• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.4
• /
• pp.361-366
• /
• 2003

Most sensor array signal processing methods for multiple source localization require knowledge of the correct shape of array(the correct positions of sensors that consist array), because sensor position uncertainty can severely degrade the performance of array signal processing. In particular, it is assumed that the correct positions of the sensors are known, but the known positions may not represent the true sensor positions. Various algorithms have been proposed for 2-D sensor array shape calibration in far field environment. However, they are not available in near field. In this paper, 3-D sensor array shape calibration algorithm is proposed, which is available in near field.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.2-5
• /
• 2022

With the advent of deep learning and the rapid development of ICT (Information and Communication Technology), research using artificial intelligence is being actively conducted in various fields of society such as politics, economy, and culture and so on. Deep learning-based artificial intelligence technology is subdivided into various domains such as natural language processing, image processing, speech processing, and recommendation system. In particular, as the industry is advanced, the need for a recommendation system that analyzes market trends and individual characteristics and recommends them to consumers is increasingly required. In line with these technological developments, this paper extracts and classifies attribute information from structured or unstructured text and image big data through deep learning-based technology development of 'language processing intelligence' and 'image processing intelligence', and We propose an artificial intelligence-based 'customized fashion advisor' service integration system that analyzes trends and new materials, discovers 'market-consumer' insights through consumer taste analysis, and can recommend style, virtual fitting, and design support.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4420-4438
• /
• 2021

Image dehazing is an ill-posed problem which is far from being solved. Traditional image dehazing methods often yield mediocre effects and possess substandard processing speed, while modern deep learning methods perform best only in certain datasets. The haze removal effect when processed by said methods is unsatisfactory, meaning the generalization performance fails to meet the requirements. Concurrently, due to the limited processing speed, most dehazing algorithms cannot be employed in the industry. To alleviate said problems, a lightweight fast dehazing network based on a multiple scale-patch framework (MSP) is proposed in the present paper. Firstly, the multi-scale structure is employed as the backbone network and the multi-patch structure as the supplementary network. Dehazing through a single network causes problems, such as loss of object details and color in some image areas, the multi-patch structure was employed for MSP as an information supplement. In the algorithm image processing module, the image is segmented up and down for processed separately. Secondly, MSP generates a clear dehazing effect and significant robustness when targeting real-world homogeneous and nonhomogeneous hazy maps and different datasets. Compared with existing dehazing methods, MSP demonstrated a fast inference speed and the feasibility of real-time processing. The overall size and model parameters of the entire dehazing model are 20.75M and 6.8M, and the processing time for the single image is 0.026s. Experiments on NTIRE 2018 and NTIRE 2020 demonstrate that MSP can achieve superior performance among the state-of-the-art methods, such as PSNR, SSIM, LPIPS, and individual subjective evaluation.

• Journal of Information Processing Systems
• /
• v.19 no.2
• /
• pp.240-257
• /
• 2023

The industrial Internet of Things (IIoT) is characterized by intelligent connection, real-time data processing, collaborative monitoring, and automatic information processing. The heterogeneous IIoT devices require a high data rate, high reliability, high coverage, and low delay, thus posing a significant challenge to information security. High-performance edge and cloud servers are a good backup solution for IIoT devices with limited capabilities. However, privacy leakage and network attack cases may occur in heterogeneous IIoT environments. Cloud-based multi-party computing is a reliable privacy-protecting technology that encourages multiparty participation in joint computing without privacy disclosure. However, the default cloud selection method does not meet the heterogeneous IIoT requirements. The server can be dishonest, significantly increasing the probability of multi-party computation failure or inefficiency. This paper proposes a blockchain and smart contract-based optimized cloud node selection framework. Different participants choose the best server that meets their performance demands, considering the communication delay. Smart contracts provide a progressive request mechanism to increase participation. The simulation results show that our framework improves overall multi-party computing efficiency by up to 44.73%.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.320-326
• /
• 1997

