Retrieval of Scholarly Articles with Similar Core Contents

Rey-Long Liu 건국대학교 지식콘텐츠연구소 2017 International Journal of Knowledge Content Develop Vol.7 No.3

Retrieval of scholarly articles about a specific research issue is a routine job of researchers to cross-validate the evidence about the issue. Two articles that focus on a research issue should share similar terms in their core contents, including their goals, backgrounds, and conclusions. In this paper, we present a technique CCSE (Core Content Similarity Estimation) that, given an article a, recommends those articles that share similar core content terms with a. CCSE works on titles and abstracts of articles, which are publicly available. It estimates and integrates three kinds of similarity: goal similarity, background similarity, and conclusion similarity. Empirical evaluation shows that CCSE performs significantly better than several state-of-the-art techniques in recommending those biomedical articles that are judged (by domain experts) to be the ones whose core contents focus on the same research issues. CCSE works for those articles that present research background followed by main results and discussion, and hence it may be used to support the identification of the closely related evidence already published in these articles, even when only titles and abstracts of the articles are available.

Motion Estimation in Video Coding & SSIM and CIR Comparison between Adaptive Search Algorithms

Srinivas Bachu,Manjunath Achari K 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.9

An adaptive search order calculations are introduced to accelerate the square or hexagon movement estimation in advanced video coding. As indicated by the movement incline, a table of the versatile inquiry request is characterized. For each seeking emphasis, a superior pursuit request is determined and after that the best coordinated square can be found in the early hunt stage. Some test results exhibit the computational point of interest of the proposed enhanced calculation when contrasted with past calculations. Block motion estimation and compensation are played a major role in the video compression to reduce the temporal redundancies of the input videos. Assortment of square pursuit example is created in the writing to coordinate the pieces with decreased calculation multifaceted nature however without influencing the visual quality. In this paper, we have talked about the precious stone, square and hexagon look design with versatile request to discover the piece movement estimation. These inquiry examples are created as adaptive order square hexagon (AOSH) look calculation to locate the best coordinating piece without much considering vast number of hunt focuses. Likewise, the seeking capacity is defined as exchange off standard where, digression weighted capacity is recently created to assess the coordinating point. The AOSH seek calculation and digression weighted exchange off paradigm is successfully connected to piece estimation process with the point of enhancing the visual quality and compressive execution. The goal of video pressure is accepted for the proposed strategy utilizing three recordings to be specific, football, garden and tennis. The quantitative execution of the proposed technique and existing strategies are broke down utilizing Structural Similarity Index (SSIM) and Compression Improvement Ratio (CIR). The outcomes demonstrate that the AOSH technique got the great visual quality and compressive execution than the past strategies.

의미 변화의 양적 추정 - 말뭉치를 이용한 의미 변화 연구 -

이민우 한국어의미학회 2021 한국어 의미학 Vol.73 No.-

This study introduces methods that can objectively and scientifically capture and describe changes in meaning using corpus data through studies applying statistical methods that have been conducted recently. For statistical inference on the change in meaning, historically recorded data must be quantified and used through a specific calculation method. A representative method of numerically analyzing language data is to use the Semantic Vector Space(SVM), which is also commonly used in the language data analysis method that has been very active in recent years. Recently, a great progress has been made in capturing and explaining semantic changes using these methods. Quantitative estimation of semantic change using computational statistics is based on frequency-based, similarity-based, and network-based methods depending on the representation of meaning can be divided into. The difference between the use of meaning in the present and the use of meaning in the past can be confirmed by comparing the context similarity of the text. If there is a large change in usage compared to the present, the context similarity will be lower, and if there is no change, the context similarity will be high. In order to grasp a detailed and specific change in meaning, a method of comparing a list of key expressions or words that well reveals the meaning of the context can be used by calculating the similarity between expressions or words in the corpus by period. Meaning expansion and reduction, which are representative results of meaning change, can be grasped by measuring the change in the scope of use, and the rise and fall of meaning can be grasped through sentiment analysis. By statistically analyzing the historical corpus in this way, it is possible to statistically grasp the historical changes in the meaning of the Korean language, and suggest implications on how to identify and analyze the change in language meaning.

