• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.177-182
• /
• 2015

The brand and product awareness of Korean electronics companies in the North American market has grown significantly and North American consumers has been recognized as an innovative technology products good performance of Korean electronics appliances. The consumer need of energy saving has led to a rise in market share because Korean electronics appliances have the excellence in energy saving aspects. The expansion of smartphones and mobile devices and the development of smart grid technology can affect electronics market. Domestic companies are continuously develop new product to provide consumers convenient with a variety of additional features combined consumer products. This study proposes a convergence model for sales prediction of electronic appliances using sales data of A company from the North American market. We develop the convergence model for sales prediction based on based on artificial neural network and genetic algorithm. In addition, we validate the superiority of the proposed convergence model by comparing the prediction performance of traditional prediction models.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.29-36
• /
• 2022

In this paper, we propose an efficient agricultural products price prediction model based on dataset which provided in DACON. This model is XGBoost and CatBoost, and as an algorithm of the Gradient Boosting series, the average accuracy and execution time are superior to the existing Logistic Regression and Random Forest. Based on these advantages, we design a machine learning model that predicts prices 1 week, 2 weeks, and 4 weeks from the previous prices of agricultural products. The XGBoost model can derive the best performance by adjusting hyperparameters using the XGBoost Regressor library, which is a regression model. The implemented model is verified using the API provided by DACON, and performance evaluation is performed for each model. Because XGBoost conducts its own overfitting regulation, it derives excellent performance despite a small dataset, but it was found that the performance was lower than LGBM in terms of temporal performance such as learning time and prediction time.

• Analytical Science and Technology
• /
• v.36 no.1
• /
• pp.22-31
• /
• 2023

As the use of e-liquid cigarettes is rapidly increasing worldwide, it multiplies the potential risk undisclosed to the health of non- and smokers. To reduce the hazard, each country has its own set of regulations for controlling e-liquids. In Korea, the narrow definition of tobacco makes it difficult and have been steadily occurring tax evasion exploiting the difference in natural and artificial nicotine. Therefore, it is very important to distinguish source of nicotine for their regulation. To find biochemical discriminant markers, this study established analysis methods based on high-performance liquid chromatography coupled with diode array detector (HPLC-DAD) and high-performance liquid chromatography coupled with triple Quadrupole mass spectrometry (HPLC-MS/MS) for nicotine enantiomers and tobacco alkaloids targeted using the difference in pathways of nicotine biosynthesis and chemical synthesis. The method was validated by experimenting linearity (R² > 0.999), recovery (80.99-108.41 %), accuracy (94.11-109.73 %) and precision (0.04-8.27 %). Then, the results for discrimination of the nicotine obtained from analysis of 65 commercial e-liquid products available in Korean market was evaluated. The method successfully applied to the e-liquids and one sample labelled 'synthetic nicotine' for tax exemption was found to contain a natural nicotine product. This method can be used to determine whether an e-liquid product uses natural or artificial nicotine and monitor non-taxable e-liquid products. The method is more scientific than the existing one, which relies only on field evidence.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.119-126
• /
• 2024

In building information model (BIM), it is difficult to train an artificial intelligence (AI) model due to the lack of sufficient data about individual projects in an architecture firm. In this paper, we present a methodology to correctly train an AI neural network model based on a large language model (LLM) to predict the steel structure product weight ratios in BIM. The proposed method, with the aid of the LLM, can overcome the inherent problem of limited data availability in BIM and handle a combination of natural language and numerical data. The experimental results showed that the proposed method demonstrated significantly higher accuracy than methods based on a smaller language model. The potential for effectively applying large language models in BIM is confirmed, leading to expectations of preventing building accidents and efficiently managing construction costs.

• Journal of Fashion Business
• /
• v.21 no.4
• /
• pp.144-158
• /
• 2017

Fur garment has long been the conventional symbol for luxury, or conspicuous consumption. However, as fashion items began to diversify as part of overall fashion trend, fur items are now more about individual taste and style than just lavishness. Synthetic fur is especially emerging as a new promising fashion material, with a touch almost like natural fur at an affordable price. Along with the emergence of 'Vegan Fashion' trend, synthetic fur is establishing itself as a popular fashion textile. This study is an attempt to investigate subjective evaluation and physical properties of natural and synthetic furs, whose results will further serve as basic data in developing synthetic fur materials. Sensory and emotional evaluations are carried out on natural and artificial furs. For analysis, factors such as weight, thickness, air permeability, gloss and compressibility were surveyed to observe how they influence the physical properties. According to the subjective evaluation, natural and artificial fur samples do not differ in conspicuous ways in appearance. Experiments on physical properties, specifically warm/cool touch experiment, show that natural fur has a slightly higher warm sensation than artificial fur. Luster analysis by using a microscope revealed that there are subtle qualitative differences between natural and artificial fur. During the subjective evaluation, subjects found it hard to state distinct quantitative differences in luster. A survey as a means of assessing qualitative differences in gloss seems to be necessary to complement the evaluation. Results from this study will potentially serve as resources for diversification of fashion product designs using synthetic fur.

