• Culinary science and hospitality research
• /
• v.14 no.1
• /
• pp.21-38
• /
• 2008

This research aimed to analyze the differences in financial variables classifying chain restaurants. A total of 126 samples were drawn from financial statements for $2001{\sim}2006$. As a result of analysis, there was a significant difference in Pillai's Trace, Wilks' Lambda, Hotelling's Trace, and Roy's Largest Root values at the significant probability value(p<0.05) based on F value in terms of stability among chain restaurants. Difference was found only in current rate and liabilities in ANOVA. There was a great difference in current rate among institutional restaurants, fast food restaurants, and cafeterias. There was a significant difference in Pillai's Trace, Wilks' Lambda, Hotelling's Trace, and Roy's Largest Root values at the significant probability value(p<0.05) based on F value in terms of restaurants' profitability. In ANOVA, difference was found only in net profits to net sales. It was revealed that all factors showed no significant differences in multiple comparison. All multi-variant test statistics showed a significant difference in growth and turnover. ANOVA showed a significant difference in net sales growth rate, net profit growth rate, and total assets growth rate.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.849-859
• /
• 2021

Prostate cancer (PCa) is a fatal disease that occurs in men. In general, PCa cells are found in the prostate gland. Early diagnosis is the key to prevent the spreading of cancers to other parts of the body. In this case, deep learning-based systems can detect and distinguish histological patterns in microscopy images. The histological grades used for the analysis were benign, grade 3, grade 4, and grade 5. In this study, we attempt to use transfer learning and fine-tuning methods as well as different model architectures to develop and compare the models. We implemented MobileNet, ResNet50, and DenseNet121 models and used three different strategies of freezing layers techniques of fine-tuning, to get various pre-trained weights to improve accuracy. Finally, transfer learning using MobileNet with the half-layer frozen showed the best results among the nine models, and 90% accuracy was obtained on the test data set.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.1-6
• /
• 2021

The purpose of this study is to improve the performance of the artificial neural network system for facial image analysis through the image landmark selection technique. For landmark selection, a CNN-based multi-layer ResNet model for classification of facial image age is required. From the configured ResNet model, a heat map that detects the change of the output node according to the change of the input node is extracted. By combining a plurality of extracted heat maps, facial landmarks related to age classification prediction are created. The importance of each pixel location can be analyzed through facial landmarks. In addition, by removing the pixels with low weights, a significant amount of input data can be reduced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• Journal of Internet Computing and Services
• /
• v.16 no.6
• /
• pp.69-78
• /
• 2015

Recently, research on the multi-agent system is developed actively in the various fields, especially on the control of complex system and optimization. In this study, we develop a multi-agent system for NPC simulation in game environment. The purpose of the development is to support quick and precise decision by inferencing the situation of the dynamic discrete domain, and to support an optimization process of the agent system. Our approach employed Petri-net as a basic agent model to simplify structure of the system, and used fuzzy inference engine to support decision making in various situation. Our experimentation describes situation of the virtual battlefield between the NPCs, which are divided two groups, such as fuzzy rule based agent and automata based agent. We calculate the percentage of winning and survival rate from the several simulations, and the result describes that the fuzzy rule based agent showed better performance than the automata based agent.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1281-1297
• /
• 2016

In recent years, personal videos have seen a tremendous growth due to the substantial increase in the use of smart devices and networking services in which users create and share video content easily without many restrictions. However, taking both into account would significantly improve event detection performance because videos generally have multiple modalities and the frame data in video varies at different time points. This paper proposes an event detection method. In this method, high-level features are first extracted from multiple modalities in the videos, and the features are rearranged according to time sequence. Then the association of the modalities is learned by means of DNN to produce a personal video event detector. In our proposed method, audio and image data are first synchronized and then extracted. Then, the result is input into GoogLeNet as well as Multi-Layer Perceptron (MLP) to extract high-level features. The results are then re-arranged in time sequence, and every video is processed to extract one feature each for training by means of DNN.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.871-884
• /
• 2021

