• The KIPS Transactions:PartA
• /
• v.8A no.4
• /
• pp.287-292
• /
• 2001

Multimedia service systems should have efficient capacity to serve the growing clients and new data. In the general streaming services, users can endure the small amount of time delay at the beginning of service. But they want to have good quality of service. A streaming server tries to transfer video files to clients from a repository of files in real time. The server must guarantee concurrent and uninterrupted delivery of each video stream requested from clients. To achieve its purpose, many stream servers adopt multi-processors, sufficient memory, and RAID or SAN in their systems. In this paper, we propose a Linux-based parallel media streaming server. It is superior to the other systems in the storing structure, fault-tolerance, and service capacity. Since this system supports the web interlace, users can operate easily through the www. This system uses unique striping policy to distribute multimedia files into the parallel storage nodes. If a service request occurs, each storage node transmits striped files concurrently to the client. Its performance is better than the single media streaming service because of the parallel architecture.

• The KIPS Transactions:PartC
• /
• v.9C no.5
• /
• pp.709-718
• /
• 2002

Cluster based VOD systems require elaborate load balancing and buffer management techniques in order to ensure real-time display for multiuser concurrently. In this paper, we propose a new load balancing technique based on the dynamic buffer partitioning in cluster based VOD servers. The proposed technique evenly distribute the user requests into each service node according to its available buffer capacity and disk access rate. In each node, the dynamic buffer partitioning technique dynamically partitions the buffer to minimize the average waiting time for the requests that access the same continuous media. The simulation results show that our proposed technique decreases the average waiting time by evenly distributing the user requests compared with the exiting techniques and then increases the throughput in each node. Particularly under the overloaded condition in the cluster server, the simulation probes that the performance of the proposed technique is better two times than the Generalized Interval Caching based technique.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.4
• /
• pp.113-124
• /
• 2009

A research of grid computing that is the combination of computer resources from multiple distributed administrative domains to get large amount of computing power is underway. This research is an application of grid technology on a urban facilities management system based on u-GIS. The sensors are set up in the urban facilities to make it monitoring. If an amount of sensors and gateways is increased, the server needs more computing resources to process the data. In this study we developed the skills that can distribute jobs to idle gateway, in case of the server capacity had approached threshold. It will be possible to develop of economic and efficient system that will apply to large amount of data processing about u-City.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.695-712
• /
• 2021

As the use of smart devices is being increased rapidly by the development of internet and IT technology, the contents production and utilization rate are showing higher increase, too. In addition, the type of contents also shows very diverse forms such as education, game, video, UCC, etc. In the meantime, the contents are reproduced in diverse forms by reprocessing the original contents, and they are being serviced through the contents service platform. Therefore, the platform to make the contents reprocessing easy and fast is needed. As the diverse contents distribution channels such as YouTube, SNS, App Service, etc, easier contents distribution platform is needed, and the development of the relevant area is expected. In addition, as the selective consumption of the contents having easy accessibility through diverse smart devices is distinguished, the demand for the platform and service that can identify the contents consumption propensity by individual is being increased. Therefore, in this study, to vitalize the online contents distribution, the contents reproduction and publishing platform, was designed and materialized, which can reproduce and distribute the contents based on the real-time contents editing technology in URL unit and the consumer propensity analysis technology using the data management-based broadcasting contents distribution metadata technology and the edited image contents streaming technology. In addition, in the results of comparing with other platforms through the experiment, the performance superiority of the suggested platform was verified. If the suggested platform is applied to the areas of education, broadcasting, press, etc, the multi-media contents can be reproduced and distributed easily, through which the vitalization of contents-related industry is expected.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.889-890
• /
• 2016

Existing machine-to-machine collaboration system is a centralized structure system fo built OpenWrt and a Web server on the router. But scarce resources of the router are getting more requests from the collaboration client when a problem has occurred with increasing probability of a client object, the higher the traffic. In this paper, in order to solve the problem, we propose a distributed system utilizing Machine Socialization cooperation algorithm. The MCU attached to the machine to minimize the traffic occurrence probability and loss of the data by processing to distribute the data between the server and the client. Also improve the response speed between the server and the client and the operation stop caused by the loss of data. The proposed system will be utilized if the IoT field will be high efficiency compared to existing systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.1
• /
• pp.3-16
• /
• 2010

