Search Results (23)

Herein, an integrated system is developed based on knitted strain sensors for real-time translation of sign language into text and audio voices. To investigate how the structural characteristics of the knit affect the electrical performance, the position of the conductive yarn and the presence or absence of elastic yarn are set as experimental variables, and five distinct sensors are manufactured. A comprehensive analysis of the electrical and mechanical performance, including sensitivity, responsiveness, reliability, and repeatability, reveals that the sensor with a plain-plated-knit structure, no elastic yarn included, and the conductive yarn positioned uniformly on the back exhibits the best performance, with a gauge factor (GF) of 88. The sensor exhibited a response time of less than 0.1 s at 50 cycles per minute (cpm), demonstrating that it detects and responds promptly to finger joint bending movements. Moreover, it exhibits stable repeatability and reliability across various angles and speeds, confirming its optimization for sign language recognition applications. Based on this design, an integrated textile-based system is developed by incorporating the sensor, interconnections, snap connectors, and a microcontroller unit (MCU) with built-in Bluetooth Low Energy (BLE) technology into the knitted glove. The complete system successfully recognized 12 Korean Sign Language (KSL) gestures in real time and output them as both text and audio through a dedicated application, achieving a high recognition accuracy of 98.67%. Thus, the present study quantitatively elucidates the structure–performance relationship of a knitted sensor and proposes a wearable system that accounts for real-world usage environments, thereby demonstrating the commercialization potential of the technology. Full article

Recent advancements in information and communication technology have driven various organizations, including businesses, government agencies, and institutions, to digitize and manage critical documents. Document digitization mitigates spatial constraints on storage and offers significant advantages in transmission and management. However, while digitization offers many benefits, the development of image processing software has also increased the risk of forgery and manipulation of digital documents. Digital documents, ranging from everyday documents to those handled by major institutions, can become targets of forgery, and the unrestricted distribution of such documents may cause social disruption. As a result, research on digital document forgery detection has been actively conducted in various countries, with recent studies focusing on improving detection accuracy using deep learning techniques. However, most of the document image datasets generated for the development of deep learning models are English-based documents. Consequently, forgery detection models trained on these English-based datasets may perform well on English documents but may not achieve the same level of accuracy when applied to documents in other languages. This study systematically examines the necessity of language-specific datasets by analyzing the impact of visual complexity on forgery detection accuracy. Specifically, this study analyzes differences in forgery characteristics between English and Korean documents as representative cases and evaluates the classification performance of a forgery detection model trained on an English dataset when applied to both English and Korean documents. The experimental results indicate that forged document images exhibit distinct visual alterations depending on the language. Furthermore, the detection performance of models trained on English-based datasets varies according to the language of the training and test data. These findings underscore the necessity of developing datasets and model architectures tailored to the linguistic and structural characteristics of each language to enhance forgery detection efficacy. Additionally, the results highlight the importance of multilingual datasets in deep learning-based forgery detection, providing a foundation for the advancement of language-specific detection models. Full article

Few-shot font generation seeks to create high-quality fonts using minimal reference style images, addressing traditional font design’s labor-intensive and time-consuming nature, particularly for languages with large character sets like Chinese and Korean. Existing methods often require multi-stage training or predefined components, which can be time-consuming and limit generalizability. This paper introduces Patch-Font, a novel single-stage method that overcomes the limitations of prior approaches, such as multi-stage training or reliance on predefined components, by integrating a patch-based attention mechanism and a multitask encoder. Patch-Font jointly captures global style elements (e.g., overall font family characteristics) and local style details (e.g., serifs, stroke shapes), ensuring high fidelity to the target style while maintaining computational efficiency. Our approach incorporates triplet margin loss with hard positive/negative mining to disentangle style from content and a style fidelity loss to enhance local style consistency. Experiments on Korean (printed and handwritten) and Chinese fonts demonstrate that Patch-Font outperforms state-of-the-art methods in style accuracy, perceptual quality, and generation speed while generalizing robustly to unseen characters and font styles. By simplifying the font creation process and delivering high-quality results, Patch-Font represents a significant step forward in making font design more accessible and scalable for diverse languages. Full article

