• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3658-3679
• /
• 2022

Classification of persons wearing and not wearing face masks in images has emerged as a new computer vision problem during the COVID-19 pandemic. In order to address this problem and scale up the research in this domain, in this paper a hybrid technique by employing ResNet-101 and multi-layer perceptron (MLP) classifier has been proposed. The proposed technique is tested and validated on a self-created face masks classification dataset and a standard dataset. On self-created dataset, the proposed technique achieved a classification accuracy of 97.3%. To embrace the proposed technique, six other state-of-the-art CNN feature extractors with six other classical machine learning classifiers have been tested and compared with the proposed technique. The proposed technique achieved better classification accuracy and 1-6% higher precision, recall, and F1 score as compared to other tested deep feature extractors and machine learning classifiers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.454-460
• /
• 2020

Artificial intelligence assistants that provide speech recognition operate through cloud-based voice recognition with high accuracy. In cloud-based speech recognition, Wake-Up-Word (WUW) detection plays an important role in activating devices on standby. In this paper, we compare the performance of Convolutional Neural Network (CNN)-based WUW detection models for mobile devices by using Google's speech commands dataset, using the spectrogram and mel-frequency cepstral coefficient features as inputs. The CNN models used in this paper are multi-layer perceptron, general convolutional neural network, VGG16, VGG19, ResNet50, ResNet101, ResNet152, MobileNet. We also propose network that reduces the model size to 1/25 while maintaining the performance of MobileNet is also proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1028-1033
• /
• 1991

This paper describes the design of a neural network estimator to estimate weld pool sizes for on-line use of quality monitoring and control in GMA welding processes. The estimator utilizes surface temperatures measured at various points on the top surface of the weldment as its input. The main task of the neural net is to realize the mapping characteristics from the point temperatures to the weld pool sizes through training, A series of bead-on plate welding experiments were performed to assess the performance of the neural estimator.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.348-352
• /
• 2000

Intelligent agents represent parts and manufacturing resources, which cooperate, negotiate, and compete with each other. The negotiation between agents is in general based on the Contract-Net-Protocol. This paper describes a new approach to negotiation-based job shop scheduling. The proposed method includes multi-negotiation strategy as well as single-negotiation. A case study showing the comparison of various negotiation strategies is also given.

• Nuclear Engineering and Technology
• /
• v.52 no.5
• /
• pp.975-983
• /
• 2020

Since the Fukushima Daiichi accident in 2011, concerns for the safety of multi-unit Nuclear Power Plant (NPP) sites have risen. This is because more than 70% of NPP sites are multi-unit sites that have two or more NPP units and a multi-unit accident occurred for the first time. After this accident, Probability Safety Assessment (PSA) has been considered in many countries as one of the tools to quantitatively assess the safety for multi-unit NPP sites. One of the biggest concerns for a multi-unit accident such as Fukushima is that the consequences (health and economic) will be significantly higher than in the case of a single-unit accident. However, many studies on multi-unit PSA have focused on Level 1 & 2 PSA, and there are many challenges in terms of public acceptance due to various speculations without an engineering background. In this study, two kinds of multi-unit Level 3 PSA for multi-unit site have been carried out. The first case was the estimation of multi-unit risk with conservative assumptions to investigate the margin between multi-unit risk and QHO, and the other was to identify the effect of time delays in releases between NPP units on the same site. Through these two kinds of assessments, we aimed at investigating the level of multi-unit risk and understanding the characteristics of risk in a multiunit context.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.4
• /
• pp.677-685
• /
• 2012

Recently, wireless multi-networking technology has been studied for supporting multi-interface in mobile node. As the related work, in the IETF NetExt WG, the extension of Proxy Mobile IPv6 protocol for supporting flow mobility is actively on going in discussion. PMIPv6 protocol supports simultaneous access through the multi-interface in a mobile node and inter-technology handover between multiple interfaces. However, this protocol can not support flow mobility. Thus, in this paper, when a mobile node connects to PMIPv6 domain through multi-interface, as a way to support flow mobility, the design of logical interface and Home Network Prefix change scheme based on logical interface are proposed, We show that the proposed scheme can perform flow mobility service without end-to-end disconnection in PMIPv6 domain.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.5
• /
• pp.1709-1718
• /
• 2017

This paper presents a hybrid stochastic deterministic multi-timescale scheduling (SDMS) approach for generation scheduling of a power grid. SDMS considers flexible resource options including conventional generation flexibility in a chance-constrained day-ahead scheduling optimization (DASO). The prime objective of the DASO is the minimization of the daily production cost in power systems with high penetration scenarios of variable generation. Furthermore, energy storage is scheduled in an hourly-ahead deterministic real-time scheduling optimization (RTSO). DASO simulation results are used as the base starting-point values in the hour-ahead online rolling RTSO with a 15-minute time interval. RTSO considers energy storage as another source of grid flexibility, to balance out the deviation between predicted and actual net load demand values. Numerical simulations, on the IEEE RTS test system with high wind penetration levels, indicate the effectiveness of the proposed SDMS framework for managing the grid flexibility to meet the net load demand, in both day-ahead and real-time timescales. Results also highlight the adequacy of the framework to adjust the scheduling, in real-time, to cope with large prediction errors of wind forecasting.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.2
• /
• pp.177-186
• /
• 2022

A network QoS model for the joint integrated C4I structure was proposed for the integration of network infrastructure and network operations(NetOps) for NCOE. Detailed QoS requirements process of the joint integrated C4I systems are needs in the Multi-Domain Operation Environment(MDOE). A process is proposed for identifying QoS requirements and establishing in the MDOE using JMT(Joint Mission Thread) reference architecture and solution architecture. Mission analysis identify JCOAs(Joint Critical Operational Activities) and related activities based on JMT & System architecture's OVs, and Information analysis identify QoS attributes using System architecture's SVs. Identifying QoS attributes will be registered at PPS Registry by pre-regulated process, and will be set-up by NetOps. MDOE QoS requirement Process will support efficiently MUM-T and smart defense platform users under the future uncertain battlefield circumstances.