• International Journal of Knowledge Content Development & Technology
• /
• 제7권1호
• /
• pp.101-120
• /
• 2017

Healthcare professionals have edited many health questions (HQs) and their answers for healthcare consumers on the Internet. The HQs provide both readable and reliable health information, and hence retrieval of those HQs that are relevant to a given question is essential for health education and promotion through the Internet. However, retrieval of relevant HQs needs to be based on the recognition of the intention of each HQ, which is difficult to be done by predefining syntactic and semantic rules. We thus model the intention recognition problem as a text classification problem, and develop two techniques to improve a learning-based text classifier for the problem. The two techniques improve the classifier by location-based and area-based feature weightings, respectively. Experimental results show that, the two techniques can work together to significantly improve a Support Vector Machine classifier in both the recognition of HQ intentions and the retrieval of relevant HQs.

• 한국의류학회지
• /
• 제33권10호
• /
• pp.1541-1551
• /
• 2009

This study gives guidelines to pattern designing by supplying various images of the transformed shape of jeans with the location of the waistline and the pants silhouette. For this study, 9 kinds of sample cloths (100% cotton denim) were designed considering the laying measurement of the jeans with the location of the waistline and the pants silhouette. The images of each sample were evaluated after the measurement of the completed samples. Clothing and textiles specialists used a semantic differential scale as the evaluation method of the images. For the statistical analysis of the data, one way Anova and Duncan test were adopted using the SPSS 12.0 program. The results of this study are as follows: 1. The visual image by the location of waistline and the change of the pants silhouette is composed of 3 factors (attraction, fashion and comfort factors) of which the attraction factor is the most important factor. 2. The visual image is positive when the location of the waistline is in the low waist position. It is attractive, fashionable, and comfortable. The visual image is negative when the location of the waistline is in the position of the natural waist. 3. The visual image is attractive when the pants silhouette is a boot-cut and fashionable when the pants silhouette are skinny. The straight-cut is comfortable but the visual image is negative. 4. There is no correlation between visual image by the location of the waistline and the change of the pants silhouette.

• 한국BIM학회 논문집
• /
• 제5권3호
• /
• pp.41-50
• /
• 2015

Increasing size and complexity of indoor structures have led to much more complication in the spatial cognition and situational awareness. Contrary to outdoor environments, occupants have limited information regarding the indoor space syntax in terms of architectural and semantic information as well as how they interact with their surroundings. The availability of such information could give conveniences to both users and managers in various aspects. In order to visualize the exact location of rooms and utilities in 3D, many studies and projects have utilized BIM models because of its promising value of representing building components. In fact, the application of BIM provides definitive spatial indoor data and creates services for indoor space management and navigation. Therefore, this paper aims to provide an overview of practices on BIM-based indoor spatial information implementation and location-based services. It is expected that enabling of technologies, data-rich content and accessibility of information products will accelerate the growth of the spatially-related markets in various fields.

• Advances in robotics research
• /
• 제2권2호
• /
• pp.129-140
• /
• 2018

With the increasing demand for the development of human pose estimation, such as human-computer interaction and human activity recognition, there have been numerous approaches to detect the 2D poses of people in images more efficiently. Despite many years of human pose estimation research, the estimation of human poses with images remains difficult to produce satisfactory results. In this study, we propose a robust 2D human body pose estimation method using an RGB camera sensor. Our pose estimation method is efficient and cost-effective since the use of RGB camera sensor is economically beneficial compared to more commonly used high-priced sensors. For the estimation of upper-body joint positions, semantic segmentation with a fully convolutional network was exploited. From acquired RGB images, joint heatmaps accurately estimate the coordinates of the location of each joint. The network architecture was designed to learn and detect the locations of joints via the sequential prediction processing method. Our proposed method was tested and validated for efficient estimation of the human upper-body pose. The obtained results reveal the potential of a simple RGB camera sensor for human pose estimation applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.3972-3988
• /
• 2020

Existing methods always rely on statistical features to extract local words for microblog user geolocation. There are many non-local words in extracted words, which makes geolocation accuracy lower. Considering the statistical and semantic features of local words, this paper proposes a microblog user geolocation method by extracting local words based on word clustering and wrapper feature selection. First, ordinary words without positional indications are initially filtered based on statistical features. Second, a word clustering algorithm based on word vectors is proposed. The remaining semantically similar words are clustered together based on the distance of word vectors with semantic meanings. Next, a wrapper feature selection algorithm based on sequential backward subset search is proposed. The cluster subset with the best geolocation effect is selected. Words in selected cluster subset are extracted as local words. Finally, the Naive Bayes classifier is trained based on local words to geolocate the microblog user. The proposed method is validated based on two different types of microblog data - Twitter and Weibo. The results show that the proposed method outperforms existing two typical methods based on statistical features in terms of accuracy, precision, recall, and F1-score.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 춘계학술발표대회
• /
• pp.722-725
• /
• 2015

