• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2024

In this paper, we fine-tuned KoAlpaca, a large-scale Korean language model, and implemented a blog text generation system utilizing it. Blogs on social media platforms are widely used as a marketing tool for businesses. We constructed training data of positive reviews through emotion analysis and refinement of collected sponsored blog texts and applied QLoRA for the lightweight training of KoAlpaca. QLoRA is a fine-tuning approach that significantly reduces the memory usage required for training, with experiments in an environment with a parameter size of 12.8B showing up to a 58.8% decrease in memory usage compared to LoRA. To evaluate the generative performance of the fine-tuned model, texts generated from 100 inputs not included in the training data produced on average more than twice the number of words compared to the pre-trained model, with texts of positive sentiment also appearing more than twice as often. In a survey conducted for qualitative evaluation of generative performance, responses indicated that the fine-tuned model's generated outputs were more relevant to the given topics on average 77.5% of the time. This demonstrates that the positive review generation language model for sponsored content in this paper can enhance the efficiency of time management for content creation and ensure consistent marketing effects. However, to reduce the generation of content that deviates from the category of positive reviews due to elements of the pre-trained model, we plan to proceed with fine-tuning using the augmentation of training data.

• Korean Journal of Plant Resources
• /
• v.37 no.1
• /
• pp.79-86
• /
• 2024

This study was conducted to determine the conditions for breaking dormancy in the seeds of the North Korean plant resource, Trollius macropetalus, and to investigate its germination characteristics. The morphological characteristics and viability of T. macropetalus seeds were examined. Germination characteristics were investigated based on temperature conditions (15/6℃ & 25/15℃), cold stratification treatment, and GA₃ treatment. The results showed that cold stratification treatment had no effect on breaking the dormancy of T. macropetalus. GA₃ treatment significantly increased the germination rate of T. macropetalus and also improved the mean germination days and germination speed. However, compared to the 15/6℃ condition, the effectiveness of GA₃ treatment for T. macropetalus decreased under the 25/15℃ condition. It was determined that T. macropetalus have a nondeep-type morpho-physiological dormancy. The most effective conditions for breaking dormancy were found to be the 15/6℃ temperature condition and GA₃ treatment at 500 mg·L^-1. The findings of this study are expected to provide valuable information for the mass propagation of T. macropetalus, which has potential applications in landscaping and pharmaceutical materials.

• Journal of Life Science
• /
• v.34 no.4
• /
• pp.236-244
• /
• 2024

Melanin is a natural pigment found in most plants and animals, and it is involved in determining the color of the skin and hair. Melanogenesis is a reactive occurrence in melanocytes aiming to protect the skin from external stimuli, such as ultraviolet rays. Tyrosine is involved in the biosynthesis of the substrate tyrosine into melanin. However, melanin overproduction can lead to skin diseases, such as melasma, blotching, hyperpigmentation, and skin cancer. Although many studies have been conducted on whitening substances, such as kojic acid and arbutin, some countries have banned or refrained from using them due to their side effects. Therefore, this study assessed the potential of horseradish (HR) as a new whitening agent in cosmetic products. For efficient extraction, subcritical water extraction was conducted. The results showed that the horseradish subcritical water 200℃ (SW 200) extract showed high DPPH radical scavenging ability, total phenolic contents (TPC), inhibiting tyrosinase activity and inhibiting melanin production of B16-F10 melanoma cell lines. To investigate its cytotoxicity to the B16-F10 melanoma cell lines, MTT reduction assay and morphological changes were observed. No cytotoxicity was found in horseradish methanol extract and SW 200. In conclusion, this research suggests the possibility of horseradish subcritical water may be useful as a natural whitening ingredient to be used in cosmetic products.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.173-188
• /
• 2024

