• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.241-251
• /
• 2022

Diagnosis and management of customer's skin condition is an important essential function in the cosmetics and beauty industry. As the social media environment spreads and generalizes to all fields of society, the interaction of questions and answers to various and delicate concerns and requirements regarding the diagnosis and management of skin conditions is being actively dealt with in the social media community. However, since social media information is very diverse and atypical big data, an intelligent skin condition diagnosis system that combines appropriate skin condition information analysis and artificial intelligence technology is necessary. In this paper, we developed the skin condition diagnosis system SCDIS to intelligently diagnose and manage the skin condition of customers by processing the text analysis information of social media into learning data. In SCDIS, an artificial neural network model, AnnTFIDF, that automatically diagnoses skin condition types using artificial neural network technology, a deep learning machine learning method, was built up and used. The performance of the artificial neural network model AnnTFIDF was analyzed using test sample data, and the accuracy of the skin condition type diagnosis prediction value showed a high performance of about 95%. Through the experimental and performance analysis results of this paper, SCDIS can be evaluated as an intelligent tool that can be used efficiently in the skin condition analysis and diagnosis management process in the cosmetic and beauty industry. And this study can be used as a basic research to solve the new technology trend, customized cosmetics manufacturing and consumer-oriented beauty industry technology demand.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.274-286
• /
• 2022

Multi-object tracking has been studied for a long time under computer vision and plays a critical role in applications such as autonomous driving and driving assistance. Multi-object tracking techniques generally consist of a detector that detects objects and a tracker that tracks the detected objects. Various publicly available datasets allow us to train a detector model without much effort. However, there are relatively few publicly available datasets for training a tracker model, and configuring own tracker datasets takes a long time compared to configuring detector datasets. Hence, the detector is often developed separately with a tracker module. However, the separated tracker should be adjusted whenever the former detector model is changed. This study proposes a system that can train a model that performs detection and tracking simultaneously using only the detector training datasets. In particular, a Siam network with augmentation is used to compose the detector and tracker. Experiments are conducted on public datasets to verify that the proposed algorithm can formulate a real-time multi-object tracker comparable to the state-of-the-art tracker models.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.487-487
• /
• 2021

탁수는 유기물 또는 무기물이 유입되면서 빛의 투과성이 낮아진 수체를 의미한다. 탁수가 발생하게 되면 어류의 폐사, 정수처리 비용의 증가 및 경관의 변화로 인한 피해가 발생하게 된다. 국내에서는 홍수기 또는 태풍 시 유역의 토사가 저수지 상류에서 유입하여 호내의 탁수를 발생시키는 경우가 있는데, 특히 낙동강 유역의 임하호에서 빈번하게 고탁수가 발생하여 왔다. 본 연구에서는 임하호에서 탁수 발생 시 신속 배제를 위한 수치적인 예측 시스템을 소개하고자 한다. 저수지 탁수관리의 기본개념은 용수공급능력을 고려한 고탁수의 신속한 배제이다. 이는 선제적 의사결정을 요구하므로, 지류에서 탁수가 발생한 즉시 향후 상황에 대한 예측이 필요하다. 이러한 예측을 위해 유역관리처는 3단계의 수치해석을 수행한다. 첫 번째는 유역 상류에서 탁수가 감지되었을 때, 호 내 탁수의 분포를 예측하는 것이다. 수심 및 수평방향의 탁수 분포에 대한 상세한 결과가 도출되어야 하기에, 3차원 수치해석 프로그램인 AEM3D를 이용한다. 이때, 과거 고탁수 유입에 대한 자료를 기반으로 산정된 매개변수가 적용된다. 두 번째는 예측된 호내 분포를 초기조건으로 댐 방류량 및 취수탑 위치(선택배제)에 따른 탁수 배제 수치해석을 수행하게 된다. 다양하고 많은 case에 대한 신속한 모의 및 3달 이상의 장기간 예측을 요구하므로, 2차원 수치모델인 CE-QUAL-W2를 활용한다. 이 단계에서 수자원의 안정적 공급이 가능한 범위 내에서 효과적인 탁수 배제 방류 방법 등이 결정되며, 방류 탁도가 예측된다. 세 번째 단계는 방류탁도를 경계조건으로 하여 하류 하천(반변천~내성천 합류 전)의 탁도를 예측하는 것이다. 하천의 탁도 예측은 국내뿐만 아니라 국외에서도 그 사례를 찾아보기가 쉽지 않은데, 이는 중소형의 지류에 대한 입력자료가 충분하지 않고 불확실성이 높기 때문이다. 이에 과거 10여 년의 data를 이용한 회귀분석을 통해 탁수 발생물질(SS)-부유사-유량과의 관계를 도출하고, 2차원 하천모델(EFDC)을 이용하여 수심 평균 탁도를 예측하게 된다. 이러한 세 단계의 예측은 탁수가 호내로 유입됨에 따라 반복되고, 점차 예측 정확도가 향상되게 된다. 세 단계의 과정을 통한 임하호 탁수의 조기 배제는 현재 적지 않은 효과를 거두고 있다고 판단된다. 그러나 탁수를 발생시키는 현탁물질의 종류는 매번 일정하지 않기 때문에, 이러한 예측 시스템에 정확도에 영향을 줄 수 있으므로, 여러 상황을 고려한 딥러닝을 도입하여 탁수 물질에 대한 정보를 예측한다면 보다 합리적인 의사결정 지원 도구가 될 수 있을 것이다.

