• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.157-167
• /
• 2023

The use of big data for transportation often involves using data that includes personal information, such as the driver's driving routes and coordinates. This study explores the creation of a route choice prediction model using a large dataset from mobile navigation apps using federated learning. This privacy-focused method used distributed computing and individual device usage. This study established preprocessing and analysis methods for driver data that can be used in route choice modeling and compared the performance and characteristics of widely used learning methods with federated learning methods. The performance of the model through federated learning did not show significantly superior results compared to previous models, but there was no substantial difference in the prediction accuracy. In conclusion, federated learning-based prediction models can be utilized appropriately in areas sensitive to privacy without requiring relatively high predictive accuracy, such as a driver's preferred route choice.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.939-951
• /
• 2022

The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1446-1455
• /
• 2016

The recent increase of fresh farm products, hazardous cargos, and high-priced goods in marine transportation has caused an increased demand of cargo owners and shipping companies with regard to the monitoring of the location and state of cargo. To meet this increase, numerous technologies are being studied for the monitoring of the cargo state. Cargo containers on a ship are loaded on a ship's deck and in a ship's hold, which is located under the deck. However, Since the developed technologies mostly transfer the container status information that collected by mobile communication, it costs a lot to install communication infrastructure on ship. And the ship's hold is completely sealed with a cover, and communication with the reader positioned at the ship's bridge is difficult. Therefore, most existing studies on container monitoring on ships have focused on the monitoring of containers loaded on a ship's deck. Accordingly, this study suggested system configuration for the monitoring of containers in a ship's hold using IP-RFID technology. The suggested system configuration was tested on an actual ship under navigation, and the test results are given in this study. The test results verified that the monitoring of containers in a ship's hold using IP-RFID technology is effective.

• Journal of Korean Society of Transportation
• /
• v.33 no.2
• /
• pp.182-191
• /
• 2015

The Korean government introduced an automated speed enforcement system (ASES), which uses traffic enforcement cameras, to counteract safety issues that are caused by speeding. As the information of the traffic enforcement camera locations is provided to the drivers via navigation systems and mobile applications in a timely manner, drivers can avoid enforcement by momentarily diminishing their speeds only near the camera locations. To prevent drivers' evasional behavior and improve the effectiveness of ASES, section control, which enforces speeding vehicles by measuring their average travel speeds over a stretch of road and checking against the speed limit, has been recently implemented. In this study, Section Speed Enforcement Zone and Comparison Zone are compared in terms of traffic stream characteristics under free flow conditions. To this end, loop detector data were obtained from the three study sites and analyzed. The study results demonstrated that drivers maintain their speeds below the speed limit over the enforcement section with a lower variance of speeds.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.12
• /
• pp.2249-2260
• /
• 2017

IMO (International Maritime Organization) has been providing GMDSS (Global Maritime Distress and Safety System) and mandating to install distress and safety systems according to SOLAS. Digital-HF(High-Frequency) coast station communication system maintains interoperability between ship and coast station and digital data exchange in maritime mobile service by digitizing existing analog base voice communication. In this paper, we analyze ITU-R M. 1798-1 established by ITU for digital HF communications and propose Advanced annex2 and new Annex 5 to improve the problems of the existing Annex 2 and Annex 4. The proposed OFDM protocol basically adopts ARQ (Automatic Retransmission Request) which retransmits when an error occurs in a half-duplex manner between an information transmitting side (ISS) and an information receiving side (IRS) and we propose a digital HF communication system and its operational concept which is more reliable and superior than the existing ITU-R M. 1798 by implementing technical development on implementation and performance improvement.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.17
• /
• pp.7853-7857
• /
• 2015

Background: Mortality from breast cancer is high in low- and middle-income countries, in part because most patients have advanced stage disease when first diagnosed. Case-finding may be one approach to changing this situation. Materials and Methods: We conducted a pilot study to explore the feasibility of population-based case finding for breast cancer by community health workers (CHWs) using different data collection methods and approaches to management of women found to have breast abnormalities. After training 8 CHWs in breast problem recognition, manual paper data collection and operation of a cell-phone software platform for reporting demographic, history and physical finding information, these CHWs visited 3150 women >age 18 and over they could find-- from 2356 households in 8 villages in rural Bangladesh. By 4 random assignments of villages, data were collected manually (Group 1), or with the cell-phone program alone (Group 2) or with management algorithms (Groups 3 and 4), and women adjudged to have a serious breast problem were shown a motivational video (Group 3), or navigated/accompanied to a breast problem center for evaluation (Group 4). Results: Only three visited women refused evaluation. The manual data acquisition group (1) had missing data in 80% of cases, and took an average of 5 minutes longer to acquire, versus no missing data in the cell phone-reporting groups (2,3 and 4). One woman was identified with stage III breast cancer, and was appropriately treated. Conclusions: Among very poor rural Bangladeshi women, there was very limited reluctance to undergo breast evaluation. The estimated rarity of clinical breast cancer is supported by these population-based findings. The feasibility and efficient use of mobile technology in this setting is supported. Successor studies may most appropriately be trials focusing on improving the suggested benefits of motivation and navigation, on increasing the numbers of cases found, and on stage of disease at diagnosis as the primary endpoint.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.3-14
• /
• 2015

