• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.76-88
• /
• 2015

This paper presents a classification method based on the combination of active learning with temporal contextual information extracted from past land-cover maps for the classification of crop cultivation areas. Iterative classification based on active learning is designed to extract reliable training data and cultivation rules from past land-cover maps are quantified as temporal contextual information to be used for not only assignment of training data but also relaxation of spectral ambiguity. To evaluate the applicability of the classification method proposed in this paper, a case study with MODIS time-series vegetation index data sets and past cropland data layers(CDLs) is carried out for the classification of corn and soybean in Illinois state, USA. Iterative classification based on active learning could reduce misclassification both between corn and soybean and between other crops and non crops. The combination of temporal contextual information also reduced the over-estimation results in major crops and led to the best classification accuracy. Thus, these case study results confirm that the proposed classification method can be effectively applied for crop cultivation areas where it is not easy to collect the sufficient number of reliable training data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2122-2140
• /
• 2020

Proper and precise embedding of commercial ads within Webpages requires Ad-hoc analysis and understanding of their content. By the successful implementation of this step, both publishers and advertisers gain mutual benefits through increasing their revenues on the one hand, and improving user experience on the other. In this research work, we propose a novel multi-level context-based ads serving approach through which ads will be served at generic publisher websites based on their contextual relevance. In the proposed approach, knowledge encoded in domain-specific and generic semantic repositories is exploited in order to analyze and segment Webpages into sets of contextually-relevant segments. Semantically-enhanced indexes are also constructed to index ads based on their textual descriptions provided by advertisers. A modified cosine similarity matching algorithm is employed to embed each ad from the Ads repository into one or more contextually-relevant segments. In order to validate our proposal, we have implemented a prototype of an ad serving system with two datasets that consist of (11429 ads and 93 documents) and (11000 documents and 15 ads), respectively. To demonstrate the effectiveness of the proposed techniques, we experimentally tested the proposed method and compared the produced results against five baseline metrics that can be used in the context of ad serving systems. In addition, we compared the results produced by our system with other state-of-the-art models. Findings demonstrate that the accuracy of conventional ad matching techniques has improved by exploiting the proposed semantically-enhanced context-based ad serving model.

• Archives of design research
• /
• v.17 no.1
• /
• pp.265-276
• /
• 2004

User experience in web site is beyond Usability, and should be understood in a context. However, the concrete contextual factors of web site experience is not systematically established enough. Therefore, the objective of this research is to establish a framework of mapping experiential context factors with analyzing real web site use cases, and to propose how it is can be applied in the process of web site contents planning. First of all, theoretical framework for the web experience and contextual factors was prepared by secondary research. Second, user experience on music casting sites was collected through web diary method, self-video recording method, and group interview. Then, collected experience was re-constructed with scenarios. Scenarios are analyzed into contextual factors and these factors are categorized, given hierarchies and located into context map. Third, the possibility of applying the context map of web site experience was discussed. The systematical and concrete sample of context map based on practical use cases can be applied in the innovative and cross-genre web contents planning process.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.339-341
• /
• 2012

This paper presents a method for generating an autonomous activity-based diary in the environment including a personal computer (PC). In order to record a user's various tasks in front of a PC, we consider the contextual information such as current time, opened programs, and user interactions. As one modality for the user interaction, a motion sensor was applied to recognize a user's hand gestures in case that the activity is conducted without interaction between the user and the PC. Moreover, we propose a temporal clustering method to recapitulate the sequential and meaningful activity in the stream of extracted PC usage logs. By combining those two processes, we summarize the user activities in the PC environment.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1588-1597
• /
• 1996

This paper describes an estimation method for lexical probabilities in Korean lexical disambiguation. In the stochastic to lexical disambiguation lexical probabilities and contextual probabilities are generally estimated on the basis of statistical data extracted form corpora. It is desirable to apply lexical probabilities in terms of word phrases for Korean because sentences are spaced in the unit of word phrase. However, Korean word phrases are so multiform that there are more or less chances that lexical probabilities cannot be estimated directly in terms of word phrases though fairly large corpora are used. To overcome this problem, similarity for word phrases is defined from the lexical analysis point of view in this research and an estimation method for Korean lexical probabilities based on the similarity is proposed. In this method, when a lexical probability for a word phrase cannot be estimated directly, it is estimated indirectly through the word phrase similar to the given one. Experimental results show that the proposed approach is effective for Korean lexical disambiguation.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• Child Health Nursing Research
• /
• v.10 no.1
• /
• pp.117-125
• /
• 2004

