• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.751-762
• /
• 1998

The purpose of this study is to enhance the quality of multimedia service under the heterogeneous end-terminals and network environment by monitoring the data receiving status of the group members regularly when the sender multicasts real-time multimedia data to a group. Especially, it focuses to reduce the total number of status information responded to the sender from the receivers. Accordingly. it upgrades the sender's performance by suppressing the number of status information packets generated by the receivers. The key idea of this study starts from how we profile the activity of all the members in a group. We assume that the receiver status in the worst status, so called primary receiver, represents the status of the whole group. This means that the whole group is assumed as being degraded in performance if the primary receiver is degraded, and that the whole group is assumed as being upgraded if the primary one is upgraded. In this algorithm, the primary receiver announces its status information to the whole group prior to other receivers, ana every receiver listening to the primary and other receivers' status compares its own status with them. Accordingly, any receiver may give up the status notification in case its status is not worse than others, resulting in the reduction of unnecessary responses to the sender.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.514-520
• /
• 2018

Presence service provides various information about users such as locations, status of on/offline and network access methods, and number of presence resources required by each users increases largely in mobile environment. Therefore an effective method which can reduce load of presence servers is needed. In this paper, a large scale distributed presence service system which can distribute effectively total presence system load of presence servers using message control session has been presented. This large scale distributed presence service system provides various presence information for massive volumes of users. In this study, a new message control session architecture which can dynamically distribute loads of the presence servers to multiple servers has been presented, and a new presence information data architecture for controlling load of the presence servers has been designed. In this architecture, each presence server can exchange current load level in real time to get variance of the total system load change according to user numbers, and can distribute system load to maintain load level of each server evenly. The performance of the proposed large scale distributed presence service system has been analysed by experiments. The results has been showed that average presence resource subscription processing time reduced from 42.6% to 73.6%, and average presence notification processing time reduced from 37.6% to 64.8%.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.849-858
• /
• 2019

Recent developments in computer graphics technology and image processing technology have increased interest in point cloud technology for inputting real space and object information as three-dimensional data. In particular, point cloud technology can accurately provide spatial information, and has attracted a great deal of interest in the field of autonomous vehicles and AR (Augmented Reality)/VR (Virtual Reality). However, in order to provide users with 3D point cloud contents that require more data than conventional 2D images, various technology developments are required. In order to solve these problems, an international standardization organization, MPEG(Moving Picture Experts Group), is in the process of discussing efficient compression and transmission schemes. In this paper, we provide a region division transfer method of 3D point cloud content through extension of existing MPEG-DASH (Dynamic Adaptive Streaming over HTTP)-SRD (Spatial Relationship Description) technology, quality parameters are further defined in the signaling message so that the quality parameters can be selectively determined according to the user's request. We also design a verification platform for ROUTE (Real Time Object Delivery Over Unidirectional Transport)/DASH based heterogeneous network environment and use the results to validate the proposed technology.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.234-240
• /
• 2021

In this paper, the mask-based speech enhancement is improved for effective speech recognition in noise environments. In the mask-based speech enhancement, enhanced spectrum is obtained by multiplying the noisy speech spectrum by the mask. The VoiceFilter (VF) model is used as the mask estimation, and the Spectrogram Inpainting (SI) technique is used to remove residual noise of enhanced spectrum. In this paper, we propose a combined loss to further improve speech enhancement. In order to effectively remove the residual noise in the speech, the positive part of the Triplet loss is used with the component loss. For the experiment TIMIT database is re-constructed using NOISEX92 noise and background music samples with various Signal to Noise Ratio (SNR) conditions. Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI) are used as the metrics of performance evaluation. When the VF was trained with the mean squared error and the SI model was trained with the combined loss, SDR, PESQ, and STOI were improved by 0.5, 0.06, and 0.002 respectively compared to the system trained only with the mean squared error.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.134-139
• /
• 2021

