• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1597-1610
• /
• 2022

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.211-214
• /
• 2005

There are emerging many eScience applications. More and more scientists want to collaborate on their investigation with international partners without space limitation by using these applications. Since these applications have to analyze the massive raw data, scientists need to send and receive the data in short time. So today's network related requirement is high speed networking. The key point of network performance is transport protocol. We can use TCP and UDP as transport protocol but we use TCP due to the data reliability. However, TCP was designed under low bandwidth network, therefore, general TCP, for example Reno, cannot utilize the whole bandwidth of high capacity network. There are several TCP variants to solve TCP problems related to high speed networking. They can be classified into two groups: loss based TCP and delay based TCP. In this paper, I will compare two approaches of TCP variants and propose a hybrid approach for high speed networking.

• Journal of Korean Society of Transportation
• /
• v.19 no.6
• /
• pp.7-17
• /
• 2001

The purpose of this paper is to develop automatic incident detection algorithm using image based detector in freeway management system. This algorithm was developed by using neutral network for high speed roadway and by using speed and occupancy variable for low speed roadway. The image detector system with the developed automatic incident detection algorithm can detect multi-lane as well as several detect areas for each lane. To evaluate this system, field tests to measure the detecting rate of incidents were performed with other systems which have APID and DES algorithm at high speed roadway(freeway) and low speed roadway(national arterial). As the results of field test, it found that the detect rate of this system was highest rate comparing to other two systems.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.64-71
• /
• 2010

When Handoff occurs at wireless network, existing AP search chooses one of various APs according to signal strength information. However, IEEE 802.11 uses Medium Access method with CSMA/CA that competes to obtain a channel by sharing medium. Therefore, network performance is heavily affected by the number of nodes and network congestion aside from signal strength. This scheme presented an additional AP selection indicator and a new handoff algorithm to realize handoff guaranteeing the network performance of mobile node in a process selecting new AP. This indicator is includes a handoff cost function reflecting the network information of mobile node, and the mobile node made handoff guaranteeing the network performance using network information possible by using this. also we classified the nodes into high-speed node and low-speed node. Then, when Handoff occurs, high-speed node was made itself choose AP by signal strength information. We also made the low-speed node choose its AP by using AP network information which is applied area. Hence, we demonstrate through simulation that gets an improvement in performance, even in the wireless network which many users concurrently access to, and it has considerable effects on aspects of resources and network management by distribution of users.

• Journal of Advanced Navigation Technology
• /
• v.11 no.2
• /
• pp.217-222
• /
• 2007

Recently PC games are trending toward online. But, mobile games are not using network actively. Because there are two problems that low speed of mobile network and low specification of mobile device in wireless internet environment. But, solving problems by these started HSDPA services and increased performance of devices. In this paper, we implement mobile on-line real time game for develop mobile network in wireless internet environment.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1274-1280
• /
• 2022

The resistance performance evaluation of general ships using computational fluid dynamics requires a lot of time and cost, and various methods are being studied to reduce the time and cost. Existing methods using main particulars or cross sections of ships have limitations in estimating resistance performance that is greatly dependent on the shape of the ship. In this paper, we propose a deep neural network model that can quickly predict the resistance performance of the hull surface by inputting the geometric information of the hullform mesh. The proposed deep neural network model based on Perceiver IO can immediately predict resistance performance, unlike computational fluid dynamics techniques that require calculation in each time step. It shows the result of estimating the resistance performance with an average error of less than 1% in the data set for a 50 K tanker ship, a type of low-speed full ship.

• Electronics and Telecommunications Trends
• /
• v.36 no.5
• /
• pp.92-102
• /
• 2021

Owing to various restrictions in-field application, the low-speed, low-power-based industrial Internet-of-Things (IoT) network built in extremely harsh industrial environment sites requires multi-hop, channel hopping, and low-latency transmission characteristics. In the past, wired networks were used in industrial facilities; however, network technologies based on the Industrial IoT Network standard standardized for industrial applications, such as WirelessIO link, WirelessHART, SmartMesh, and eStar Link satisfy industrial requirements. Recently, the use of industrial IoT networks in industrial facilities has rapidly expanded. This paper covers the developments in industrial IoT network technologies and summarizes the major industrial IoT standard technologies that meets the requirements of industrial sites.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.12
• /
• pp.1227-1236
• /
• 2012

The low speed machinery faults are usually caused by the bearing failure of the rolling elements. As the life time of the bearing is limited, the condition monitoring of bearing is very important to maintain the continuous operation without failures. A few monitoring techniques using time domain, frequency domain and fuzzy neural network vibration analysis are introduced to detect and diagnose the faults of the low speed machinery. This paper presents a method of fault detection for the rolling element bearing in the low speed machinery using the Wiener filtering and shock pulse counting techniques. Wiener filter is used for noise cancellation and it clearly makes the shock pulse emerge from the time signal with the high level of noise. The shock pulse counting is used to determine the various faults obviously from the shock signal with transient pulses not related with the bearing fault. Machine fault simulator is used for the experimental measurement in order to verify this technique is the powerful tool for the low speed machine compared with the frequency analysis. The test results show that the method proposed is very effective parameter even for the signal with high contaminated noise, speed variation and very low energy. The presented method shows the optimal tool for the condition monitoring purpose to detect the various bearing fault with high accuracy.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.857-860
• /
• 1991

This paper describes a High-Speed 8-bit Current-Mode BiCMOS A/D Converter. The characteristics of this A/D Converter are as fellows. First, as ADC is operating in current-mode we can obtain the properties of increase of converting speed, low noise, and wideband. Second, the properties of high switching speed in bipolar transistor and of high packing density, low power consumption in MOS trnsistor are combined. Finally we reduce chip area by designing it with subranging mode and improve the converting speed by performing subtraction directly, which doesn't need D/A convertings, using current switching element. This converter is composed of two 4-bit ADC, current soure array which provides signal and reference current, current comparator and encoding network.

• Journal of Power Electronics
• /
• v.6 no.1
• /
• pp.38-44
• /
• 2006

In this paper, a speed sensorless control for an ultrasonic motor (USM) using a neural network (NN) is presented. In the proposed method, rotor speed is estimated by a three-layer NN which adapts nonlinearities associated with load torque and motor temperature into control. The intrinsic properties of a USM, such as high torque for low speeds, high static torque, compact size, etc., offer great advantages for industrial applications. However, the speed property of a USM has strong nonlinear properties associated with motor temperature and load torque, which make accurate speed control difficult. These properties are considered in designing a control method through the application of mathematical models. In these strategies, a detailed speed model of the USM is required which makes actual applications impractical. In the proposed method, a three-layer NN estimates the speed of the USM from the drive frequency, the root mean square value of input voltage and the surface temperature of the USM, where no mechanical speed sensor is needed. The NN speed based estimator enables inclusion of variations in driving conditions due to input signals of the NN involved during the driving state of the USM. The disuse of sensors offers many advantages on both the cost and maintenance front. Moreover, the model free sensorless control method offers practical controller construction within a small number of parameters. To validate the proposed speed sensorless control method for a USM, experiments have been executed under several conditions.