• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.263-264
• /
• 2023

오늘날 출산율 감소와 의료기술 등의 발달에 따라 고령화 사회 현상이 급부상하고 있으며, 이 비율은 계속 증가할 것이다. 또한 노인 인구가 많아지는 만큼 노안을 가진 사람들도 많아진다. 고령화 사회가 지속되는 만큼 고령층이 이용할 수 있는 디지털 기기 또한 많아져야 하지만 그렇지 않다. 그중에 하나인 ATM은 고령층을 제외한 고객들은 모바일뱅킹과 같은 서비스를 이용하고 고령층이 주로 ATM을 이용한다. 주요 고객인 고령층이 사용하는 ATM이지만 고령층을 배려한 ATM은 찾아보기 힘들다. 이에 본 논문에서는 딥러닝 모델을 이용하여 노안을 갖고 있거나 고령층이라는 것을 나이로 판단하여 고령층과 일반적인 노안을 갖는 연령층이 보다 쉽게 ATM을 이용 할 수 있는 선택적 ATM UI 간편화 시스템을 구축하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.21-28
• /
• 2023

In manufacturing companies that focus on small-scale production of multiple product varieties, defective products are manually selected by workers rather than relying on automated inspection. Consequently, there is a higher risk of incorrect sorting due to variations in selection criteria based on the workers' experience and expertise, without consistent standards. Moreover, for non-standardized flexible objects with varying sizes and shapes, there can be even greater deviations in the selection criteria. To address these issues, this paper designs a quality inspection system using artificial intelligence-based unsupervised learning methods and conducts research by experimenting with accuracy using a dataset obtained from real manufacturing environments.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.47-48
• /
• 2024

Heating, Ventilating, and Air Conditioning(HVAC) 시스템은 난방(Heating), 환기(Ventilating), 공기조화(Air Conditioning)를 제공하는 공조시스템으로, 실내 환경의 온도, 습도 조절 및 지속적인 순환 및 여과를 통해 실내 공기 질을 개선한다. 이러한 HVAC 시스템에 이상이 생기는 경우 공기 여과율이 낮아지며, COVID-19와 같은 법정 감염병 예방에 취약해진다. 또한 장비의 과부하를 유발하여, 시스템의 효율성 저하 및 에너지 낭비를 불러올 수 있다. 따라서 본 논문에서는 HVAC 시스템의 이상 탐지 및 조기 조치를 위한 Transformer 기반 이상 탐지 기법의 적용을 제안한다. Transformer는 기존 시계열 데이터 처리를 위한 기법인 Recurrent Neural Network(RNN)기반 모델의 구조적 한계점을 극복함에 따라 Long Term Dependency 문제를 해결하고, 병렬처리를 통해 효율적인 Feature 추출이 가능하다. Transformer 모델이 HVAC 시스템의 이상 탐지에서 RNN 기반의 비교군 모델보다 약 1.31%의 향상을 보이며, Transformer 모델을 통한 HVAC의 이상 탐지에 효율적임을 확인하였다.

• Journal of Radiation Industry
• /
• v.18 no.3
• /
• pp.177-182
• /
• 2024

The purpose of this study is to develop a CNN based deep learning model that can effectively detect pneumonia by analyzing chest X-ray images of adults over the age of 20 and compare it with VUNO, LUNIT a commercialized AI model. The data of chest X-ray image was evaluate based on accuracy, precision, recall, F1 score, and AUC score. The CNN model recored an accuracy of 82%, precision 76%, recall 99%, F1 score 86%, and AUC score 0.7937. The VUNO model recordded an accuracy of 84%, precision 81%, recall 94%, F1 score 87%, and AUC score 0.8233. The LUNIT model recorded an accuracy of 77%, precision 72%, recall 96%, F1 score 83%, and AUC score 0.7436. As a result of the Confusion Matrix analysis, the CNN model showe FN (3), showing the highest recall rate (99%) in the diagnosis of pneumonia. The VUNO model showed excellent overall perfomance with high accuracy (84%) and AUC score (0.8233), and the LUNIT model showed high recall rate (96%) but the accuracy and precision showed relatively low results. This study will be able to provide basic data useful for the development of a pneumonia diagnosis system by comprehensively considers the perfomance of the medel is necessary to effectively discriminate between penumonia and normal groups.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.87-94
• /
• 2024

