• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.73-82
• /
• 2009

This paper proposes a variance recovery method for character strokes that can be missed in applying the previously proposed color variance approach in text detection of natural scene images. The previous method has a shortcoming of missing the color variance due to the fixed length of horizontal and vertical windows of variance detection when the character strokes are thick or long. Thus, this paper proposes a variance recovery method by using geometric information of bounding boxes of connected components and heuristic knowledge. We have tested the proposed method using various kinds of document-style and natural scene images such as billboards, signboards, etc captured by digital cameras and mobile-phone cameras. And we showed the improved text detection accuracy even in the images of containing large characters.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2022

Recent deep learning-based research shows excellent performance in most natural language processing (NLP) fields with pre-trained language models. In particular, the auto-encoder-based language model proves its excellent performance and usefulness in various fields of Korean language understanding. However, the decoder-based Korean generative model even suffers from generating simple sentences. Also, there is few detailed research and data for the field of conversation where generative models are most commonly utilized. Therefore, this paper constructs multi-turn dialogue data for a Korean generative model. In addition, we compare and analyze the performance by improving the dialogue ability of the generative model through transfer learning. In addition, we propose a method of supplementing the insufficient dialogue generation ability of the model by extracting recommended response candidates from external knowledge information through a retrival model.

• Journal of Korean Society of Spine Surgery
• /
• v.26 no.1
• /
• pp.26-32
• /
• 2019

Study Design: Review article. Objectives: To present the latest knowledge on spine surgery using augmented reality (AR). Summary of Literature Review: AR is a new technology that simulates interactions with real-world surroundings using computer graphics, and it is a field that has recently been highlighted as part of the fourth industrial revolution. Materials and Methods: Review of related literature and introduction of latest research. Results: Spine surgery using AR is currently in its early stages. If industry, academia, and research institutes cooperate and develop, spine surgery using AR is highly likely to develop to the next level. Conclusions: Spine surgeons should strive to develop relevant technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Safety and Health at Work
• /
• v.14 no.2
• /
• pp.163-173
• /
• 2023

In many industrial sectors, workers are exposed to manufactured or unintentionally emitted airborne nanoparticles (NPs). To develop prevention and enhance knowledge surrounding exposure, it has become crucial to achieve a consensus on how to assess exposure to airborne NPs by inhalation in the workplace. Here, we review the literature presenting recommendations on assessing occupational exposure to NPs. The 23 distinct strategies retained were analyzed in terms of the following points: target NPs, objectives, steps, "measurement strategy" (instruments, physicochemical analysis, and data processing), "contextual information" presented, and "work activity" analysis. The robustness (consistency of information) and practical aspects (detailed methodology) of each strategy were estimated. The objectives and methodological steps varied, as did the measurement techniques. Strategies were essentially based on NPs measurement, but improvements could be made to better account for "contextual information" and "work activity". Based on this review, recommendations for an operational strategy were formulated, integrating the work activity with the measurement to provide a more complete assessment of situations leading to airborne NP exposure. These recommendations can be used with the objective of producing homogeneous exposure data for epidemiological purposes and to help improve prevention strategies.

• Korean Journal of Legislative Studies
• /
• v.26 no.3
• /
• pp.85-123
• /
• 2020

Under representative democracy, members of the National Assembly exercise their authority to propose, enact, and revise bills on behalf of the people, and the legislation of such lawmakers has a great impact on individuals and society. There exist criticisms that the quality of legislator-sponsored bills has not improved while the number of them has been expanding recently. This study examines the type, productivity, and efficiency of legislation in the 17~19th National Assembly, and empirical analysis is conducted on how the lawmaker's legislations respond to election-related variables such as voter turnout and election competition. The results show that legislator-sponsored bills are mainly produced in the area of governance, finance, macroeconomic policy, social welfare, and health. The number of legislator's proposals increases, while the passing rate decreases, and the processing period extends. Constituents' participation in voting has been shown to enhance legislative efficiency. Based on the results, the paper emphasizes the enhancement of transparency in the legislative process, the improvement of the people's political knowledge, and the revitalization of election functions for the improvement of parliamentary legislation.

