• ETRI Journal
• /
• v.41 no.6
• /
• pp.797-810
• /
• 2019

Image saliency detection is the basis of perceptual image processing, which is significant to subsequent image processing methods. Most saliency detection methods can detect only a single object with a high-contrast background, but they have no effect on the extraction of a salient object from images with complex low-contrast backgrounds. With the prior knowledge, this paper proposes a method for detecting salient objects by combining the boundary contrast map and the geodesics-like maps. This method can highlight the foreground uniformly and extract the salient objects efficiently in images with low-contrast backgrounds. The classical receiver operating characteristics (ROC) curve, which compares the salient map with the ground truth map, does not reflect the human perception. An ROC curve with distance (distance receiver operating characteristic, DROC) is proposed in this paper, which takes the ROC curve closer to the human subjective perception. Experiments on three benchmark datasets and three low-contrast image datasets, with four evaluation methods including DROC, show that on comparing the eight state-of-the-art approaches, the proposed approach performs well.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.3
• /
• pp.418-426
• /
• 1994

Auto Navigation System is to provide a vehicle driver with more driving information by developing a computer-based system which supports advanced knowledge to a vehicle driving automation system and a driver. In this paper, we propose a new algorithm for the extraction of passing car which removes a background region using a series of images. First, we generate two difference images from three original images by getting the difference values between every two of them in sequence. Second, we generate two mask images from the two difference images. Finally, we extract passing car using the one original image and the two mask images. Using this algorithm we can extract the moving object in the outdoors.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.200-205
• /
• 2005

The objectives of this study were to introduce the easiest and most proper applications of datamining in industrial processes. Applying datamining in manufacturing is very different from applying it in marketing. Misapplication of datamining in manufacturing system results in significant problems. Therefore, it is very important to determine the best procedure and technique in advance. In previous studies, related literature has been introduced, but there has not been much description of datamining applications. Research has not often referred to descriptions of particular examples dealing with application problems in manufacturing. In this study, a datamining roadmap was proposed to support datamining applications for industrial processes. The roadmap was classified into three stages, and each stage was categorized into reasonable classes according to the datamining purposed. Each category includes representative techniques for datamining that have been broadly applied over decades. Those techniques differ according to developers and application purposes; however, in this paper, exemplary methods are described. Based on the datamining roadmap, nonexperts can determine procedures and techniques for datamining in their applications.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.149-155
• /
• 2018

In this paper we propose an algorithm for generating role-performer bipartite matrix for analyzing BPM-based human resource affiliations. Firstly, the proposed algorithm conducts the extraction of role-performer affiliation relationships from ICN(Infromation Contorl Net) based business process models. Then, the role-performer bipartite matrix is constructed in the final step of the algorithm. Conclusively, the bipartite matrix generated through the proposed algorithm ought to be used as the fundamental data structure for discovering the role-performer affiliation networking knowledge, and by using a variety of social network analysis techniques it enables us to acquire valuable analysis results about BPM-based human resource affiliations.

• Parasites, Hosts and Diseases
• /
• v.57 no.6
• /
• pp.613-619
• /
• 2019

Paleoparasitological analysis was carried on 4 Merovingian skeletons, dated from the late-5th to the late-9th centuries, and recovered in the church of Saint-Martin-au-Val in Chartres (Center region, France). The corpses were buried in stone sarcophagi, which were still sealed at the time of excavation. Parasite marker extraction was conducted on sediment samples taken from the abdominal and pelvic regions, but also on samples taken from under the head and the feet as control samples. Microscopic observation revealed the presence of 3 gastrointestinal parasites, namely the roundworm (Ascaris lumbricoides), the whipworm (Trichuris trichiura) and the fish tapeworm (genus Diphyllobothrium). This analysis contributes to a better knowledge of the health status and the lifestyle of ancient medieval populations during the Merovingian period, for which very few paleoparasitological data were available, up until now. It demonstrates the presence of the fish tapeworm for the first time during this period.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.629-644
• /
• 2010