Purpose: The research was conducted to investigate the experience of maternal role attainment of mothers of premature infants admitted in NICU and to conceptualize the phenomena. Method: The grounded theory method was utilized for data collection and analysis. 8 mothers of premature infants were selected and in-depth interview was performed. Paradigm model was utilized for data analysis and presentation. Result: The central category was 'unstable maternal identity'. The properties of the core phenomena was 'ambivalent feeling to baby' 'negative emotion' 'commitment to baby'. The loss of control due to premature delivery was the causal condition. contextual condition was the 'perceived threats' due to severity of the premature infant and uncerainty of the baby's life. The mother's health status, economic status, and familial and social support was recognized as intervening conditions during the process of maternal role attainment. The strategic action/interactions were emotion-focused coping, reappraisal of the situation, problem-focused coping, and information seeking. The consequence was the maternal role attainment with competence and expectation. Conclusion: The process of maternal role attainment was affected by threats due to severity of the baby and intervening factors and interaction strategy. Further research is recommended to develop adequate intervention method during the process of maternal role attainment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1795-1811
• /
• 2019

In order to achieve rapid and accurate detection of vehicle objects in complex traffic conditions, we propose a novel vehicle detection method. Firstly, more contextual and small-object vehicle information can be obtained by our Joint Feature Network (JFN). Secondly, our Evolved Region Proposal Network (EPRN) generates initial anchor boxes by adding an improved version of the region proposal network in this network, and at the same time filters out a large number of false vehicle boxes by soft-Non Maximum Suppression (NMS). Then, our Mask Network (MaskN) generates an example that includes the vehicle occlusion, the generator and discriminator can learn from each other in order to further improve the vehicle object detection capability. Finally, these candidate vehicle detection boxes are optimized to obtain the final vehicle detection boxes by the Fine-Tuning Network(FTN). Through the evaluation experiment on the DETRAC benchmark dataset, we find that in terms of mAP, our method exceeds Faster-RCNN by 11.15%, YOLO by 11.88%, and EB by 1.64%. Besides, our algorithm also has achieved top2 comaring with MS-CNN, YOLO-v3, RefineNet, RetinaNet, Faster-rcnn, DSSD and YOLO-v2 of vehicle category in KITTI dataset.

• Korean Journal of Social Welfare
• /
• v.61 no.4
• /
• pp.137-161
• /
• 2009

In an effort to identify predictors of job performance, research studies in social work administration has been so far on the individual practitioners' levels of knowledge and skills, which could be used in a workplace. As the theoretical concept of organizational environment was fully introduced into social work administration research, however, studies on practitioners' job performance began to have interest in the team or the organizational level variables as well as individual level variables. Along the course of this tendency, this study attempted to test the effect of individual, team, and organizational level variables on the job performance of human service workers. The individual level variables consisted of knowledge, skills, job satisfaction, personality, and counter-productive work behaviors of workers. The team or the organizational level variables included situational constraint, organizational justice, job characteristics, government-dependency, and inter-organizational cooperation. Multi-level complex survey data collected by cluster sampling method from 314 practitioners in 23 organizations were analyzed using Hierarchial Linear Model. Results showed that both task and contextual performance were affected by individual, team, and organizational level variables in various ways.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.3
• /
• pp.11-17
• /
• 2013

With high social demands for the diverse utilizations of forest lands, the illegal forest land use changes have increased. We studied change detection technique to detect changes in forest land use using an object-oriented segmentation of RED bands differencing in multi-temporal aerial photographs. The new object-oriented segmentation method consists of the 5 steps, "Image Composite - Segmentation - Reshaping - Noise Remover - Change Detection". The method enabled extraction of deforested objects by selecting a suitable threshold to determine whether the objects was divided or merged, based on the relations between the objects, spectral characteristics and contextual information from multi-temporal aerial photographs. The results found that the object-oriented segmentation method detected 12% of changes in forest land use, with 96% of the average detection accuracy compared by visual interpretation. Therefore this research showed that the spatial data by the object-oriented segmentation method can be complementary to the one by a visual interpretation method, and proved the possibility of automatically detecting and extracting changes in forest land use from multi-temporal aerial photographs.