• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.161-168
• /
• 2021

Cracks affect the robustness of infrastructures such as buildings, bridge, pavement, and pipelines. This paper presents an automated crack detection system which detect cracks in diverse surfaces. We first constructed the combined crack dataset, consists of multiple crack datasets in diverse domains presented in prior studies. Then, state-of-the-art deep learning models in computer vision tasks including VGG, ResNet, WideResNet, ResNeXt, DenseNet, and EfficientNet, were used to validate the performance of crack detection. We divided the combined dataset into train (80%) and test set (20%) to evaluate the employed models. DenseNet121 showed the highest accuracy at 96.20% with relatively low number of parameters compared to other models. Based on the validation procedures of the advanced deep learning models in crack detection task, we shed light on the cost-effective automated crack detection system which can be applied to different surfaces and structures with low computing resources.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.76-90
• /
• 2024

Although artificial intelligence (AI) can be utilized in various domains such as smart city, healthcare, it is limited due to concerns about the exposure of personal and sensitive information. In response, the concept of distributed machine learning has emerged, wherein learning occurs locally before training a global model, mitigating the concentration of data on a central server. However, overall learning phase in a collaborative way among multiple participants poses threats to data privacy. In this paper, we systematically analyzes recent trends in privacy protection within the realm of distributed machine learning, considering factors such as the presence of a central server, distribution environment of the training datasets, and performance variations among participants. In particular, we focus on key distributed machine learning techniques, including horizontal federated learning, vertical federated learning, and swarm learning. We examine privacy protection mechanisms within these techniques and explores potential directions for future research.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.133-142
• /
• 2021

With the recent advancements of deep learning, companies such as smart home, healthcare, and intelligent transportation systems are utilizing its functionality to provide high-quality services for vehicle detection, emergency situation detection, and controlling energy consumption. To provide reliable services in such sensitive systems, deep learning models are required to have high accuracy. In order to develop a deep learning model for analyzing previously mentioned services, developers should utilize the state of the art deep learning models that have already been verified for higher accuracy. The developers can verify the accuracy of the referenced model by validating the model on the dataset. For this validation, the developer needs structural information to document and apply deep learning models, including metadata such as learning dataset, network architecture, and development environments. In this paper, we propose a description language that represents the network architecture of the deep learning model along with its metadata that are necessary to develop a deep learning model. Through the proposed description language, developers can easily verify the accuracy of the referenced deep learning model. Our experiments demonstrate the application scenario of a deep learning description document that focuses on the license plate recognition for the detection of illegally parked vehicles.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.509-512
• /
• 2024

자연어 처리 기술은 인간 언어의 이해와 처리에서 큰 진전을 이루었으나, 학습 데이터에 내재한 성별 편향이 모델의 예측 정확도와 신뢰성을 저하하는 주요한 문제로 남아 있다. 특히 성별 예측에서 이러한 편향은 더욱 두드러진다. 제로샷 분류 기법은 기존에 학습되지 않은 새로운 클래스를 효과적으로 예측할 수 있는 기술로, 학습 데이터의 제한적인 의존성을 극복하고 다양한 언어 및 데이터 제한 상황에서도 효율적으로 작동한다. 본 논문은 성별 클래스 확장과 데이터 구조 개선을 통해 성별 편향을 최소화한 새로운 데이터셋을 구축하고, 이를 제로샷 분류 기법을 통해 학습시켜 성별 편향성이 완화된 새로운 성별 예측 모델을 제안한다. 이 연구는 다양한 언어로 구성된 자연어 데이터를 추가 학습하여 성별 예측에 최적화된 모델을 개발하고, 제한된 데이터 환경에서도 모델의 유연성과 범용성을 입증한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.1235-1238
• /
• 2005

