• Journal of Information Processing Systems
• /
• 제14권2호
• /
• pp.499-509
• /
• 2018

Recently, hybrid transactional memory (HyTM) has gained much interest from researchers because it combines the advantages of hardware transactional memory (HTM) and software transactional memory (STM). To provide the concurrency control of transactions, the existing HyTM-based studies use a bloom filter. However, they fail to overcome the typical false positive errors of a bloom filter. Though the existing studies use a global lock, the efficiency of global lock-based memory allocation is significantly low in multi-core environment. In this paper, we propose an efficient hybrid transactional memory scheme using near-optimal retry computation and sophisticated memory management in order to efficiently process transactions in multi-core environment. First, we propose a near-optimal retry computation algorithm that provides an efficient HTM configuration using machine learning algorithms, according to the characteristic of a given workload. Second, we provide an efficient concurrency control for transactions in different environments by using a sophisticated bloom filter. Third, we propose a memory management scheme being optimized for the CPU cache line, in order to provide a fast transaction processing. Finally, it is shown from our performance evaluation that our HyTM scheme achieves up to 2.5 times better performance by using the Stanford transactional applications for multi-processing (STAMP) benchmarks than the state-of-the-art algorithms.

• The Journal of the Acoustical Society of Korea
• /
• 제24권2E호
• /
• pp.46-53
• /
• 2005

Agency for Defense Development (ADD) developed the Submarine Acoustic Information Management System (SAIMS Version 1.0) capable of interfacing some submarine sensors in operation and predicting detection environments for sonars. The major design concepts are as follows: 1) A proper acoustic model is examined and optimized to cover wide spectra of frequency ranges for both active and passive sonars. 2) Interfacing the submarine sensors to an electric navigation chart, the system attempts to maximize the applicability of the information produced. 3) The state-of-the-art database in large area is built and managed on the system. 4) An algorithm, which is able to estimate a full sound speed profile from the limited oceanographic data, is developed and employed on the system. This paper briefly describes design concepts and algorithms embedded in the SAIMS. The applicability of the SAIMS was verified through three sea experiments in October 2003-February 2004.

• 방송공학회논문지
• /
• 제21권2호
• /
• pp.268-271
• /
• 2016

배경 모델과 배경 차분화로 구성되어 있는 전경객체 추출은 다양한 컴퓨터 비젼 응용에서 중요한 기능이다. 조명 변화를 고려하지 않은 기존 방법들은 급격한 조명 변화에서는 성능이 저하된다. 본 레터에서는 이 문제를 해결할 수 있는 조명 변화에 강인한 배경 모델링 방법을 제안한다. 제안 방법은 다른 적응률을 가진 두 개의 배경 모델을 사용함으로써 조명 조건에 신속하게 적응할 수 있다. 본 논문의 제안 방법은 non-parametric 기법으로서 실험에서는 기존 non-parametric 기법들보다 우수한 성능 및 낮은 복잡도를 보여줌을 증명하였다.

• 대한임베디드공학회논문지
• /
• 제15권2호
• /
• pp.51-60
• /
• 2020

Optical character recognition (OCR) has been studied for decades because it is very useful in a variety of places. Nowadays, OCR's performance has improved significantly due to outstanding deep learning technology. Thus, there is an increasing demand for commercial-grade but affordable OCR systems. We have developed a low-cost, high-performance OCR system for the industry with the cheapest embedded developer kit that supports GPU acceleration. To achieve high accuracy for industrial use on limited computing resources, we chose a state-of-the-art text recognition algorithm that uses an end-to-end deep learning network as a baseline model. The model was then improved by replacing the feature extraction network with the best one suited to our conditions. Among the various candidate networks, EfficientNet-B3 has shown the best performance: excellent recognition accuracy with relatively low memory consumption. Besides, we have optimized the model written in TensorFlow's Python API using TensorFlow-TensorRT integration and TensorFlow's C++ API, respectively.

• 전자공학회논문지SC
• /
• 제42권4호
• /
• pp.35-44
• /
• 2005

생체인식 기술 중 변별력과 활용성, 편리성이 뛰어난 얼굴인식 기술은 출입통제나 금융관련 업무 처리와 같이 보안관련 응용분야에서 필요성이 급속도로 요구되고 있다. 따라서 얼굴인식 알고리즘의 발전과 더불어 현 기술의 상태를 파악하고 발전 방향을 제시하기 위한 성능 시험 방법에 대한 연구 또한 중대한 이슈로 부각되고 있다. 본 연구에서는 얼굴인식 시스템의 성능 시험을 위한 프로토콜의 설계 기준을 제시하고 XM2VTS 데이터베이스를 사용하여 PCA를 기반으로 한 인식 시스템을 디자인하여 Identification 시나리오와 Verification 시나리오 상에서 성능 시험 결과를 제시한다.

