• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.57-78
• /
• 2023

COVID-19, which started in Wuhan, China in November 2019, spread beyond China in 2020 and spread worldwide in March 2020. It is important to prevent a highly contagious virus like COVID-19 in advance and to actively treat it when confirmed, but it is more important to identify the confirmed fact quickly and prevent its spread since it is a virus that spreads quickly. However, PCR test to check for infection is costly and time consuming, and self-kit test is also easy to access, but the cost of the kit is not easy to receive every time. Therefore, if it is possible to determine whether or not a person is positive for COVID-19 based on the sound of a cough so that anyone can use it easily, anyone can easily check whether or not they are confirmed at anytime, anywhere, and it can have great economic advantages. In this study, an experiment was conducted on a method to identify whether or not COVID-19 was confirmed based on a cough sound. Cough sound features were extracted through MFCC, Mel-Spectrogram, and spectral contrast. For the quality of cough sound, noisy data was deleted through SNR, and only the cough sound was extracted from the voice file through chunk. Since the objective is COVID-19 positive and negative classification, learning was performed through XGBoost, LightGBM, and FCNN algorithms, which are often used for classification, and the results were compared. Additionally, we conducted a comparative experiment on the performance of the model using multidimensional vectors obtained by converting cough sounds into both images and vectors. The experimental results showed that the LightGBM model utilizing features obtained by converting basic information about health status and cough sounds into multidimensional vectors through MFCC, Mel-Spectogram, Spectral contrast, and Spectrogram achieved the highest accuracy of 0.74.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.167-183
• /
• 2023

In the recent field of recommendation systems, various studies have been conducted to model sparse data effectively. Among these, GLocal-K(Global and Local Kernels for Recommender Systems) is a research endeavor combining global and local kernels to provide personalized recommendations by considering global data patterns and individual user characteristics. However, due to its utilization of kernel tricks, GLocal-K exhibits diminished performance on highly sparse data and struggles to offer recommendations for new users or items due to the absence of side information. In this paper, to address these limitations of GLocal-K, we propose the GEase-K (Global and EASE kernels for Recommender Systems) model, incorporating the EASE(Embarrassingly Shallow Autoencoders for Sparse Data) model and leveraging side information. Initially, we substitute EASE for the local kernel in GLocal-K to enhance recommendation performance on highly sparse data. EASE, functioning as a simple linear operational structure, is an autoencoder that performs highly on extremely sparse data through regularization and learning item similarity. Additionally, we utilize side information to alleviate the cold-start problem. We enhance the understanding of user-item similarities by employing a conditional autoencoder structure during the training process to incorporate side information. In conclusion, GEase-K demonstrates resilience in highly sparse data and cold-start situations by combining linear and nonlinear structures and utilizing side information. Experimental results show that GEase-K outperforms GLocal-K based on the RMSE and MAE metrics on the highly sparse GoodReads and ModCloth datasets. Furthermore, in cold-start experiments divided into four groups using the GoodReads and ModCloth datasets, GEase-K denotes superior performance compared to GLocal-K.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.361-381
• /
• 2023

Research on corporate bankruptcy prediction has been focused on financial information. Since the company's financial information is updated quarterly, there is a problem that timeliness is insufficient in predicting the possibility of a company's business closure in real time. Evaluated companies that want to improve this need a method of judging the soundness of a company that uses information other than financial information to judge the soundness of a target company. To this end, as information technology has made it easier to collect non-financial information about companies, research has been conducted to apply additional variables and various methodologies other than financial information to predict corporate bankruptcy. It has become an important research task to determine whether it has an effect. In this study, we examined the impact of electronic payment-related information, which constitutes non-financial information, when predicting the closure of business operators using electronic payment service and examined the difference in closure prediction accuracy according to the combination of financial and non-financial information. Specifically, three research models consisting of a financial information model, a non-financial information model, and a combined model were designed, and the closure prediction accuracy was confirmed with six algorithms including the Multi Layer Perceptron (MLP) algorithm. The model combining financial and non-financial information showed the highest prediction accuracy, followed by the non-financial information model and the financial information model in order. As for the prediction accuracy of business closure by algorithm, XGBoost showed the highest prediction accuracy among the six algorithms. As a result of examining the relative importance of a total of 87 variables used to predict business closure, it was confirmed that more than 70% of the top 20 variables that had a significant impact on the prediction of business closure were non-financial information. Through this, it was confirmed that electronic payment-related information of non-financial information is an important variable in predicting business closure, and the possibility of using non-financial information as an alternative to financial information was also examined. Based on this study, the importance of collecting and utilizing non-financial information as information that can predict business closure is recognized, and a plan to utilize it for corporate decision-making is also proposed.

• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.73-82
• /
• 2009

Due to the many advantages including low price, low power consumption, and miniaturization, the CMOS camera has been utilized in many applications, including mobile phones, the automotive industry, medical sciences and sensoring, robotic controls, and research in the security field. In particular, the 360 degree omni-directional camera when utilized in multi-camera applications has displayed issues of software nature, interface communication management, delays, and a complicated image display control. Other issues include energy management problems, and miniaturization of a multi-camera in the hardware field. Traditional CMOS camera systems are comprised of an embedded system that consists of a high-performance MCU enabling a camera to send and receive images and a multi-layer system similar to an individual control system that consists of the camera's high performance Micro Controller Unit. We proposed the SL-AVS (Small Size/Low power Around-View System) to be able to control a camera while collecting image data using a high speed synchronization technique on the foundation of a single layer low performance MCU. It is an initial model of the omni-directional camera that takes images from a 360 view drawing from several CMOS camera utilizing a 110 degree view. We then connected a single MCU with four low-power CMOS cameras and implemented controls that include synchronization, controlling, and transmit/receive functions of individual camera compared with the traditional system. The synchronization of the respective cameras were controlled and then memorized by handling each interrupt through the MCU. We were able to improve the efficiency of data transmission that minimizes re-synchronization amongst a target, the CMOS camera, and the MCU. Further, depending on the choice of users, respective or groups of images divided into 4 domains were then provided with a target. We finally analyzed and compared the performance of the developed camera system including the synchronization and time of data transfer and image data loss, etc.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.2
• /
• pp.205-216
• /
• 2023

This study aimed to compare the color stability and surface roughness of three-dimensional (3D) printing resin according to polishing methods. 3D-printed resin specimens were fabricated at TC-80DP (Graphy, Seoul, Korea) with a stereolithography 3D printer, and the specimens were divided into three groups, each of which was not polished, was polished using Enhance^®, and was polished using a Sof-Lex^TM disc. The CIE L^*a^*b^* value and the surface roughness of each group were measured and immersed in artificial saliva and orange juice after 0, 1, 7, 30, and 60 days, and the color difference (ΔE^*) was calculated. As a result of the study, no noticeable color change was observed in artificial saliva, but a noticeable color change was demonstrated in orange juice after 60 days of immersion, and the difference was significant. In the Sof-Lex^TM group, surface roughness according to the solution was found to be significantly higher in the orange juice than that in artificial saliva. No significant difference in color change was found according to the polishing method, but surface roughness was significantly lower in the Sof-Lex^TM group than both that of the unpolished group and that of the Enhance^® group. Nevertheless, all groups exhibited clinically acceptable properties regardless of their higher surface roughness than the threshold for plaque accumulation. Overall, this study recommends utilizing Sof-Lex^TM for polishing 3D printing resin when used in primary anterior tooth coverage.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.4 no.1
• /
• pp.128-137
• /
• 2002

This study was conducted to develop the heat exchanger by utilizing the heat energy of underground water(15℃), which might be used for cooling and heating system of the agricultural facilities. We developed the heat exchanger by using the parallel type plat fin tube made of Aluminum(Al 6063), which was named Aloo-Heat(No. 0247164, offered by Korean Intellectual property Office). The trial manufactures were made from Aloo-heat which was 600mm, 700mm length respectively, and It were welded to the end "U" type in order to direct flow of the underground water. The performance test was carried out under the condition of open space and room temperature with the change of flow rate of the underground water and air. The results are as follows. 1. The trial manufactures had convection heat value from 33 to 156 W/m²℃, and It was coincided with design assumption. 2. The amount of energy transfer was increased with the increment of the area of heat transfer, the air flow, the gap of temperature inlet & outlet the underground water and the air. 3. The heat value was 6,825W when the air flow was 6,000m³/h and the gap of temperature between inlet and outlet of the underground water was 6℃, and It dropped from 25.8℃ to 23.2℃(-2.6℃ difference). The convection heat value was 88.5W/m²℃. 4. The heat value was 2.625W when the air flow was 4,000m³/h and the gap of temperature between inlet and outlet the underground water was 2℃, and It dropped from 27℃ to 22.5℃(-4.5℃ difference). The convection heat value was 33.6W/m²℃. 5. Correlation values(R²) of the testing heat values of the trial manufacture type I, II, and III were 0.9141, 0.8935, and 0.9323 respectively, and correlation values(R²) of the amount of the air flow 6,000m³/h, 5,000m³/h, 4,000m³/h were 0.9513, 0.9414, and 0.9003 respectively.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.6 no.1
• /
• pp.102-115
• /
• 2004