A real-time image georeferencing system requires all inputs to be determined in real-time. The intrinsic camera parameters can be identified in advance from a camera calibration process while other control information can be derived instantaneously from real-time GPS/INS data. The bottleneck process is tie point acquisition since manual operations will be definitely obstacles for real-time system while the existing extraction methods are not fast enough. In this paper, we present a fast-and-automated image matching technique based on the KLT tracker to obtain a set of tie-points in real-time. The proposed work accelerates the KLT tracker by supplying the initial guessed tie-points computed using the GPS/INS data. Originally, the KLT only works effectively when the displacement between tie-points is small. To drive an automated solution, this paper suggests an appropriate number of depth levels for multi-resolution tracking under large displacement using the knowledge of uncertainties the GPS/INS data measurements. The experimental results show that our suggested depth levels is promising and the proposed work can obtain tie-points faster than the ordinary KLT by 13% with no less accuracy. This promising result suggests that our proposed algorithm can be effectively integrated into the real-time image georeferencing for further developing a real-time surveillance application.

• Journal of East-West Nursing Research
• /
• v.27 no.2
• /
• pp.153-165
• /
• 2021

Purpose: The aim of study was to identify ranges of Korean nurses' competency in disaster nursing. Methods: A scoping review was conducted using the Joanna Briggs Institute methodology. The review used information from four databases: RISS, ScienceON, EBSCO Discovery Service, and CINAHL. In this review, key words were 'disaster', 'nurs*', 'competenc*', 'ability' and 'preparedness'. Inclusion and exclusion criteria were identified as strategies to use in this review. The inclusion criteria for this review focused on the following: Korean nurse, articles related to disaster nursing competency, peer-review articles published in the full text in Korean and English. Review articles were excluded. Results: Nineteen studies were eligible for result extraction. A total of 10 categories of disaster nursing competency were identified: Knowledge of disaster nursing, crisis management, disaster preparation, information collection and sharing, nursing record and document management, communication, disaster plan, nursing activities in disaster response, infection management, and chemical, biological, radiation, nuclear, and explosive management. Conclusion: It is necessary to distinguish between Korean nurses' common disaster nursing competency, professional disaster nursing competency, and disaster nursing competency required in nursing practice. Therefore, future research will be needed to explore and describe disaster nursing competency.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• Microbiology and Biotechnology Letters
• /
• v.47 no.2
• /
• pp.303-309
• /
• 2019

Earlier studies by our group revealed that gallic acid in phytochemicals stimulated biofilm production in epiphytes, while caffeic acid in phytochemicals inhibited biofilm production in non-epiphytes. It is well documented that antimicrobial secretion by some epiphytic bacteria inhibits non-epiphytic bacterial growth on leaf surfaces. These selection criteria help plants choose their microbial inhabitants. Calcium and iron in phytochemicals also stimulate biofilm formation and thus, may be selection criteria adopted by plants with respect to their native epiphytic population. Furthermore, the processing of leaves during phytochemical extraction impacts the composition of the extract, and therefore its ability to affect bacterial biofilm formation. Computation of the Hurst exponent using biofilm thickness data obtained from the Ellipsometry of Brewster Angle Microscopic (BAM) images is an efficient tool for understanding the impact of phytochemicals on epiphytic and non-epiphytic populations when compared to fluorescent microscopy, scanning electron microscopy, and staining techniques. To the best of our knowledge, this is the first report that uses the Hurst exponent to elucidate the mechanism involved in plant microbe interaction.

• Research in Community and Public Health Nursing
• /
• v.30 no.1
• /
• pp.25-37
• /
• 2019

Purpose: The purpose of this study was to develop an instrument for measuring nursing information literacy competency, and then to examine the validity and reliability of the instrument. Methods: The developmental process of the instrument includes construction of a conceptual framework, generation of initial items, verification of content validity, preliminary study, extraction of final items, and psychometric testing. Its content validity was verified by three experts from nursing and nursing informatics. Its construct, convergent, and discriminant validity was examined in confirmatory factor analysis. Finally, its criterion validity was measured with Pearson's correlation. The tool's reliability was examined by Cronbach's ${\alpha}$. The participants include 382 nurses from four hospitals and one university hospital. Results: Twenty seven items in total were selected for the final scale, and the results of the confirmatory factor analysis were supported with acceptable model fit, which were named competency for identifying problem, potential sources for information, searching fine information, evaluating information, acquising and managing of information, using information ethically, and integrating new information. The convergent, discriminant and criterion validities were also supported. The Cronbach's ${\alpha}$ coefficient was .93. Conclusion: The instrument is valid and reliable to comprehensively assess nurses' information literacy competency, and to provide a basic direction for developing nursing information literacy program.