• Transactions of the Society of Information Storage Systems
• /
• v.9 no.2
• /
• pp.56-61
• /
• 2013

The recent increased use of mobile phone has resulted in a technical focusing on reliability issues related to drop performance. Since mobile phone may be dropped several times during their use, it is required to survive common drop accidents. The plastic injection parts such as base stopper and carrier in the encoder type actuator can be broken easily in the actual reliability test of 1.5m free drop. So, we analyzed the shock resistance characteristics of auto focus actuator with variables in the material properties using finite element method. By applying the new resin materials, we can decrease the breakage of plastic injection parts and improve the reliability of mobile phone.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.52-54
• /
• 2022

Aerial images are being one of the important aspects of satellite imagery, delivers effective information on landcovers. Their special characteristics includes the viewpoint from space which clarifies data related to land examining processes. Aerial images taken by satellites employed radio waves to wirelessly transmit images to ground stations. Due to transmission errors, images get distorted and unable to perform in landcover examining. This paper proposes an aerial image enhancement method using deep autoencoders. A properly trained autoencoder can enhance an aerial image to a considerable level of improvement. Results showed that the achieved enhancement is better than that was obtained from traditional image denoising methods.

• Journal of Auto-vehicle Safety Association
• /
• v.16 no.1
• /
• pp.29-34
• /
• 2024

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.714-717
• /
• 2019

IOT는 복잡하고 이질적인 네트워크 환경이며 저전력 장치를 위한 새로운 라우팅 프로토콜의 존재로 인해 혁신적인 침입탐지 시스템이 필요하다. 특히 접근이 어려운 IOT 환경에서는 공격을 받았을 때 정확하고 빠른 탐지가 용이하여야 한다. 따라서 본 논문에서는 탐지의 정확성과 희소의 공격을 잘 탐지하기 위한 효과적인 특징 추출과 분류를 위한 SAR(Stacked Auto Encoder+Random Forest) 시스템을 제안한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.5
• /
• pp.1161-1170
• /
• 2016

In this paper, we provide an authentication technology for verifying dynamic signature made by finger on smart phone. In the proposed method, we are using the Auto-Encoder-based 1 class model in order to effectively distinguish skilled forgery signature. In addition to the basic dynamic signature characteristic information such as appearance and velocity of a signature, we use accelerometer value supported by most of the smartphone. Signed data is re-sampled to give the same length and is normalized to a constant size. We built a test set for evaluation and conducted experiment in three ways. As results of the experiment, the proposed acceleration sensor value and 1 class model shows 6.9% less EER than previous method.

• Convergence Security Journal
• /
• v.21 no.3
• /
• pp.13-23
• /
• 2021

The attacker's techniques and tools are becoming intelligent and sophisticated. Existing Anti-Virus cannot prevent security accident. So the security threats on the endpoint should also be considered. Recently, EDR security solutions to protect endpoints have emerged, but they focus on visibility. There is still a lack of detection and responsiveness. In this paper, we use real-world EDR event logs to aggregate knowledge-based MITRE ATT&CK and autoencoder-based anomaly detection techniques to detect anomalies in order to screen effective analysis and analysis targets from a security manager perspective. After that, detected anomaly attack signs show the security manager an alarm along with log information and can be connected to legacy systems. The experiment detected EDR event logs for 5 days, and verified them with hybrid analysis search. Therefore, it is expected to produce results on when, which IPs and processes is suspected based on the EDR event log and create a secure endpoint environment through measures on the suspicious IP/Process.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.75-86
• /
• 2022

This study aims to solve the problem of class imbalance in numerical data by using a deep learning-based Variational AutoEncoder and to improve the performance of the learning model by augmenting the learning data. We propose 'D-VAE' to artificially increase the number of records for a given table data. The main features of the proposed technique go through discretization and feature selection in the preprocessing process to optimize the data. In the discretization process, K-means are applied and grouped, and then converted into one-hot vectors by one-hot encoding technique. Subsequently, for memory efficiency, sample data are generated with Variational AutoEncoder using only features that help predict with RFECV among feature selection techniques. To verify the performance of the proposed model, we demonstrate its validity by conducting experiments by data augmentation ratio.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.35-43
• /
• 2023

Emotion recognition while driving is an essential task to prevent accidents. Furthermore, in the era of autonomous driving, automobiles are the subject of mobility, requiring more emotional communication with drivers, and the emotion recognition market is gradually spreading. Accordingly, in this research plan, the driver's emotions are classified into seven categories using psychological and behavioral data, which are relatively easy to collect. The latent vectors extracted through the auto-encoder model were also used as features in this classification model, confirming that this affected performance improvement. Furthermore, it also confirmed that the performance was improved when using the framework presented in this paper compared to when the existing EEG data were included. Finally, 81% of the driver's emotion classification accuracy and 80% of F1-Score were achieved only through psychological, personal information, and behavioral data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.687-697
• /
• 2023

Botnets, whose attack patterns are becoming more sophisticated and diverse, are recognized as one of the most serious cybersecurity threats today. This paper revisits the experimental results of botnet detection using autoencoder, a semi-supervised deep learning model, for UGR and CTU-13 data sets. To prepare the input vectors of autoencoder, we create data points by grouping the NetFlow records into sliding windows based on source IP address and aggregating them to form features. In particular, we discover a simple power-law; that is the number of data points that have some flow-degree is proportional to the number of NetFlow records aggregated in them. Moreover, we show that our power-law fits the real data very well resulting in correlation coefficients of 97% or higher. We also show that this power-law has an impact on the learning of autoencoder and, as a result, influences the performance of botnet detection. Furthermore, we evaluate the performance of autoencoder using the area under the Receiver Operating Characteristic (ROC) curve.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2022

Recent deep learning-based research shows excellent performance in most natural language processing (NLP) fields with pre-trained language models. In particular, the auto-encoder-based language model proves its excellent performance and usefulness in various fields of Korean language understanding. However, the decoder-based Korean generative model even suffers from generating simple sentences. Also, there is few detailed research and data for the field of conversation where generative models are most commonly utilized. Therefore, this paper constructs multi-turn dialogue data for a Korean generative model. In addition, we compare and analyze the performance by improving the dialogue ability of the generative model through transfer learning. In addition, we propose a method of supplementing the insufficient dialogue generation ability of the model by extracting recommended response candidates from external knowledge information through a retrival model.