자연어 정보처리 분야의 거듭된 발전은 다양한 언어처리 도구들의 출현을 가져왔다. 그러나 객관적인 성능 평가 기준의 부재로 인해, 개발된 도구들은 임의의 기준에 따라 평가될 수 밖에 없었다. 그 결과 성능 평가 결과는 평가자와 평가자가 제안한 기준에 따라 다를 수 밖에 없었고 따라서 평가 결과 자체 역시 설득력을 갖을 수가 없었다. 이와 같은 문제에 대한 해결책을 찾고자 하는 노력의 일환으로, 본 연구에서는 한국어처리 도구들 중 특히 구문분석기의 체계적이고도 객관적인 성능 평가를 목적으로 제작된 문장들과 관련 주석 정보들로 구성된 SERI Test Suites '97을 소개한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.409-410
• /
• 2010

미국, 영국, 호주 등은 도로교통시설을 기존의 사후 대응적 방식에서 예방적 유지관리 방식으로 전환하기 위해 자산관리체계를 도입하고 있다. 본 연구는 외국에서 추진하고 있는 자산관리 체계 사례와 자산관리정보시스템과 관련한 연구들 조사, 분석하여 국외의 자산관리정보시스템이 갖는 특성을 조사, 분석하였다. 이 결과를 토대로 국내 실정에 적합한 도로교통시설의 유지관리를 위한 자산관리정보시스템 도입 방안을 제시하였다.

• The Journal of Korean Association of Computer Education
• /
• v.13 no.2
• /
• pp.35-43
• /
• 2010

The "Information and Communication Technology Education Guidelines" was revised in December, 2005. However, students are still not taught the contents in the "Information and Communication Technology Education Guidelines Rev." and are not taught the contents in the "Understanding of the Information Processing" area among them in particular. Therefore, we analyzed the contents in the "Understanding of the Information Processing" area of the elementary ICT textbooks published on and after June 2006. In the result, the contents of many textbooks are not based on the "Information and Communication Technology Education Revised Guidelines" and programming languages using elementary school are too many. The revision of the elementary ICT textbooks must be settled without delay and the certification systems of elementary ICT textbooks must be improved.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.1035-1037
• /
• 2007

Ad-hoc 네트워크는 자율적으로 네트워크를 구성함으로써 유연하고 확장 가능한 특성을 가진다. 하지만 익명으로 구성되는 네트워크의 특성은 사용자의 안전을 보장하지 못함으로 Ad-hoc 네트워크 활성화에 걸림돌이 되고 있다. 여기서는 소수의 악의적인 공격자가 있는 경우에 높은 확률로 연산 결과를 신뢰할 수 있는 안전한 연산 기법들을 활용하여 Ad-hoc 네트워크에서 이루어지는 연산을 보다 안전하게 수행할 수 있는 방안을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04a
• /
• pp.473-476
• /
• 2001

본 논문에서는 HOL 블록킹 현상과 데드락을 줄이기 위해 공유 메모리 스위치를 이용하고 셀에 형태에 따라 유니캐스트 셀과 멀티캐스트 셀을 따로 저장하는 방법을 이용하여 셀의 부하를 줄이는 멀티캐스트 ATM 스위치를 제안한다. 그리고, 트래픽 셀의 손실을 줄이고, 효과적으로 출력하기 위해 제어부에서 출력 포트에 따라 스케줄링하는 기법을 택하였다. 제안한 스위치의 성능을 시뮬레이션을 통해 그 유효성을 보였다.

• Journal of Information Processing Systems
• /
• v.5 no.3
• /
• pp.159-166
• /
• 2009

As shown in Wikipedia, tagging or cross-linking through major keywords in a document collection improves not only the readability of documents but also responsive and adaptive navigation among related documents. In recent years, the Semantic Web has increased the importance of social tagging as a key feature of the Web 2.0 and, as its crucial phenotype, Tag Cloud has emerged to the public. In this paper we provide an efficient method of automated in-text keyword tagging based on large-scale controlled term collection or keyword dictionary, where the computational complexity of O(mN) - if a pattern matching algorithm is used - can be reduced to O(mlogN) - if an Information Retrieval technique is adopted - while m is the length of target document and N is the total number of candidate terms to be tagged. The result shows that automatic in-text tagging with keywords filtered by Information Retrieval speeds up to about 6 $\sim$ 40 times compared with the fastest pattern matching algorithm.