• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2012년도 추계학술발표대회
• /
• pp.148-151
• /
• 2012

범용 GPU (general-purpose computing on graphics processing units, GPGPU)는 GPU를 일반적인 목적으로 사용하고자 하는 병렬 컴퓨터 구조로써, 과학 연산 등 여러 분야에서 응용 프로그램의 성능을 향상시키기 위하여 사용되고 있다. 본 연구에서는 음성인식기에서 주로 사용되는 가우시안 혼합 모델(Gaussian mixture model, GMM)에서 많은 연산시간을 차지하는 관측확률 계산의 성능을 향상시키고자 GPGPU를 이용하는 알고리즘을 구현하였으며, 기존 CPU 기반 알고리즘 대비 약 13배 연산시간을 단축하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제23권4호
• /
• pp.423-430
• /
• 2019

The convergence of the automotive industry and the ICT technology can be broadly divided into the commercial service sector and the Cooperative-ITS (C-ITS) service sector. The C-ITS service sector is using V2X communication technology as a field that aims to provide safer transportation, more green and efficient transportation, and more predictable and productive mobility. The recent convergence of self-driving cars and connected cars requires high data rates, low transmission delays, and low transmission error rates. Interest in comparison of performance between WAVE and C-V2X (LTE-V2X, 5G-V2X) has been amplified and application services by communication technology are being studied. In this paper, we design the application performance evaluation method of Hybrid V2X communication system and confirm that the decrease of packet error rate (PER) performance is caused by the increase of communication distance, not the vehicle speed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제41권12호
• /
• pp.1824-1833
• /
• 2016

In this paper, we propose networked airborne relay-based positioning scheme (N-ARPS) based on time division multiple access (TDMA) networks to improve the performance of relative navigation (RelNav). To integrate the ARPS into TDMA, there are three problems such as slot allocation, selection of airborne relays, and method for signal loss to be solved. A subframe of N-ARPS is designed to assign the slots for broadcast and relay of navigation signals consecutively to minimize the effect of mobility. The selection algorithm determines the optimum set of airborne relays by selecting evenly distributed nodes depending on their distances to the master station. Finally, we uses precise position location information (PPLI) messages, which are received in data transmission period, to estimate a user position when the navigation signals are missing. The simulation results indicate that N-ARPS significantly improves user accuracy over RelNav.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제21권3호
• /
• pp.175-181
• /
• 2021

This paper analyzes the artificial intelligence-based approach for short-term energy consumption prediction. In this paper, we employ the reinforcement learning algorithms to improve the limitation of the supervised learning algorithms which usually utilize to the short-term energy consumption prediction technologies. The supervised learning algorithm-based approaches have high complexity because the approaches require contextual information as well as energy consumption data for sufficient performance. We propose a deep reinforcement learning algorithm based on multi-agent to predict energy consumption only with energy consumption data for improving the complexity of data and learning models. The proposed scheme is simulated using public energy consumption data and confirmed the performance. The proposed scheme can predict a similar value to the actual value except for the outlier data.

• KIPS Transactions on Computer and Communication Systems
• /
• 제11권9호
• /
• pp.281-288
• /
• 2022

AGVs are often used in industrial applications to transport heavy materials around a large industrial building, such as factories or warehouses. In particular, in fulfillment centers their usefulness is maximized for automation. To increase productivity in warehouses such as fulfillment centers, sophisticated path planning of AGVs is required. We propose a scheme that can be applied to QMIX, a popular cooperative MARL algorithm. The performance was measured with three metrics in several fulfillment center layouts, and the results are presented through comparison with the performance of the existing QMIX. Additionally, we visualize the transport paths of trained AGVs for a visible analysis of the behavior patterns of the AGVs as heat maps.

• Information and Communications Magazine
• /
• 제28권11호
• /
• pp.16-23
• /
• 2011

휴대폰은 스마트화되면서 퍼스널 컴퓨터에 버금가는 성능으로 발전하고 있다. 또한 모바일 환경에서 높은 데이터 전송 속도 및 많은 사용자가 동시에 사용할 수 있는 시스템을 적용하고 있다. 차세대 이동통신서비스나 B4G(Beyond 4 Generation)에서는 다중밴드/다중 모드/다중경로 처리구조의 융합 단말기가 시장을 형성하게 되며, 갈수록 휴대폰의 RF Front-End는 복잡하게 된다. 또한 FEM(Front End Module)의 성능은 단말기 시스템의 품질(QoS, Quality of Services)을 좌우하는 핵심부품으로 High Data Rate를 위하여 고성능화가 요구되고 있다. 본고에서는 FEM의 발전 트랜드와 구성하는 블록도 및 주요 핵심부품의 특성과 모듈의 소형화 패키징 기술에 관하여 제시하였다. 또한 4G LTE와 Wimax듀얼밴드 Tx/Rx통합 FEM을 소개하였고, 향후에 구성되게 되는 Future FEM의 블록도를 제시하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제12권11호
• /
• pp.1999-2004
• /
• 2008

While a lot of comparisons of DBMS performance for processing large scale database are given as results of bench-mark tests, there are few comparisons of DBMS performance for processing small scale database. Therefore, in this study, we compared and analyzed on the performance of commercial DBMS and public DBMS for small scale database. Analysis results show that while Oracle has low performance on the operations of update and insert due to the overhead of rollback for data safely, MySQL and MS-SOL have good performance without additional overhead.

• Journal of Advanced Marine Engineering and Technology
• /
• 제40권6호
• /
• pp.535-541
• /
• 2016

In this paper, we analyzed efficient decoding scheme with FTN(Faster than Nyquist) method that is transmission method faster than Nyquist theory and increase the throughput. Applying the FTN method to satellite and underwater communication, we proposed an efficient transceiver model. To minimize ISI(Inter-Symbol Interference) induced by FTN signal, turbo equalization algorithms that iteratively exchange probabilistic information between Viterbi equalizer based on BCJR algorithm and LDPC decoder are used in satellite communication. In others, for underwater communication, DFE equalizer and LDPC decoder are concatenated to improve performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제19권5호
• /
• pp.93-99
• /
• 2019

In this paper, we propose a smart meter that uses GRU model, which is one of artificial neural networks, for the efficient energy management. We collected power consumption data that train GRU model through the proposed smart meter. The implemented smart meter has automatic power measurement and real-time observation function and load control function through power consumption prediction. We determined a reference value to control the load by using Root Mean Squared Error (RMS), which is one of performance evaluation indexes, with 20% margin. We confirmed that the smart meter with automatic load control increases the efficiency of energy management.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.191-194
• /
• 2022

이동통신 산업이 급속도로 발전됨과 동시에 사물인터넷도 빠르게 발전하고 있다. 사물인터넷의 성능이 향상되면서 무선 네트워크에 포함된 많은 데이터를 포함하고 있는 사물인터넷이 증가하였다. 사물인터넷에 사용되는 저사양 프로세서들은 일반 컴퓨터에 비해 제한적이다. 그러므로, 사물인터넷에서 효율적으로 동작되는 암호 알고리즘에 대한 연구는 필수적이다. 따라서, 본 논문에서는 많은 분야에서 널리 사용되고 있는 마이크로 컨트롤러인 ARMv8 프로세서 상에서의 블록 암호 최적 구현에 대한 연구 동향에 대해 알아본다.