• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.716-718
• /
• 2023

엔데믹 시대, 외식 비중이 증가하고 온라인 커뮤니티를 중심으로 인기있는 식당에 대한 공유가 활발하게 일어나며 특정 식당으로 쏠리는 현상 심화, 주요 시간대에 식사를 하기 위해 줄을 서거나 아예 헛걸음을 하는 경우가 많아지고 있다. 본 연구에서는 대부분의 식당에 설치되어 있는 CCTV에서 촬영 이미지를 활용해서 딥러닝을 활용한 Data Labeling을 시행, 현재 식당의 남은 자리를 분석하여 사용자에게 전달하는 프로젝트에 대한 방식을 서술한다. Client를 통해 사용자는 실시간으로 특정 식당의 남은 좌석 수를 확인할 수 있고, 이 정보를 바탕으로 해당 식당에 방문할지 말지를 결정할 수 있을 것이다. 프로젝트 진행에 앞서 데이터를 분석하는 딥러닝 모델인 YOLO에 대해 분석하였고, 각 버전에 대해 특징을 비교 및 대조, 본 프로젝트에 적합한 버전으로 YOLOv5s를 선정하였다.

• 한국정보통신학회논문지
• /
• 제25권6호
• /
• pp.825-833
• /
• 2021

비행시험에서 비행체의 경우 실시간으로 빠르게 이동하므로 비행체 상태를 파악하기 위하여 사용되는 계측/측정장비들의 데이터는 비행시험통제시스템들에 필요한 형태로 처리되고 송신되는 것이 실시간으로 이루어지는 것이 중요하다. 그래서 통제컴퓨터 자료처리시스템에서 발생하는 원격측정자료 처리시간의 감소 및 처리 주기의 향상을 통하여 계측레이더/원격측정장비 연동자료 처리, 비행안전 판단시스템, 비상종료 송신시스템 등에 연동자료 및 안전판단 정보를 현재보다 빠르고 유연하게 제공하기 위해 현 운용중인 원격측정자료처리시스템의 PCM 데이터와 레이더 정보를 동시에 수신/처리할 수 있는 자료처리 소프트웨어를 탑재하여 독립 운용이 가능한 PCM 자료처리시스템 을 개발하였다. 본 논문에서는 기존 시스템을 보완하여 개발된 PCM 자료처리시스템의 전체적인 구조부터 소프트웨어 기능을 세부적으로 분류하여 중점적으로 설명하고 있다. 또한, PCM 자료처리시스템은 시스템 안정화 및 시험운영을 통하여 점차 보완해 나갈 것이다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권6호
• /
• pp.286-295
• /
• 2006

This paper presents a design of a real-time software GPS receiver which runs on a PC. The software GPS receiver has advantages over conventional hardware based receivers in terms of flexibility and efficiency in application oriented system design and modification. In odor to reduce the processing time of the software operations in the receiver, a shared memory structure is used with a dynamic data control, and the byte-type IF data is processed through an Open Multi-Processing technique in the mixer and integrator which requires the most computational load. A high speed data acquisition device is used to capture the incoming high-rate IF signals. The FFT-IFFT correlation technique is used for initial acquisition and FLL assisted PLL is used for carrier tracking. All software modules are operated in sequence and are synchronized with pre-defined time scheduling. The performance of the designed software GPS receiver is evaluated by running it in real-time using the real GPS signals.

• 한국정보시스템학회지:정보시스템연구
• /
• 제25권4호
• /
• pp.121-139
• /
• 2016

Purpose In this study, we propose the special purposed R package named ""new_Noun()" to process nonstandard texts appeared in various social networks. As the Big data is getting interested, R - analysis tool and open source software is also getting more attention in many fields. Design/methodology/approach With more than 9,000 R packages, R provides a user-friendly functions of a variety of data mining, social network analysis and simulation functions such as statistical analysis, classification, prediction, clustering and association analysis. Especially, "KoNLP" - natural language processing package for Korean language - has reduced the time and effort of many researchers. However, as the social data increases, the informal expressions of Hangeul (Korean character) such as emoticons, informal terms and symbols make the difficulties increase in natural language processing. Findings In this study, to solve the these difficulties, special algorithms that upgrade existing open source natural language processing package have been researched. By utilizing the "KoNLP" package and analyzing the main functions in noun extracting command, we developed a new integrated noun processing package "new_Noun()" function to extract nouns which improves more than 29.1% compared with existing package.