Main objectives of this study were to increase digestibilities of indigestible ingredients in spent mushroom composts (SMC) consisted of sawdust mainly as well as to fortify conversion of inorganic Se present in SMC to organic Se via fermentable microbial actions. Experimental feeds were designed to contain the increasing level of selenium (0.06ppm, 0.54ppm, 1.26ppm and 1.86ppm) in combination with SMCs of Se-enriched and non-Se mushrooms. Feeds were also fermented using commercial microbial feed additives (Sambae, Ltd., Korea) comprised Saccharomyces, Bacillus, Aspergillus, Streptococcus and Actinomycetes before feeding trial for Hanwoo (Korean native cattle). Those were fermented for 0, 12, 24, and 48 hrs. Initial pH was linearly increased as Se concentration increases or the proportion of SMC of Se-enriched mushroom increased (p<0.0001). pH values of fermented feeds (0.54ppm, 1.26ppm and 1.86ppm) containing SMC of Se-enriched mushroom were not different since 12 hrs of fermentation time and their pH was significantly lowered compared to control group. The increasing level of Se concentration in fermented feeds showed significant differences in organic and inorganic Se contents and proportion of organic Se among treatments. As a SMC proportion of Se-enriched mushrooms in the fermented feed was increased, organic Se proportion was significantly decreased (p<0.0001). The control treatment (0.06ppm) comprising the non-Se SMC only was estimated of the organic Se to be 100% and the treatment groups containing the increasing level of Se were estimated of organic Se to be approximately 70%.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.6 no.1
• /
• pp.116-135
• /
• 2004

This study was conducted to investigate effects of spent composts of Se-enriched mushrooms as the dietary Se source on muscular Se deposition and plasma glutathione peroxidase (GSH-Px) activity in the finishing Hanwoo steer. Twenty Hanwoo steers were used in the experiment and they were divided into four groups in a randomized complete block design with five replicates. Treatments were four levels (0.1, 0.3, 0.6 and 0.9ppm as fed basis) of dietary Se from the combination with spent composts of Se-enriched mushrooms and/or Se non-enriched mushrooms, in which each treatment was formulated with corn and corn gluten meal and so forth. Treatment diets were fed to Hanwoo steers for 90 days until the slaughter. Dry matter intakes had no significant differences among treatments and there were no significant differences for performances such as total BW gain and ADG among treatments. The Se concentration in blood was linearly increased with increasing dietary selenium levels and reached a plateau level after 8 weeks (p<0.001). Plasma GSH-Px activities had the similar trends to blood Se concentrations by showing that the increased dietary Se level significantly increased plasma GSH-Px activities of both total and Se-dependent (p<0.001). Muscle Se contents of Se-supplemented groups were linearly increased by 1.35 ~ 1.68 folds compared with the control group (0.1ppm; 0.273㎍/dry g) and especially those of the hind legs for 0.9ppm treatment showed the highest Se content as shown 0.457㎍ per dry gram (p<0.01) corresponding to approximately 70% increase of the control group. Se retention rate in the muscle of dietary Se originated from spent composts of Se-enriched mushrooms was estimated of maximum approximately 30% and dietary Se content showed the significant correlation with plasma GSH-Px activities and muscle Se contents (p<0.01). Accordingly, Se present in spent composts of Se-enriched mushroom as the dietary Se source not only had great bioavailabilities showing higher blood Se concentration and plasma GSH-Px activities, but also increased Se deposition in the muscle for Hanwoo beef cattle.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.4 no.1
• /
• pp.119-127
• /
• 2002

This study was conducted to develop the heat exchanger by utilizing the heat energy of underground water(15℃), which might be used for cooling and heating system of the agricultural facilities. We developed the heat exchanger, parallel type plat fin tube made of Aluminum(Al 6063), which was named Aloo-Heat(No. of The registration design : 0247164, by Korean Intellectual property Office). The fin of exchanger was design of the granulated surface for minimizing fouling factor and dew forms, and also placed parallel to the tube in order to minimized the resistance of flows. 1. Aloo-heat was designed to have 0.03m for inside diameter, 0.036m for outside diameter of tube, 0.0012m for thickness of fin and 0.032m for length of plat fin. 2. t was also designed to have 1.5248m²/m for outside area of heat transfer, 0.0942m²/m for inside area contacting hot liquid, and the ratio (Ra) was 16.1869. 3. Efficiency of the fin was 93 percentage when fin length was 0.032m, and the fin thickness satisfied equation $\frac{h{\rho}}{k}$< 0.2 when it was 0.0012m. 4. According to the performance test of Aloo-heat, as the temperature and rate increased, the heating value also increased, heating value was 504kJ/h·m and 6,048kJ/h·m when it was 60℃, 10 𝑙/min and 80℃, 40 𝑙/min respectively. 5. The test of heating value was confident, because correlation value(R²) was 0.9898 for the temperature and 0.9721 for flow rate of hot liquid, respectively.