Yeon-Kug Moon

Prof. Yeon-Kug Moon


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
SMSathishkumar Moorthy
Sathishkumar Moorthy
YMYeon-Kug Moon
Yeon-Kug Moon
Multimodal emotion recognition involves leveraging complementary relationships across modalities to enhance the assessment of human emotions. Networks that integrate diverse information sources outperform single-modal approaches while offering greater robustness against noisy or missing data. Current emotion recognition approaches often rely on cross-modal attention mechanisms, particularly audio and visual modalities; however, these methods do not assume the complementary nature of the data. Despite making this assumption, it is not uncommon to see non-complementary relationships arise in real-world data, reducing the effectiveness of feature integration that assumes consistent complementarity. While audio–visual co-learning provides a broader understanding of contextual information for practical implementation, discrepancies between audio and visual data, such as semantic inconsistencies, pose challenges and lay the groundwork for inaccurate predictions. In this way, they have limitations in modeling the intramodal and cross-modal interactions. In order to address these problems, we propose a multimodal learning framework for emotion recognition, called the Hybrid Multi-ATtention Network (HMATN). Specifically, we introduce a collaborative cross-attentional paradigm for audio–visual amalgamation, intending to effectively capture salient features over modalities while preserving both intermodal and intramodal relationships. The model calculates cross-attention weights by analyzing the relationship between combined feature illustrations and distinct modes. Meanwhile, the network employs the Hybrid Attention of Single and Parallel Cross-Modal (HASPCM) mechanism, comprising a single-modal attention component and a parallel cross-modal attention component, to harness complementary multimodal data and hidden features to improve representation. Additionally, these modules exploit complementary and concealed multimodal information to enhance the richness of feature representation. Finally, the efficiency of the proposed method is demonstrated through experiments on complex videos from the AffWild2 and AFEW-VA datasets. The findings of these tests show that the developed attentional audio–visual fusion model offers a cost-efficient solution that surpasses state-of-the-art techniques, even when the input data are noisy or missing modalities.

7 June 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
AMAxel Gedeon Mengara Mengara
Axel Gedeon Mengara Mengara
YMYeon-Kug Moon
Yeon-Kug Moon
Multimodal emotion recognition faces substantial challenges due to the inherent heterogeneity of data sources, each with its own temporal resolution, noise characteristics, and potential for incompleteness. For example, physiological signals, audio features, and textual data capture complementary yet distinct aspects of emotion, requiring specialized processing to extract meaningful cues. These challenges include aligning disparate modalities, handling varying levels of noise and missing data, and effectively fusing features without diluting critical contextual information. In this work, we propose a novel Mixture of Experts (MoE) framework that addresses these challenges by integrating specialized transformer-based sub-expert networks, a dynamic gating mechanism with sparse Top-k activation, and a cross-modal attention module. Each modality is processed by multiple dedicated sub-experts designed to capture intricate temporal and contextual patterns, while the dynamic gating network selectively weights the contributions of the most relevant experts. Our cross-modal attention module further enhances the integration by facilitating precise exchange of information among modalities, thereby reinforcing robustness in the presence of noisy or incomplete data. Additionally, an auxiliary diversity loss encourages expert specialization, ensuring the fused representation remains highly discriminative. Extensive theoretical analysis and rigorous experiments on benchmark datasets—the Korean Emotion Multimodal Database (KEMDy20) and the ASCERTAIN dataset—demonstrate that our approach significantly outperforms state-of-the-art methods in emotion recognition, setting new performance baselines in affective computing.

27 November 2024 in Electronics
Verified
Journal Article
Open access
PDF file
HIHammad Iqbal
Hammad Iqbal
AKArshad Khan
Arshad Khan
NNNarayan Nepal
Narayan Nepal
FKFaheem Khan
Faheem Khan
YMYeon-Kug Moon
Yeon-Kug Moon
Lung diseases are a major global health concern, with nearly 4 million deaths annually, according to the World Health Organization (WHO). Chest X-rays (CXR) are widely used as a cost-effective and efficient diagnostic tool by radiologists to detect conditions such as pneumonia, tuberculosis, COVID-19, and lung cancer. This review paper provides an overview of the current research on diagnosing lung diseases using CXR images and Artificial Intelligence (AI), without focusing on any specific disease. It examines different approaches employed by researchers to leverage CXR, an accessible diagnostic medium, for early lung disease detection. This review shortlisted 11 research papers addressing this problem through AI, exploring the datasets used and their sources. Results varied across studies: for lung cancer, Deep Convolutional Neural Network (DCNN) achieved 97.20% accuracy, while multiclass frameworks like ResNet152V2+Bi-GRU (gated reccurent unit) reached 79.78% and 93.38%, respectively. For COVID-19 detection, accuracy rates of 98% and 99.37% were achieved using EfficientNet and Parallel Convolutional Neural Network-Extreme Learning Machine (CNN-ELM). Additionally, studies on the CXR-14 dataset (14 classes) showed high accuracy, with MobileNet V2 reaching 94%. Other notable results include 73% accuracy with VDSNet, 98.05% with VGG19+CNN for three classes, and high accuracy in detecting pediatric pneumonia, lung opacity, pneumothorax, and tuberculosis.

