• The KIPS Transactions:PartC
• /
• v.13C no.4 s.107
• /
• pp.471-480
• /
• 2006

Recently, multimedia communication services, such as video conferencing and voice over IP, have been rapidly spread. H.323 is an international standard that specifies the components, protocols and procedures that provide multimedia communication services of real-time audio, video, and data communications over packet networks, including IP based networks. H.323 is applied to many commercial services because it supports various network environments and has a good performance. But communication services based on H.323 may have some problem because of current network trouble or mis-implementation of H.323. The understanding of this problem is a critical issue because it improves the quality of service and is easy to service maintenance. In this paper, we implement the analysis system for H.323 protocol wihch includes H.245, H.225.0, RTP, RTCP, and so on. Tills system is able to capture, parse, and present the H.323 protocol in real-time. Through the operation test and performance evaluation, we prove that our system is a useful to analyze and understand the problems for communication services based on H.323.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.4
• /
• pp.307-326
• /
• 2021

Real-time sea level observations from tide gauges include missing and erroneous values. Classification as abnormal values can be done for the latter by the quality control procedure. Although the 3𝜎 (three standard deviations) rule has been applied in general to eliminate them, it is difficult to apply it to the sea-level data where extreme values can exist due to weather events, etc., or where erroneous values can exist even within the 3𝜎 range. An artificial intelligence model set designed in this study consists of non-annotated recurrent neural networks and ensemble techniques that do not require pre-labeling of the abnormal values. The developed model can identify an erroneous value less than 20 minutes of tide gauge recording an abnormal sea level. The validated model well separates normal and abnormal values during normal times and weather events. It was also confirmed that abnormal values can be detected even in the period of years when the sea level data have not been used for training. The artificial neural network algorithm utilized in this study is not limited to the coastal sea level, and hence it can be extended to the detection model of erroneous values in various oceanic and atmospheric data.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.117-125
• /
• 2023

In the development of clothing design through virtual simulation, it is essential to minimize the differences between the virtual and the real world as much as possible. The most critical task to enhance the similarity between virtual and real garments is to find simulation parameters that can closely emulate the physical properties of the actual fabric in use. The simulation parameter optimization process requires manual tuning by experts, demanding high expertise and a significant amount of time. Especially, considerable time is consumed in repeatedly running simulations to check the results of applying the tuned simulation parameters. Recently, to tackle this issue, artificial neural network learning models have been proposed that swiftly estimate the results of drape test simulations, which are predominantly used for parameter tuning. In these earlier studies, relatively simple linear stiffness models were used, and instead of estimating the entirety of the drape mesh, they estimated only a portion of the mesh and interpolated the rest. However, there is still a scarcity of research on non-linear stiffness models, which are commonly used in actual garment design. In this paper, we propose a learning model for estimating the results of drape simulations for non-linear stiffness models. Our learning model estimates the full high-resolution mesh model of drape. To validate the performance of the proposed method, experiments were conducted using three different drape test methods, demonstrating high accuracy in estimation.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.5
• /
• pp.11-20
• /
• 2023

In this paper, we propose a novel deep learning-based motion reconstruction approach that facilitates the generation of full-body motions, including finger motions, while also enabling the online adjustment of motion generation delays. The proposed method combines the Vive Tracker with a deep learning method to achieve more accurate motion reconstruction while effectively mitigating foot skating issues through the use of an Inverse Kinematics (IK) solver. The proposed method utilizes a trained AutoEncoder to reconstruct character body motions using tracker data in real-time while offering the flexibility to adjust motion generation delays as needed. To generate hand motions suitable for the reconstructed body motion, we employ a Fully Connected Network (FCN). By combining the reconstructed body motion from the AutoEncoder with the hand motions generated by the FCN, we can generate full-body motions of characters that include hand movements. In order to alleviate foot skating issues in motions generated by deep learning-based methods, we use an IK solver. By setting the trackers located near the character's feet as end-effectors for the IK solver, our method precisely controls and corrects the character's foot movements, thereby enhancing the overall accuracy of the generated motions. Through experiments, we validate the accuracy of motion generation in the proposed deep learning-based motion reconstruction scheme, as well as the ability to adjust latency based on user input. Additionally, we assess the correction performance by comparing motions with the IK solver applied to those without it, focusing particularly on how it addresses the foot skating issue in the generated full-body motions.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.208-215
• /
• 2003

