• Annual Conference of KIPS
• /
• 2020.05a
• /
• pp.451-454
• /
• 2020

딥러닝 기술을 이용한 정치적 성향의 편향성 분류를 위하여 신문 뉴스 기사를 수집하고, 머신러닝을 위한 학습 데이터를 구축하였다. 학습 데이터의 구축은 보수 성향과 진보 성향을 대표하는 6개 언론사의 뉴스에서 정치적 성향을 이진 분류 데이터로 구축하였다. 뉴스 기사의 수집 방법으로 최근 이슈들 중에서 정치적 성향과 밀접하게 관련이 있는 키워드 15개를 선정하고 이에 관한 뉴스 기사들을 수집하였다. 그 결과로 11,584개의 학습 및 실험용 데이터를 구축하였으며, 정치적 편향성 분류를 위한 머신러닝 모델을 설계하였다. 머신러닝 기법으로 학습 및 실험을 위해 형태소 단위의 임베딩을 이용하여 문장 및 문서 임베딩으로 확장하였으며, SVM(Support Vector Machine)을 이용하여 정치적 편향성 분류 실험을 수행한 결과로 75%의 정확도를 달성하였다.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.82-83
• /
• 2022

Ad-hoc On-demand Distance Vector (AODV), is one of well-designed routing protocols in mobile ad hoc networks. It supports the functionality of node mobility modules through multiple control messages to create and maintain paths for data transfer. Even though a number of studies have been conducted to achieve rapid discovery of paths across the network, but few have focused on impact of control messages. This paper proposes a method to adjust the transmission time of messages used in path recovery according to their individual characteristics. Simulation results show the improved performance of the proposed algorithm rather than traditional AODV routing protocol.

• International conference on construction engineering and project management
• /
• 2017.10a
• /
• pp.252-259
• /
• 2017

Nowadays, the existing manual method for recording actual progress of the construction site has some drawbacks, such as great reliance on the experience of professional engineers, work-intensive, time consuming and error prone. A method integrating computer vision and BIM(Building Information Modeling) is presented for indoor automatic progress monitoring. The developed method can accurately calculate the engineering quantity of target component in the time-lapse images. Firstly, sample images of on-site target are collected for training the classifier. After the construction images are identified by edge detection and classifier, a voting algorithm based on mathematical geometry and vector operation will divide the target contour. Then, according to the camera calibration principle, the image pixel coordinates are conversed into the real world Coordinate and the real coordinates would be corrected with the help of the geometric information in BIM model. Finally, the actual engineering quantity is calculated.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.86-89
• /
• 2008

본 논문에서는 H.264/AVC 비디오의 고속 부호화를 구현 하기 위하여 인터 프레임 상에서 움직임 벡터의 상관관계를 이용한 빠른 인트라 모드 스킵 알고리즘을 보인다. 제안한 인트라 모드 스킵은 이웃 블록 사이의 움직임 벡터간의 상관관계와 이전 프레임의 매크로블록(Macroblock)의 모드를 이용하여 인트라 예측을 생략함으로써 계산량을 줄이는 방법이다. 새로운 물체가 나타나거나 복잡한 움직임을 보이는 매크로블록들이 인트라 모드로 결정될 확률이 높기 때문에, 주변블록의 분산을 이용하여 임계값을 계산하고, 현재 매크로블록의 분산값과 비교하여 조건에 맞는 매크로블록에 대해 인트라 예측을 생략한다. 또한 시간적 상관관계가 높은 이전 프레임의 같은 위치의 매크로블록의 모드가 인트라 모드로 선택 되었을 경우, 인트라 예측을 실행한다. 제안한 방법으로 실험하였을 때, 기존의 논문과 비교하여 부호화 시간이 평균 26.02% 정도 감소하였다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.1220-1223
• /
• 2023

폐기물을 처리하는데 있어 배출과 수거에 대한 프로세스 자동화를 위해 폐기물 객체 유사도 판별이 요구된다. 이를 위해 본 연구에서는 폐기물 데이터셋에서 SIFT(Scale-Invariant Feature Transform)와 HSV(Hue, Saturation, Value)기반으로 두 이미지의 공통된 특징을 추출해 융합하고, 기계학습을 통해 이미지 객체 간의 유사도를 측정하는 모델을 제안한다. 실험을 위해 수집된 폐기물 데이터셋 81,072 장을 활용하여 이미지를 학습시키고, 전통적인 임계치 기반 유사도 측정과 본 논문에서 제시하는 유사도 측정을 비교하여 성능을 확인하였다. 임계치 기반 측정에서 SIFT 와 HSV 는 각각 0.82, 0.89(Acc)가 측정되었고, 본 논문에서 제시한 특징 추출 방법을 사용한 기계학습의 성능은 DT(Decision Tree)와 SVM(Support Vector Machine) 모두 0.93 (Acc)로 4%의 정확도가 향상되었다.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.294-299
• /
• 2023

Micro ribonucleic acids (miRNAs) can regulate the protein expression levels of genes in the human body and have recently been reported to be closely related to the cause of disease. Determining the genes related to miRNAs will aid in understanding the mechanisms underlying complex miRNAs. However, the identification of miRNA-related genes through wet experiments (in vivo, traditional methods are time- and cost-consuming). To overcome these problems, recent studies have investigated the prediction of miRNA relevance using deep learning models. This study presents a method for predicting the relationships between miRNAs and genes. First, we reconstruct a negative dataset using the proposed method. We then extracted the feature using an autoencoder, after which the feature vector was concatenated with the original data. Thereafter, the concatenated data were used to train a long short-term memory model. Our model exhibited an area under the curve of 0.9609, outperforming previously reported models trained using the same dataset.

