• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.182-196
• /
• 2024

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.295-304
• /
• 2022

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s ( 4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2020

With the advent of high-speed railways, railways are one of the most frequently used means of transportation at home and abroad. In addition, in terms of environment, carbon dioxide emissions are lower and energy efficiency is higher than other transportation. As the interest in railways increases, the issue related to railway safety is one of the important concerns. Among them, visual abnormalities occur when various obstacles such as animals and people suddenly appear in front of the railroad. To prevent these accidents, detecting rail tracks is one of the areas that must basically be detected. Images can be collected through cameras installed on railways, and the method of detecting railway rails has a traditional method and a method using deep learning algorithm. The traditional method is difficult to detect accurately due to the various noise around the rail, and using the deep learning algorithm, it can detect accurately, and it combines the two algorithms to detect the exact rail. The proposed algorithm determines the accuracy of railway rail detection based on the data collected.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.113-127
• /
• 2015

Recently, there has been a growing interest in UAS(Unmanned Aerial System), and it is required to develop techniques to effectively detect water body from the recorded images in order to implement flood monitoring using UAS. This study used a UAS with RGB and NIR+RG bands to achieve images, and applied supervised classification method to evaluate the accuracy of water body detection. Firstly, the result for accuracy in water body image classification by RGB images showed high Kappa coefficients of 0.791 and 0.783 for the artificial neural network and minimum distance method respectively, and the maximum likelihood method showed the lowest, 0.561. Moreover, in the evaluation of accuracy in water body image classification by NIR+RG images, the magalanobis and minimum distance method showed high values of 0.869 and 0.830 respectively, and in the artificial neural network method, it was very low as 0.779. Especially, RGB band revealed errors to classify trees or grasslands of Songsan amusement park as water body, but NIR+RG presented noticeable improvement in this matter. Therefore, it was concluded that images with NIR+RG band, compared those with RGB band, are more effective for detection of water body when the mahalanobis and minimum distance method were applied.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.211-221
• /
• 2019

The death toll for every 10,000 cars registered in Korea is 1.4, which is still the lowest among OECD members, and the need for rescue and response systems is emerging. In response, the company is developing a vehicle ICT-based emergency rescue system (e-Call) that can handle accidents such as rapid and accurate life saving by automatically sending accident detection and related information to the central center in the event of a traffic accident. However, ordinary citizens are negative about the installation and cost of e-Call services. To solve these problems, various introduction and operation methods of e-Call were proposed for activation of terminal distribution. In addition, the effect of introducing e-Call was analyzed by predicting the penetration rate of e-Call terminals. Analysis shows that 463 to 926 deaths and 3,335 to 6,66.9 billion won will be saved in 10 years after the introduction of e-Call terminals.

• Ocean and Polar Research
• /
• v.44 no.4
• /
• pp.355-364
• /
• 2022

When the 60-ton-class patrol boat '72' of the Korea Coast Guard (KCG) was on duty and she accidentally collided with another patrol boat ('207', 200-ton-class) and sank. A month-long search found a small amount of lost items, but neither the crew nor the ship was found. For the first time in 39 years since the accident, the Korea Institute of Ocean Science and Technology (KIOST) searched the boat 72 using the latest integrated geophysical techniques. A number of sonar images presumed to be of a sunken ship was acquired using a combined system of side scan sonar and marine magnetometer, operated at an altitude of approximately 30 m from the seabed. At the same time, a strong magnetic anomaly (100 nT) was detected in one place, indicating the presence of an iron ship. A video survey using a remotely operated underwater vehicle (ROV) confirmed the presence of a shielding part of a personal firearm at the stern of the sunken vessel. Based on these comprehensive data, the sunken vessel discovered in this exploration was assumed to be '72'. This result is meaningful in terms of future ocean exploration and underwater archaeology, as the integrated system of various geophysical methods is an efficient means of identifying objects present in the water.

• Journal of Korean Society for Atmospheric Environment
• /
• v.34 no.3
• /
• pp.457-468
• /
• 2018

To improve understanding of the physico-chemical characteristics of aerosols in the national park and comparing the air pollution between national park and the urban area nearby national park, the aerosol characterization study was conducted in Bukhansan National Park, Seoul, from July through September 2017. Semi-continuous measurements of $PM_{2.5}$ using PILS (Particle Into Liquid System) coupled with IC (Ion Chromatography) and TOC (Total Organic Carbon) analyzer allowed quantification of concentrations of major ionic species($Cl^-$, $SO_4{^{2-}}$, $NO_3{^-}$, $Na^+$, $NH_4{^+}$, $K^+$, $Mg{^{2+}}$ and $Ca{^{2+}}$) and water soluble organic carbon (WSOC) with 30-minute time resolution. The total mass concentration of $PM_{2.5}$ was measured by T640 (Teledyne) with 5-minute time resolution. The black carbon (BC) and ozone were measured with a minute time resolution. The timeline of aerosol chemical compositions reveals a strong influence from urban area (Seoul) at the site in Bukhansan National Park. Inorganic aerosol composition was observed to be dominated by ammoniated sulfate at most times with ranging from $0.1{\sim}32.6{\mu}g/m^3$ (6.5~76.1% of total mass of $PM_{2.5}$). The concentration of ammonium nitrate, a potential indicator of the presence of local source, ranged from below detection limits to $20{\mu}g/m^3$ and was observed to be highest during times of maximum local urban (Seoul) impact. The total mass of $PM_{2.5}$ in Bukhansan National Park was observed to be 10~23% lower than the total mass of $PM_{2.5}$ in urban area (Gireum-dong and Bulgwang-dong, Seoul). In general, ozone concentration in Bukhansan National Park was observed to be similar or higher than urban sites in Seoul, suggesting additional biogenic VOCs with $NO_x$ from vehicle emission were to be precursors for ozone formation in Bukhansan National Park.

