• The Journal of the Acoustical Society of Korea
• /
• v.41 no.4
• /
• pp.461-467
• /
• 2022

Sonobuoy is a disposable device that collects underwater acoustic information and is designed to transmit signals collected in a particular area to nearby aircraft or ships and sink to the seabed upon completion of its mission. In a conventional sonobouy signal transmission and reception system, collected signals are modulated and transmitted using techniques such as frequency division modulation or Gaussian frequency shift keying, and received and demodulated by an aircraft or a ship. However, this method has the disadvantage of the large amount of information to be transmitted and low security due to relatively simple modulation and demodulation methods. Therefore, in this paper, we propose a method that uses an autoencoder to encode a transmission signal into a low-dimensional latent vector to transmit the latent vector to an aircraft or ship and decode the received latent vector to improve signal security and to reduce the amount of transmission information by approximately a factor of a hundred compared to the conventional method. As a result of confirming the sample spectrogram reconstructed by the proposed method through simulation, it was confirmed that the original signal could be restored from a low-dimensional latent vector.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.952-955
• /
• 2014

본 논문에서는 정보 검색 분야에서 잘 알려진 잠재 의미 분석 방법과 계층적 군집화 방법의 단점을 상호 보완하여 보다 효율적인 정보 검색을 위한 혼합형 군집화 방법을 제안한다. 먼저, 잠재 의미 분석 방법은 벡터 연산을 통하여 자동적으로 문서 내에 있는 잠재적인 의미를 찾는 정보 검색분야에서 많이 사용되는 고전적인 방법이다. 그러나 이 방법은 언어의 유의성이나 다의성으로 인하여 발생되는 백-오브-워드(bag-of-word) 문제를 가지고 있다. 두 번째 방법인 문서 군집화를 위하여 범용적으로 사용되고 있는 계층적 군집화 방법이다. 이 방법은 이를 통하여 분석된 군집의 질적 측면에서 볼 때, 여전히 단층적 군집들이 많이 형성되어 세부적인 분석을 통한 추가적인 군집화가 필요함을 알 수 있다. 따라서, 본 논문에서는 앞서 언급한 문제점을 해결하기 위하여 혼합적인 방법으로 잠재 의미 분석 방법을 이용한 응집 계층 군집화 방법을 제안한다. 제안한 방법을 이용하여 잘 알려진 두 개의 데이터에 적용하고 기존의 방법과 그 결과를 비교함으로써 군집의 질적 측면에서의 우수함을 보인다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.1
• /
• pp.36-42
• /
• 2004

In this paper, we compare the vector model performance with the probabilistic model of information system. We use LSI(Latent Semantic Indexing) model for vector model, while Condor information search system that is ready to sell on business is used as a probabilistic model. Each model produces the search results from the original queries and the queries extended by a dictionary definition. We compare those results between two models and find out the vector model is much better than the probabilistic model for the most queries.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.27-33
• /
• 2022

In this paper, we propose a novel generator architecture for multi-domain style transfer method not an image to image translation, as a method of generating a styled image by transfering a style to the content image. A latent vector and Gaussian noises are added to the generator of GAN so that a high quality image is generated while considering the characteristics of various data distributions for each domain and preserving the features of the content data. With the generator architecture of the proposed GAN, networks are configured and presented so that the content image can learn the styles for each domain well, and it is applied to the domain composed of images of the four seasons to show the high resolution style transfer results.

• Journal of Korea Multimedia Society
• /
• v.12 no.8
• /
• pp.1155-1163
• /
• 2009

This paper proposes an automatic facial expression generation system of vector graphic character using gaussian process model. Proposed method extracts the main feature vectors from twenty-six facial data of character redefined based on Russell's internal emotion state. Also by using new gaussian process model, SGPLVM, we find low-dimensional feature data from extracted high-dimensional feature vectors, and learn probability distribution function (PDF). All parameters of PDF are estimated by maximization the likelihood of learned expression data, and these are used to select wanted facial expressions on two-dimensional space in real time. As a result of simulation, we confirm that proposed facial expression generation tool is working in the small facial expression datasets and can generate various facial expressions without prior knowledge about relation between facial expression and emotion.

• Microbiology and Biotechnology Letters
• /
• v.36 no.4
• /
• pp.260-267
• /
• 2008

The choice of expression vector is very important for industrial production of proteins. Therefore, the systematic mining of promoters over a wider range of genetic resource and/or host is required. We previously reported a novel bidirectional reporting system (pBGR) for the isolation of promoters from metagenome and screened useful promoters that functioned constitutively in E. coli under general culture conditions. Among them, three promoter sequences including each upstream region were amplified by PCR and used to construct new expression vectors. To facilitate subcloning, a multi-cloning site was incorporated into the downstream region of the revere primer sequence. At these sites, GFP, esterase and $\beta$-glucosidase were subcloned and analyzed the constitutive expression ability of new promoter in terms of protein solubility and expression level. As a result, these vectors expressed the proteins constitutively to a level of $2{\sim}3%$ of the total cell protein in soluble fraction (>80 %). This study suggested that excavation of metagenomic promoters for construction of expression vector in a certain strain could provide a way for the development of the expression systems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.22-24
• /
• 2001

정보검색 시스템에서 사용자의 질의어가 불완전함에 따라 생기는 검색 효율의 저하를 줄이기 위하여 용어의 상호관련성을 반영함과 동시에 벡터의 공간을 축소하는 LSI 모델을 사용하여 문서 집합으로부터 잠재적 의미 공간을 구축하였다. 또한 의미 공간상에 있는 문서의 분포에 따라 \"개념\"을 추출하기 하기 위해 k-means algorithm을 사용하여 군집화 시켰다. 이로부터 불완전한 초기 사용자 질의어를 의미 공간에 구축된 클러스터링 정보로 수정하여 새로운 질의어를 생성함으로 검색의 효율을 높이고자 하였다. 검색 효율을 측정하기 위해 TREC 데이터를 이용하여 분석하였으며 결과는 질의어의 성격에 따라 달라졌으나 대체적으로 우수한 성능을 보였다.한 성능을 보였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.91-97
• /
• 2023

Recent research shows that latent directions can be used to image process towards certain attributes. However, controlling the generation process of generative model is very difficult. Though the latent directions are used to image process for certain attributes, many restrictions are required to enhance the attributes received the latent vectors according to certain text and prompts and other attributes largely unaffected. This study presents a generative model having certain restriction to the latent vectors for image generation and manipulation. The suggested method requires only few minutes per manipulation, and the simulation results through Tensorflow Variational Auto-encoder show the effectiveness of the suggested approach with extensive results.