• Asia Marketing Journal
• /
• v.14 no.4
• /
• pp.167-188
• /
• 2013

In today's society with its emphasis on unlimited information access, control of available information about high-technology products is often vital to their success. When a product is released, consumers may initially be attracted through information about its remarkable internal and external features. They may also perceive a degree of congruence between their own personalities and the product image as more information becomes available over time. Consumers' changing impressions of the product may influence personality congruence negatively or positively. These changes and their effects on preference for high-technology products are the focus of this paper. A survey was given to a sample of 206 students at K University to investigate the degree to which consumer behavior can be influenced by personality congruence. The need for clear and definite product knowledge in this process and the effect of product information on preference were also investigated. Three analyses were conducted. The results of Analysis 1 showed the influence of personality congruence on preference for high-technology products. Judgments about personality congruence were based on non-compensatory rather than compensatory information processing. The respondents considered certain aspects of a product's personality rather than the product as a whole when making preference decisions. The results of Analysis 2 indicated that when less information was available about a product, consumers who perceived high personality congruence with the product tended to have higher preference for it compared to those who perceived low personality congruence with the product. On the other hand, when consumers were given more information, no difference was observed in the impact of personality on preference between perceived high and low personality congruence. Lastly, the results of Analysis 3 showed that when consumers with high need for closure (NFC) perceived high congruence between their own personalities and a product, objective information regarding the product was not used in decision-making: instead, judgments about the product were based on perceived personality congruence. On the other hand, high-NFC consumers who perceived low personality congruence between themselves and the product tended to require more information about the product in order to give it a positive evaluation. In contrast, low-NFC consumers who perceived high personality congruence felt comfortable with large amounts of information. For low-NFC consumers who perceived low congruence, the level of information had no influence on preference.

• Communications of Mathematical Education
• /
• v.37 no.3
• /
• pp.443-465
• /
• 2023

This study examines the content of vectors and matrices in Artificial Intelligence Mathematics textbooks (AIMTs) from the 2015 revised mathematics curriculum. We analyzed the implementation of foundational mathematical concepts, specifically definitions and related sub-concepts of vectors and matrices, in these textbooks, given their importance for understanding AI. The findings reveal significant variations in the presentation of vector-related concepts, definitions, sub-concepts, and levels of contextual information and descriptions such as vector size, distance between vectors, and mathematical interpretation. While there are few discrepancies in the presentation of fundamental matrix concepts, differences emerge in the subtypes of matrices used and the matrix operations applied in image data processing across textbooks. There is also variation in how textbooks emphasize the interconnectedness of mathematics for explaining vector-related concepts versus the textbooks place more emphasis on AI-related knowledge than on mathematical concepts and principles. The implications for future curriculum development and textbook design are discussed, providing insights into improving AI mathematics education.

• Food Science of Animal Resources
• /
• v.43 no.6
• /
• pp.1111-1127
• /
• 2023

Health-promoting preparations of inanimate microorganisms or their components are postbiotics. Since probiotics are sensitive to heat and oxygen, postbiotics are stable during industrial processing and storage. Postbiotics boost poultry growth, feed efficiency, intestinal pathogen reduction, and health, making them acceptable drivers of sustainable poultry production. It contains many important biological properties, such as immunomodulatory, antioxidant, and anti-inflammatory responses. Postbiotics revealed promising antioxidant effects due to higher concentrations of uronic acid and due to some enzyme's production of antioxidants, e.g., superoxide dismutase, glutathione peroxidase, and nicotinamide adenine dinucleotide oxidases and peroxidases. Postbiotics improve intestinal villi, increase lactic acid production, and reduce Enterobacteriaceae and fecal pH, all of which lead to a better immune reaction and health of the gut, as well as better growth performance. P13K/AKT as a potential target pathway for postbiotics-improved intestinal barrier functions. Similarly, postbiotics reduce yolk and plasma cholesterol levels in layers and improve egg quality. It was revealed that favorable outcomes were obtained with various inclusion levels at 1 kg and 0.5 kg. According to several studies, postbiotic compounds significantly increased poultry performance. This review article presents the most recent research investigating the beneficial results of postbiotics in poultry.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.417-426
• /
• 2024

In general, the implementation of machine learning requires prior knowledge and experience with deep learning models, and substantial computational resources and time are necessary for data processing. As a result, machine learning encounters several limitations when deployed on embedded processors. To address these challenges, this paper introduces a novel approach where a genetic algorithm is applied to the convolution operation within the machine learning process, specifically for performing a selective convolution operation.In the selective convolution operation, the convolution is executed exclusively on pixels identified by a genetic algorithm. This method selects and computes pixels based on a ratio determined by the genetic algorithm, effectively reducing the computational workload by the specified ratio. The paper thoroughly explores the integration of genetic algorithms into machine learning computations, monitoring the fitness of each generation to ascertain if it reaches the target value. This approach is then compared with the computational requirements of existing methods.The learning process involves iteratively training generations to ensure that the fitness adequately converges.