Children with speech sound disorders (SSDs) face various challenges in producing speech sounds, which often lead to significant social and educational barriers. Detecting and treating SSDs in children is complex due to the variability in disorder severity and diagnostic boundaries. This study aims to develop an automated SSD detection system using deep learning models, leveraging their ability to transcribe audio, efficiently capture sound patterns on a vast scale, and address the limitations of traditional methods involving speech-language pathologists. For this study, we collected audio recordings from 573 children aged two to nine using standardized prompts from the Assessment of Phonology and Articulation for Children. Speech-language pathologists analyzed the recordings and identified 92 children with SSDs. To build an automatic SSD detection system, we used a dataset to train neural network models for automatic speech recognition and audio classification. Five different methods are studied, with the best method achieving 73.9% unweighted average recall. While the results show the potential of using deep learning models for the automatic detection of SSDs in children, further research is needed to improve the reliability of the models widely used in practice.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.861-866
• /
• 2022

Seoul introduced the shared bicycle system, "Seoul Public Bike" in 2015 to help reduce traffic volume and air pollution. Hence, to solve various problems according to the supply and demand of the shared bicycle system, "Seoul Public Bike," several studies are being conducted. Most of the research is a strategic "Bicycle Rearrangement" in regard to the imbalance between supply and demand. Moreover, most of these studies predict demand by grouping features such as weather or season. In previous studies, demand was predicted by time-series-analysis. However, recently, studies that predict demand using deep learning or machine learning are emerging. In this paper, we can show that demand prediction can be made a little better by discovering new features or ordering the importance of various features based on well-known feature-patterns. In this study, by ordering the selection of new features or the importance of the features, a better coefficient of determination can be obtained even if the well-known deep learning or machine learning or time-series-analysis is exploited as it is. Therefore, we could be a better one for demand prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.19-27
• /
• 2022

In this study, we propose a language and platform to describe and manage the MLOps(Machine Learning Operations) workflow for time series data anomaly detection. Time series data is collected in many fields, such as IoT sensors, system performance indicators, and user access. In addition, it is used in many applications such as system monitoring and anomaly detection. In order to perform prediction and anomaly detection of time series data, the MLOps platform that can quickly and flexibly apply the analyzed model to the production environment is required. Thus, we developed Python-based AI/ML Modeling Language (AMML) to easily configure and execute MLOps workflows. Python is widely used in data analysis. The proposed MLOps platform can extract and preprocess time series data from various data sources (R-DB, NoSql DB, Log File, etc.) using AMML and predict it through a deep learning model. To verify the applicability of AMML, the workflow for generating a transformer oil temperature prediction deep learning model was configured with AMML and it was confirmed that the training was performed normally.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.58-64
• /
• 2021

As the number of registered vehicles increases, traffic congestion will worsen worse, which may act as an inhibitory factor for urban social and economic development. Through accurate traffic flow prediction, various AI techniques have been used to prevent traffic congestion. This paper uses the data from a VDS (Vehicle Detection System) as input variables. This study predicted traffic flow in five levels (free flow, somewhat delayed, delayed, somewhat congested, and congested), rather than predicting traffic flow in two levels (free flow and congested). The Catboost model, which is a machine-learning algorithm, was used in this study. This model predicts traffic flow in five levels and compares and analyzes the accuracy of the prediction with other algorithms. In addition, the preprocessed model that went through RandomizedSerachCv and One-Hot Encoding was compared with the naive one. As a result, the Catboost model without any hyper-parameter showed the highest accuracy of 93%. Overall, the Catboost model analyzes and predicts a large number of categorical traffic data better than any other machine learning and deep learning models, and the initial set parameters are optimized for Catboost.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.1-7
• /
• 2019

Recently, various approaches to detect network attacks using machine learning have been studied and are being applied to detect new attacks and to increase precision. However, the machine learning method is dependent on feature extraction and takes a long time and complexity. It also has limitation of performace due to learning data imbalance. In this study, we propose a method to solve the degradation of classification performance due to imbalance of learning data among the limit points of detection system. To do this, we generate data using Generative Adversarial Networks (GANs) and propose a classification method using Convolutional Neural Networks (CNNs). Through this approach, we can confirm that the accuracy is improved when applied to the NSL-KDD and UNSW-NB15 datasets.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.