• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.358-366
• /
• 2023

This study aimed to provide a solution for improving ship collision alert of the 'accident vulnerable ship monitoring service' among the 'intelligent marine traffic information system' services of the Ministry of Oceans and Fisheries. The current ship collision alert uses a supervised learning (SL) model with survey labels based on large ship-oriented data and its operators. Consequently, the small ship data and the operator's opinion are not reflected in the current collision-supervised learning model, and the effect is insufficient because the alarm is provided from a longer distance than the small ship operator feels. In addition, the supervised learning (SL) method requires a large number of labeled data, and the labeling process requires a lot of resources and time. To overcome these limitations, in this paper, the classification model of collision alerts for small ships using unlabeled data with the semi-supervised learning (SSL) algorithms (Label Propagation and TabNet) was studied. Results of real-time experiments on small ship operators using the classification model of collision alerts showed that the satisfaction of operators increased.

• Journal of Korean Society of Transportation
• /
• v.27 no.2
• /
• pp.207-214
• /
• 2009

This study proposed an advanced warning information system based on real-time traffic conflict analysis. An algorithm to detect and analyze unsafe traffic events associated with car-following and lane-changes using individual vehicle trajectories was developed. A positive guidance procedure was adopted to provide warning information to alert drivers to hazardous traffic conditions derived from the outcomes of the algorithm. In addition, autoregressive integrated moving average (ARIMA) analyses were conducted to investigate the predictability of warning information for the enhancement of information reliability.

• Journal of Computing Science and Engineering
• /
• v.2 no.2
• /
• pp.180-199
• /
• 2008

Technology has had a tremendous impact on our daily lives. Recently, technology and its impact on aging has become an expanding field of inquiry. A major reason for this interest is that the use of technology can help older people who experience deteriorating health to live independently. In this paper we give a brief review of the in-home monitoring technologies for the elderly. In the pilot study, we analyze the possibility of employing the data generated by a continuous, unobtrusive nursing home monitoring system for predicting elevated(abnormal)pulse pressure(PP) in elderly(PP=systolic blood pressure-diastolic blood pressure). Our sensor data capture external information(behavioral) about the resident that is subsequently reflected in the predicted PP. By continuously predicting the possibility of elevated pulse pressure we may alert the nursing staff when some predefined threshold is exceeded. This approach may provide additional blood pressure monitoring for the elderly persons susceptible to blood pressure variations during the time between two nursing visits. We conducted a retrospective pilot study on two residents of the TigerPlace aging in place facility with age over 70, that had blood pressure measured between 100 and 300 times during a period of two years. The pilot study suggested that abnormal pulse pressure can be reasonably well estimated (an area under ROC curve of about 0.75) using apartment bed and motion sensors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.65-68
• /
• 2005

Privacy preservation is crucial in ubiquitous computing environment in which lots of privacy- sensitive information can be collected and distributed without appropriate control. The anonymity-based approach is a famous one used for privacy preservation communication, which allows users to use pseudonyms instead of real ID so as not to reveal their identities. This approach is effective in that it can hide the identity of users. However, it makes it difficult to provide ID-based services like buddy service, dangerous area alert, P2P communication in the ubiquitous computing. We proposes a system architecture which enables ID-based services in the ubiquitous computing environment employing anonymity - based privacy - preserving approach.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.7
• /
• pp.673-678
• /
• 2013

Driving gear units can be affected by various problems, including those associated with external or internal defects in the bearing, problems with the lubricant oil, high-loading of the railway, and frequent impacts generated by rail joints. Temperature monitoring is a basic method in diagnosing abnormal conditions in the reduction gear and other components. This paper describes a new wireless monitoring system for the temperature diagnosis of abnormal conditions of the reduction gear. Integrated circuit (IC)-type temperature sensors were installed in the reduction gear box of a high-speed railway car. The temperature data from the reduction gear were acquired and analyzed in situ during high-speed rail operation. Analysis of these data was used to alert the driver and/or maintenance personnel when problems occurred.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.5
• /
• pp.283-290
• /
• 2012

In this paper, a system for wake-up method for T-DMB AEAS is introduced. Wake-up function is important in emergency alert service. But there was no AEAS receiver that has the method. Google C2DM is efficient method for wake-up in android platform. So this paper suggests wake-up method in android smartphone with T-DMB by C2DM. This method will be an alternative plan until native broadcasting wake-up technology.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.4
• /
• pp.673-680
• /
• 2010

The effects of different auditory warnings on response time and accuracy were studied in a laboratory ship-bridge work environment. Subjective preference on the type of auditory warnings was also of a primary concern. Twenty five subjects were asked to select an appropriate button for the warning sound presented with three types of auditory warning (abstract sound, auditory icon, and voice alarm) and five levels of warning situation (fire, steering failure, collision, engine failure, and low power). Results showed that the response time and accuracy was significantly affected by the types of auditory warning. The voice alarm resulted in a higher accuracy and subjective preference, as compared to the auditory icon and abstract sound. Regarding the response time, auditory icons and voice alarms were equivalent and superior to abstract sounds. Actual or potential applications of this research include guidelines for the design of integrated ship bridge systems.

• Journal of Advanced Navigation Technology
• /
• v.16 no.1
• /
• pp.163-170
• /
• 2012

This thesis suggests the application to the people who are using smart phone which is based on the Android operation system that makes it available to check their call and sms by a repeater and display in the limited places such as at the swimming pool or spa. This application is designed to save user's basic information. And when the user gets a call or a sms, it can make the sender number and fundamental information a data by PhonStateListener and SmsReceiver. The data is uploaded by bluetooth of a repeater. The smart phone user can use the repeater to check the received information by display.

• Journal of the Korean Solar Energy Society
• /
• v.31 no.5
• /
• pp.47-59
• /
• 2011

The purpose of this paper is to simulate the high ozone concentration in Shiwha Banwol indusrial complex. High pollution episodes (ozone alert) of this area are the results of geographical location and its air pollutants emission. This research has used meteorological model (RAMS) and photochemical air pollution Model (CIT model). As first step of the evaluate of this combined model system simulations are done in terms of meteorological characteristics like wind fields, PBL-height, etc.. Numerical simulations are carried out with real meteorological synoptic data on June. 24-25, 2010. In comparison with real measurement and another research the model reflects well local meteorological phenomena and shows the possibility to be utilized to analyse the pollutant dispersion over irregular terrain region. The high ozone concentration is deeply correlated to the ambient air temperature, wind speed and solar radiation. Local meteorological phenomena like sea-land breeze impact on horizontal dispersion of ozone. This analysis of meteorological characteristics can, in turn, help to predict their influences on air quality and to manage the high ozone episodes.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.29 no.3
• /
• pp.134-141
• /
• 2017

The purpose of this study was to analyze physiological changes via a cold air reaction experiment to generate basic data that are useful for the development of an automobile active air conditioning system to prevent drowsiness. The $CO_2$ concentration causing drowsiness in vehicle operation was kept below a certain level. Air was blown to the driver's face by using an indoor air cooling apparatus. Sleepiness and the arousal state of the driver in cold wind were measured by physiological signals. It was evident in the EEG that alpha waves decreased and beta waves increased, caused by cold air stimulation. The ${\alpha}/{\beta}$ ratio was reduced by about 52.9% and an alert state confirmed. In the electrocardiogram analysis, the efficiency of cold air stimulation was confirmed by the mean heart rate interval change. The R-R interval had a delay time of about one minute compared to the EEG response. The findings confirmed an arousal effect from sleepiness due to cold air stimulation.