• Asian Journal of Atmospheric Environment
• /
• v.6 no.3
• /
• pp.206-221
• /
• 2012

Hazardous chemicals can be released from artificial turf used in some school playgrounds. To distinguish between Health risk assessment (HRA) exposure scenarios for this study, the ratio of elementary, middle and high schools was considered before final selection. Considering exposure pathways (inhalational, oral and dermal), media and materials were examined, targeting hazardous chemicals released from artificial turf playground-related products. Upon evaluation, the quantity of infill chips was shown to exceed the domestic product content standard (90 mg/kg) at eight (16%) out of 50 schools. PAHs were shown to exceed standards (10 mg/kg) at two (4%) out of the 50 schools. The excess cancer risk (ECR) of carcinogens was shown to be $1{\times}10^{-6}$ in most users for the worst exposure scenario. In children with pica, who represented the most extreme exposure group, the ECR was expected to be as high as $1{\times}10^{-4}$, showing the low risk level of carcinogens. The hazard index (HI) for individual chemicals was shown to be low, at around 0.1 or less, except for children with pica, according to the mean exposure scenario of artificial turf playground exposure. However, the HI was shown to exceed 1.0 in children with pica. Therefore, no direct health risk was found in using artificial turf playgrounds and urethane flooring tracks for the mean exposure scenario, except in children with pica.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.199-206
• /
• 2020

In this study, the factors affecting consumers' intention to use AI speakers were focused on the perceived value of the product and the perceived necessity of the product. Factors affectationist consumers' perceived value of the product were divided into benefits and costs. Reflecting the characteristics of information technology products, I included perceptions of usefulness of products. Empirical results show that consumers' perceptions of perceived benefits and usefulness of AI speaker products have a positive effect on perceived value and perceived necessity. Perception of necessity had a positive (+) significant effect on perception of value. Perception of necessity and perception of value had a positive(+) and positive effect on each intention of use. However, the cost perceived by consumers did not have a significant effect on perception of value.

• Journal of Information Technology Services
• /
• v.17 no.2
• /
• pp.191-205
• /
• 2018

With the advancement of artificial intelligence (AI) techniques, many consumer products have adopted AI features for providing proactive and personalized services to customers. One of the most prominent products featuring AI techniques is a smart speaker. The fundamental of smart speaker is a portable wireless Internet connecting speaker which already have existed in a consumer market. By applying AI techniques, smart speakers can recognize human voices and communicate with them. In addition, they can control other connecting devices and provide offline services. The goal of this study is to identify the impact of AI techniques for customer rating to the products. We compared customer reviews of other portable speakers without AI features and those of a smart speaker. Amazon echo is used for a smart speaker and JBL Flip 4 Bluetooth Speaker and Ultimate Ears BOOM 2 Panther Limited Edition are used for the comparison. These products are in the same price range ($50~100) and selected as featured products in Amazon.com. All reviews for the products were collected and common words for all products and unique words of the smart speaker were identified. Information gain values were calculated to identify the influences of words to be rated as positive or negative. Positive and negative words in all the products or in Amazon echo were identified, too. Topic modeling was applied to the customer reviews on Amazon echo and the importance of each topic were measured by summating information gain values of each topic. This study provides a way of identifying customer responses on the AI feature and measuring the importance of the feature among diverse features of the products.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2003.11a
• /
• pp.534-538
• /
• 2003

Final disposal of radioactive waste generated from Nuclear Power Plant (NPP) requires the detailed knowledge of the natures and quantities of radionuclides in waste package. Many of these radionuclides are difficult to measure and expensive to assay. Thus it is suggested to the Indirect method by which the concentrations of DTM (Difficult-to-Measure) nuclide is decided using the relation of concentrations (Scaling Factor) between Key (Easy-to-Measure) nuclide and DTM nuclide with measured concentrations of Key nuclide. In general, scaling factor is determined by using of log mean average (LMA) and regression. These methods are adequate to apply most corrosion product nuclides. But in case of fission product nuclides and some corrosion product nuclides, the predicted values aren't well matched with the original values. In this study, the models using artificial neural network (ANN) for C-14 and Sr-90 are compared with those using LMA and regression. The assessment of models is executed in the two parts divided by a training part and a validation part. For all of two nuclides in the training part, the predicted values using ANN are well matched with the measured values compared with those using LMA and regression. In the validation part, the accuracy of the predicted values using ANN is better than that using LMA and is similar to or better than that using regression. It is concluded that the predicted values using ANN model are better than those using conventional model in some nuclides and ANN model can be used as the complement of LMA and regression model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.