance, etc. The path loss exponent obtained by the path loss model is changed according to the environment. REKF, PF estimate the position of the terminal by using measured value from the AP with path loss exponent. For more accurate position estimation, we select positioning system by the value of threshold measured by experiments rather than a single positioning system. Experimental results using the proposed hybrid algorithm show that the performance is improved by about 17% than the conventional single positioning method.

• Tunnel and Underground Space
• /
• v.13 no.4
• /
• pp.294-303
• /
• 2003

The structural behaviour of rock mass structure, such as tunnel or slope is critically dependent on the various characteristics of discontinuities. Therefore, it is important to survey and analyze discontinuities correctly for the design and construction of rock mass structure. One inevitable Procedure of discontinuity survey and analysis is joint set identification from a lot of raw directional joint data. The identification procedure is generally done by a graphical method. This type of analysis has some shortcomings such as subjective identification results, inability to use extra information on discontinuity, and so on. In this study, a computer program for joint set identification based on the fuzzy clustering algorithm was implemented and tested using two kinds of joint data. It was confirmed that fuzzy clustering method is effective and valid for joint set identification and estimation of mean direction and degree of clustering of huge joint data through the applications.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.05a
• /
• pp.167-172
• /
• 2000

This paper is aimed at developing an location tracking for mobile station employing currently available mobile communication network of cellular phone and PCS(Personal Communication System). When the location tracking of mobile stations is in services, the services such as Emergency-119, crime investigation, effective urban traffic management or the safety protection of Alzheimer's patients, ran be available. This paper is to track the mobile station in communication network in NLOS environment. To achieve reduction of the standard noise, Kalman filter is used. In terms of the distance, positions are located by using TOA and TDOA methods in the environment that removes NLOS bias in the measured data. And then smoothing method is used. to achieve reduction of the position error values

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.551-560
• /
• 2011

Recently, There has been increasing concern about WLAN-based indoor positioning system. Most of the existing WLAN-based positioning systems use a fingerprinting method as a main approach. In the fingerprinting approach, the accuracy of the location of a mobile objects is proportional to the number of reference points. However, depending on the increasing number of reference points in the training phase, it requires more time and effort to create fingerprint database. To solve these problems, we propose the new indoor positioning algorithm that calculate the distance between a mobile objects and an AP using the information of surrounding environment WLAN based APs and applied the particle filter to the proposed algorithm in order to improve the accuracy of the estimated location in this paper. To implement this algorithm, at first environmental information database such as wall, iron door, glass door, partition etc. existing in the periphery of the AP should be established. The positioning use attenuation model and path loss model. Our experimental results with proposed algorithm are verified that the positioning accuracy was low but solved the problems with fingerprinting, compared with other positioning algorithms.

• Journal of Auto-vehicle Safety Association
• /
• v.5 no.1
• /
• pp.44-49
• /
• 2013

This paper presents a lateral collision risk index between an ego vehicle and a rear-side vehicle. The lateral collision risk is designed to represent a lateral collision risk and provide the appropriate threshold value of activation of the lateral collision management system such as the Blind Spot Detection(BSD). The lateral collision risk index is designed using the Time to Line Crossing(TLC) and the longitudinal collision index at the predicted TLC. TLC and the longitudinal collision index are calculated with the signals from the exterior sensor such as the radar equipped on the rear-side of a vehicle and a vision sensor which detects the distance and time to the lane departure. For the robust situation assessment, the perception of driving environment determining whether the road is straighten or curved should be determined. The relative motion estimation method has been proposed with the road information via the integrated estimator using the environment sensors and vehicle sensor. A lateral collision risk index was composed with the estimated relative motion considering the relative yaw angle. The performance of the proposed lateral collision risk index is investigated via computer simulations conducted using the vehicle dynamics software CARSIM and Matlab/Simulink.

• Animal cells and systems
• /
• v.16 no.4
• /
• pp.321-328
• /
• 2012

The oily bittering Acheilognathus koreensis is a freshwater species that is endemic to Korea and is experiencing severe declines in natural populations as a result of habitat fragmentation and water pollution. For the conservation and restoration of this species, it is necessary to assess its genetic diversity at the population level. We developed 13 polymorphic microsatellite loci that were used to analyze the genetic diversity of two populations collected from the Kum River and the Tamjin River in Korea. All loci exhibited Mendelian inheritance patterns when examined in controlled crosses. Both populations revealed high levels of variability, with the number of alleles ranging from 3 to 20 and observed and expected heterozygosities ranging from 0.500 to 0.969 and from 0.529 to 0.938, respectively. None of the loci showed significant deviation from Hardy-Weinberg equilibrium, and one pair of loci showed significant linkage disequilibrium after Bonferroni correction. Pairwise $F_{ST}$ and genetic distance estimation showed significant differences between two populations. These results suggest that the microsatellites developed herein can be used to study the genetic diversity, population structure and conservation measure of A. koreensis.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.2
• /
• pp.146-149
• /
• 2018

A monopulse sensor is used to estimate the angle of a target with respect to each received single pulse. It is well known that the cross-eye technique can result in an angle deception effect against monopulse sensors. To verify this effect, we propose a test environment configuration for the angle deception using monopulse receiving antennae and cross-eye transmitters in an anechoic chamber. Using the proposed test environment configuration, we have measured powers of the sum and difference of the signals received by the monopulse receiving antennae when the distance of the two cross-eye transmitters is varied. Finally, the angle deception performance related to the powers of the sum and difference signals was analyzed.

• Journal of the Korean Society of Groundwater Environment
• /
• v.6 no.3
• /
• pp.133-139
• /
• 1999

The geostatistical method Kriging is used to estimate the areal distributions of the depth to the water table and the altitude of the water table measured from the sea level. A northern part of the city of Pohang, Kyeong-Buk, Korea has been chosen and the digital map of the area with 1:5,000 scale from the National Geographic Information System (NGIS) project by National Geographic Institute has bun used to reproduce the ground surface distribution. The water table depth appears to be in the range between 7 m and 9.5 m except a few localities where mountain tops exist and the use of groundwater for agicultural purposes is believed to be heavy. The overall distribution of the water table altitude shows a monotonic gradual decrease from the west to the east (seaward direction from the inland) and to the south with maximum rate approximately at 90 m over 6 km in horizontal distance and indicates that the groundwater is moving several meters per day there.