As buildings in the downtown area, such as the complex building connected to the skyscraper and the underground facility, have become large and complex, the range of target domain of the space information service is rapidly expanding to the interior space; it is considered that this change will create various demands of service such as the indoor geospatial information base safety, the management of facility, and the interior navigation in the future, along with spread of mobile devices and development of IT technology. As for the indoor geospatial information, however, there is no certification standard of the established indoor geospatial information data quality, so preparing the certification standard is urgent. Thus, this study reviewed foreign and domestic research cases and prepared measures for quality verification of the indoor geospatial information to conduct a verification test of the Yeongdeungpo Station indoor geospatial information, established in 2014. As a result, through the verification test of the method and standard of the indoor geospatial information quality certification suggested by this research, it was identified that the uniform and higher quality data could be classified, and the types of error high frequently occurring could be investigated. These results are expected to be utilized as the basic data for establishing quality certification system for the indoor geospatial information in the future.

• Spatial Information Research
• /
• v.18 no.2
• /
• pp.67-75
• /
• 2010

When people are shopping at a large shopping mall, they usually become to go around many stores for looking for better products and comparing them. In this paper, we design and implement a purchasing activity support system based on an Ambient Service Model that provides relevant stores information on map interface hierarchically through user contexts based search, to support such user's purchasing activities with the help of relevant information. In this system, users can search for relevant stores information through the system by Ambient Query which is created by their location and stores information with a mobile device. Then, users obtain relevant stores information provided in the form of hierarchy of keywords as a highly condensed summary and easily figure out the locations of the stores on a map interface. Moreover, users search additional other kinds of relevant stores information over the hierarchy of keywords. Eventually, users can obtain relevant stores information intuitively and conveniently without complex search processes. We implemented this system by integrating the subordinate technologies such as RFID, map-based, location-based and ontology technology. We also performed experiments on a well-known shopping region (Ilsan Lapesta shopping mall, Goyang-city Gyeonggi-do, Korea). Finally, we also confirmed that users' shopping activities were significantly improved by utility the present system.

• Journal of Practical Engineering Education
• /
• v.10 no.1
• /
• pp.17-24
• /
• 2018

Through the design and production of works for the third semester as a major unit, It is proposed the process of satisfying the graduation standards with the design and production process of the drone which can be applied to various mobile environments. Using the shape of Ring Propeller, it is made to be able to play both the role of generating lift as a propeller and the role of a wheel that touches the ground through the surface of the rim. In addition, the Servo Motor is used to convert the drive shaft of the motor to the correct angle according to the command. Then, based on the idea, the 3D printing is implemented to confirm the result of the configuration, and the circuit for driving the propulsion is designed and manufactured. As a result, the conversion of the desired propulsion system during air navigation and operation failed due to the weight increase of the propellant. It is confirmed that the size of the thrust and the tolerance limit of the ring propeller are the errors. Through these processes, it has been recognized to have experience of creative thinking and cooperation through engineering approach and comprehensive design, and confirmed to satisfy the graduation criteria by writing an engineering paper on the result.

• Archives of design research
• /
• v.18 no.2 s.60
• /
• pp.155-164
• /
• 2005

Home-service robots need to have sufficient spatial information about the surroundings for interacting with human intelligently and performing services efficiently. It is very important to investigate the efficient interaction style that supports map building task through human-robot collaboration. We first analyzed map building task with a cleaning robot and drew 4 design factors and tentative solutions, including map building procedure (task-preferred procedure/space- preferred procedure), LCD display installation (robot/robot+remote control), navigation method (push type/pull type), feedback modality(GUI/GUI+TTS). The design factors and tentative solutions were defined as independent variables and levels. This research investigated how those variables affect to the human task performance and behavior in map building tast. 8 kinds of experiment prototypes were built and usability test among 16 house wives was conducted for acquiring empirical data. As the experiment result, in terms of map building procedure, space-preferred procedure indicated better task performance than task-proffered procedure as we expected. For the LCD display installation factor, remote control with LCD display indicated higher task performance and subjective satisfaction. In robot navigation method, it was very difficult to find a significant difference between push type and pull type which contrary to our expectation. In fact, push type indicated higher subjective satisfaction. Also in feedback modality, we have acquired negative feedback an additional TTS operation guidance. It seems that robot's autonomy before achieving spatial information is rudiment condition which means users are just interacting with a mobile appliance. Thus they prefer remote-control-based interaction style in robot map building process as they used in traditional appliance control.