• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.201-202
• /
• 2018

본 논문에서는 기존 ImageNet과 Oxford-IIIT Pet Image의 Dataset에서 제공하는 개 품종 이미지와 인터넷 상에서 개 품종 이미지를 데이터 마이닝을 통해 획득된 개 품종 이미지를 결합하고 Random-Label을 추가 하여 개 품종 122개의 클래스와 개 품종이 아닌 1개의 클래스를 인식하는 방법에 대해 소개 한다. 기존 DB만을 사용하였을 때 개 품종 인식률 대비 기존 DB와 수집 DB를 모두 사용한 개 품종 인식률이 Top-1에 대해서 1.5% 개선되었다. 개가 아닌 이미지 인식은 랜덤 DB를 10000장의 경우 93% 인식률을 확인했다.

• Journal of Information Processing Systems
• /
• 제16권1호
• /
• pp.201-209
• /
• 2020

The graph data structure is popular because it can intuitively represent real-world knowledge. Graph databases have attracted attention in academia and industry because they can be used to maintain graph data and allow users to mine knowledge. Mining reachability relationships between two nodes in a graph, termed reachability query processing, is an important functionality of graph databases. Online traversals, such as the breadth-first and depth-first search, are inefficient in processing reachability queries when dealing with large-scale graphs. Labeling schemes have been proposed to overcome these disadvantages. The state-of-the-art is the 2-hop labeling scheme: each node has in and out labels containing reachable node IDs as integers. Unfortunately, existing 2-hop labeling schemes generate huge 2-hop label sizes because they only consider local features, such as degrees. In this paper, we propose a more efficient 2-hop label size reduction approach. We consider the topological sort index, which is a global feature. A linear combination is suggested for utilizing both local and global features. We conduct experiments over real-world and synthetic directed acyclic graph datasets and show that the proposed approach generates smaller labels than existing approaches.

• 정보저장시스템학회논문집
• /
• 제9권1호
• /
• pp.28-31
• /
• 2013

We proposed a method to fabricate label-free protein sensor with sub-wavelength nanograting structures to be used for diagnosing acute myocardial infarction. A nickel stamp for the injection molding of nanograting integrated protein sensor was fabricated by electroforming process with high fidelity. By using metallic stamp, we replicated label-free protein sensor via injection molding, which is an outstanding method for low-cost and mass production of polymer products. Finally, we performed a feasibility test, examining cardiac troponin T (cTnT) and anti-cTnT interactions. From the results, we demonstrated that the fabricated protein sensor can provide information for the early and accurate detection of cardiac diseases such as acute myocardial infarction.

• 센서학회지
• /
• 제19권6호
• /
• pp.403-420
• /
• 2010

Nano and micro structure-based biosensors are promising tool for label-free detection of biomolecular interactions with great accuracy. This review gives a brief survey on nano and micro platforms to sense a variety of analytes such as DNA, proteins and viruses. Among incredible nano and micro structure for bio-analytical applications, the scope of this paper will be limited to micro and nano resonators and nanowire field-effect transistors. Nanomechanical motion of the resonators transducers biological information to readable signals. They are commonly combined with an optical, capacitive or piezo-resistive detection systems. Binding of target molecule to the modified surface of nanowire modulates the current of the nanowire through electrical field-effect. Both detection methods have advantages of label-free, real-time and high sensitive detection. These structures can be extended to fabricate array-type sensors for multiplexed detection and high-throughput analysis. The biosensors based on these structures will be applied to lab-on-a-chip platforms and point-of-care diagnostics. Basic concepts including detection mechanisms and trends in their fields will be covered in this review.

• 한국의류학회지
• /
• 제22권6호
• /
• pp.716-724
• /
• 1998

The purpose of this study is to investigate the washing methods specified on care labels of blue jeans and to examine the appropriateness of the specification. In the study, the present condition of care labels on 100% cotton blue jeans was investigated and the consumers' washing methods of blue jeans were surveyed. Also, the shrinkage of blue jeans after washing was measured. The major results were as follows: 1. In spite of the fact that same materials of 100% cotton denim were used in all cases, washing signs on care labels showed very differently and the symbols of hand wash, using light duty detergent, no wring, drying in shade, and warm ironing with a covering cloth were demanding too high level of care for the protection of blue jeans. 2. Almost all consumers didn't follow instructions proposed on care labels because they didn't anticipate problem. In reality, most consumers washed blue jeans by machine in cold water with heavy duty detergent at standard course, dried under the sun, and didn't iron. The 40.8% of consumers didn't have problems even if they didn't follow instructions. Most problems happened after washing were shrinkage in length, but in shrinkage test after 15 times washings, it was found that there was no serious shrinkage problem. 3. For ideal care of blue jean, it is necessary for manufacturers to recognize the importance of care label and to stick correct appropriate care label. Also, consumers have to trust and follow instructions on care label.

