• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.2
• /
• pp.91-100
• /
• 2023

The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.88-90
• /
• 2022

Semi Supervised Learning 은 일부의 data 에는 labeling 을 하고 나머지 data 에는 labeling 을 안한채로 학습을 진행하는 방법이다. Object Detection 은 이미지에서 여러개의 객체들의 대한 위치를 여러개의 바운딩 박스로 지정해서 찾는 Computer Vision task 이다. 당연하게도, model training 단계에서 사용되는 data set 의 크기가 크고 객체가 많을 수록 일반적으로 model 의 성능이 좋아 질 것이다. 하지만 실험 환경에 따라 data set 을 잘 확보하지 못하던가, 실험 장치가 데이터 셋을 감당하지 못하는 등의 문제가 발생 할 수 있다. 그렇기에 본 논문에서는 semi supervised learning based object detection model 을 알아보고 data set 의 크기를 조절해가며 modle 을 training 시킨 뒤 data set 의 크기에 따라 성능이 어떻게 변화하는 지를 알아 볼 것이다.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.65-75
• /
• 2017

The Detection Model is the model to find the result of a certain purpose using artificial intelligent, data mining, intelligent algorithms In Cyber Security, it usually uses to detect intrusion, malwares, cyber incident, and attacks etc. There are an amount of unlabeled data that are collected in a real environment such as security data. Since the most of data are not defined the class labels, it is difficult to know type of data. Therefore, the label determination process is required to detect and analysis with accuracy. In this paper, we proposed a KDFL(K-means and D-S Fusion based Labeling) method using D-S inference and k-means(unsupervised) algorithms to decide label of data records by fusion, and a detection model architecture using a proposed labeling method. A proposed method has shown better performance on detection rate, accuracy, F1-measure index than other methods. In addition, since it has shown the improved results in error rate, we have verified good performance of our proposed method.

• Korean Journal of Human Ecology
• /
• v.19 no.1
• /
• pp.167-177
• /
• 2010

This study examined consumer perception and use on labeling of cooking utensils made of plastic and glass to get information about improving the labeling. The data were collected from 505 adults in Seoul, Busan, Daegu, Daejeon, Incheon, and Gwangju. The data were analyzed by SPSS Windows V.14.0. Frequencies, t tests, one-way analysis of variance, and Duncan's multiple range tests were carried out. Many respondents checked off 'precautions in use' more than any other notice when they purchased the cooking utensils made of plastic and glass. Respondents were dissatisfied with the letter size and intelligibility of foreign language on the labeling. Most respondents preferred 'tag' for most cooking utensils made of plastic and glass. In addition, on necessity of precautions for each category of plastic cooking utensils, frying pans, plastic baskets, plastic water buckets, plastic seasoning bottles, the frying pan showed the highest need for 'do not place close to the fire'. Plastic cups and plastic containers showed the highest in 'whether utensils could be used in the microwave oven and accompanying precautions', and plastic cutting board showed the highest in 'matters relating to washing before use.' In the case of cooking utensils made of glass, 'precaution on shock' was the highest for glass cups and mugs and 'whether utensils could be used in the microwave oven and accompanying precautions' was the highest for glass pans, dishes and containers.

• Journal of the Korean Society for information Management
• /
• v.33 no.1
• /
• pp.181-196
• /
• 2016

The objective of this study is to evaluate the organization system and the labeling system of information architecture of a website for the elderly. To achieve this aims, we selected a representative website, i.e., Naver, and the participants were conducted given three types of search tasks using their own information literacy skills and they were answered to the questionnaire and an additional interview, if necessary. A total of 74 valid data were collected through the experiment, and we analyzed the data using SPSS Ver. 20. It revealed that Naver received a positive evaluation in the organization system aspect, particularly its systematic subject categorization and chronological browsing mechanisms. Old adults were preferred the icon-based labeling than the text-based labeling system, and showed a significant difference among their academic backgrounds.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.5
• /
• pp.631-636
• /
• 2019