With the advancement of human-computer interaction, the role of emotion recognition has become increasingly significant. Emotion recognition technology provides practical benefits across various industries, including user experience enhancement, education, and organizational productivity. For instance, in educational settings, it enables real-time understanding of students’ emotional states, facilitating tailored feedback. In workplaces, monitoring employees’ emotions can contribute to improved job performance and satisfaction. Recently, emotion recognition has also gained attention in media applications such as automated movie dubbing, where it enhances the naturalness of dubbed performances by synchronizing emotional expression in both audio and visuals. Consequently, multimodal emotion recognition research, which integrates text, speech, and video data, has gained momentum in diverse fields. In this study, we propose an emotion recognition approach that combines text and speech data, specifically incorporating the characteristics of the Korean language. For text data, we utilize KoELECTRA to generate embeddings, and for speech data, we extract features using HuBERT embeddings. The proposed multimodal transformer model processes text and speech data independently, subsequently learning interactions between the two modalities through a Cross-Modal Attention mechanism. This approach effectively combines complementary information from text and speech, enhancing the accuracy of emotion recognition. Our experimental results demonstrate that the proposed model surpasses single-modality models, achieving a high accuracy of 77.01% and an F1-Score of 0.7703 in emotion classification. This study contributes to the advancement of emotion recognition technology by integrating diverse language and modality data, suggesting the potential for further improvements through the inclusion of additional modalities in future work. Full article

With increasing industrial sophistication and complexity, workplaces are increasingly prone to occupational accidents, causing negative impacts on workers and employers, including economic losses and decreased productivity. South Korea occupational safety and health has implemented new policies addressing potential risks to overcome stagnation in industrial accident reduction and predict site accidents from past cases. Cases are human-classified according to rules, including occurrence type or original causal materials. However, human errors, subjective judgments, synonyms, and terms incorrectly used by classifiers reduce original data quality and impede developments or applications of policies, technologies, and methods preventing accidents based on past accidents. This study proposes three artificial intelligence models to objectively classify the occurrence type of accident cases. Models are developed based on a natural language processing model (KoBERT), which considers Korean language characteristics. Each model is tested by sequentially performing sentence preprocessing, keyword replacement, and morphological analysis. The proposed Model 3 exhibits 93.1% accuracy, which was the highest among tested models. Up to three classification categories for occurrence type are allowed to assist objective classification. The accident case-based occurrence type classification model is effective for industrial accident prevention, aiding in strategy development and reducing social costs. Full article

This study examined the content characteristics and user responses of athlete-run sports YouTube channels, providing empirical insights for content production strategies and contributing to the development of athlete-run sports YouTube channels. Content analysis was conducted on 3306 videos posted on 20 popular YouTube channels of South Korean athletes from 1 January 2020 to 31 December 2021. The formal characteristics analyzed included video length, the presence of foreign language subtitles, paid advertisements, and information sources. The content characteristics examined were the types of sports events, main content themes, and whether the content matched the athlete’s sport. Results revealed significant differences in content characteristics and user responses based on whether the athletes were active or retired. This study’s distinctive contribution lies in highlighting the evolving role of athletes as content creators and providing strategic implications for enhancing the competitiveness of athlete-run sports YouTube channels. Future research should consider a broader range of sports YouTubers and a wider variety of YouTube channels to gain comprehensive insights into the sports content ecosystem on this platform. Full article

The present study aimed to elucidate the neural mechanisms underpinning the visual recognition of morphologically complex verbs in Korean, a morphologically rich, agglutinative language with inherent polymorphemic characteristics. In an fMRI experiment with a lexical decision paradigm, we investigated whether verb inflection types (base, regular, and irregular) are processed through separate mechanisms or a single system. Furthermore, we explored the semantic influence in processing inflectional morphology by manipulating the semantic ambiguity (homonymous vs. unambiguous) of inflected verbs. The results showed equivalent activation levels in the left inferior frontal gyrus for both regular and irregular verbs, challenging the dichotomy between the two. Graded effects of verb regularity were observed in the occipitotemporal regions, with regular inflections eliciting increased activation in the fusiform and lingual gyri. In the middle occipital gyrus, homonyms showed decreased activation relative to that of unambiguous words, specifically for base and irregular forms. Furthermore, the angular gyrus exhibited significant modulation with all verb types, indicating a semantic influence during morphological processing. These findings support single-system theories and the connectionist framework, challenging the assumptions of purely orthographic morphological decomposition and dual-mechanism accounts. Furthermore, they provide evidence for a semantic influence during morphological processing, with differential reliance on semantic activation for regular and irregular inflections. Full article