• 한국의류산업학회지
• /
• 제17권2호
• /
• pp.278-286
• /
• 2015

Fashion industry has tried to adopt the virtual garment technology to reduce the time and effort spent on sample creation. For garment manufacturers to adopt the virtual garment technology as an alternative to sample creation, 3D avatars that meet the needs of each brand should be developed. Virtual garment softwares that are available in the market provide avatars with standardized body models and allow to modify the size by manually entering size specifications. This study proposed a methodology to develop size specifications for 3D avatars as well as brand-customized production sizes. For this, a man's fashion brand which is using virtual garment technology is selected. And the Size Korea database is used to develop size specification based on the customers' body shape. This study developed regression equations on body size specifications, which in turn proposed a regression model to proportionately change size specifications of 3D fitting-models. Based on the each body size calculated by the regression model, a standard model is created, and the skeleton-skin algorithm is applied to the regression model to obtain the results of size changes. Then, the 3D model sizes are tested for size changes as well as measured, which verifies that the regression model reflects body size changes.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.275-278
• /
• 2007

이 논문에서는 곤충의 발자국을 인식하기 위한 전 단계로서 인식대상이 되는 의미 있는 단위의 발자국 영역을 자동 추출하고자 한다. 인식의 대상이 되는 곤충들은 크기와 종류에 따라 남겨지는 발자국 패턴의 크기 및 간격이 다르게 나타난다. 따라서 이 논문에서는 패턴의 크기와 간격에 관계 없이 인식의 기본 단위가 되는 영역을 추출할 수 있도록 하기위해 개선된 군집화 알고리듬을 제안하였다. 제안한 알고리듬에서는 군집화를 위한 임계값이 군집화의 대상이 되는 모든 패턴들의 거리를 축적한 그래프의 형태에 따라 자동으로 설정되도록 하였다. 이러한 제안된 기법으로 군집화 된 영역은 의미 있는 주변 정보에 의해 곤충 인식에 기본 단계의 세그먼트를 자동 추출하게 된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3295-3311
• /
• 2020

With the wide application of hyperspectral images, it becomes more and more important to compress hyperspectral images. Conventional recursive least squares (CRLS) algorithm has great potentiality in lossless compression for hyperspectral images. The prediction accuracy of CRLS is closely related to the correlations between the reference bands and the current band, and the similarity between pixels in prediction context. According to this characteristic, we present an improved CRLS with adaptive band selection and adaptive predictor selection (CRLS-ABS-APS). Firstly, a spectral vector correlation coefficient-based k-means clustering algorithm is employed to generate clustering map. Afterwards, an adaptive band selection strategy based on inter-spectral correlation coefficient is adopted to select the reference bands for each band. Then, an adaptive predictor selection strategy based on clustering map is adopted to select the optimal CRLS predictor for each pixel. In addition, a double snake scan mode is used to further improve the similarity of prediction context, and a recursive average estimation method is used to accelerate the local average calculation. Finally, the prediction residuals are entropy encoded by arithmetic encoder. Experiments on the Airborne Visible Infrared Imaging Spectrometer (AVIRIS) 2006 data set show that the CRLS-ABS-APS achieves average bit rates of 3.28 bpp, 5.55 bpp and 2.39 bpp on the three subsets, respectively. The results indicate that the CRLS-ABS-APS effectively improves the compression effect with lower computation complexity, and outperforms to the current state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.520-541
• /
• 2023

In CRNs, SS is of utmost significance. Every CR user generates a sensing report during the training phase beneath various circumstances, and depending on a collective process, either communicates or remains silent. In the training stage, the fusion centre combines the local judgments made by CR users by a majority vote, and then returns a final conclusion to every CR user. Enough data regarding the environment, including the activity of PU and every CR's response to that activity, is acquired and sensing classes are created during the training stage. Every CR user compares their most recent sensing report to the previous sensing classes during the classification stage, and distance vectors are generated. The posterior probability of every sensing class is derived on the basis of quantitative data, and the sensing report is then classified as either signifying the presence or absence of PU. The ISVM technique is utilized to compute the quantitative variables necessary to compute the posterior probability. Here, the iterations of SVM are tuned by novel GO-PSA by combining GOA and PSO. Novel GO-PSA is developed since it overcomes the problem of computational complexity, returns minimum error, and also saves time when compared with various state-of-the-art algorithms. The dependability of every CR user is taken into consideration as these local choices are then integrated at the fusion centre utilizing an innovative decision combination technique. Depending on the collective choice, the CR users will then communicate or remain silent.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권2호
• /
• pp.331-339
• /
• 2017

본 논문에서는 임베디드 시스템에 적용 가능한 웹소켓 서버의 스레드 풀 관리 기법을 제안한다. 웹소켓은 동적인 웹을 구성하기 위하여 제안된 기술로서, HTML5와 jQuery를 이용하여 구성한다. 동적인 웹을 구성하기 위하여 Apache, Oracle등에서 다양한 연구가 진행되어 오고 있다. 기존의 웹 서비스 시스템은 대용량, 고성능의 하드웨어 사양을 필요로 하며, 임베디드 시스템에 적용하기엔 부적합하다. HTML5와 jQuery로 구성된 Node.js는 오픈소스로 구성된 대표적인 웹소켓 서버이며, 단일 스레드로 이루어진 자바스크립트 기반의 웹 어플리케이션이다. 이러한 Node.js는 임베디드 시스템에 적용하여 고속의 데이터를 처리하기에는 성능상의 한계가 있다. 본 논문에서는 이러한 문제점을 해결하기 위하여 스레드 풀로 운영되는 웹소켓 서버를 구성한다. 제안하는 웹소켓 서버의 스레드 풀은 비트 레지스터를 기반으로 관리되며, 임베디드 시스템에 적합하도록 구성한다. 제안하는 알고리즘의 성능을 평가하기 위하여 네트워크 성능 테스트 도구인 JMeter를 이용한다.