With the advancement of autonomous vehicle (AV) technology, autonomous driving on real roads has become feasible. However, there are challenges in achieving complete autonomy due to perceptual blind areas, which occur when the AV's sensory range or capabilities are limited or impaired by surrounding objects or environmental factors. This study aims to analyze AV accident patterns and safety issues of perceptual blind area that may occur in urban areas, with the goal of developing test scenarios for Level 4+ autonomous driving. It utilized AV accident data from the California Department of Motor Vehicles (DMV) to compare accident patterns and characteristics between AVs and conventional vehicles based on activation status of autonomous mode. It also categorized AV disengagement data to identify types and real-world cases of disengagements caused by perceptual blind areas. The analysis revealed that AVs exhibit different accident types due to their safe driving maneuvers, and three types of perceptual blind area scenarios were identified. The findings of this study serve as crucial foundational data for developing Level 4+ autonomous driving test scenarios, enabling the design of efficient strategies to mitigate perceptual blind areas in various scenarios. This, in turn, is expected to contribute to the effective evaluation and enhancement of AV driving safety on real roads.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.119-131
• /
• 2024

Understanding accurate traffic performance is crucial for ensuring efficient highway operation and providing a sustainable mobility environment. On the other hand, an immediate and precise estimation of highway traffic performance faces challenges because of infrastructure and technological constraints, data processing complexities, and limitations in using integrated big data. This paper introduces a framework for estimating traffic performance by analyzing real-time data sourced from toll collection systems and dedicated short-range communications used on highways. In particular, this study addresses the data errors arising from segmented information in data, influencing the individual travel trajectories of vehicles and establishing a more reliable Origin-Destination (OD) framework. The study revealed the necessity of trip linkage for accurate estimations when consecutive segments of individual vehicle travel within the OD occur within a 20-minute window. By linking these trip ODs, the daily average highway traffic performance for South Korea was estimated to be248,624 thousand vehicle kilometers per day. This value shows an increase of approximately 458 thousand vehicle kilometers per day compared to the 248,166 thousand vehicle kilometers per day reported in the highway operations manual. This outcome highlights the potential for supplementing previously omitted traffic performance data through the methodology proposed in this study.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.225-237
• /
• 2024

In the analysis of competing risks data, some of covariates may not be fully observed for some subjects. In such cases, excluding subjects with missing covariate values from the analysis may result in biased estimates and loss of efficiency. In this paper, we studied multiple imputation and the augmented inverse probability weighting method for regression parameter estimation in the cause-specific proportional hazards model with missing covariates. The performance of estimators obtained from multiple imputation and the augmented inverse probability weighting method is evaluated by simulation studies, which show that those methods perform well. Multiple imputation and the augmented inverse probability weighting method were applied to investigate significant risk factors for the risk of death from breast cancer and from other causes for breast cancer data with missing values for tumor size obtained from the Prostate, Lung, Colorectal, and Ovarian Cancer Screen Trial Study. Under the cause-specific proportional hazards model, the methods show that race, marital status, stage, grade, and tumor size are significant risk factors for breast cancer mortality, and stage has the greatest effect on increasing the risk of breast cancer death. Age at diagnosis and tumor size have significant effects on increasing the risk of other-cause death.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.48-59
• /
• 2024

As functions that support virtualization on their own in hardware are developed, user applications having various workloads are operating efficiently in the virtualization system. SR-IOV is a virtualization support function that takes direct access to PCI devices, thus giving a high I/O performance by minimizing the need for hypervisor or operating system interventions. With SR-IOV, network I/O acceleration can be realized in virtualization systems that have relatively long I/O paths compared to bare-metal systems and frequent context switches between the user area and kernel area. To take performance advantages of SR-IOV, network resource management policies that can derive optimal network performance when SR-IOV is applied to an instance such as a virtual machine(VM) or container are being actively studied.This paper evaluates and analyzes the network performance of SR-IOV implementing I/O acceleration is compared with Virtio in terms of 1) network delay, 2) network throughput, 3) network fairness, 4) performance interference, and 5) multi-network. The contributions of this paper are as follows. First, the network I/O process of Virtio and SR-IOV was clearly explained in the virtualization system, and second, the evaluation results of the network performance of Virtio and SR-IOV were analyzed based on various performance metrics. Third, the system overhead and the possibility of optimization for the SR-IOV network in a virtualization system with high VM density were experimentally confirmed. The experimental results and analysis of the paper are expected to be referenced in the network resource management policy for virtualization systems that operate network-intensive services such as smart factories, connected cars, deep learning inference models, and crowdsourcing.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.135-144
• /
• 2024

