• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.92-101
• /
• 2015

As one type of power quality (PQ) disturbance sources, high-speed rail (HSR) can have major impacts on the power supply grid. Providing timely and accurate warning information for PQ problems of HSR is important for the safe and stable operation of traction power supply systems and the power supply grid. This study proposes a novel warning approach to identify PQ problems and provide warning prompts based on the monitored data of HSR. To embody the displacement and status change of monitored data, multi-features of different sliding windows are computed. To reflect the relative importance degree of these features in the overall evaluation, an analytic hierarchy process (AHP) is used to analyse the weights of multi-features. Finally, a multi-features similarity algorithm is applied to analyse the difference between monitored data and the reference data of HSR, and PQ warning results based on dynamic thresholds can be analysed to quantify its severity. Cases studies demonstrate that the proposed approach is effective and feasible, and it has now been applied to an actual PQ monitoring platform.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.2
• /
• pp.15-21
• /
• 2018

In this paper, a detection and warning system is proposed for the remaining kids in a school bus. For detecting the remaining kids, an ultrasonic sensor is used. The basic experiments of the ultrasonic sensor are performed, and a modified ultrasonic sensor is proposed. Also, the appropriate location of the ultrasonic sensor is proposed by considering various sitting positions. Based on the above kid detection system, a warning algorithm is designed. Using the above detection and warning system, experiments are performed. From the experimental results, it is found that the proposed system, based on the modified ultrasonic sensor, can detect the remaining kids in a school bus. The proposed system can also give an appropriate warning signal.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.6
• /
• pp.2793-2800
• /
• 2011

The purpose of this research is to develop and optimize a lane departure warning application based on a smartphone which can be applicable as a new platform for various mobile information applications. Recently, a lane detection warning system which is a representative application among safe driving assistant solutions is being commercialized. Due to the necessity of powerful embedded hardware platform and its price, its market is still not growing. In this research, it is proposed to develop and optimize a lane departure warning application on iPhone 3GS. OpenCV is used for efficient image processing, and for lane detection a heuristic algorithm based on Hough Transform is proposed. The application was developed under Macintosh PC platform with Xcode 3.2.4 development tools, downloaded to the iPhone and has been tested on the real paved road. The experimental result has shown that the detection ratio of the straight lane was over 90% and the processing speed was 1.52fps. For the enhancement of the speed, a few optimization methods were introduced and the fastest speed was 3.84fps. Through the improvement of lane detection algorithm, additional optimization works and the adoption of a new powerful platform, it will be successfully commercialized on smartphone application market.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.11
• /
• pp.2069-2076
• /
• 2008

In this paper, we develop an electrostatic monitoring system which is composed of an electrostatic prediction system and a warning message transmission system. The electrostatic prediction system in a factory receives the value of electrostatic charge from the electrostatic sensor and predicts the next value by using past data and sends the value to the warning message transmission system through the bluetooth communication. The warning message transmission system gets a warning signal and transmits the warning message to the worker's cellphone through a commercial SMS web by a socket program running on Windows PC in a control room. We propose electrostatic forecasting algorithms based on LSR(least square regression) using weight factors in an electrostatic prediction system. Simulation results show that the algorithm with dynamically variable weight factors is best with 64.69V standard deviation and a warning message transmitted by the warning message transmission system is displayed on cellphone after about 5 seconds.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.19-22
• /
• 2009

This thesis offers forecast & warning algorithm about the accessing networks though statistical sampling methods to prevent computer terrors. These networks are occurred among U-city network groups. The main characteristic of current computer attacks is avoiding well-known detection patterns by successive changes in spreading speeds and attacking codes. The improvement of attacking stills leads to a problem causing the defense-time delay and creates vicious cycle that tries to fix networks after damage. Proposed algorithm notices and warns the potential attacking areas through defecting previous attacking signs, analysing attaching results ed tracing attaching sources at the beginning of the attack.

• Journal of Mechanical Science and Technology
• /
• v.15 no.9
• /
• pp.1248-1256
• /
• 2001

In this study, a test bed for vehicle longitudinal control is developed using a chassis dynamometer and real time 3-D graphics. The proposed test bed system consists of a chassis dynamometer on which test vehicle can run longitudinally, a video system that shows virtual driver view, and computers that control the test vehicle and realize the real time 3-D graphics. The purpose of the proposed system is to test vehicle longitudinal control and warning algorithms such as Adaptive Cruise Control(ACC), stop and go systems, and collision warning systems. For acceleration and deceleration situations which only need throttle movements, a vehicle longitudinal spacing control algorithm has been tested on the test bed. The spacing control algorithm has been designed based on sliding mode control and road grade estimation scheme which utilizes the vehicle engine torque map and gear shift information.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.389-389
• /
• 2000

The number of automobiles is rapidly increasing , as are the importance of the car as a way of transportation, and the variety of its uses. In these surroundings, a safety, one of the primary factors which must be considered in automotive engineering, demands a system that aids the driver's vision and perception. In this point of view, development of the more promoted system that complement the existing passive method which relies on just man's ability is the important issue of the advanced traffic system including ITS. In this paper, we provide an algorithm and implementation of a control system that warns the collisions ahead and avoids this situation, using informations about the host-car, target-car and surroundings. The warning is made by an algorithm that decides the degree of safely. With this degree of safely, the controller automatically controls a vehicle's speed to a proper level.

• 한국ITS학회:학술대회논문집
• /
• 2003.11a
• /
• pp.275-279
• /
• 2003

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.223-229
• /
• 2008

In this paper. we propose the real-time vision system which judges drowsiness driving based on levels of drivers' fatigue. The proposed system is to prevent traffic accidents by warning the drowsiness and carelessness using face-image analysis and fuzzy logic algorithm. We find the face position and eye areas by using fuzzy skin filter and virtual face model in order to develop the real-time face detection algorithm, and we measure the eye blinking frequency and eye closure duration by using their informations. And then we propose the method for estimating the levels of drivel's fatigue based on measured data by using the fuzzy logic and for deciding whether drowsiness driving is or not. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.2
• /
• pp.25-31
• /
• 2019

As artificial intelligence technology has been developed rapidly, many researchers who are interested in next-generation vehicles have been studying on applying the artificial intelligence technology to advanced driver assistance systems (ADAS). In this paper, a method of applying deep learning algorithm to the lane departure warning system which is one of the main components of the ADAS was proposed. The performance of the proposed method was evaluated by taking a comparative experiments with the existing algorithm which is based on the line detection using image processing techniques. The experiments were carried out for two different driving situations with image databases for driving on a highway and on the urban streets. The experimental results showed that the proposed system has higher accuracy and precision than the existing method under both situations.