Tae-Kook Kim

Prof. Tae-Kook Kim

Tongmyong university
orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
5 May 2025 in IEEE Access
Verified
Journal Article
Open access
BPBo Peng
Bo Peng
Tae-Kook KimTae-Kook Kim
Tae-Kook Kim
Domestic fires (residential and indoor) result in substantially higher deaths compared to other types of conflagrations, making early detection crucial to minimizing the loss of life and property. Existing studies and datasets predominantly focus on wildfire detection, with few datasets that capture the complexity of indoor environments and the subtle characteristics of early-stage fires. This gap causes object detection algorithms to produce high false positive and false negative rates in research on the early detection of such fires. To address this, we developed a domestic-fire dataset and proposed YOLO-HF, an early home-fire detection model based on YOLOv5s. To enhance the detection performance for small flames and smoke in a fire’s early stages, we proposed the parametric boosted channel attention (PBCA) mechanism. PBCA fuses global information and adaptively adjusts weights, improving the model’s ability to select and represent key features with minimal parameter overhead. Additionally, we incorporated the RepNCSPELAN4 feature extraction module, which preserves and leverages multi-scale feature information through multi-stage convolution and multi-layer feature fusion. To mitigate information loss caused by the stride setting in traditional downsampling methods, we employed space-to-depth (SPD) downsampling, which retains more spatial details. The experimental results demonstrate that YOLO-HF achieves a 4.6% improvement in Recall, 2.8% in mAP50, and 4.2% in mAP50-95 compared to existing models, all while maintaining its lightweight design. The model size is 13.8 MB, and its frame rate of 66.9 fps, meets real-time detection requirements. Detection experiments using content captured with domestic cameras validated the model’s generalization capability and robustness.

16 August 2014 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
Tae-Kook KimTae-Kook Kim
Tae-Kook Kim
EKEui-Jik Kim
Eui-Jik Kim

22 June 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Yeunwoong KyungYeunwoong Kyung
Yeunwoong Kyung
Tae-Kook KimTae-Kook Kim
Tae-Kook Kim
Handover support is one of the important issues in mobile networks to guarantee the quality of service (QoS) requirements for mobile users. Alongside the development of network technologies, handover management to provide service continuity has been researched and applied for the Internet or cellular networks such as 3G/4G/5G. However, each network paradigm provides its own individual handover management system, even though there are different kinds of QoS requirements for various mobile services. This causes inefficient network resource utilization from the network operators’ perspectives. Therefore, this paper proposes a QoS-aware flexible mobility management scheme for software-defined networking (SDN)-based mobile networks. The proposed scheme classifies flows into four classes based on the QoS requirements of services in terms of delay and loss tolerance. According to the classified service characteristics, it provides a differential handover method for each flow class to support efficient network operation without any service degradation by interacting between the forwarding plane nodes and SDN controller. The performance analysis shows that the proposed scheme enables flexible network resource utilization, satisfying the QoS requirements for each class well compared to the conventional schemes that only consider their own individual handover procedure.

1 April 2014 in International Journal of Distributed Sensor Networks
Verified
Journal Article
Open access
Tae-Kook KimTae-Kook Kim
Tae-Kook Kim
EKEui-Jik Kim
Eui-Jik Kim
The global positioning system (GPS) is a popular choice for accurate location sensing and is often used in navigation systems. However, GPS fails to operate inside buildings because satellite signals are blocked. Thus, GPS cannot be used for localization indoors. Moreover, it is difficult to distinguish between the different floors. Research to overcome this problem using the ultrawideband (UWB), radio frequency identification (RFID), and infrared ray (IR) has been conducted. These methods, however, have drawbacks, such as the need for an additional communication module and database. Wireless local area network (WLAN) access point (AP) is widely installed at various locations, and using these WLAN APs can be a viable alternative. The proposed system in this paper indicates the location information in the service set identifier (SSID) of virtual AP. Therefore, merely by scanning the WLAN signals, mobile users can detect their location indoors.

1 January 2014 in IEICE Transactions on Information and Systems
Verified
Journal Article
Closed access
YKYeunwoong Kyung
Yeunwoong Kyung
TYTaihyong Yim
Taihyong Yim
Tae-Kook KimTae-Kook Kim
Tae-Kook Kim
TNTri M. Nguyen
Tri M. Nguyen
JPJinwoo Park
Jinwoo Park

21 November 2015 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
Tae-Kook KimTae-Kook Kim
Tae-Kook Kim
EKEui-Jik Kim
Eui-Jik Kim