• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.613-615
• /
• 2001

최단경로 탐색에 있어서 출발지와 목적지 사이의 최단경로를 계산하는데 있어서 Label-Setting 알고리즘이 Label-Correcting 알고리즘보다 낫다고 믿어왔다. 하지만 특수한 경우에는 Label-Correcting 알고리즘이 GIS기반의 도로에서 더 좋은 결과를 보인다고 Benjamin의 논문에서 밝혔다[1]. 본 논문에서는 Label-Correcting 알고리즘인 Pallottino의 Graph Growth 알고리즘을 수정하여 One-to-One 최단경로탐색에 적합한 알고리즘을 제안한다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4092-4107
• /
• 2015

We propose a background subtraction method for moving cameras based on trajectory classification, image segmentation and label inference. In the trajectory classification process, PCA-based outlier detection strategy is used to remove the outliers in the foreground trajectories. Combining optical flow trajectory with watershed algorithm, we propose a trajectory-controlled watershed segmentation algorithm which effectively improves the edge-preserving performance and prevents the over-smooth problem. Finally, label inference based on Markov Random field is conducted for labeling the unlabeled pixels. Experimental results on the motionseg database demonstrate the promising performance of the proposed approach compared with other competing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1749-1756
• /
• 2014

Knowledge about protein subcellular localization provides important information about protein function. This paper improves a label power-set multi-label classification for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. Among multi-label classification methods, label power-set method can effectively model the correlation between subcellular locations of proteins performing certain biological function. With constrained optimization, this paper calculates combination weights which are used in the linear combination representation of a multi-label by other multi-labels. Using these weights, the prediction probabilities of multi-labels are combined to give final prediction results. Experimental results on human protein dataset show that the proposed method achieves higher performance than other prediction methods for protein subcellular localization. This shows that the proposed method can successfully enrich the prediction probability of multi-labels by exploiting the overlapping information between multi-labels.

• The Journal of Information Technology
• /
• v.5 no.4
• /
• pp.155-164
• /
• 2002

MPLS is a integrated technology by using routing function and label swapping in the network layer. Based on the previous forwarding equivalence classes, it adds the fixed length label in ingress of the MPLS domain. For the routing, without the packet header information, it uses label for the forwarding decisions. In this paper, traffic engineering requirements in the MPLS internet will be setup. The traffic engineering function have to be performed previously with the network topology. In addition to, we presents the IP network topology and main function with MPLS signaling protocol.

• Korean Journal of Human Ecology
• /
• v.20 no.1
• /
• pp.143-154
• /
• 2011

The purpose of this study was to examine consumers' ability to distinguish advertorial and editorial about consumer information. The data were collected between June, 28 and July, 2 in 2010 through the Internet surveys. Total of 603 respondents were included in the analysis. The findings are follows as: First, consumers showed better ability to discern advertorial than ability to discern editorial. It implied that editorials could be considered as advertorial rather than advertorial could be considered as editorials. Second, it seems likely that rather than executional cues such as format and source information, the types of products/services were used as source cues among consumers. Third, consumers tend to prefer 'consumer information', 'advertorial' and 'advertisement' among 10 given advertising labels. In Conclusion, to prevent misleading potentials of advertorial and editorials, standardized advertising label should be used and notify consumers of advertising label.

• Journal of the East Asian Society of Dietary Life
• /
• v.6 no.3
• /
• pp.335-344
• /
• 1996

This study was to investigate consumer recognition on food label of food package. The results of this study were as follows: 1. when shopping for food, the items considered the most were taste of family, food safety, nutrition and price, respectively. 2. 95.5% of respondents confirmed of the food label of food package when shopping for food. The items confirmed the most on food label were expiration date, manufacture date, manufacturer, food additives and nutrition, respectively. 3. 85.3% of respondents did not satisfy on the food label of food label of food package. 43.6% of respondents demanded food additives more detailed. 28.2% of respondents demanded nutrition information more detailed. 28.2% of respondents demanded food function more detailed. 4. The food which respondents satisfied on food label most were snack '||'&'||' cookies, nuddle, spices, can '||'&'||' bottled food, instant food, processed meat foo, frozen food and imported food, respectively. 5. The group with the most hphrases falling in the top rank was nutrition/calories. The phrases in the nutrition/calories group scored in the top rank were 3 "positive" nutritional characteristics(addition of vitamins, addition of DHA, high dietary fiber) and 5 "nagative" nutritional characteristics(no sugar, low sugar, low calories, low salt and low cholesterol). The group with the most phrases falling in the third rank was ingredient. The phrases in the ingredient scored in the third rank were add of food additives. 6. 55.5% of respondents did not know Recommended Daily Allowance(RDA) information and 61.9% of respondents did not understand the nutrition declaration(content) of food package but 65.7% of resspondents understood the nutrition claim of food package. From these result, respondents were more affected by nutrition claim than by nutrition declaration on food package when shopping for food.ood.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2249-2261
• /
• 1999

In this paper, we describe the design and implementation of the Label Distribution Protocol (LDP) for Multiprotocol Label Switching System. We review the implementation issues of LDP that is required to make a gigabit switched router, and propose a detail design of it. We present the data structures and procedures for the LDP as a result, which are based on IETF standard. We present design issues for applying this to carrier class products. The implemented protocol could afford 40,000 entries of the IP routing table that is required for deploying this system to commercialized data network. Furthermore this system implemented using the standard API of Unix, as a result, it has portability. By implementing LDP based on the international standard and these implementation issues, we expect that the implemented LDP will be interoperable with other commercialized products. We prove the validity of the design of the LDP through prototyping, and also verify the prototype with the specification using the process algebra and the performance analysis.

• Journal of the Korean Home Economics Association
• /
• v.33 no.2
• /
• pp.159-166
• /
• 1995

The purpose of the present study is to investigate how closely care labels comply with the 1984 version of the Care Labeling Rule, as well as the change in degree of compliance prior to and after the 1988 IFI care label campaign. Label information was analyzed on the basis of country of origin. The information was also divided into two sets. The basis for dividing the data into two sets was the beginning of the IFI care label campaign in 1988 The data were obtained from 1147 checklists. The information for 1147 samples in six clothing categories were collected from department, specialty, and discount stores. Chi-square analyses were conducted to test hypotheses. While there was no significant difference in the number of incorrect labels on domestically produced garments compared to imported garments in set 1, there was a significant difference in set 2. Also, there was a significnat differnece in the number of incorrect labels between in set 1 and in set 2.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.01a
• /
• pp.147-148
• /
• 2018

다중 레이블 분류 문제는 다중 레이블 데이터를 입력받았을 때 연관된 다수의 레이블을 추측하는 문제이다. 본 논문에서는 다중 레이블 분류 문제의 기법 중 하나인 나이브 베이지안 분류기에 레이블 의존성을 계산하여 결과에 반영한 결과 다중 레이블 분류 문제의 성능이 개선됨을 확인하였다.