• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.277-282
• /
• 2006

It is well known that Kalman filtering is an optimal real-time data fusion method for GPS/INS integration. However, it has some limitations in terms of stability, adaptability and observability. A Kalman filter can perform optimally only when its dynamic model is correctly defined and the noise statistics for the measurement and process are completely known. It is found that estimated Kalman filter states could be influenced by several factors, including vehicle dynamic variations, filter tuning results, and environment changes, etc., which are difficult to model. Neural networks can map input-output relationships without apriori knowledge about them; hence a proper designed neural network is capable of learning and extracting these complex relationships with enough training. This paper presents a GPS/INS integrated system that combines Kalman filtering and neural network algorithms to improve navigation solutions during GPS outages. An Extended Kalman filter estimates INS measurement errors, plus position, velocity and attitude errors etc. Kalman filter states, and gives precise navigation solutions while GPS signals are available. At the same time, a multi-layer neural network is trained to map the vehicle dynamics with corresponding Kalman filter states, at the same rate of measurement update. After the output of the neural network meets a similarity threshold, it can be used to correct INS measurements when no GPS measurements are available. Selecting suitable inputs and outputs of the neural network is critical for this hybrid method. Detailed analysis unveils that some Kalman filter states are highly correlated with vehicle dynamic variations. The filter states that heavily impact system navigation solutions are selected as the neural network outputs. The principle of this hybrid method and the neural network design are presented. Field test data are processed to evaluate the performance of the proposed method.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.671-683
• /
• 2018

The flood damage caused by heavy rains in urban watershed is increasing, and, as evidenced by many previous studies, urban flooding usually exceeds the water capacity of drainage networks. The flood on the area which considerably urbanized and densely populated cause serious social and economic damage. To solve this problem, deterministic and probabilistic studies have been conducted for the prediction flooding in urban areas. However, it is insufficient to obtain lead times and to derive the prediction results for the flood volume in a short period of time. In this study, IDNN, TDNN and NARX were compared for real-time flood prediction based on urban runoff analysis to present the optimal real-time urban flood prediction technique. As a result of the flood prediction with rainfall event of 2010 and 2011 in Gangnam area, the Nash efficiency coefficient of the input delay artificial neural network, the time delay neural network and nonlinear autoregressive network with exogenous inputs are 0.86, 0.92, 0.99 and 0.53, 0.41, 0.98 respectively. Comparing with the result of the error analysis on the predicted result, it is revealed that the use of nonlinear autoregressive network with exogenous inputs must be appropriate for the establishment of urban flood response system in the future.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2014.06a
• /
• pp.107-108
• /
• 2014

As the demand for precise navigation has increased, more focus is put on the precise positioning, RTK(Real Time Kinematics) which has been used in the surveying field. The Position of Single Reference Station RTK or two-way network RTK such as VRS (Virtual Reference Station) is accurate enough to be used as a main technology in land surveying, however its service area and number of users is limited and the users are assumed static. This characteristic is not suitable to the navigation, whose service target is infinite number of users moving over a wide area. One-way network RTK has recently been suggested as a solution for the precise navigation technique for the mobile user. This paper shows the performance prediction of the one-way network RTK such as MAC(Master-Auxiliary Concept), or FKP (Flachenkorrekturparameter). To show the performance variation by the rover position, we constructed a simulation data of users on the grid with 0.1 degree spacing between 36.5 and 37 degree latitude and between 127 and 127.5 degree longitude.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.405-410
• /
• 2016

Elevator industry is a field that is mechanical, electrical and electronic technology and constantly requires inspection and maintenance considering various applications and various types. Recently, various elevator control and monitoring technologies with IT are developing for elevators on land. But technologies with IT have been hardly done in marine elevator that is consistently assured safety and reliability of life cycle for its parts in poor environment. In this paper, we implemented embedded main controller, floor controller and car controller that meet the requirements and use NMEA network protocol by analyzing home and abroad integrated elevator operation and management systems. Especially, we secured reliability of maintenance by real-time fault diagnosis and control that was implemented with limit switch, gyro sensor, temperature/humidity/barometric pressure sensor and fire detection sensor thinking over the environmental conditions of terrestrial and marine elevator.

• Convergence Security Journal
• /
• v.12 no.1
• /
• pp.49-54
• /
• 2012

Special applications designed for smart phone, so called "Apps" are rapidly emerging as unique and effective sources of environmental monitoring tools. Using the advantages of Information and Communication Technology (ICT), this paper propose an application that provides Indoor Gas Monitoring System. In this paper, use four wireless gas sensor modules to acquire sensors data wirelessly coupled with the advantages of existing portable smart device based on Android platform to display the real-time data from the sensor modules. Additionally, this paper adapts a simple gas classification algorithm to inform in-door Gas for users real-time based.

• Proceedings of the IEEK Conference
• /
• 2004.06a
• /
• pp.281-284
• /
• 2004

This paper presents the design and implementation of a QoS based enhanced collaboration system in MDO. This is an efficient distributed communication tool between designers. It supports text communication, audio/video communication, file transfer and XML data sending/receiving. Specially, this system supports a dynamic QoS self-adaptation by using the improved direct adjustment algorithm (DAA+). The original direct adjustment algorithm adjusts the transmission rate according to the congestion level of the network, based on the end to end real time transport protocol (RTP), and controls the transmission rate by using the information of loss ratio in real time transport control protocol (RTCP). But the direct adjustment algorithm does not consider when the RTCP packets are lost. We suggest an improved direct adjustment algorithm to solve this problem. We apply our improved direct adjustment algorithm to our of QoS (Quality of Service) [1] based collaboration system and show the improved performance of transmission rate and loss ratio.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.1
• /
• pp.9-15
• /
• 2018

This paper describes the applicability of Bluetooth and ZigBee networks for real-time control in wireless networked control system and suggests an effective usage of them. The Bluetooth SCO link, SPP and HID profiles and the ZigBee non-beacon enabled network are analyzed and the latency of them are measured. A number of wireless networked control system experiments are performed via DC motor control system and the various profiles of Bluetooth and ZigBee in real-time wireless networked control system are compared.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.6
• /
• pp.301-309
• /
• 2012

In this paper, a real-time monitoring system based on WSN is designed and implemented to monitor livestock growth environment information which includes the temperature, humidity and harmful gases such as $CO_{2},\;CO,\;NH_{3},\;H_{2}S$ and so on. The proposed system consists of the wireless sensor nodes, the monitoring management device, the management server and the user interface program based on PC/Smart phone. To verify the performance of the implemented system, gas measurement experiments are performed in laboratory environment by using the designed wireless sensor nodes. And it is able to estimate the concentration of gases. The implemented system is able to monitor the proposed environmental element information through the developed GUI.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.410-413
• /
• 2004

In this paper, a simulator system for Fuel Cell Hybrid Electric Vehicles(FCHEV) is implemented using DSP boards with CAN bus. The subsystems of a FCHEV i.e., the fuel cell system, the battery system, the vehicle dynamics with the transmission mechanism are coded into 3 DSP boards. The power distribution control algorithm and battery SOC control are also coded into a DSP board. The real-time monitoring program is also developed to examine the control performance of power control and SOC control algorithms.