• The Journal of Society for e-Business Studies
• /
• v.19 no.3
• /
• pp.107-123
• /
• 2014

Current text mining techniques suffer from the problem that the conventional text representation models cannot express the semantic or conceptual information for the textual documents written with natural languages. The conventional text models represent the textual documents as bag of words, which include vector space model, Boolean model, statistical model, and tensor space model. These models express documents only with the term literals for indexing and the frequency-based weights for their corresponding terms; that is, they ignore semantical information, sequential order information, and structural information of terms. Most of the text mining techniques have been developed assuming that the given documents are represented as 'bag-of-words' based text models. However, currently, confronting the big data era, a new paradigm of text representation model is required which can analyse huge amounts of textual documents more precisely. Our text model regards the 'concept' as an independent space equated with the 'term' and 'document' spaces used in the vector space model, and it expresses the relatedness among the three spaces. To develop the concept space, we use Wikipedia data, each of which defines a single concept. Consequently, a document collection is represented as a 3-order tensor with semantic information, and then the proposed model is called text cuboid model in our paper. Through experiments using the popular 20NewsGroup document corpus, we prove the superiority of the proposed text model in terms of document clustering and concept clustering.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.1
• /
• pp.42-50
• /
• 2008

Unlike a cellular network, a mobile ad hoc network(MANET) is constructed only by mobile nodes without access point. Mobile nodes in MANET operate with scarce resources and restricted battery. If battery of intermediate node is exhausted, overall network might be diverged. Therefore, power-aware is really important. An on-demand multipath routing protocol which is proposed to compensate for shortcoming of on-demand single path routing protocol can reduce mute discovery overhead because route discovery starts only when all routes are disconnected. AOMDV(Ad hoc On-demand Multipath Distance Vector) which is on-demand multipath routing protocol based on AODV, reduces 40% of route discovery frequency. However, AOMDV have none of power-aware. So AOMDV have problem that route discovery for power exhaustion is not reduced at all. This paper proposes new power-aware path selection algorithm for AOMDV and scheme that broadcast REER packets when mobile node's battery can be gone. Performance comparison of proposed algorithm with AOMDV using ns-2 simulator shows that route discovery of proposed algorithm is reduced maximally 36.57% than AOMDV's.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.8
• /
• pp.35-44
• /
• 2014

This paper proposes a 3D pointing interface that is designed for the efficient application of a hand mouse. The proposed method uses depth images to secure high-quality results even in response to changes in lighting and environmental conditions and uses the normal vector of the palm of the hand to perform 3D pointing. First, the hand region is detected and tracked using the existing conventional method; based on the information thus obtained, the region of the palm is predicted and the region of interest is obtained. Once the region of interest has been identified, this region is approximated by the plane equation and the normal vector is extracted. Next, to ensure stable control, interpolation is performed using the extracted normal vector and the intersection point is detected. For stability and efficiency, the dynamic weight using the sigmoid function is applied to the above detected intersection point, and finally, this is converted into the 2D coordinate system. This paper explains the methods of detecting the region of interest and the direction vector and proposes a method of interpolating and applying the dynamic weight in order to stabilize control. Lastly, qualitative and quantitative analyses are performed on the proposed 3D pointing method to verify its ability to deliver stable control.

• Journal of the Korea Computer Graphics Society
• /
• v.9 no.3
• /
• pp.23-29
• /
• 2003

There is the temporal correlation of the video sequence between the motion vector of current block and the motion vector of the previous block. If we can obtain useful and enough information from the motion vector of the same coordinate block of the previous frame, the total number of search points used to find the motion vector of the current block may be reduced significantly. In this paper, we propose the block-matching motion estimation using an adaptive initial search point by the predicted motion information from the same block of the previous frame. And the first search point of the proposed algorithm is moved an initial point on the location of being possibility and the searching process after moving the first search point is processed according to the fast search pattern. Simulation results show that PSNR(Peak-to-Signal Noise Ratio) values are improved UP to the 1.05dB as depend on the image sequences and improved about 0.33~0.37dB on an average. Search times are reduced about 29~97% than the other fast search algorithms. Simulation results also show that the performance of the proposed scheme gives better subjective picture quality than the other fast search algorithms and is closer to that of the FS(Full Search) algorithm.