• Knowledge Management Research
• /
• v.23 no.2
• /
• pp.277-299
• /
• 2022

The massive card transaction data generated in the tourism industry has become an important resource that implies tourist consumption behaviors and patterns. Based on the transaction data, developing a smart service system becomes one of major goals in both tourism businesses and knowledge management system developer communities. However, the lack of rating scores, which is the basis of traditional recommendation techniques, makes it hard for system designers to evaluate a learning process. In addition, other auxiliary factors such as temporal, spatial, and demographic information are needed to increase the performance of a recommendation system; but, gathering those are not easy in the card transaction context. In this paper, we introduce CTDDTR, a novel approach using card transaction data to recommend tourism services. It consists of two main components: i) Temporal preference Embedding (TE) represents tourist groups and services into vectors through Doc2Vec. And ii) Deep tourism Recommendation (DR) integrates the vectors and the auxiliary factors from a tourism RDF (resource description framework) through MLP (multi-layer perceptron) to provide services to tourist groups. In addition, we adopt RFM analysis from the field of knowledge management to generate explicit feedback (i.e., rating scores) used in the DR part. To evaluate CTDDTR, the card transactions data that happened over eight years on Jeju island is used. Experimental results demonstrate that the proposed method is more positive in effectiveness and efficacies.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.41-49
• /
• 2023

A convolutional neural network (CNN) is a representative algorithm for implementing artificial neural networks. CNNs have improved on the issues of rapid increase in calculation amount and low object classification rates, which are associated with a conventional multi-layered fully-connected neural network (FNN). However, because of the rapid development of IT devices, the maximum resolution of images captured by current smartphone and tablet cameras has reached 108 million pixels (MP). Specifically, a traditional CNN algorithm requires a significant cost and time to learn and process simple, high-resolution images. Therefore, this study proposes an improved CNN algorithm for implementing an object classification learning model for simple, high-resolution images. The proposed method alters the adjacency matrix value of the pooling layer's max pooling operation for the CNN algorithm to reduce the high-resolution image learning model's creation time. This study implemented a learning model capable of processing 4, 8, and 12 MP high-resolution images for each altered matrix value. The performance evaluation result showed that the creation time of the learning model implemented with the proposed algorithm decreased by 36.26% for 12 MP images. Compared to the conventional model, the proposed learning model's object recognition accuracy and loss rate were less than 1%, which is within the acceptable error range. Practical verification is necessary through future studies by implementing a learning model with more varied image types and a larger amount of image data than those used in this study.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.36 no.1
• /
• pp.88-92
• /
• 2023

The ferroelectricity in Hf_0.5Zr_0.5O₂ (HZO) thin films is one of the most interesting topics for next-generation nonvolatile memory applications. It is known that a crystallization process is required at a temperature of 400℃ or higher to form an orthorhombic phase that results in the ferroelectric properties of the HZO film. However, to realize the integration of ferroelectric HZO films in the back-end-of-line, it is necessary to reduce the annealing temperature below 400℃. This study aims to comprehensively analyze the ferroelectric properties according to the annealing temperature (350-500℃) and time (1-5 h) using a furnace as a crystallization method for HZO films. As a result, the ferroelectric behaviors of the HZO films were achieved at a temperature of 400℃ or higher regardless of the annealing time. At the annealing temperature of 350℃, the ferroelectric properties appeared only when the annealing time was sufficiently increased (4 h or more). Based on these results, it was experimentally confirmed that the optimization of the annealing temperature and time is very important for the ferroelectric phase crystallization of HZO films and the improvement of their ferroelectric properties.

• Journal of Korean Medicine Rehabilitation
• /
• v.33 no.2
• /
• pp.1-18
• /
• 2023

Objectives The purpose of this study was to evaluate the antioxidant, anti-inflammatory and wound healing effects of Samul-tang-ga-dansam water extract (SD) in wound-induced mice. Methods The mice were divided into five groups (n=7): the normal group, the control group, the positive control group, the low-dose SD group and the high-dose SD group. The normal group had no wounds and the other groups were wounded on the back with a leather punch. Distilled water was administered to the control group, 200 mg/kg of vitamin E was administered to the positive control group. In the low-dose SD group and the high-dose SD group, 1.23 g/kg and 2.47 g/kg of SD were administered, respectively. Antioxidant and anti-inflammatory protein levels were evaluated using western blot analysis. Skin tissue was analyzed by H&E, Masson's trichrome staining method. Results Oral administration of the SD significantly reduced the visible skin damage and decreased the reactive oxygen species and ONOO^- activity of the serum. It significantly increased heme oxygenase-1, superoxide dismutase, catalase, GPx-1/2, Nrf2 and Keap-1 which are antioxidant-related factors in skin tissue and reduced NF-κB p65, inducible nitric oxide synthase, cyclooxygenase-2, tumor necrosis factor α, interleukin (IL)-1β, IL-6 which are inflammation-related factors. Also, SD significantly decreased NOX2, p22^phox and p47^phox and increased α-smooth muscle actin and COL1A1 protein expression in fibroblasts involved in connective tissue repair. According to histological examination, the thickened epithelial layer was thinned and collagen fibers were increased to accelerate wound healing. Conclusions It is suggested that Samul-tang-ga-dansam has antioxidant and anti-inflammatory effects and promotes wound tissue repair.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.33 no.4
• /
• pp.153-157
• /
• 2023