Over the last decade, many researchers have investigated a number of vision-based construction object detection algorithms for the purpose of construction site monitoring. However, previous methods require the ground truth labeling, which is a process of manually marking types and locations of target objects from training image data, and thus a large amount of time and effort is being wasted. To address this drawback, this paper proposes a vision-based construction object detection framework that employs an active learning technique while reducing manual labeling efforts. For the validation, the research team performed experiments using an open construction benchmark dataset. The results showed that the method was able to successfully detect construction objects that have various visual characteristics, and also indicated that it is possible to develop the high performance of an object detection model using smaller amount of training data and less iterative training steps compared to the previous approaches. The findings of this study can be used to reduce the manual labeling processes and minimize the time and costs required to build a training database.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1096-1107
• /
• 2019

In this paper, we present an ontology-based approach to labeling influential topics of scientific articles. First, to look for influential topics from scientific article, topic modeling is performed, and then social network analysis is applied to the selected topic models. Abstracts of research papers related to data mining published over the 20 years from 1995 to 2015 are collected and analyzed in this research. Second, to interpret and to explain selected influential topics, the UniDM ontology is constructed from Wikipedia and serves as concept hierarchies of topic models. Our experimental results show that the subjects of data management and queries are identified in the most interrelated topic among other topics, which is followed by that of recommender systems and text mining. Also, the subjects of recommender systems and context-aware systems belong to the most influential topic, and the subject of k-nearest neighbor classifier belongs to the closest topic to other topics. The proposed framework provides a general model for interpreting topics in topic models, which plays an important role in overcoming ambiguous and arbitrary interpretation of topics in topic modeling.

• Journal of Environmental Policy
• /
• v.13 no.3
• /
• pp.109-133
• /
• 2014

With a growing concern about climate change and green house gases mitigation, carbon labeling policy has been launched in several countries as an environmental policy which connects low carbon production to low carbon consumption. This research aims to propose a model that explains consumers' attitude and brand loyalty toward carbon labeling products. This model specifies the consumer's psychological processes by which consumer values, such as autonomy and environmental values, affect carbon labeling product and corporate images and finally form brand loyalty toward carbon labeling products. Panel data were collected in two separate surveys and analyzed using a structural equation technique. Results are summarized as follows. First, consumers' autonomy value(AV) positively affects locus of control(LC) and corporate image(CI). Second, consumers' environmental value(EV) positively influences perceived consumer effectiveness(PCE), which in turn has a negative effect on perceived barriers(PB). Perceived barriers finally affect product image(PI) negatively. Third, both corporate image and product image have causal relationships with brand loyalty. Our results suggest that carbon labeling policy contributes not only to the reduction of greenhouse gases but also to the increase of consumers' attitude and brand loyalty toward carbon labeling products. This research also provides governments with directions for efficient environmental policy and firms with guidance on effective marketing strategies about carbon labeling.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.38-41
• /
• 2002

Many scientifc applications include manipulation of data points tying in a space. We describe a method, based on sector labeling to generate a space-filling curve for partitioning such given data points. Our method is straightforward and flexible, equipping a one-one correspondence between point-values on the curve and data points in space in more efficient than designated methods found in the literature. It is widely believed that the Hilbert curve achieves the desired properties on linear mappings due to the locality between data points. Therefore we focus on the Hilbert curve since, later on, we identify it as the most suitable for our application. We demonstrate on using our method for the data particles of an n-body simulation that based on Barnes-Hut algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.8
• /
• pp.1780-1784
• /
• 2015

Traditional IP routing, see only the Destination Address When Forwarding Layer 3 routing and exchange information and Destination-Based Routing Lookup is required for all Hop. Thus, all routers Full Internet routing information, the route information of more than about 120,000 may require. Therefore, the router configuration, which can be dispersed in the environment, the traffic load is required in accordance with this congestion. In this study, a unique characteristic of the Internet in the environment of an existing network Best Effect for QoS guarantee and hardware high speed switching of large multimedia data transmitted using a Labeling for forwarding a packet environment configuration is required. Video Stream Broadcast Transport Labeling rather than in much of the higher performance of the multi-step policy to most of the Video Stream Packet deulim was fixed to Labeling Header Format proposes a method of applying an effective QoS policy to a more simplified policy.