홈 트레이닝을 위한 관절 핵심점 검출 및 자세 유사도 측정

강도희(Do-hee Kang),이준민(Jun-min Lee),송병철(Byung Cheol Song) 대한전자공학회 2021 전자공학회논문지 Vol.58 No.8

최근 개인 건강에 관한 관심과 더불어 홈 트레이닝이 언택트 문화의 발전 아래에서 주목받고 있다. 이에 따라 많은 홈 트레이닝 애플리케이션들이 신체 핵심점 검출을 기반으로 한 자세 유사도 측정 기능을 제공한다. 하지만, 자체 콘텐츠만 사용 가능하다는 점에서 한계를 갖는다. 이러한 점을 보완하기 위해 본 논문에서는 사용자가 자유롭게 설정한 목표 영상에 대해 실시간 자세 유사도를 측정하는 애플리케이션을 제안한다. 제안 애플리케이션은 딥러닝 기반의 신체 핵심점 검출기인 AlphaPose와 학습된 오토인코더를 결합하여 자세에 대한 특징을 담은 잠재 벡터를 추출한다. 그 다음, RBF(radial basis function)를 통해 두 자세의 유사도를 점수화하여 사용자에게 제공한다. 본 애플리케이션에서 활용된 자세 유사도 측정 방법은 기존에 Action Recognition task 혹은 Anticipation task에서 자주 사용되는 메트릭인 AP(average precision)와 cosine similarity를 통해 가장 적절한 유사도 비교 메트릭을 선정했다. 제안 애플리케이션을 통해 홈 트레이닝의 효과를 극대화하고 범용성을 높일 수 있다. Home training is drawing attention under the development of a ‘Untact Culture’ along with an interest in personal health. As a result, many home training applications provide posture similarity measurement based on body core point detection. However, it has limitations in that its own contents are available. To compensate for this point, in this paper, we propose an application to measure real-time pose similarity on target images freely set by the user. The proposed application combines AlphaPose, a deep learning-based body-core point detector, and learned autoencoders to extract latent vectors featuring postural features. Then, the similarity between the two postures is scored through a radial basis function(RBF) and provided to the user. The method of pose similarity measurement used in this application selected the most appropriate similarity comparison metric by comparing and analyzing the commonly used metrics in existing Action Recognition tasks or Anticipation tasks, such as AP(average precision), cosine similarity. The proposed application maximizes the effectiveness of home training and increases usability.

유사도 기반의 조립 성패 판별 알고리즘

나민우,김태정,송재복 대한기계학회 2020 大韓機械學會論文集A Vol.44 No.1

Mobile IT products, such as tablet PCs, are not only composed of parts with complex shapes, but also include various assembly processes, which makes it difficult to automate processes. Robot assembly based on position control exhibits a fast assembling speed, but if assembly fails, excessive contact force may occur and thus parts or robot may be damaged. In this study, we proposed a similarity-based assembly success/failure estimation algorithm to solve this problem. Several similarity evaluation methods were applied to the battery assembly process, which is a part of tablet PC. It is shown that a combination of similarities on Mahalanobis distance and singular value decomposition offer the best performance. 태블릿 PC와 같은 모바일 IT제품은 복잡한 형상을 갖는 부품으로 구성되어 있을 뿐 아니라, 여러 조립 과정을 수반하므로 공정의 자동화가 어려워서, 현장의 조립 공정은 수작업으로 수행되고 있는 실정이다. 위치 제어 기반의 로봇 조립은 조립 속도는 빠르지만, 조립이 실패하면 과도한 접촉력이 발생하여 부품이 파손되거나 로봇이 손상될 수 있다. 본 연구에서는 이러한 문제를 해결하기 위해 유사도 기반의 조립 성패 판별 알고리즘을 제안하였다. 태블릿 PC의 부품인 배터리 조립 공정에 대하여 여러 유사도 평가 방법을 적용하였고, 마할라노비스 거리 기반의 유사도와 특이값 분해 기반의 유사도를 혼합하여 사용하는 것이 최적의 평가 방식임을 보였다.

동영상에서 추출한 키포인트 정보의 동적 시간워핑(DTW)을 이용한 인체 동작 유사도의 정량화 기법

임준석(June-Seok Im),김진헌(Jin-Heon Kim) 한국전기전자학회 2020 전기전자학회논문지 Vol.24 No.4

사람이 따라 하는 능력을 평가하는 스코어는 아동의 발달 단계 혹은 골프, 무용 동작 등을 점검하는 좋은 수단이 될 수 있다. 또한, 이는 AR, VR 응용에서 HCI로도 활용될 수 있다. 본 논문에서는 동작을 주도해서 수행하는 시범자와 그 동작을 따라 하는 참여자 간의 동작 유사도를 평가하는 방안을 제시하고, 여기서 우리는 Openpose의 키포인트 벡터 유사도의 유클리디안 L2 거리를 활용하는 동작 유사도를 제안한다. 제안된 기법은 DTW를 사용하기 때문에 시간 지연차가 있는 동작에 유연하게 대처할 수 있다. The matching score evaluating human copying ability can be a good measure to check children"s developmental stages, or sports movements like golf swing and dance, etc. It also can be used as HCI for AR, VR applications. This paper presents a method to evaluate the motion similarity between demonstrator who initiates movement and participant who follows the demonstrator action. We present a quantification method of the similarity which utilizes Euclidean L2 distance of Openpose keypoins vector similarity. The proposed method adapts DTW, thus can flexibly cope with the time delayed motions.