Currently, the autonomous vehicle market is commercializing a level 3 autonomous vehicle, but it still requires the attention of the driver. After the level 3 autonomous driving, the most notable aspect of level 4 autonomous vehicles is vehicle stability. This is because, unlike Level 3, autonomous vehicles after level 4 must perform autonomous driving, including the driver's carelessness. Therefore, in this paper, we propose the Emergency-notification and Driver-response Confirmation System(EDCS) for an autonomousvehicle safety that notifies the driver of an emergency situation and recognizes the driver's reaction in a situation where the driver is careless. The EDCS uses the emergency situation delivery module to make the emergency situation to text and transmits it to the driver by voice, and the driver response confirmation module recognizes the driver's reaction to the emergency situation and gives the driver permission Decide whether to pass. As a result of the experiment, the HMM of the emergency delivery module learned speech at 25% faster than RNN and 42.86% faster than LSTM. The Tacotron2 of the driver's response confirmation module converted text to speech about 20ms faster than deep voice and 50ms faster than deep mind. Therefore, the emergency notification and driver response confirmation system can efficiently learn the neural network model and check the driver's response in real time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.77-83
• /
• 2020

The heat treatment facility is in a situation where the scope of application of the remote IOT system is expanding due to the harsh environment caused by high heat and long working hours among the root industries. In this heat treatment process environment, the IOT middleware is required to play a pivotal role in interpreting, managing and controlling data information of IoT devices (sensors, etc.). Until now, the system controlled by the heat treatment remotely was operated with the command of the operator's batch system without overall monitoring of the site situation. However, for the safety and precise control of the heat treatment facility, it is necessary to control various sensors and recognize the surrounding work environment. As a solution to this, the heat treatment safety support system presented in this paper proposes a support system that can detect the access of the work manpower to the heat treatment furnace through thermal image detection and operate safely when ordering work from a remote location. In addition, an OPEN CV-based deterioration analysis system using DNN deep learning network was constructed for faster and more accurate recognition than general fixed hot spot monitoring-based thermal image analysis. Through this, we would like to propose a system that can be used universally in the heat treatment environment and support the safety management specialized in the heat treatment industry.

• Journal of Internet of Things and Convergence
• /
• v.6 no.4
• /
• pp.89-92
• /
• 2020

According to the various IoT(Internet of Things) services, there have been lots of task offloading researches for IoT devices. Since there are service response delay and core network load issues in conventional cloud computing based offloadings, fog computing based offloading has been focused whose location is close to the IoT devices. However, even in the fog computing architecture, the load can be concentrated on the for computing node when the number of requests increase. To solve this problem, the opportunistic fog computing concept which offloads task to available computing resources such as cars and drones is introduced. In previous fog and opportunistic fog node researches, the offloading is performed immediately whenever the service request occurs. This means that the service requests can be offloaded to the opportunistic fog nodes only while they are available. However, if the service response delay requirement is satisfied, there is no need to offload the request immediately. In addition, the load can be distributed by making the best use of the opportunistic fog nodes. Therefore, this paper proposes a delayed offloading scheme to satisfy the response delay requirements and offload the request to the opportunistic fog nodes as efficiently as possible.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.319-325
• /
• 2022

The variation of utterance lengths is a representative factor that can degrade the performance of speaker verification systems. To handle this issue, previous studies had attempted to extract speaker features from various branches or to use convolution layers with different receptive fields. Combining the advantages of the previous two approaches for variable-length input, this paper proposes integrated receptive field diversification that extracts speaker features through more diverse receptive field. The proposed method processes the input features by convolutional layers with different receptive fields at multiple time-axis branches, and extracts speaker embedding by dynamically aggregating the processed features according to the lengths of input utterances. The deep neural networks in this study were trained on the VoxCeleb2 dataset and tested on the VoxCeleb1 evaluation dataset that divided into 1 s, 2 s, 5 s, and full-length. Experimental results demonstrated that the proposed method reduces the equal error rate by 19.7 % compared to the baseline.