In order to manufacture a semiconductor circuit, etching, cleaning, and deposition processes are repeated. During these processes, the inside of the processing chamber is exposed to corrosive plasma. Therefore, the coating of the inner wall of the semiconductor equipment with a plasma-resistant material has been attempted to minimize the etching of the coating and particle contaminant generation. In this study, we mixed AlF₃ powder with the solid-state reacted yttrium oxyfluoride (YOF) in order to increase plasma-etching resistance of the plasma spray coated YOF layer. Effects of the mixing ratio of AlF₃ with YOF powder on crystal structure, microstructure and chemical composition were investigated using XRD and FE-SEM. The plasma-etching ratios of the plasma-spray coated layers were calculated and correlation with AlF₃ mixing ratio was analyzed.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.382-392
• /
• 2023

Recent reports have indicated a rapid increase in the frequency of sediment disasters due to climate change and other changes in the geological environment. Given this alarming situation and the recent increase in the frequency of land creep in Korea, systematic and efficient recovery and management of land creep areas is essential. The purpose of this study is to identify disaster vulnerability by conducting a physical exploration of land creep in San 4-1, Jayeon-ri, Gaegun-myeon, Yangpyeong-gun, Gyeonggi-do, and examine stability by identifying the overall geological structure of the affected ground. In addition, drilling surveys are conducted to verify the reliability of the measured data. The results of the study reveal that low specific resistance abnormalities are distributed in the upper part of the soil layer and weathering zone and that this section is a 50-120 m exploration line. It is also confirmed to be a low-hardness ground area where tensile cracks are observed. Therefore, there is a need for research focused on developing measures to reduce economic and social damage within the domestic context by continuously monitoring indicators of land creep and identifying land creep risks.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.363-373
• /
• 2023

Forest biomass surveys are regularly conducted to assess and manage forests as carbon sinks. LiDAR (Light Detection and Ranging), a remote sensing technology, has attracted considerable attention, as it allows for objective acquisition of forest structure information with minimal labor. In this study, we propose a method for estimating overstory and understory biomass in forest stands using backpack laser scanning (BPLS) and unmanned aerial vehicle laser scanning (UAV-LS), and assessed its accuracy. For overstory biomass, we analyzed the accuracy of BPLS and UAV-LS in estimating diameter at breast height (DBH) and tree height. For understory biomass, we developed a multiple regression model for estimating understory biomass using the best combination of vertical structure metrics extracted from the BPLS data. The results indicated that BPLS provided accurate estimations of DBH (R² =0.92), but underestimated tree height (R² =0.63, bias=-5.56 m), whereas UAV-LS showed strong performance in estimating tree height (R² =0.91). For understory biomass, metrics representing the mean height of the points and the point density of the fourth layer were selected to develop the model. The cross-validation result of the understory biomass estimation model showed a coefficient of determination of 0.68. The study findings suggest that the proposed overstory and understory biomass survey methods using BPLS and UAV-LS can effectively replace traditional biomass survey methods.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.31 no.3
• /
• pp.35-41
• /
• 2023

In this study, silicon sludge generated in semiconductor manufacturing process is recycled and applied as materials for pigments and paints. In detail, metallic impurities are removed from silicon sludge to obtain plate-like silicon sludge powder (SW-sludge), which is then coated with titanium dioxide via sol-gel method (TCS-sludge). SW-sludge and TCS-sludge are dispersed in hydrophilic transparent varnish and sprayed onto glass substrates to observe the possibility for the application as materials for pigments and paints. Notably, the applicability of TCS-sludge-based paint is improved compared to SW-sludge-based paint after the titanium dioxide coating. Moreover, the color of TCS-sludge-based paint turns into white. Accordingly, it is confirmed that the applicability and hydrophilicity are improved by the presence of outer titanium dioxide layer. In this regard, it is expected that the recycled TCS-sludge may be a future material for the application as pigments and paints.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.9
• /
• pp.13-24
• /
• 2023

To investigate the stability of temporary retaining walls during excavation, it is essential to develop reverse analysis technologies capable of precisely evaluating the properties of the ground and a learning model that can assess stability by analyzing real-time data. In this study, we targeted excavation sites where the C.I.P method was applied. We developed a Deep Neural Network (DNN) model capable of evaluating the stability of the retaining wall, and estimated the physical properties of the ground being excavated using a Differential Evolution Algorithm. We performed reverse analysis on a model composed of a two-layer ground for the applicability analysis of the Differential Evolution Algorithm. The results from this analysis allowed us to predict the properties of the ground, such as the elastic modulus, cohesion, and internal friction angle, with an accuracy of 97%. We analyzed 30,000 cases to construct the training data for the DNN model. We proposed stability evaluation grades for each assessment factor, including anchor axial force, uneven subsidence, wall displacement, and structural stability of the wall, and trained the data based on these factors. The application analysis of the trained DNN model showed that the model could predict the stability of the retaining wall with an average accuracy of over 94%, considering factors such as the axial force of the anchor, uneven subsidence, displacement of the wall, and structural stability of the wall.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.