• Korean Journal of Clinical Pharmacy
• /
• v.8 no.2
• /
• pp.122-132
• /
• 1998

SB-31 which contains Pursatilla, Licoris and Ginseng extracts was recently proved as an anticancer agent. In a preclinical effort to be applied this drug to human, pharmacokinetics of SB-31 was carried out in rats and rabbits. Glycyrrhizin(GZ), a saponin of Licoris was used as a standard ingradient for the pharmacokinetics of SB-31. The rat's blood, bile and urine samples were serially collected in femoral vein, common bile duct and bladder, respectively, after bolus i.v. injection at a dose of 1 or 1/5 ampul/rat and rabbit's blood samples from the marginal ear vein at a dose of 1 or 3 amp./rabbit. GZ and glycyrrhetic acid(GA), a major metabolite of GZ in the physiological samples were analysed by HPLC with UV detection. The decline of GZ in plasma concentration was generally biexponential at each dose. GZ was almost completely recovered in bile within 18 hour. GA wasn't detected in the samples with UV detector. In the rat, Vss and Kel at a dose of 1 and 1/5 ampul of SB-31 were $98.06\pm6.07\;ml,\;0.33\pm0.05\;hr^{-1}\;and\;65.46\pm11.19\;ml,\;0.68\pm0.25\;hr^{-1}$, respectively. Those in rabbits at a dose of 3 and 1 ampul of SB-31 were $235.24\pm30.72\;ml,\;0.13\pm0.36\;hr^{-1}\;and\;341.32\pm28.58\;ml,\;0.27\pm0.04\;hr^{-1}$, respectively. 'WinNonlin' was utilized for the compartmental analysis. A two-compartment model was chosen as the most appropriate pbarmaco-kinetic model. The data were best described by using a weighting factor of $1/y^2$. To evaluate the effect of SB-31 on cardiovascular system, serially diluted SB-31 was directly injected into coronary artery in the isolated perfused rat heart and the effect of PSF, PSH, saponins of Pursatilla, and SB-31 on PT, APTT of healthy human plasma was examined. Except the positive inotropic effect of ten times diluted solution of SB-31, there was no significant effect on LVDP, (- dp/dt)/(+dp/dt), heart rate and coronary flow in comparision with that of vehicle. SB-31 had no effect on PT but slightly delayed APTT about $6.9{\sim}11.5\%$. There was no significant effect of PSF and PSH on PT & APTT. Conclusively, SB-31 did not show any notable toxic effects on cardiovascular system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.255-257
• /
• 2017

These days automotive markets are launching models that include a variety of IT technologies. Tesla's Tesla model S and Google's unmanned automobiles are emerging one after another. This type of automobile with IT technology provides various convenience to the driver and the driver is getting benefit by various conveience services. on the contrary, it is also true that defects for errors in electronic components cause accidents that threaten the safety of drivers. There is a sudden unintended acceleration among these accidents. The cause of the accident is not clear yet, but the claim that the ECU device caused by the magnetic field causes accident of the car due is the most reliable. But, in Korea, when occur a car sudden unintended acceleration accident, the char maker often claims that an accident occurred due to driver's pedal malfunction. Also most drivers are responsible for the lack of grounds to refute. In this paper, the pedal operation image of the driver is acquired and the sensor is attached to the control part such as the excel and brake so as to discriminate whether the vehicle sudden unintended acceleration accident is the driver's pedal operation error or the fault of. i have implemented a system that can do this.

• Journal of Convergence for Information Technology
• /
• v.9 no.9
• /
• pp.13-19
• /
• 2019

This paper analyzed the SCMS and pilot policy, which is pursued by the U.S. government in connected vehicles. SCMS ensures authentication, integrity, privacy and interoperability. The SCMS Support Committee of U.S. government has established the National Unit SCMS and is responsible for system-wide control. Of course, it introduces security policy, procedures and training programs making. In this paper, the need for SCMS to be applied to C-ITS was discussed. The structure of the SCMS was analyzed and the U.S. government's filot policy for connected vehicles was discussed. The discussion of the need for SCMS highlighted the importance of the role and responsibilities of SCMS between vehicles and vehicles. The security certificate management system looked at the structure and analyzed the type of certificate used in the vehicle or road side unit (RSU). The functions and characteristics of the certificates were reviewed. In addition, the functions of basic safety messages were analyzed with consideration of the detection and warning functions of abnormal behavior in SCMS. Finally, the status of the pilot project for connected vehicles currently being pursued by the U.S. government was analyzed. In addition to the environment used for the test, the relevant messages were also discussed. We also looked at some of the issues that arise in the course of the pilot project.