• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.337-338
• /
• 2022

시퀀스제어는 제조, 유통, 건설, 의료 산업분야의 기계, 전기, 전자, 자동화 등에 응용되어 널리 사용하고 있다. 4차산업의 발전으로 제어분야에 인공지능 융합 기술이 산업에 중요한 요소가 되어가고 있다. 특히 기존 시스템에 마이크로프로세서와 인공지능이 융합된 설비의 안전성과 혁신성을 평가하고 신뢰성 높은 장비개발이 요구되고 있어 교육목적의 장비를 개발하여 해당분야의 발전을 견인하고자 한다. 자체 개발한 일체형 인공지능 컨트롤러 모듈은 기존의 시퀀스 및 PLC제어 회로에 인공지능 능력을 융합한 장비이다. 본 장비의 성능평가항목으로 동작, 음성, 문자, 색상 등의 인식 능력과 회로의 안정성, 신뢰성을 평가하였다. 시퀀스 및 PLC 회로를 설계 후 융합된 일체형 인공지능 컨트롤러 모듈의 성능평가항목이 모두 만족하였고 회로의 안전성과 신뢰성에 문제가 없는 것으로 나타났다.

• 월간 기계설비
• /
• no.11 s.208
• /
• pp.78-82
• /
• 2007

내년 1월부터 2,000세대 이상 공동주택을 건설하는 사업주는 입주자 모집공고안에 주택에 대한 성능등급(주택의 소음, 구조, 환경, 생활환경 등급, 평가 항목에 따라 1-5등급으로 구분)을 미리 표시해야 한다. 이에 따라 건설업체는 성능등급을 받은 자재를 선호할 것으로 보여져 성능등급을 받은 자재에 대한 관심이 높아질 전망이다. (주)청완산업이 새로 개발한 Double Up System은 화장실 소음 1등급과 구조부문 수리용이성 1등급을 획득, 건설업계의 러브콜이 예상된다. 또한 욕실 배관을 층상배관으로 시공 함으로써 시공의 용이성과 함께 소음걱정 해소, 쾌적한 환경 및 다양한 인테리어가 기대된다.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1672-1683
• /
• 2004

Recommender system is a kind of web intelligence techniques to make a daily information filtering for people. Researchers have developed collaborative recommenders (social recommenders), content-based recommenders, and some hybrid systems. In this paper, we introduce a new hybrid recommender method - ICHM where clustering techniques have been applied to the item-based collaborative filtering framework. It provides a way to integrate the content information into the collaborative filtering, which contributes to not only reducing the sparsity of data set but also solving the cold start problem. Extensive experiments have been conducted on MovieLense data to analyze the characteristics of our technique. The results show that our approach contributes to the improvement of prediction quality of the item-based collaborative filtering, especially for the cold start problem.

• International Journal of Highway Engineering
• /
• v.11 no.3
• /
• pp.111-120
• /
• 2009

Recently, pay adjustment regulation (PAR) has been developed to induce better performing road pavements around the country. This regulation was successfully applied during rehabilitation of highway flexible pavements for the first time, and their results are the focus of this paper. For highway pavements, a lot has been defined by typical amount of works a day. This lot was further divided into several sublots depending on field conditions. According to AASHTO Quality Assurance Guide Specification, pay factors for each lot were statistically determined with field measurements of five performance indicators. And composite pay factors were calculated by accounting for the impact of individual performance indicators on a long-term performance of pavement. In 2008, the PAR was tested with asphalt overlays conducted at all six local headquarters of Korea Expressway Corporation. Also, concerns raised during implementation are discussed in this paper. Limited data used in this study showed that if all performance indicators fall within the construction limits with less variances final construction costs may increase by 50%, whereas 10% reduction in construction costs could be necessary if key performance indicators such as density do not meet the construction quality requirements.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.901-911
• /
• 2005