• 한국정보통신학회논문지
• /
• 제18권10호
• /
• pp.2562-2570
• /
• 2014

단백질의 기능을 유추할 수 있는 중요한 정보중의 하나는 단백질이 존재하는 세포내 위치이다. 최근에는 하나의 단백질이 동시에 존재하는 여러 세포내 위치를 예측하는 연구가 활발하다. 본 논문에서는 단백질이 존재하는 세포내의 다중위치를 예측하기 위해서 레이블 멱집합 방법을 개선한다. 레이블 멱집합 방법으로 분류한 다중위치들을 예측 확률에 따라 결합하여 최종적인 다중레이블로 분류한다. 각 다중위치에 대한 정확한 확률적 기여를 구하기 위하여 쌍별 비교와 오류정정 출력코드를 사용한 다중클래스 확률추정 방법을 적용하였다. 단백질 세포내 위치 예측 실험에 제안한 방법을 적용하여 성능이 향상됨을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권9호
• /
• pp.3211-3230
• /
• 2014

Recently, sparse coding has achieved remarkable success in image representation tasks. In practice, the performance of clustering can be significantly improved if limited label information is incorporated into sparse coding. To this end, in this paper, a novel semi-supervised algorithm, called constrained sparse concept coding (CSCC), is proposed for image representation. CSCC considers limited label information into graph embedding as additional hard constraints, and hence obtains embedding results that are consistent with label information and manifold structure information of the original data. Therefore, CSCC can provide a sparse representation which explicitly utilizes the prior knowledge of the data to improve the discriminative power in clustering. Besides, a kernelized version of our proposed CSCC, namely kernel constrained sparse concept coding (KCSCC), is developed to deal with nonlinear data, which leads to more effective clustering performance. The experimental evaluations on the MNIST, PIE and Yale image sets show the effectiveness of our proposed algorithms.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.273-276
• /
• 2019

There is a lot of information in our world, quick access to the most accurate information or finding the information we need is more difficult and complicated. The recommendation system has become important for users to quickly find the product according to user's preference. A social recommendation system using community detection based on label propagation is proposed. In this paper, we applied community detection based on label propagation and collaborative filtering in the movie recommendation system. We implement with MovieLens dataset, the users will be clustering to the community by using label propagation algorithm, Our proposed algorithm will be recommended movie with finding the most similar community to the new user according to the personal propensity of users. Mean Absolute Error (MAE) is used to shown efficient of our proposed method.

• 한국환경과학회지
• /
• 제27권12호
• /
• pp.1195-1203
• /
• 2018

Many consumers intend to make environmentally purchase. However, this is not always what occurs. A gap exists between consumer intentions to purchase environmentally friendly products and their actual purchase behavior. In this study, we examined the effect of situational factors such as price sensitivity, product quality perception, and label trust on the relationship between purchase intention and purchase behavior for environmentally friendly products. First, we conducted a theoretical consideration through a review of literature on price sensitivity, product quality perception, label trust, purchase intention and purchase behavior. Based on the literature review, we designed a structural model and developed the hypotheses. Next, we collected data using a survey and processed them statistically in order to verify the hypotheses. A total of 213 samples were collected and the data were analyzed using a structural equation model (LISREL 8.70). The results suggest that the situational factor of label trust has a moderating effect on the relationship between purchase intention and purchase behavior for environmentally friendly products. However, price sensitivity and product quality perception have no moderating effect. This means that trust in labels is important when consumers want to buy environmentally friendly products. Although this study has some limitations, it is expected that it will positively trigger follow-up research.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권2호
• /
• pp.1063-1070
• /
• 2021

The study aims to investigate the role of consumer's social risk perceptions in retailing private label brands. Since private label brands are exclusively available at retail stores, consumers make their purchase decisions regarding them based on the image of that retail outlet. While buying them, risk perceptions are influenced by the retail store's image. The study identifies various retail store dimensions. For this purpose, primary data was collected using a survey questionnaire that was administered to a representative sample of retail store consumers in Riyadh. The data was analyzed and exploratory factor analysis was applied using SPSS 25 version to extract store image dimensions. The results showed six significant dimensions of retail store image namely 'Sales Staff', 'Promotion', 'Store Environment', 'Store Services', 'Product Assortment', and 'Customer Convenience'. Regression Analysis was performed and the effect of these retail store image dimensions was tested on social risk perceptions of consumers. Results indicate that store image dimensions significantly influence consumer's perceived social risk perceptions. However, the relationship is not consistent across all the six identified store image dimensions. The study brings forth several valuable consumer insights and the findings of the study have some very interesting and practical implications for retailers.