For playing a multimedia presentation in a Internet, the case that the presentation QoS(Quality of Services) at a destination nay be different from the QoS of multimedia data at the source occurs frequently. In this case, the process of trancoding the multimedia data at the source Into the multimedia data satisfying the QoS at the destination should be requited. In addition, even the presentation description having the homogeneous QoS at both sides may have different transcoding paths due to the limitation of display terminals or network bandwidth. That is, for a multimedia description, it is required to regenerate a proper transcoding path whenever the displaying terminals or the network environment gets decided. And the delay time required to go through the transcoding path may affect the playability of the give presentation. Therefore it should be checked whether the presentation requiring a transcoding process is able to be played in a real time. In this paper, the algorithm for generating all the possible transcoding paths for a given multimedia description under a fixed set of transcoders and the network environment is proposed. The algorithm adopts the concept of QoS transition diagram to Prevent from a trancoding Path being cycled by the repetition of a cyclic Path which generates the same QoS of multimedia data as its input QoS. By eliminating all the cyclic Paths, the algorithm can guarantee the termination of the process. And for the playability check, a method of computing the transcoding time and the delay lime between logical data units are proposed.Finally all the proposed methods were implemented in the stream engine, called TransCore and the presentation-authoring tool, called VIP, we had developed. And the test results with sample scenarios were presented at the last.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.4 no.3
• /
• pp.230-235
• /
• 2009

The TMO may contain two types of methods, time-triggered methods(also called the spontaneous methods of SpMs) which are clearly separated from the conventional service methods (SvMs). The SpM executions are triggered upon design time whereas the SvM executions are triggered by service request message from clients. In this paper, we describes the application environment as the patient monitor telemedicine system with TMO structure. Vital sign information web viewer systems is also the standard protocol for medical image and transfer. We have to design to obtain useful vital sign information, which is generated at parsing data receiver modulor of HIS with TMO structure, that is offered by the central monitor of ICU. In order to embrace new technologies as telemedicine service, it is important to develope the standard protocol between different systems in the hospital, as well as the communication with external hospital systems.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.166-168
• /
• 2014

Coarse-grained reconfigurable architectures (CGRAs) present a potential of high compute throughput with energy efficiency. A CGRA consists of an array of functional units (FU), which communicate with each other through an interconnect network containing transmission nodes and register files. To achieve high performance from the software solutions mapped onto CGRAs, modulo scheduling of loops is generally employed. One of the key challenges in modulo scheduling for CGRAs is to explicitly handle routings of operands from a source to a destination operations through various routing resources. Existing modulo schedulers for CGRAs are slow because finding a valid routing is generally a searching problem over a large space, even with the guidance of well-defined cost metrics. Applications in traditional embedded multimedia domains are regarded relatively tolerant to a slow compile time in exchange of a high quality solution. However, many rapidly growing domains of applications, such as 3D graphics, require a fast compilation. Entrances of CGRAs to these domains have been blocked mainly due to its long compile time. We attack this problem by utilizing patternized routes, for which resources and time slots for a success can be estimated in advance when a source operation is placed. By conservatively reserving predefined resources at predefined time slots, future routings originated from the source operation are guaranteed. Experiments on a real-world 3D graphics benchmark suite show that our scheduler improves the compile time up to 6000 times while achieving average 70% throughputs of the state-of-art CGRA modulo scheduler, edge-centric modulo scheduler (EMS).

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.149-158
• /
• 2005

The object of this paper is to develop the shortest path algorithm. The existing shortest path algorithm models are developed while considering travel time and travel distance. A few problems occur in these shortest path algorithm models, which have paid no regard to cognition of users, such as when user who doesn't have complete information about the trip meets a strange road or when the route searched from the shortest path algorithm model is not commonly used by users in real network. This paper develops a shortest path algorithm model to provide ideal route that many people actually prefer. In order to provide the ideal shortest path with the consideration of travel time, travel distance and road cognition, travel time is predicted by using Kalman filtering and travel distance is predicted by using GIS attributions. The road cognition is considered by using space data of GIS. Optimal routes provided from this paper are shortest distance path, shortest time path, shortest path considering distance and cognition and shortest path considering time and cognition.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.76-89
• /
• 2014

In this paper, we propose a MAC(Media Access Control) protocol based on flexible RWT(RTS Waiting Time) for underwater mobile ad-hoc networks with a three-way handshaking mechanism. This protocol can solve a problem of collision between RTS(Request-To-Send) and CTS(Clear-To-Send) packets in existing MACA(Multiple Access with Collision Avoidance) protocol. This proposed MAC protocol is also an effective protocol which can apply to underwater mobile ad-hoc networks in a real field by using implementable technologies. We set flexible RTS Waiting Time called RWT, considering various characteristics of underwater environment. It is possible to support variable network size according to node mobility. Finally, we conduct a performance evaluation between proposed MAC protocol and existing MACA based MAC protocol through practical implementation and experiment. As a result, we verify the superiority of our proposed MAC protocol in terms of throughput, packet drop rate, average transmission time, energy consumption and channel utilization.