Daesub Yoon

Driving characteristics analysis of young and middle-aged drivers

From the statistics about rental car accidents, traffic accident death by drunken driving, speeding, and centerline invasion occurs frequently to the twenties drivers compared with the other age groups. Specially, speeding is a dangerous driving behavior. In this paper, we analyzed driving characteristics of young and middle-aged drivers using FOT (Field of Test) data which was collected on the real urban, local road and highway. We performed independent samples t-test to know the difference of driving time, average speed and maximum speed dependent on ages and gender. We found that young male drivers drove more fast than middle-aged drivers on the local roads and highways. Also, we performed ANOVA analysis to know the speeding characteristics of drivers. The speeding time of young driver is longer than that of middle-aged driver on the local road and highway. The results of this study can be utilized in the device to limit the speed through monitoring the running speed of the driver. It can be derived indirectly safe driving services to reflect the speed factor of driver in the driving insurance fee calculation method.

Fusion of driver-information based driver status recognition for co-pilot system

This paper presents a driver status recognition method based on data fusion that changes the autonomous driving mode in our co-pilot system. Our research has the following two novelties: first, the fusion of information-based driver-status recognition between a direct method using the states of the drivers face and eyes and an indirect method of recognition based on the drivers driving patterns using vehicle information; and second, the ability to transfer from the driving mode to an autonomous mode through fusion of the information of the two methods. Four parameters are calculated in the fusion of these direct and indirect methods: the percent of eye closure, gaze direction, steering wheel angle, and vehicle speed. These parameters are combined to infer the level of drowsiness and attention dispersion of the driver. The system was tested under different circumstances for day and night driving conditions using different driving scenarios on a roadway. Our driver status recognition method utilized a smart device connected to our prototype autonomous vehicle.

Postal delivery area Management System

One of the important issues in postal business in Korea is to distribute the delivery areas equally and to calculate optimal delivery routes to reduce delivery cost. However, it is difficult problems because postal managers distribute the delivery areas by heuristic methods and postmen have simply decided optimal delivery routes b y the ir experiences. Also raw data of delivery activity log have not been collected systematically and have not been managed. Postal system could not calculate optimal solution due to small or absence of daily delivery log data. This paper describes the development of a system designed to create delivery area using building information and delivery route optimization: Postal delivery area Management System (PMS). Using a map data and openlayers library, the PMS provide function of creating delivery areas by selecting zone code and drawing polygon on the map. Also the PMS is able to calculate the shortest distance routes using the list of daily delivery addresses.

A Proposed Methodology for the Theory-Based Prediction of Mental Workload with a Cognitive Architecture:

In the early stage of system development, a prototype that is adequate for testing will be unavailable; then, it would be difficult to empirically predict mental workload through various measures. For this reason, task analytic methods based on task analysis probably have been the most popular for predicting mental workload though they are somewhat task-specific. A theory-based cognitive architecture could directly represent an operators cognitive processes and make predictions for cognitive activity in general situations at the sub-second scale. In this study, a methodology to predict the mental workload with a cognitive architecture is proposed. In empirical results, subjective measures of the mental workload with NASA-TLX were well matched with model predictions. It is suggested that the proposed method could be generally applied to predict mental workload in an early design phase.

Implementation of QoS-aware dynamic multimedia content adaptation system

The rapid evolution in the hardware sector brought up various end user devices like PDAs or cell phones on which online multimedia contents can be consumed. Due to different capabilities of these devices as well as individual user preferences, original multimedia resources have to be adapted in order to fit the specific constraints of such devices and to meet the user requirements. Adapting multimedia contents through user preferences is an important aspect of QoS (Quality of Service). There has been a vast amount of activities in research and standard development in this area. In this paper, we present methods for adapting multimedia contents to accommodate user preference. In addition, we propose a user preference content value model (u-CVM) that relates the content value of different modalities with resources. Implemented system shows that modality conversion brings a wider range of adaptation for QoS support. Moreover, the proposed approach is to be effective to apply in Digital Multimedia Broadcasting (DMB) and Telematics.

Learning control policy for parcel singulation

Parcel singulation is one of the key technology in the automated logistics process. In order to manipulate parcels independently, we propose to use sparse actuator array, which has advantages of cost reduction while the control of singulation is difficult because of actuator sharing. In this paper, intuitive control is introduced to make a bundle of parcels lined in order of priority, whose assignment function is learned from massive simulated episodes. Numerical simulation validates the proposed algorithm and the results show that the learning improves the singulation performance.

A real-time tracking system of postal motorcyclists

National postal services have developed tracking-enabled delivery management systems to provide improved service and more effective management of deliveries. This paper presents a real-time tracking system of postal motorcyclists that we developed with the support of funds from Korea Post. The system tracks movement of postmen during all their working hours and visualizes their delivery routes in real-time. To improve safety, the system also extracts a postmans driving patterns to identify any elements of risky driving.

Request Based Telematics Contents Providing System using DMB

This paper describes a system for providing the telematics contents through DMB, according to the requests which are demanded by users. This paper includes the structure of the system which collects the messages requested by users, and makes the list of requests priority, and broadcasts telematics contents through the data channel on DMB. This system enables users to receive the requested telematics contents which are categorized by regions and services. Therefore, the proposed structures help users to receive the distinctive DMB data services. Moreover, the system can reduce the amount of each service data as the service vendors increase the bandwidth of the content requested frequently within the limited bandwidth by collecting and analyzing the requested contents.