The purpose of this study was to determine ways to increase efficiency in constructing and verifying artificial intelligence learning data on land cover using aerial and satellite images, and in applying the data to AI learning algorithms. To this end, multi-resolution datasets of 0.51 m and 10 m each for 8 categories of land cover were constructed using high-resolution aerial images and satellite images obtained from Sentinel-2 satellites. Furthermore, fine data (a total of 17,000 pieces) and coarse data (a total of 33,000 pieces) were simultaneously constructed to achieve the following two goals: precise detection of land cover changes and the establishment of large-scale learning datasets. To secure the accuracy of the learning data, the verification was performed in three steps, which included data refining, annotation, and sampling. The learning data that wasfinally verified was applied to the semantic segmentation algorithms U-Net and DeeplabV3+, and the results were analyzed. Based on the analysis, the average accuracy for land cover based on aerial imagery was 77.8% for U-Net and 76.3% for Deeplab V3+, while for land cover based on satellite imagery it was 91.4% for U-Net and 85.8% for Deeplab V3+. The artificial intelligence learning datasets on land cover constructed using high-resolution aerial and satellite images in this study can be used as reference data to help classify land cover and identify relevant changes. Therefore, it is expected that this study's findings can be used in the future in various fields of artificial intelligence studying land cover in constructing an artificial intelligence learning dataset on land cover of the whole of Korea.

• Nuclear Engineering and Technology
• /
• v.49 no.2
• /
• pp.286-294
• /
• 2017

The events at the Fukushima Daiichi Nuclear Power Station in March 2011 point out, among other matters, that concurrent accidents at multiple units of a site can occur in reality. Although site risk has been deterministically considered to some extent in nuclear power plant siting and design, potential occurrence of multi-unit accident sequences at a site was not investigated in sufficient detail thus far in the nuclear power community. Therefore, there is considerable worldwide interest and research effort directed toward multi-unit site risk assessment, especially in the countries with high-density nuclear-power-plant sites such as Korea. As the technique of probabilistic safety assessment (PSA) has been successfully applied to evaluate the risk associated with operation of nuclear power plants in the past several decades, the PSA having primarily focused on single-unit risks is now being extended to the multi-unit PSA. In this paper we first characterize the site risk with explicit consideration of the risk associated with spent fuel pools as well as the reactor risks. The status of multi-unit risk assessment is discussed next, followed by a description of the emerging issues relevant to the multi-unit risk evaluation from a practical standpoint.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1284-1288
• /
• 2021

In this work, we propose and design a GaN-based diode with a p-doped GaN (p-GaN) multi-well structure for high efficiency betavoltaic (BV) cells. The short-circuit current density (J_SC) and opencircuit voltage (V_OC) of the devices were investigated with variations of parameters such as the doping concentration, height, width of the p-GaN well region, well-to-well gap, and number of well regions. The J_SC of the device was significantly improved by a wider depletion area, which was obtained by applying the multi-well structure. The optimized device achieved a higher output power density by 8.6% than that of the conventional diode due to the enhancement of J_SC. The proposed device structure showed a high potential for a high efficiency BV cell candidate.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.92-99
• /
• 2024

To minimize the cumulative radiation dose, various path-finding approaches for single agent have been proposed. However, for emergence situations such as nuclear power plant accident, these methods cannot be effectively utilized for evacuating a large number of workers because no multi-agent method is valid to conduct the mission. In this study, a novel algorithm for solving the multi-agent path-finding problem is proposed using the conflict-based search approach and the objective function redefined in terms of the cumulative radiation dose. The proposed method can find multi paths that all agents arrive at the destinations with reducing the overall radiation dose. To verify the proposed method, three problems were defined. In the single-agent problem, the objective function proposed in this study reduces the cumulative dose by 82% compared with that of the shortest distance algorithm in experiment environment of this study. It was also verified in the two multi-agent problems that multi paths with minimized the overall radiation dose, in which all agents can reach the destination without collision, can be found. The method proposed in this study will contribute to establishing evacuation plans for improving the safety of workers in radiation-related facilities.