14 November 2024 in IEEE Access
Verified
Journal Article
Open access
GCGovind Ram Chhimpa
Govind Ram Chhimpa
AKAjay Kumar
Ajay Kumar
SGSunita Garhwal
Sunita Garhwal
DHDhiraj
Dhiraj
FKFaheem Khan
Faheem Khan
YMYeon-Kug Moon
Yeon-Kug Moon
Eye movements are essential in human-computer interaction (HCI) because they offer insights into individuals’ cognitive states and visual attention. Techniques for adequately assessing gaze have increased in the last two decades. Notably, video-based tracking methods have gained considerable interest within the research community due to their nonintrusive nature, enabling precise and convenient gaze estimation without physical contact or invasive measures. This paper introduces a video-based gaze-tracking method that presents an affordable, user-friendly, and dependable human-computer interaction (HCI) system based on iris movement. By utilizing the MediaPipe face mesh model, facial features are extracted from real-time video sequences. A 5-point user-specific calibration and multiple regression techniques are employed to predict the gaze point on the screen accurately. The proposed system effectively handles changes in body position and user posture through real-time re-calibration using z-index tracking. Furthermore, it compensates for minor head movements that may introduce inaccuracies. The proposed system is cost-effective, with a general cost below $25, which may vary based on camera usage. Thirteen participants were involved in the system testing. The system demonstrates a high level of sensitivity to low light conditions, a strong response to changes in distance, and a moderate reaction to glasses, with an average frame processing time of 0.047 seconds. On average, it achieves a visual angle accuracy of 1.12 degrees with head movement and 1.3 degrees without head movement.

14 November 2024 in Journal of Cloud Computing
Verified
Journal Article
Open access
PDF file
YAYasir Ali
Yasir Ali
HKHabib Ullah Khan
Habib Ullah Khan
FKFaheem Khan
Faheem Khan
YMYeon-Kug Moon
Yeon-Kug Moon
Internet of Things (IoT) platforms have become the building blocks of any automated system but they are more important in case of industrial systems where sensitive data are captured and handled by the information system. Therefore, it is imperative to deploy the right IoT platform to perform the computational and operational tasks in a better way. During the last few years, an array of IoT technologies/platforms with different capabilities and features were introduced in the markets. This abrupt rise created selection and decision-making issues particularly for the network engineers, designers, and industrial managers due to a lack of technical understanding and skill in this area. Therefore, we present an integrated assessment model focusing on evaluating and ranking IoT platforms in the industrial environment. It encompasses multiple methods such as the proposed model leverages a well-known data collection technique such as Delphi for data collection related to the criteria features. It adopts the Analytic Hierarchy Process (AHP) for giving weights to the criteria features. The technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method has been applied for the evaluation of the top twenty (20) Industrial IoT(IIoT) platform alternatives according to the proposed criteria. It selects the most rational choice of IoT platform that can be employed in the Industry 4.0 setting. The proposed integrated assessment model produces the most accurate and consistent outcomes. Hence, it is believed that it can be used as a guideline by different stakeholders like researchers, developers, network engineers, and policymakers for the assessment and deployment of IoT platforms in the industrial environment. It is believed that it is the first kind of multi-methods integrated assessment mode for the assessment, decision-making, and prioritization of IoT technologies in the industry 4.0 domain.

14 January 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
Habib Ullah KhanHabib Ullah Khan
Habib Ullah Khan
MAMuhammad Abbas
Muhammad Abbas
SNShah Nazir
Shah Nazir
FKFaheem Khan
Faheem Khan
YMYeon-Kug Moon
Yeon-Kug Moon
The adoption of Financial Technology (FinTech), along with the enhancement of Human Resource (HR) competencies, service innovation, and firm growth, plays a crucial role in the development of the banking sector. Despite their importance, obtaining reliable results is often challenging due to the complex, high-dimensional correlations among various features that affect the industry. To address this issue, this research introduces a hybrid Multi-Criteria Decision-Making (MCDM) model that integrates the Entropy-Weighted Method (EWM) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The primary objective of this study is to systematically evaluate and rank multiple alternatives based on key criteria using the EWM-TOPSIS approaches. Specifically, the analysis considers eleven multifaceted characteristics and eight potential alternatives (A1 to A8), revealing the significant influence of the proposed MCDM approaches in assessing FinTech adoption, HR competency, service innovation, and firm growth. The findings underscore the effectiveness of the entropy-TOPSIS approaches in providing a structured analysis for a smarter and well-informed decision-making. Ultimately, this research proposes the best alternative from the evaluated options, contributing valuable insights into the future role of FinTech, HR competencies, service innovation, and firm growth within the banking sector.