Recently in the field of the wireless sensor network, many researchers are attracted to pairing cryptography since it has ability to distribute keys without additive communication. In this paper, we propose efficient hardware implementation of ${\eta}_T$ pairing which is one of various pairing scheme. we suggest efficient hardware architecture of ${\eta}_T$ pairing based on parallel processing and register/resource optimization, and then we present the result of our FPGA implementation over GF($2^{239}$). Our implementation gives 15% better result than others in Area Time Product.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.6
• /
• pp.714-721
• /
• 2020

DNN is expanding its use in embedded systems such as robots and autonomous vehicles. For high recognition accuracy, computational complexity is greatly increased, and multiple DNNs are running aperiodically. Therefore, the ability processing multiple DNNs in embedded environments is a crucial issue. Accordingly, multicore based platforms are being released. However, most DNN models are operated in a batch process, and when multiple DNNs are operated in multicore together, the execution time deviation between each DNN may be large and the end-to-end execution time of the whole DNNs could be long depending on how they are allocated to the cores. In this paper, we solve these problems by providing a framework that decompose each DNN into individual layers and then distribute to multicores through a global queue. As a result of the experiment, the total DNN execution time was reduced by 31%, and when operating multiple identical DNNs, the deviation in execution time was reduced by up to 95.1%.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3587-3594
• /
• 2022

A distributed high-speed data acquisition and monitoring system for the RF negative ion source at Huazhong University of Science and Technology (HUST) is developed, which consists of data acquisition, data forwarding and data processing. Firstly, the data acquisition modules sample physical signals at high speed and upload the sampling data with corresponding absolute-time labels over UDP, which builds the time correlation among different signals. And a special data packet format is proposed for the data upload, which is convenient for packing or parsing a fixed-length packet, especially when the span of the time labels in a packet crosses an absolute second. The data forwarding modules then receive the UDP messages and distribute their data packets to the real-time display module and the data storage modules by PUB/SUB-pattern message queue of ZeroMQ. As for the data storage, a scheme combining the file server and MySQL database is adopted to increase the storage rate and facilitate the data query. The test results show that the loss rate of the data packets is within the range of 0-5% and the storage rate is higher than 20 Mbps, both acceptable for the HUST RF negative ion source.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.473-478
• /
• 2022

Evaluation learning based on code testing is becoming a popular solution in programming education via Online judge(OJ). In the recent past, many papers have been published on how to detect plagiarism through source code similarity analysis to support OJ. However, deep learning-based research to support automated tutoring is insufficient. In this paper, we propose Input & Output side FiLM models to predict whether the input code will pass or fail. By applying Feature-wise Linear Modulation(FiLM) technique to GRU, our model can learn combined information of Java byte codes and problem information that it tries to solve. On experimental design, a balanced sampling technique was applied to evenly distribute the data due to the occurrence of asymmetry in data collected by OJ. Among the proposed models, the Input Side FiLM model showed the highest performance of 73.63%. Based on result, it has been shown that students can check whether their codes will pass or fail before receiving the OJ evaluation which could provide basic feedback for improvements.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1800-1808
• /
• 2022

During the election period, many polling agencies survey and distribute the approval ratings for each candidate. In the past, public opinion was expressed through the Internet, mobile SNS, or community, although in the past, people had no choice but to survey the approval rating by relying on opinion polls. Therefore, if the public opinion expressed on the Internet is understood through natural language analysis, it is possible to determine the candidate's approval rate as accurately as the result of the opinion poll. Therefore, this paper proposes a method of inferring the approval rate of candidates during the election period by synthesizing the political comments of users through internet community posting data. In order to analyze the approval rate in the post, I would like to suggest a method for generating the model that has the highest correlation with the actual opinion poll by using the KoBert, KcBert, and KoELECTRA models.