• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.11
• /
• pp.1008-1016
• /
• 2015

This paper proposes a method for detecting the front side of vehicles. The method can find the car side with a license plate even with complicated and cluttered backgrounds. A convolutional neural network (CNN) is used to solve the detection problem as a unified framework combining feature detection, classification, searching, and localization estimation and improve the reliability of the system with simplicity of usage. The proposed CNN structure avoids sliding window search to find the locations of vehicles and reduces the computing time to achieve real-time processing. Multiple responses of the network for vehicle position are further processed by a weighted clustering and probabilistic threshold decision method. Experiments using real images in parking lots show the reliability of the method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1691-1697
• /
• 2018

There has been a steady study of unmanned vehicle. So far, continuous research has brought news of the commercialization of unmanned vehicle. In addition, it has been applied in a variety of fields with another industry. A lot of research has been done, too, to apply inert driving indoors. Using LoRa network, which is a network dedicated to IoT, unmanned vehicle control system that is applied to LoRa network from a small space, or from an office hospital to a factory, is installed to increase efficiency when the performs special tasks. This paper presents solutions to a variety of problems by using LoRa network, which is dedicated to IoT, to recognize an unmanned vehicle as a single object, to communicate with surrounding objects, and to receive information necessary for driving indoors from a cloud server.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.21 no.2
• /
• pp.151-155
• /
• 2008

KHST(Korean High Speed Train) has been utilized the total measurement system which evaluates the efficiency and a breakdown of the vehicle and it's results effect to secure reliability of the vehicle. Generally KHST has been received pulse signals from the wheel. It calculates the travel distance after counter the signals to confirm location information of the vehicle. However, there is a limit to measure the location of the vehicle due to slip, slide and the wheel attrition. We have developed a new measurement system by using GPS to complement those errors. In general, GPS receivers are composed of an antenna, tuned to the frequencies transmitted by the satellites, receiver-processors, and a highly-stable clock The GPS mounted on the roof of TT4 in KHST receives a signal from the RS232 communication port. It is connected to the network system in TT3 after converting with TCPIP communication. It is able to track the position of vehicle and synchronize the signal from different measurement system simultaneously. Therefore it is able to chase the fault occurrence, track inspection and electrical interruption at real-time situation more accurately. There is not an error coursed by vehicle conditions such as slip and the slide.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.5
• /
• pp.48-55
• /
• 2007

A bushing component of a vehicle suspension system is tested to capture the nonlinear behavior of rubber bushing element using the MTS 3-axes rubber test machine. The results of the tests are used to model the artificial neural network bushing model. The performances from the neural network model usually are dependent on the structure of the neural network. In this paper, maximum error, peak error, root mean square error, and error-to-signal ratio are employed to evaluate the performances of the neural network bushing model. A simple simulation is carried out to show the usefulness of the developed procedure.

• Journal of Navigation and Port Research
• /
• v.28 no.3
• /
• pp.227-232
• /
• 2004

Vehicle dynamics control systems are complex and non-linear, so they have difficulties in developing a controller for the anti-lock braking systems and the auto-traction systems. Currently the fuzzy-logic technique to estimate the absolute vehicle speed supplies good results in normal conditions. But the estimation error in severe braking is discontented In this paper, we estimate the absolute vehicle speed of UCT(Unmanned Container Transporter) by using the wheel speed data from standard anti-lock braking system wheel speed sensors. Radial symmetric basis function of the neural network model is proposed to implement and estimate the absolute vehicle speed, and principal component analysis on input data is used 10 algorithms are verified experimentally to estimate the absolute vehicle speed and one of them is perfectly shown to estimate the vehicle speed within 4％ error during a braking maneuver.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.16 no.2
• /
• pp.115-124
• /
• 2003

In this paper, the effects of vehicle loads on flat slab system are investigated on the basis of the previous studies for beam-gilder parking structural system. The influence surfaces of flat slab for a typical design section are constructed lot the purpose of obtaining maximum member forces under vehicle loads. In addition, the equivalent vehicle load factors for flat slab parking structures are suggested using artificial neural network. The network responses we compared with the results obtained by numerical analyses to verify the validation of Levenberg-Marquardt algorithm adopted as training method in this Paper. Many parameter studies for the flat slab structural system show dominant vehicle load effects at the center positive moments in both column and middle strips, like the beam-girder parking structural system.