P2P(peer-to-peer) 웹 캐슁 모델은 서버 쪽에 집중되는 트래픽을 완화시킴으로써 전통적인 웹 캐슁 모델을 보완할 수 있다는 측면에서 최근에 활발히 연구되어 왔다. P2P 웹 캐슁은 클라이언트들의 로컬 캐쉬를 활용하여 부가적인 인프라의 추가없이 캐쉬 공간이 확대되는 효과를 얻을 수 있지만, 각 클라이언트들은 독립된 피어로서의 자율성(autonomy)을 가지므로 이러한 자율성의 제한을 최소화해야한다. 본 논문에서는 피어의 자율적인 동적 참여와 로컬 캐슁 전략을 보장하여 시스템의 실행 가능성(feasibility)을 높인 환경에서 효율적인 디렉토리 기반 P2P 웹 캐슁 시스템을 제안하였다. 제안하는 P2P 웹 캐슁 시스템은 동적인 P2P 네트워크 상에서의 오브젝트의 lifetime을 예상하여 이를 저장 공간 관리(storage management)에 적용하였다. 시스템의 성능 평가를 위하여 클라이언트의 http 요청 로그 데이터셋을 이용하여 트레이스 기반(trace-driven) 실험을 수행하고, 제안하는 시스템이 기존의 시스템에 비하여 주어진 동일한 환경에서 더 높은 정확성을 가짐을 확인하였다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.795-805
• /
• 2019

Recently, there is a growing interest in network anomaly detection technology to tackle unknown attacks. For this purpose, diverse studies using data mining, machine learning, and deep learning have been applied to detect network anomalies. In this paper, we evaluate the decision tree to see its feasibility for network anomaly detection on NSL-KDD data set, which is one of the most popular data mining techniques for classification. In order to handle the over-fitting problem of decision tree, we select 13 features from the original 41 features of the data set using chi-square test, and then model the decision tree using TensorFlow and Scik-Learn, yielding 84% and 70% of binary classification accuracies on the KDDTest+ and KDDTest-21 of NSL-KDD test data set. This result shows 3% and 6% improvements compared to the previous 81% and 64% of binary classification accuracies by decision tree technologies, respectively.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.899-904
• /
• 2022

As the world becomes an aging society due to a decrease in the birth rate and an increase in life expectancy, a system for health management of the elderly population is needed. Among them, various studies on occupancy and activity types are being conducted for smart home care services for indoor health management. In this paper, we propose a random forest model that classifies activity type as well as occupancy status through indoor temperature and humidity, CO2, fine dust values and UWB radar positioning for smart home care service. The experiment measures indoor environment and occupant positioning data at 2-second intervals using three sensors that measure indoor temperature and humidity, CO2, and fine dust and two UWB radars. The measured data is divided into 80% training set data and 20% test set data after correcting outliers and missing values, and the random forest model is applied to evaluate the list of important variables, accuracy, sensitivity, and specificity.

• Journal of the Korean GEO-environmental Society
• /
• v.23 no.8
• /
• pp.5-10
• /
• 2022

Ground Subsidence has been continuously occurring in densely populated downtown. The main cause of ground subsidence is the damaged underground facility like sewer. Currently, ground subsidence is being dealt with by discovering cavities in ground using GPR. However, this consumes large amount of manpower and cost, so it is necessary to predict hazardous area for efficient operation of GPR. In this study, ◯◯city is divided into 500 m×500 m grids. Then, data set was constructed using the characteristics of the underground facility and ground subsidence in grids. Data set used to machine learning model for ground subsidence risk grade prediction. The purposed model would be used to present a ground subsidence risk map of target area.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.339-342
• /
• 2020

본 논문에서는 AI 학습을 위한 데이터 수집을 위해 윈도우 환경에서 YOLO 시스템을 사용한 객체 인식에 대한 방법을 제안한다. 이 방법은 아나콘다, 리눅스 등의 가상환경을 요구하지 않기 때문에 실사용 이전 사전 환경설정 작업 시간을 최소화한다. 또한 이 방법은 Visual Studio, OpenCV, CUDA 등 익숙한 플랫폼 및 라이브러리를 요구하기 때문에 다른 사람들에게 편안한 작업환경 제공한다. 또한 기존의 COCO 데이터 셋을 사용한 YOLOv3가 아닌 추가 학습 방법을 제안함으로써 보다 보편적인 객체 인식이 가능하다. 따라서 빠른 시간 내에 자신이 원하는 객체를 인식할 수 있는 시스템을 구축하는 방법을 제안한다.