• Knowledge Management Research
• /
• v.24 no.3
• /
• pp.95-125
• /
• 2023

As the aviation industry has rapidly been grown, there are more factors for customers to consider when choosing an airline. In response, airlines are trying to increase customer value by providing high-quality services and differentiated experiential value. While early customer value research centered on utilitarian value, which is the trade-off between cost and benefit in terms of utility for products and services, the importance of experiential value has recently been emphasized. However, experiential value needs to be studied in a specific context that fully represents customer preferences because what constitutes customer value changes depending on the product or service context. In addition, customer value has an important influence on customers' decision-making, so it is necessary for airlines to accurately understand what constitutes customer value. In this study, we collected customer reviews and ratings from Skytrax, a website specializing in airlines, and utilized the BERTopic technique to derive factors of customer value. The results revealed nine factors that constitute customer value in airlines, and six of them are related to customer satisfaction. This study proposes a new methodology that enables a granular understanding of customer value and provides airlines with specific directions for improving service quality.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.50 no.2
• /
• pp.119-129
• /
• 2024

The cutaneous lymphatic system in humans plays a crucial role in draining interstitial fluid and activating the immune system. Environmental factors, such as ultraviolet light and natural aging, often affect structural changes of such lymphatic vessels, causing skin dysfunction. However, some limitations still exist because of no alternatives to animal testing. To better understand the skin lymphatic system, a biomimetic microfluidic platform, skin-lymph-on-a-chip, was fabricated to develop a novel in vitro skin lymphatic model of humans and to investigate the molecular and physiological changes involved in lymphangiogenesis, the formation of lymphatic vessels. Briefly, the platform involved co-culturing differentiated primary normal human epidermal keratinocytes (NHEKs) and dermal lymphatic endothelial cells (HDLECs) in vitro. Based on our system, Lymphanax^TM, which is a condensed Panax ginseng root extract obtained through thermal conversion for 21 days, was applied to evaluate the lymphangiogenic effect, and the changes in molecular factors were analyzed using a deep-learning-based algorithm. Lymphanax^TM promoted healthy lymphangiogenesis in skin-lymphon-a-chip and indirectly affected HDELCs as its components rarely penetrated differentiated NHEKs in the chip. Overall, this study provides a new perspective on Lymphanax^TM and its effects using an innovative in vitro system.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.33-48
• /
• 2024

With the advent of 5G, characterized by Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communications (URLLC), and Massive Machine Type Communications (mMTC), efficient network management and service provision are becoming increasingly critical. This paper proposes a novel approach to address key challenges of 5G networks, namely ultra-high speed, ultra-low latency, and ultra-reliability, while dynamically optimizing network slicing and resource allocation using machine learning (ML) and deep learning (DL) techniques. The proposed methodology utilizes prediction models for network traffic and resource allocation, and employs Federated Learning (FL) techniques to simultaneously optimize network bandwidth, latency, and enhance privacy and security. Specifically, this paper extensively covers the implementation methods of various algorithms and models such as Random Forest and LSTM, thereby presenting methodologies for the automation and intelligence of 5G network operations. Finally, the performance enhancement effects achievable by applying ML and DL to 5G networks are validated through performance evaluation and analysis, and solutions for network slicing and resource management optimization are proposed for various industrial applications.