With the development of e-commerce and the proliferation of easily accessible information, information filtering has become a popular technique to prune large information spaces so that users are directed toward those items that best meet their needs and preferences. While many collaborative filtering systems have succeeded in capturing the similarities among users or items based on ratings to provide good recommendations, there are still some challenges for them to be more efficient, especially the user bias problem, non-transitive association problem and cold start problem. Those three problems impede us to capture more accurate similarities among users or items. In this paper, we provide probabilistic model approaches for UCHM and ICHM which are suggested to solve the addressed problems in hopes of achieving better performance. In this probabilistic model, objects (users or items) are classified into groups and predictions are made for users considering the Gaussian distribution of user ratings. Experiments on a real-word data set illustrate that our proposed approach is comparable with others.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.203-210
• /
• 2020

Memory-based collaborative filtering is one of the representative types of the recommender system, but it suffers from the inherent problem of data sparsity. Although many works have been devoted to solving this problem, there is still a request for more systematic approaches to the problem. This study exploits distribution of user ratings given to items for computing similarity. All user ratings are utilized in the proposed method, compared to previous ones which use ratings for only common items between users. Moreover, for similarity computation, it takes a global view of ratings for items by reflecting other users' ratings for that item. Performance is evaluated through experiments and compared to that of other relevant methods. The results reveal that the proposed demonstrates superior performance in prediction and rank accuracies. This improvement in prediction accuracy is as high as 2.6 times more than that achieved by the state-of-the-art method over the traditional similarity measures.

• KIPE Magazine
• /
• v.14 no.5
• /
• pp.36-41
• /
• 2009

전기철도차량에는 대용량 추진제어 컨버터/인버터부터 소용량 스위칭 모드 전원장치에 이르기까지 철도차량의 운행에 필요한 각종 동력 및 전력을 공급하기 위한 여러 가지 형태의 전력변환장치가 사용되고 있다. 그 중 가장 대표적인 전력변환장치가 추진제어인버터와 보조전원장치이다. 전기철도차량의 성능평가는 전력변환장치의 성능평가라 할 수 있을 정도로 많은 비중을 전력변환장치가 차지하고 있다. 한국철도기술연구원은 국토해양부로부터 지정받은 성능시험기관으로서 국내 도시철도 및 철도차량의 성능평가를 수행하고 있다. 성능시험은 차량의 제작공정에 따라 부품시험, 구성품시험, 완성차시험, 예비주행 및 본선시운전의 각 단계별로 실시하고 그 시험기준으로 도시철도차량의 성능시험에관한기준 및 철도차량성능시험 시행지침이 적용된다. 성능시험기준을 근간으로 추진제어인버터와 보조전원장치의 성능시험 대한 시험항목과 시험방법에 대하여 소개한다.

• Journal of The Korean Association of Information Education
• /
• v.17 no.4
• /
• pp.375-382
• /
• 2013

Collaborative filtering has been most widely used in commercial sites to recommend items based on the history of user preferences for items. The basic idea behind this method is to find similar users whose ratings for items are incorporated to make recommendations for new items. Hence, similarity calculation is most critical in recommendation performance. This paper presents a new similarity measure that takes each rating of a user relatively to his own ratings. Extensive experiments revealed that the proposed measure is more reliable than the classic measures in that it significantly decreases generation of extreme similarity values and its performance improves when consulting neighbors with high similarites only. In particular, the results show that the proposed measure is superior to the classic ones for datasets with large rating scales.

• Convergence Security Journal
• /
• v.20 no.1
• /
• pp.3-8
• /
• 2020

Blockchain can enhance data transparency and security through decentralized data management that is out of the centralized system. permissioned blockchain of the blockchain platform, only trust-based authorized nodes can participate in the distributed network. Considering the characteristics of the permissioned blockchain, it is necessary to consider the network communication speed, transaction finality agreement, and stability as a condition for selecting the consensus algorithm. The consensus algorithms of the permissioned blockchain environment are diverse such as PoA, PBFT, Raft, etc., but there are no various evaluation factors for selecting consensus algorithms. In this paper, various performance evaluation factors are proposed to analyze the characteristics of each consensus algorithm of the permissioned blockchain and to select an efficient consensus algorithm considering the characteristics of the user environment that composes the network. The proposed performance evaluation factor can consider the network speed, stability, and consensus of the finality agreement between nodes under the premise of trust. Through this, a more efficient blockchain network environment can be constructed.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.