• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.50-56
• /
• 2020

With the rapid development of deep neural network theory and application research, the effect of face detection has been improved. However, due to the complexity of deep neural network calculation and the high complexity of the detection environment, how to detect face quickly and accurately becomes the main problem. This paper is based on the relatively simple model of the MTCNN model, using FDDB (Face Detection Dataset and Benchmark Homepage), LFW (Field Label Face) and FaceScrub public datasets as training samples. At the same time of sorting out and introducing MTCNN(Multi-Task Cascaded Convolutional Neural Network) model, it explores how to improve training speed and Increase performance at the same time. In this paper, the dynamic image pyramid technology is used to replace the traditional image pyramid technology to segment samples, and OHEM (the online hard example mine) function in MTCNN model is deleted in training, so as to improve the training speed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1330-1336
• /
• 2019

As the Fourth Industrial Revolution era began, a variety of devices are running on the cloud. These various devices continue to generate various types of data or large amounts of multimedia data. To handle this situation, a large amount of storage is required, and big data technology is required to process stored data and obtain accurate information. NAS (Network Attached Storage) or SAN (Storage Area Network) technology is typically used to build high-speed, high-capacity storage in a network-based environment. In this paper, we propose a method to construct a mass storage device using Network-DAS which is an extension technology of DAS (Direct Attached Storage). Benchmark experiments were performed to verify the scalability of the storage system with 76 HDD. Experimental results show that the proposed high performance mass storage system is scalable and reliable.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.87-101
• /
• 2021

ESG Investment is emerging as a trend and common sense in the financial market. ESG Investment is an investment method that simultaneously pursue social sustainability and investment returns from a long-term perspective by reflecting non-financial factors such as environment, society and governance in addition to corporate financial performance in investment decisions. This study checked how the characteristics of ESG investment have been changed after Covid-19. Afterwards, it was confirmed that Covid-19 actually acted as a negative factor in the securities market by applying VAR model. At the same time, it was demonstrated that ESG indices of the US and Korea outperformed their benchmark in terms of return and risk during the pandemic regime. The result of this study hints that the importance of ESG investment will be unchanged after Covid-19. At the same time, it suggests that managers should avoid passive ESG management and engage in strategic ESG management based on knowledge management.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.6
• /
• pp.363-370
• /
• 2021

In this paper, we presented an optimized crack and flexural strength analysis of a glass-fiber reinforced polymer (GFRP) rebar, used as reinforcements for in-site railway concrete slabs. The insulation performance of a GFRP rebar has the advantage of avoiding the loss of signal current in an audio frequency (AF) track circuit. A full-scale experiment, and three-dimensional finite element simulation results were compared to validate our approaches. Parametric numerical results revealed that the diameters and arrangements of the GFRP rebar had a significant effect on the flexural strength and crack control performances of the concrete track slabs. The results of this study could serve as a benchmark for future guidelines in designing more efficient, and economical concrete slabs using the GFRP rebar.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1477-1482
• /
• 2022

Haze is a local weather phenomenon in which very small droplets float in the atmosphere, and the amount and characteristics of haze may vary depending on the region. In particular, these haze reduce visibility, which can cause air traffic interference and vehicle traffic accidents, and degrade the quality of security CCTVs and so on. Therefore, in the past 10 years, research on haze removal has been actively conducted to reduce damage caused by haze. In this study, local haze removal is performed by weight generation using a haziness degree evaluator to adaptively respond to haze-free, homogeneous haze, and non-homogeneous haze cases. And the proposed method improves the limitations of the existing static haze removal method, which assumes that there is haze in the input image and removes the haze. We also demonstrate the superiority of the proposed method through quantitative and qualitative performance evaluations with benchmark algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1816-1825
• /
• 2022

In this paper, we propose a new approach for tracking each human in a surveillance camera network with various resolution cameras. When tracking human on multiple non-overlapping cameras, the traditional appearance features are easily affected by various camera viewing conditions. To overcome this limitation, the proposed system utilizes facial information along with appearance information. In general, human images captured by the surveillance camera are often low resolution, so it is necessary to be able to extract useful features even from low-resolution faces to facilitate tracking. In the proposed tracking scheme, texture-based face descriptor is exploited to extract features from detected face after face frontalization. In addition, when the size of the face captured by the surveillance camera is very small, a super-resolution technique that enlarges the face is also exploited. The experimental results on the public benchmark Dana36 dataset show promising performance of the proposed algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.365-380
• /
• 2022

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

• Steel and Composite Structures
• /
• v.43 no.3
• /
• pp.327-340
• /
• 2022

A vast amount of experimental and analytical research has been conducted related to the seismic behavior and performance of concrete filled steel tubular (CFT) columns. This research has resulted in a wealth of information on the component behavior. However, analytical and experimental data for structural systems with CFT columns is limited, and the well-known behavior of steel or concrete structures is assumed valid for designing these systems. This paper presents the development of an analytical model for nonlinear analysis of composite moment resisting frame (CFT-MRF) systems with CFT columns and steel wide-flange (WF) beams under seismic loading. The model integrates component models for steel WF beams, CFT columns, connections between CFT columns and WF beams, and CFT panel zones. These component models account for nonlinear behavior due to steel yielding and local buckling in the beams and columns, concrete cracking and crushing in the columns, and yielding of panel zones and connections. Component tests were used to validate the component models. The model for a CFT-MRF considers second order geometric effects from the gravity load bearing system using a lean-on column. The experimental results from the testing of a four-story CFT-MRF test structure are used as a benchmark to validate the modeling procedure. An analytical model of the test structure was created using the modeling procedure and imposed-displacement analyses were used to reproduce the tests with the analytical model of the test structure. Good agreement was found at the global and local level. The model reproduced reasonably well the story shear-story drift response as well as the column, beam and connection moment-rotation response, but overpredicted the inelastic deformation of the panel zone.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.109-117
• /
• 2022

Most of real-world decision-making processes are used to optimize problems with many objectives of conflicting. Since the betterment of some objectives requires the sacrifice of other objectives, different objectives may not be optimized simultaneously. Consequently, Pareto solution can be considered as candidates of a solution with respect to a multi-objective optimization (MOP). Such problem involves two main procedures: finding Pareto solutions and choosing one solution among them. So-called multi-objective genetic algorithms have been proved to be effective for finding many Pareto solutions. In this study, we suggest a fitness evaluation method based on the achievement level up to the target value to improve the solution search performance by the multi-objective genetic algorithm. Using numerical examples and benchmark problems, we compare the proposed method, which considers the achievement level, with conventional Pareto ranking methods. Based on the comparison, it is verified that the proposed method can generate a highly convergent and diverse solution set. Most of the existing multi-objective genetic algorithms mainly focus on finding solutions, however the ultimate aim of MOP is not to find the entire set of Pareto solutions, but to choose one solution among many obtained solutions. We further propose an interactive decision-making process based on a visualized trade-off analysis that incorporates the satisfaction of the decision maker. The findings of the study will serve as a reference to build a multi-objective decision-making support system.