In this study, we propose an automatic classification model for quantitative multidimensional analysis based on facet theory to understand public opinions and demands on major issues through big data analysis. Civil complaints, as a form of public feedback, are generated by various individuals on multiple topics repeatedly and continuously in real-time, which can be challenging for officials to read and analyze efficiently. Specifically, our research introduces a new classification framework that utilizes facet theory and political analysis models to analyze the characteristics of citizen complaints and apply them to the policy-making process. Furthermore, to reduce administrative tasks related to complaint analysis and processing and to facilitate citizen policy participation, we employ deep learning to automatically extract and classify attributes based on the facet analysis framework. The results of this study are expected to provide important insights into understanding and analyzing the characteristics of big data related to citizen complaints, which can pave the way for future research in various fields beyond the public sector, such as education, industry, and healthcare, for quantifying unstructured data and utilizing multidimensional analysis. In practical terms, improving the processing system for large-scale electronic complaints and automation through deep learning can enhance the efficiency and responsiveness of complaint handling, and this approach can also be applied to text data processing in other fields.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.1
• /
• pp.1-10
• /
• 2024

In immersive virtual environments including mixed reality (MR) and virtual reality (VR), avatars or agents, which are virtual humans, are being studied and applied in various ways as factors that increase users' social presence. Recently, studies are being conducted to apply generative AI as an agent to improve user learning effects or suggest a collaborative environment in an immersive virtual environment. This study proposes a novel method for interface application of a virtual assistant agent (VAA) using OpenAI's ChatGPT in an immersive virtual environment including VR and MR. The proposed method consists of an information agent that responds to user queries and a control agent that controls virtual objects and environments according to user needs. We set up a development environment that integrates the Unity 3D engine, OpenAI, and packages and development tools for user participation in MR and VR. Additionally, we set up a workflow that leads from voice input to the creation of a question query to an answer query, or a control request query to a control script. Based on this, MR and VR experience environments were produced, and experiments to confirm the performance of VAA were divided into response time of information agent and accuracy of control agent. It was confirmed that the interface application of the proposed VAA can increase efficiency in simple and repetitive tasks along with user-friendly features. We present a novel direction for the interface application of an immersive virtual environment through the proposed VAA and clarify the discovered problems and limitations so far.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.75-92
• /
• 2020

As population and generation structures change, more and more customers tend to avoid facing relation due to the development of information technology and spread of smart phones. This phenomenon consists with efficiency and immediacy, which are the consumption patterns of modern customers who are used to information technology, so offline network-oriented distribution companies actively try to switch their sales and services to untact patterns. Recently, untact services are boosted in various fields, but beauty products are not easy to be recommended through untact services due to many options depending on skin types and conditions. There have been many studies on recommendations and development of recommendation systems in the online beauty field, but most of them are the ones that develop recommendation algorithm using survey or social data. In other words, there were not enough studies that classify segments based on user information such as skin types and product preference. Therefore, this study classifies customer segments using machine learning technique K-prototypesalgorithm based on customer information and search log data of mobile application, which is one of untact services in the beauty field, based on which, untact marketing strategy is suggested. This study expands the scope of the previous literature by classifying customer segments using the machine learning technique. This study is practically meaningful in that it classifies customer segments by reflecting new consumption trend of untact service, and based on this, it suggests a specific plan that can be used in untact services of the beauty field.