• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.768-783
• /
• 2020

Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship's drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.4 s.304
• /
• pp.59-68
• /
• 2005

In this paper, we design a PCI Express controller for future communication system The controller supports the full functionality of Transaction Layer and Data Link Layer of PCI Express. The designed controller has the proposed transmitter buffer architecture to obey Replay mechanism. This scheme merges the transmitting buffer and the replay buffer. The proposed buffer has the higher data transfer efficiency than the conventional buffer architecture because it can dynamically adjust size of a replay buffer space. We also design transmitter of Transmitter Transaction Layer to effectively support the proposed buffer, The receiver device of PCI Express must possess the buffer for three types of transaction to support Flow Control. And it must report the amount of the buffer space regularly to the Port at the opposite end of the link. We propose the simple receiver buffer scheme using only one buffer to easily support Flow Control. And the designed controller is verified under proposed test bench

• Journal of Digital Contents Society
• /
• v.16 no.3
• /
• pp.365-371
• /
• 2015

In wireless network, the amount of video streaming packet information in receiver replay buffer can be varied according tothe wireless network condition. By the effect, unforeseeable delay and jitter are generated and then busty video traffics can be made. If the amount of buffer information coming in receiver replay buffer is larger than the amount of a specific buffer information, buffer overflow is generated. Such a problem makes the image skip effect and packet loss, and then causes the quality degradation and replay discontinuity of the video streaming service in destination receiver. To solve the buffer overflow problem, this paper applies the token bucket for the busty traffic to the receiver terminal and analyzes the effect of the token bucket. The simulation result using NS-2 and JSVM shows that the proposed scheme with the token bucket has significantly better performance than the conventional scheme without the token bucket in terms of overflow generation number, packet loss rate and PSNR.

• Journal of Digital Contents Society
• /
• v.17 no.3
• /
• pp.135-142
• /
• 2016

When video service is performed in simulation using NS-2(Network Simulation-2), the video replay is performed as the received frame order. In the existing video replay method based on the received frame order, as the frame orders of receiver and transmitter are different, the receiver buffer does not have the effect that the packets between the frames of transmitter buffer holds a regular size and packet dense and sparsity phenomenon in the receiver buffer is made by the irregular packet size due to the unpredictable reversed order of received partial frames. The above dense and sparsity phenomenon increases the probability of buffer overflow and underflow generation. To prevent these problems, the proposed frame receive order relocation method adds an extra replay buffer which rearranges the order of receive frame as the order of transmit frame, so it has the effect that the packets between the transmit frames keeps a regular size. Through the simulation using NS-2 and JSVM(Joint Scalable Video Model), the generation number of buffer overflow and underflow, and PSNR(Required Peak Signal to Noise Ratio) performance between the existing method and proposed method were compared. As a result, it was found that the proposed method would have better performance than the existing method.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.101-110
• /
• 2009

The 6LoWPAN(IPv6 Low-power Wireless Personal Area Network) performs IPv6 header compression, TCP/UDP/IGMP header compression, packet fragmentation and re-assemble to transmit IPv6 packet over IEEE 802,15.4 MAC/PHY. However, from the point of view of security. It has the existing security threats issued by IP packet fragmenting and reassembling, and new security threats issued by 6LoWPAN packet fragmenting and reassembling would be introduced additionally. If fragmented packets are retransmitted by replay attacks frequently, sensor nodes will be confronted with the communication disruption. This paper analysis security threats introduced by 6LoWPAN fragmenting and reassembling, and proposes a re-transmission mechanism that could minimize re-transmission to be issued by replay attacks. Re-transmission procedure and fragmented packet structure based on the 6LoWPAN standard(RFC4944) are designed. We estimate also re-transmission delay of the proposed mechanism. The mechanism utilizes timestamp, nonce, and checksum to protect replay attacks. It could minimize reassemble buffer overflow, waste of computing resource, node rebooting etc., by removing packet fragmentation and reassemble unnecessary.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of Digital Contents Society
• /
• v.17 no.3
• /
• pp.181-188
• /
• 2016

Video streaming traffics which are arrived in receiver have irregular traffic patterns by many problems over the network path. Particularly, if these received traffics enter into replay buffer without any operation, the overflow and underflow effects are made according to the buffer status. There was an existing scheme which automatically set up token bucket parameters using the video information file under the assumption of the lossless packet on network. The existing scheme has a problem which can set up the wrong token bucket parameters by the lost packets on the practical networks with video packet loss. Therefore, this paper proposes a new scheme which reset up video file information to correct the wrong token bucket parameters in case of packet loss in practical networks with packet loss. Through the simulation, it was found that the proposed scheme would have better performance than the existing scheme in terms of overflow generation and packet loss.

• The KIPS Transactions:PartC
• /
• v.8C no.5
• /
• pp.647-656
• /
• 2001

Video delivery from a server to a client across a network system is an important part of many multimedia applications. Usually, the network system has constraint in both the amount of network bandwidth and the buffer size in the client. While delivering a video stream across such a constrained network system, loss of frames may be unavoidable. The system resources consumed by the dropped frames are wasted, and the losses of frames would result in discontinuous display at the client. In this paper, for delivering hierarchically encoded video stream, we introduce the notion of selective layer discard algorithm at the server which not only preemptively discards data at the server but also drops less important part of a frame instead of the entire frame. By the simulation, we compare the proposed selective layer discard algorithm and the existing selective frame discard algorithm. The simulation results show that the proposed algorithm may improve the quality of decoded video, and decrease the replay discontinuity at the client.

• Journal of Korea Multimedia Society
• /
• v.5 no.6
• /
• pp.697-703
• /
• 2002

In this paper, we propose the adaptive multi stream transmission technique based on SPIHT video signal for the highest quality service over the current Internet that does not guarantee QoS. In addition to the reliable transmission of the video stream over the asynchronous packet network, the proposed approach provides the transmission using the adaptive frame pattern control and multi steam over the TCP for continuous replay. The adaptive frame pattern control makes the transmission date scalable in accordance with the client's buffer status. Apart from this, the multi stream transmission improves the efficiency of video stream, and is robust to the network jitter problem, and maximally utilizes the bandwidth of the client's. As a result of the experiment, the DR(delay ratio) in the proposed adaptive multi-stream transmission is more close to zero than in the existing signal stream transmission, which enables the best-efforts service to be implemented.