Recently, the analysis of emotions in social media has been considered a significant NLP task in digital and social-media-driven environments due to their pervasive influence on communication, culture, and consumer behavior. In particular, the task of Aspect-Based Emotion Analysis (ABEA), which involves analyzing the emotions of various targets within a single sentence, has drawn attention to understanding complex and sophisticated human language. However, ABEA is a challenging task in languages with limited data and complex linguistic properties, such as Korean, which follows spiral thought patterns and has agglutinative characteristics. Therefore, we propose a Korean Target-Attention-Based Emotion Classifier (KOTAC) designed to utilize target information by unveiling emotions buried within intricate Korean language patterns. In the experiment section, we compare various methods of utilizing and representing vectors of target information for the attention mechanism. Specifically, our final model, KOTAC, shows a performance enhancement on the MTME (Multiple Targets Multiple Emotions) samples, which include multiple targets and distinct emotions within a single sentence, achieving a 0.72% increase in F1 score over a baseline model without effective target utilization. This research contributes to the development of Korean language models that better reflect syntactic features by innovating methods to not only obtain but also utilize target-focused representations. Full article

This study explores the dynamics of questioning practices and speech-style shifting in Korean entertainment talk shows. While prior research has examined the topic of questioning practices in the Korean language, mostly in everyday conversation or educational discourse, this article expands this investigation to encompass semi-institutional discourse, particularly focusing on the context of entertainment talk shows. This research also contributes to understanding the pragmatic characteristics of two Korean honorific speech styles, namely the polite (-yo) and deferential (-(su)pnita/-(su)pnikka) styles, by investigating their interplay and transitions. Adopting an interactional approach to discourse and drawing upon membership categorization analysis and conversation analysis, this study analyzes the discourse of 15 entertainment talk shows, with a special focus on approximately 1500 sentential units, 325 of which are questions. The analysis of these utterances provides an account of the utilization of linguistic resources in questioning practices and the utilization of the two Korean honorific speech styles in the joint construction of social activities and identities within the entertainment talk show setting. The selection of linguistic resources for questioning practices and style shifting is closely intertwined with the management of entertainment and institutional dynamics among the participants in this particular setting. Full article

This paper proposes a hybrid deep learning emotion classification system (HDECS), a hybrid multimodal deep learning system designed for emotion classification in a specific national language. Emotion classification is important in diverse fields, including tailored corporate services, AI advancement, and more. Additionally, most sentiment classification techniques in speaking situations are based on a single modality: voice, conversational text, vital signs, etc. However, analyzing these data presents challenges because of the variations in vocal intonation, text structures, and the impact of external stimuli on physiological signals. Korean poses challenges in natural language processing, including subject omission and spacing issues. To overcome these challenges and enhance emotion classification performance, this paper presents a case study using Korean multimodal data. The case study model involves retraining two pretrained models, LSTM and CNN, until their predictions on the entire dataset reach an agreement rate exceeding 0.75. Predictions are used to generate emotional sentences appended to script data, which are further processed using BERT for final emotion prediction. The research result is evaluated by using categorical cross-entropy (CCE) to measure the difference between the model’s predictions and actual labels, F1 score, and accuracy. According to the evaluation, the case model outperforms the existing KLUE/roBERTa model with improvements of 0.5 in CCE, 0.09 in accuracy, and 0.11 in F1 score. As a result, the HDECS is expected to perform well not only on Korean multimodal datasets but also on sentiment classification considering the speech characteristics of various languages and regions. Full article

Background: Alzheimer’s disease (AD) is the most common form of dementia, which makes the lives of patients and their families difficult for various reasons. Therefore, early detection of AD is crucial to alleviating the symptoms through medication and treatment. Objective: Given that AD strongly induces language disorders, this study aims to detect AD rapidly by analyzing the language characteristics. Materials and Methods: The mini-mental state examination for dementia screening (MMSE-DS), which is most commonly used in South Korean public health centers, is used to obtain negative answers based on the questionnaire. Among the acquired voices, significant questionnaires and answers are selected and converted into mel-frequency cepstral coefficient (MFCC)-based spectrogram images. After accumulating the significant answers, validated data augmentation was achieved using the Densenet121 model. Five deep learning models, Inception v3, VGG19, Xception, Resnet50, and Densenet121, were used to train and confirm the results. Results: Considering the amount of data, the results of the five-fold cross-validation are more significant than those of the hold-out method. Densenet121 exhibits a sensitivity of 0.9550, a specificity of 0.8333, and an accuracy of 0.9000 in a five-fold cross-validation to separate AD patients from the control group. Conclusions: The potential for remote health care can be increased by simplifying the AD screening process. Furthermore, by facilitating remote health care, the proposed method can enhance the accessibility of AD screening and increase the rate of early AD detection. Full article