• 한국수산과학회지
• /
• 제51권2호
• /
• pp.178-186
• /
• 2018

A chirp-echo data acquisition and processing system was developed for use as a simplified, PC-based chirp echo-sounder with some data processing software modules. The design of the software and hardware system was implemented via a field-programmable gate array (FPGA). Digital signal processing algorithms for driving a single-channel chirp transmitter and dual-channel receivers with independent TVG (time varied gain) amplifier modules were incorporated into the FPGA for better real-time performance. The chirp-echo data acquisition and processing system consisted of a notebook PC, an FPGA board, and chirp sonar transmitter and receiver modules, which were constructed using three chirp transducers operating over a frequency range of 35-210 kHz. The functionality of this PC-based chirp echo-sounder was tested in various field experiments. The results of these experiments showed that the developed PC-based chirp echo-sounder could be used in the acquisition, processing and analysis of broadband acoustic echoes related to fish species identification.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.366-369
• /
• 2022

The glut of information aggravated the process of data analysis and other procedures including data mining. Many algorithms were devised in Big Data and Data Mining to solve such an intricate problem. In this paper, we conducted research about the comparison of several similarity measures and community detection algorithms in collaborative filtering for movie recommendation systems. Movielense data set was used to do an empirical experiment. We applied three different similarity measures: Cosine, Euclidean, and Pearson. Moreover, betweenness and eigenvector centrality were used to detect communities from the network. As a result, we elucidated which algorithm is more suitable than its counterpart in terms of recommendation accuracy.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.145-148
• /
• 2019

Principal Component Analysis (PCA) is a powerful technique in data analysis and widely used to detect anomalies in Wireless Sensor Networks. However, the performance of conventional PCA is not high on time-series data collected by sensors. In this paper, we propose a Joint Exponential Smoothing and Trend-based Principal Component Analysis (JES-TBPCA) for Anomaly Detection which is based on conventional PCA. Experimental results on a real dataset show a remarkably higher performance of JES-TBPCA comparing to conventional PCA model in detection of stuck-at and offset anomalies.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.350-352
• /
• 2022

발병률이 낮은 병은 데이터 불균형 문제가 발생하며, 이는 의료계에서 겪는 원초적인 문제이다. 이런 불균형 문제를 해결하고자 Pix2Pix 로 생성적 적대 신경망 기반 의료 이미지 증강 기법을 설계하여 데이터 불균형 문제 해결 및 성능을 향상시켰다. 합성 데이터의 추가 및 기하학적 데이터 증강의 유무에 대한 4 가지 시나리오로 성능을 비교하여 제안된 기법이 가장 효과적임을 보인다.

• Journal of Positioning, Navigation, and Timing
• /
• 제3권3호
• /
• pp.99-105
• /
• 2014

A graphic processing unit (GPU) can perform the same calculation on multiple data (SIMD: single instruction multiple data) using hundreds of to thousands of special purpose processors for graphic processing. Thus, high efficiency is expected when GPU is used for the generation and correlation of satellite navigation signals, which perform generation and processing by applying the same calculation procedure to tens of millions of discrete signal samples per second. In this study, the structure of a GPU-based GNSS simulator for the generation and processing of satellite navigation signals was designed, developed, and verified. To verify the developed satellite navigation signal generator, generated signals were applied to the OEM-V3 receiver of Novatel Inc., and the measured values were examined. To verify the satellite navigation signal processor, the performance was examined by collecting and processing actual GNSS intermediate frequency signals. The results of the verification indicated that satellite navigation signals could be generated and processed in real time using two GPUs.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.229-232
• /
• 1998

Modern telecommunications are increasingly demanding the addition of complex switching features to switching system software. These improvements also should satisfy customer demands for quick provisioning of new service features. But whenever we have developed the switching system in various types, we met problems that are lack of system engineers and short developments terms. We need new guidelines of software design to meet the demands and overcome our problems. So we propose new software platform, scenario driven call control engine (SDCCE) for ATM switching system software and implement an effective call control software using scenarios for ATM Switching System. A scenario is a set of procedures and supplementary scenarios written in data structure and gives benefits to easy adapt new or modified function by adding a scenario. The goal of SDCCE is to increase reusability and readability of software. Especially, it gives a good software extensibility and maintainability. And when we developed ptmp call processing control software, we could get high productivity by reusing scenarios and procedures of ptp call processing control software. We applied the scenario driven call control software to ATM switching system.