모바일 환경에서 사용자의 GPS 궤적은 위치기반서비스(Location Based Service)에서 새로운 자원으로써 활용되고 있다. 위치기반서비스의 확장을 위해 단순히 사용자의 위치를 지도에 표시하는 것뿐만 아니라 사용자들이 위치했던 장소들이 내포하고 있는 의미를 발견해 내는 것이 필요하다. 이를 위해 최근 사용자의 위치정보에 관심지점(POI: Point of Interest)의 정보를 결합하여 시맨틱 궤적(Semantic Trajectory)을 생성하고 분석하는 연구들이 진행되고 있다. 이러한 기존연구의 경우 시맨틱 궤적을 생성하기 위해, 사용자의 GPS 궤적과 POI의 면적 정보(polygon)가 겹칠 경우를 찾아내서 이를 시맨틱 궤적으로 생성하였다. 하지만 대부분 공개된 POI 정보는 실제 장소들의 면적 정보를 제공하지 않고 좌표(point) 값 만을 제공하기 때문에 기존의 방법으로는 시맨틱 궤적을 생성하지 못하는 문제가 있다. 본 논문에서는 사용자의 GPS 궤적과 POI의 좌표 값을 이용하여 사용자가 실제 방문했을 것으로 예상되는 POI 를 추정하고 이를 시맨틱 궤적으로 생성해 내는 방법을 제안한다. 제안하는 기법은 GPS 궤적의 속력 정보를 사용하여 사용자가 정지했었던 구간을 판별하고, 정지 구간 주변의 POI 밀도에 따라 정지 구간을 영역으로 확장한다. 그리고 영역에 포함된 POI 중 정지 구간과의 거리가 가장 가깝고, 가장 오랜 시간 포함되었던 POI를 사용자가 방문했던 POI로 판단한다. 이 방법은 POI의 면적정보가 없는 제한적인 상황에서도 시맨틱 궤적을 생성할 수 있다는 장점을 가진다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권7호
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.

• 한국어교육
• /
• 제28권4호
• /
• pp.337-366
• /
• 2017

이 연구는 미국 대학에서 제2외국어로 한국어를 배우는 영어권 학습자의 부사형 조사 '-에'의 다양한 의미론적 뜻의 습득을 고찰한다. 이 연구는 초급반, 중급반, 고급반의 45명 참가자들을 대상으로, 한국어 학습 첫 학기 교실에서 이 조사가 가르쳐 졌을 때 각 단계의 학습자들이 어떻게 그 의미를 해석하며 실제로 어떻게 사용하는가에 대한 수행능력을 중심으로 이루어졌다. 이 연구 결과는 다양한 의미론적 뜻에 대해 서로 다른 발달 과정을 보여주고 있다. 통계 분석 결과에 따르면 초급반과 중급반에서는 이 연구 과제 '-에'의 의미 중 시간과 목표, 정적인 위치적 의미의 습득이 접촉의 의미나, 개별의 의미보다 좀 더 쉽게 습득 된다는 것을 보여주고 있다. 반면에 고급반에서는 개별의 의미를 제외하고는 모든 의미론적인 의미가 거의 목표점까지 도달하였다. 이 연구는 의미론적 복합성과 다른 언어권 간의 영향과 같은 요인과 함께, 제2 언어 빈도수, 언어학적 입력, 습득 방식과 같은 다양한 요인이 '-에'의 습득에 영향을 미친다는 것을 제시하고 있다.

• 대한원격탐사학회지
• /
• 제39권5_3호
• /
• pp.967-978
• /
• 2023

본 연구에서는 다양한 드론 영상 데이터셋을 효과적으로 학습하여 의미론적 분할의 정확도를 향상시키기 위한 combined segmentation network (CSN)를 제안하고 검증하였다. CSN은 세 가지 드론 데이터셋의 다양성을 고려하기 위하여 인코딩 영역의 전체를 공유하며, 디코딩 영역은 독립적으로 학습된다. CSN의 경우, 학습 시 모든 데이터셋에 대한 손실값을 고려하기 때문에 U-Net 및 pyramid scene parsing network (PSPNet)으로 단일 데이터셋을 학습할 때보다 학습 효율이 떨어졌다. 그러나 국내 자율주행 드론 영상에 CSN을 적용한 결과, CSN이 PSPNet에 비해 초기 학습 없이도 영상 내 화소를 적절한 클래스로 분류할 수 있는 것을 확인하였다. 본 연구를 통하여 CSN이 다양한 드론 영상 데이터셋을 효과적으로 학습하고 새로운 지역에 대한 객체 인식 정확성을 향상시키는 데 중요한 도구로써 활용될 수 있을 것으로 기대할 수 있다.