• Journal of Korean Society of Transportation
• /
• v.28 no.4
• /
• pp.141-156
• /
• 2010

In this paper, understanding there is a limitation with a comprehensive and network approach for the evaluation of existing vehicle and pedestrian environments, the authors focus on developing an integrated approach to assessing these environments. The network evaluation here means the assessment at a three-dimensional level that includes evaluation methods of lines/axes in a spatial concept as well as integration of evaluation indicators being used for vehicles and the walking environment. Grey System Theory (GST) was applied based on the theoretical background for network and comprehensive integrated evaluation, and the evaluation of the vehicle and pedestrian environment was performed by assigning target areas to walking preference zones. As a result of the comprehensive evaluation and analysis by GST, even if the service level is the same as the operating indicators (Highway Capacity Manual) of the vehicle and pedestrian environment, or relatively better, it was identified that the total score could be varied over Grey Category because the observed data are calculated after considering the weights between evaluation indicators by the range of Grey Category on the comprehensive evaluation. Considering comprehensively these points, although the indicators on the operation of roads are relatively good, in the event that the indicators on the safety of roads are bad, it was known that the scores over Grey Category also could be changed. The result is that this evaluation method can be used to evaluate the network concept per lane (per axis) as well as to diagnose the current state by type of urban street in the future.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1107-1109
• /
• 1996

In this paper, we discuss the automatic recognition system of vehicle types and licence plate numbers using artificial neural networks, which will be used as vehicle identifier. We confine to expose the vehicle licence number for violating bus lane and stolen cars. Therefore, the vehicle height, width and distribution profile are used as the feature parameters of vehicle type. This system is composed of two parts: one is an image preprocessor of vehicle images and the other one is a pattern classifier by neural networks. The experimental results show that our method has good results for the recognition of vehicle types and numbers.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.5
• /
• pp.1049-1057
• /
• 2017

In-vehicle multimedia systems are one of the most important factors in the automotive industry. Especially, multimedia systems are more important in advanced commercial vehicles such as premium express buses. In this paper, we proposed a multimedia streaming system architecture using MEP(MOST Ethernet Packets) for premium express buses based on MOST150. We have designed and implemented the prototype of proposed multimedia streaming system. We have designed a board based on i.MX6 to operate a proposed multimedia streaming system. The software has designed a multimedia system for premium express buses based on Android which is an open source platform. MOST(Media Oriented Systems Transport) is a high-speed multimedia network technology for in-vehicle multimedia system. The MOST network is able to manage up to 64 devices and ring topology is used basically. In addition, the MOST Network meets EMI(Electro-Magnetic Interference)/ EMC(Electro-Magnetic Compatibility) requirements because it uses plastic optical fibers(POF).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.107-109
• /
• 2022

This paper proposes a new security system to detect cyber-attacks based on message authentication in a in-vehicle network. In the in-vehicle network, when a sending node transmits messages in a broadcast manner, it only uses a message identifier, rather than a node's identifier. It leads to a problem not identifying the source. In the proposed system, the sending node generates a message authentication code (MAC) using a cryptographic hash function to the control data and transmits it with the control data. When generating the MAC for each message, a multidimensional chaotic map is applied to increase the randomness of the result. The receiving node compares its MAC generated from the control data in the received message with the MAC of the received message to detect whether the message transmitted from the sending node is forged or not. We evaluate the performance of the proposed system by using CANoe and CAPL (Communication Access Programming Language). Our system shows a 100% of detection rate against cyber-attacks injected.