• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.243-252
• /
• 2024

Among the Foley sound generation models that have recently begun to be studied, a sound generation technique using the Vector Quantized-Variational AutoEncoder (VQ-VAE) structure and generation model such as Pixelsnail are one of the important research subjects. On the other hand, in the field of deep learning-based acoustic signal compression, residual vector quantization technology is reported to be more suitable than the conventional VQ-VAE structure. Therefore, in this paper, we aim to study whether residual vector quantization technology can be effectively applied to the Foley sound generation. In order to tackle the problem, this paper applies the residual vector quantization technique to the conventional VQ-VAE-based Foley sound generation model, and in particular, derives a model that is compatible with the existing models such as Pixelsnail and does not increase computational resource consumption. In order to evaluate the model, an experiment was conducted using DCASE2023 Task7 data. The results show that the proposed model enhances about 0.3 of the Fréchet audio distance. Unfortunately, the performance enhancement was limited, which is believed to be due to the decrease in the resolution of time-frequency domains in order to do not increase consumption of the computational resources.

• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.174-176
• /
• 2022

In this paper, we present a mobile application for 'personalized customized learning' for children with articulation disorders using an artificial intelligence (AI) algorithm. A dataset (Data Set) to analyze, judge, and predict the learner's articulation situation and degree. In particular, we designed a prototype model by looking at how AI can be improved and advanced compared to existing applications from the UX/UI (GUI) aspect. So far, the focus has been on visual experience, but now it is an important time to process data and provide a UX/UI (GUI) experience to users. The UX/UI (GUI) of the proposed mobile application was to be provided according to the learner's articulation level and situation by using CRNN (Convolution Recurrent Neural Network) of DeepLearning and Auto Encoder GPT-3 (Generative Pretrained Transformer). The use of artificial intelligence algorithms will provide a learning environment with a high degree of perfection to children with articulation disorders, thereby enhancing the learning effect. I hope that you do not have any fear or discomfort in conversation by improving the perfection of articulation with 'personalized and customized learning'.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.631-640
• /
• 2017

The estimation of rice yield affects the income of farmers as well as the fields related to agriculture. Moreover, it has an important effect on the government's policy making including the control of supply demand and the price estimation. Thus, it is necessary to build the crop yield estimation model and from the past, many studies utilizing empirical statistical models or artificial neural network algorithms have been conducted through climatic and satellite data. Presently, scientists have achieved successful results with deep learning algorithms in the field of pattern recognition, computer vision, speech recognition, etc. Among deep learning algorithms, the SSAE (Stacked Sparse AutoEncoder) algorithm has been confirmed to be applicable in the field of forecasting through time series data and in this study, SSAE was utilized to estimate the rice yield in South Korea. The climatic and satellite data were used as the input variables and different types of input data were constructed according to the period of rice growth in South Korea. As a result, the combination of the satellite data from May to September and the climatic data using the 16 day average value showed the best performance with showing average annual %RMSE (percent Root Mean Square Error) and region %RMSE of 7.43% and 7.16% that the applicability of the SSAE algorithm could be proved in the field of rice yield estimation.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.

• Journal of Aerospace System Engineering
• /
• v.18 no.3
• /
• pp.41-47
• /
• 2024

Recently, as the practical application and commercialization of unmanned aerial vehicles (UAVs) is pursued, interest in ensuring the safety of the UAV is increasing. Because UAV accidents can result in property damage and loss of life, it is important to develop technology to prevent accidents. For this reason, a technique to detect the abnormal flight state of UAVs has been developed based on the AutoEncoder model. However, the existing detection technique is limited in terms of performance and real-time processing. In this paper, we propose a U-Net based abnormal flight detection technique. In the proposed technique, abnormal flight is detected based on the increasing rate of Mahalanobis distance for the reconstruction error obtained from the U-Net model. Through simulation experiments, it can be shown that the proposed detection technique has superior detection performance compared to the existing detection technique, and can operate in real-time in an on-board environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.639-641
• /
• 2023

이미지 기반 폐기물 처리시스템에서 품목별 상이한 수집 난이도로 인해 발생하는 데이터 불균형으로 분류 모델 학습에 어려움이 따른다. 따라서 본 논문에서는 폐기물 분류 모델의 성능 비교를 통해 적합한 이미지 생성 모델을 탐색한다. 데이터의 불균형을 해결할 수 있도록 VAE(Variational Auto-Encoder), GAN(Generative Adversarial Networks) 및 Diffusion Model을 이용하여 이미지를 생성한다. 이후 각각의 생성 방법에 따라 학습데이터와 병합하여 객체 분류를 진행하였다. 정확도는 VAE가 84.41%로 3.3%의 성능 향상을, F1-점수는 Diffusion Model이 91.94%로 6.14%의 성능 향상을 이루었다. 이를 통해, 데이터 수집에서 나타나는 데이터 불균형을 해결하여 실 사용환경에 알맞은 시스템을 구축이 가능함을 확인하였다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.491-494
• /
• 2020

최근 언어 모델(Language model)의 기술이 발전함에 따라, 자연어처리 분야의 많은 연구들이 좋은 성능을 내고 있다. 정해진 주제 없이 인간과 잡담을 나눌 수 있는 오픈 도메인 대화 시스템(Open-domain dialogue system) 분야에서 역시 이전보다 더 자연스러운 발화를 생성할 수 있게 되었다. 언어 모델의 발전은 응답 선택(Response selection) 분야에서도 모델이 맥락에 알맞은 답변을 선택하도록 하는 데 기여를 했다. 하지만, 대화 모델이 답변을 생성할 때 일관성 없는 답변을 만들거나, 구체적이지 않고 일반적인 답변만을 하는 문제가 대두되었다. 이를 해결하기 위하여 화자의 개인화된 정보에 기반한 대화인 페르소나(Persona) 대화 데이터 및 태스크가 연구되고 있다. 페르소나 대화 태스크에서는 화자마다 주어진 페르소나가 있고, 대화를 할 때 주어진 페르소나와 일관성이 있는 답변을 선택하거나 생성해야 한다. 이에 우리는 대용량의 코퍼스(Corpus)에 사전 학습(Pre-trained) 된 언어 모델을 활용하여 더 적절한 답변을 선택하는 페르소나 대화 시스템에 대하여 논의한다. 언어 모델 중 자기 회귀(Auto-regressive) 방식으로 모델링을 하는 GPT-2, DialoGPT와 오토인코더(Auto-encoder)를 이용한 BERT, 두 모델이 결합되어 있는 구조인 BART가 실험에 활용되었다. 이와 같이 본 논문에서는 여러 종류의 언어 모델을 페르소나 대화 태스크에 대해 비교 실험을 진행했고, 그 결과 Hits@1 점수에서 BERT가 가장 우수한 성능을 보이는 것을 확인할 수 있었다.