Spam detection is an essential and unavoidable problem in today’s society. Most of the existing studies have used string-based detection methods with models and have been conducted on a single language, especially with English datasets. However, in the current global society, research on languages other than English is needed. String-based spam detection methods perform different preprocessing steps depending on language type due to differences in grammatical characteristics. Therefore, our study proposes a text-processing method and a string-imaging method. The CNN 2D visualization technology used in this paper can be applied to datasets of various languages by processing the data as images, so they can be equally applied to languages other than English. In this study, English and Korean spam data were used. As a result of this study, the string-based detection models of RNN, LSTM, and CNN 1D showed average accuracies of 0.9871, 0.9906, and 0.9912, respectively. On the other hand, the CNN 2D image-based detection model was confirmed to have an average accuracy of 0.9957. Through this study, we present a solution that shows that image-based processing is more effective than string-based processing for string data and that multilingual processing is possible based on the CNN 2D model. Full article

Background and Objectives: The Temperament Evaluation of Memphis, Pisa, Paris and San Diego Autoquestionnaire (TEMPS-A) is designed to assess affective temperaments. The short version of the TEMPS-A (TEMPS-A-SV) has been translated into various languages for use in research and clinical settings. However, no research has been conducted to validate the Korean version of the TEMPS-A-SV in patients with mood disorders. The goal of this study is to evaluate the reliability and validity of the TEMPS-A-SV in Korean mood disorder patients. Materials and Methods: In this cross-sectional retrospective study, a total of 715 patients (267 patients with major depressive disorder, 94 patients with bipolar disorder I, and 354 patients with bipolar disorder II) completed the Korean TEMPS-A-SV. Cronbach’s alpha and McDonald’s omega were used to assess the reliability. Exploratory factor analysis (EFA) was also performed. Spearman’s correlation coefficient was used to examine associations between the five temperaments. The difference in five temperament scores between the gender or diagnosis groups was analyzed, and the correlation between five temperament scores and age was tested. Results: The Korean TEMPS-A-SV displayed good internal consistency (α = 0.65–0.88, ω = 0.66–0.9) and significant correlations between the subscales except one (the correlation between hyperthymic and anxious). Using EFA, a two-factor structure was produced: Factor I (cyclothymic, depressive, irritable, and anxious) and Factor II (hyperthymic). The cyclothymic temperament score differed by gender and the anxious temperament score was significantly correlated with age. All the temperaments, except for irritable temperament, showed significant differences between diagnosis groups. Conclusions: Overall, the results show that the TEMPS-A-SV is a reliable and valid measurement that can be used for estimating Koreans’ affective temperaments. However, more research is required on affective temperaments and associated characteristics in people with mood disorders. Full article

Formed alongside the arrival of the first Korean immigrants in Hawaii in 1903, the Korean American Protestant Church has played a significant role in the social, political, and religious lives of Koreans in the United States. However today, membership is declining and the newer generations represent a smaller part of the movement leading the Korean American Protestant Church to review and reform its current respective practices of ministry in terms of language, teaching, preaching, worship, and theological orientation. This article focuses on the critical issues that the Korean American Protestant Church is facing and examines the current common practice of Korean American worship. Additionally, this article proposes theological and liturgical suggestions that could be utilized to help realize the goal of Korean American intergenerational worship. These suggestions are formed against the background of five notable characteristics of the Trinity—flexibility (innovation), communication (sharing and empathy), interconnection, ubiquity, and holistic artistry—which are essential to achieving intergenerational worship and its design. As a sample liturgy, worship combined with a meal invites children and young adults, born and raised in the United States, to participate in leadership roles with first-generation adults, which directly correlates with the aforementioned characteristics. As such, in essence, liturgies like these will lead worshippers to experience the embodied theology of intergenerational worship, based on a practical and theological concept of interdependence and awareness. Full article

This study aimed to identify all of the characteristics of bee venom acupuncture (BVA) for the treatment of lower back pain (LBP) that are described in the Korean literature, and to provide English-speaking researchers with bibliometrics. Six Korean electronic databases and sixteen Korean journals on BVA treatment for back pain were searched up to February 2022. This report included and analyzed 64 clinical studies on BVA interventions for back pain and 1297 patients with LBP. The most common disease in patients with back pain was lumbar herniated intervertebral discs (HIVD) of the lumbar spine (L-spine). All studies used bee venom (BV) diluted with distilled water. The concentration of BVA for HIVD of L-spine patients with LBP ranged from 0.01 to 5.0 mg/mL; the dosage per treatment was 0.02–2.0 mL, and for a total session was 0.3–40.0 mL. The most used outcome measure was the visual analogue scale for back pain (n = 45, 70.3%), and most of the papers reported that each outcome measure had a positive effect. Korean clinical studies were typically omitted from the review research, resulting in potential language bias. This study provides clinical cases in Korea for future development and standardization of BVA treatment for back pain. Full article