Research on dynamic load estimation method of crawler travel system

Zhihong Zhang,Hong Zhang,You Chen,Honghong Yan 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.2

This paper proposed a novel approach for dynamic load estimation. The similarity criteria between the model vehicle and the prototype vehicle were established based on the structural, operating, and contact parameters of the crawler travel system. The rigid and flexible coupling simulation models of the model vehicle and the prototype vehicle were established, respectively. The accuracy of the simulation model of the model vehicle was verified by the vibration acceleration and stress load obtained by the experiment of the model vehicle. The accuracy of the simulation model of the prototype vehicle (SMOP) was verified by theoretical calculation of the travel resistance torque. Results indicated that the relative error between the dynamic load estimated based on the similarity theory and the dynamic load obtained by the SMOP was 14.6 %. This research helps to reduce the test cost and provides a theoretical basis for the preliminary research on construction machinery.

Cultural Differences in How People Estimate Public Consensus for Opinions and Attributes

( Hee Sun Park ) 고려대학교 정보문화연구소(구 고려대학교 언론연구소) 2015 커뮤니케이션 科學 Vol.31 No.1

본 연구는 잘못된 동의의견 현상과 유사 추정을 하는 경향이 서로 다른 속성(의견과 능력)에 대해 한국인(343명)과 미국인(335명)이 어떤 다른 점을 보이는지 살펴보았다. 추정을 하는 경향을 측정하는 두 가지 연구방법을 채택하여 비교를 해 본 결과 전반적으로 유사점이 발견되었다. 즉, 잘못된 동의의견 현상과 유사 추정을 하는 경향 모두에서 비슷한 형태의 추즉 오류가 관찰되었다. 문화간 비교의 경우, 한국인과 미국인의 차이점이 보였다. 미국인에 비해서 한국인들이 능력에 관련된 속성에 대해서는 하향추정을 덜 하고, 잘못된 동의의견 현상은 더 강하게 보이고, 유사추정을 더 많이 하는 경향이 있었다. 이와 관련된 결과를 비롯 다른 결과에 대해서는 본 논문에서 더 자세히 논의를 한다. False consensus effect and assumed similarity were investigated with people from different cultures(Koreans n=343; Americans n=335) and different attributes(opinions vs. abilities) to estimate. The two different measures of estimation(false consensus paradigm and assumed similarity paradigm) yielded similar findings. Koreans showed less underestimation, greater false consensus effect, and greater assumed similarity for their abilities than Americans. These and other findings, and implications of thereof are discussed in the paper.

Gender differences in friendship: Perceived similarity and estimation accuracy regarding attitudes

( Hee Sun Park ) 고려대학교 정보문화연구소(구 고려대학교 언론연구소) 2016 커뮤니케이션 科學 Vol.32 No.1

Gender differences in friendship were examined for perceived attitude similarity regarding activities and issues, and for accuracy in estimating friends’ attitudes regarding activities and issues. Findings showed that females perceived greater attitude similarity with their friends than did males. Females perceived greater similarity with female friends than with male friends, while males did not show differences for their female and male friends. Furthermore, based on Bem’s (1974) gender schematicity, sex-typed females were more accurate in estimating their friends’ attitudes on issues than were sex-typed males. Regarding the relationship between perceived similarity and estimation accuracy, for males, perceived similarity is significantly related to estimation accuracy only for attitudes regarding activities, whereas, for females, perceived similarity is significantly related to estimation accuracy only for attitudes regarding issues.

An Adaptive Proportional Integral Active Queue Management Algorithm based on Self-Similar Traffic Rate Estimation in WSN

( Heng Liu ),( Yan Wang ) 한국인터넷정보학회 2011 KSII Transactions on Internet and Information Syst Vol.5 No.11

Wireless Sensor Network (WSN) is made up of a number of sensor nodes and base stations. Traffic flow in WSN appears self-similar due to its data delivery process, and this impacts queue length greatly and makes queuing delay worse. Active queue management can be designed to improve QoS performance for WSN. In this paper, we propose self-similar traffic rate estimating algorithm named Power-Law Moving Averaging (PLMA) to regulate packet marking probability. This algorithm improves the availability of the rate estimation algorithm under the self-similar traffic condition. Then, we propose an adaptive Proportional Integral algorithm (SSPI) based on the estimation of the Self-Similar traffic rate by PLMA. Simulation results show that SSPI can achieve lower queue length jitter and smaller setting time than PI.