• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.135-145
• /
• 2020

Recently, deep-learning based methods for low-light image enhancement accomplish great success through supervised learning. However, they still suffer from the lack of sufficient training data due to difficulty of obtaining a large amount of low-/normal-light image pairs in real environments. In this paper, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP), which gives the constraint that the brightest pixel in a small patch is likely to be close to 1. With this prior, pseudo ground-truth is first generated to establish an unsupervised loss function. The proposed enhancement network is then trained using the proposed unsupervised loss function. To the best of our knowledge, this is the first attempt that performs a low-light image enhancement through unsupervised learning. In addition, we introduce a self-attention map for preserving image details and naturalness in the enhanced result. We validate the proposed method on various public datasets, demonstrating that our method achieves competitive performance over state-of-the-arts.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.557-569
• /
• 2022

Vibration-based structural health monitoring (SHM) is crucial for the dynamic maintenance of civil building structures to protect property security and the lives of the public. Analyzing these vibrations with modern artificial intelligence and deep learning (DL) methods is a new trend. This paper proposed an unsupervised deep learning method based on a convolutional autoencoder (CAE), which can overcome the limitations of conventional supervised deep learning. With the convolutional core applied to the DL network, the method can extract features self-adaptively and efficiently. The effectiveness of the method in detecting damage is then tested using a benchmark model. Thereafter, this method is used to detect damage and instant disaster events in a rubber bearing-isolated gymnasium structure. The results indicate that the method enables the CAE network to learn the intact vibrations, so as to distinguish between different damage states of the benchmark model, and the outcome meets the high-dimensional data distribution characteristics visualized by the t-SNE method. Besides, the CAE-based network trained with daily vibrations of the isolating layer in the gymnasium can precisely recover newly collected vibration and detect the occurrence of the ground motion. The proposed method is effective at identifying nonlinear variations in the dynamic responses and has the potential to be used for structural condition assessment and safety warning.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.39-42
• /
• 1995

문장 안에서 한 단어가 가지는 올바른 의미를 얻기 위해 모듈화된 신경망을 이용하였다. 앞부분에 놓인 신경망은 코호넨 신경망으로 사용자의 지도가 개입되지 않은 상태로 자율학습(Unsupervised learning)이 이루어지고, 뒤에 놓인 신경망은 앞에서 결과로 얻은 2차원의 자기 조직화 형상지도(Self-organizing feature map)를 바탕으로 역전파 신경망을 이용한 지도학습(Supervised learning)을 하게 하였다. 입력 자료는 구문분석된 문장의 조사 정보를 활용하여 입력 위치를 정해준 명사의 의미표지와 동사의 의미표지를 사용하였다. 중의성이 있는 단어를 가지는 문장은 중의성의 가지수 만큼 테스트 입력 자료가 되어 신경망을 통과하여 의미를 결정하도록 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.63-66
• /
• 2022

본 논문에서는 분자의 특성을 정확하게 예측하기 위해 효과적인 사전학습(pretraining) 전략과 트랜스포머(Transformer) 모델을 활용한 방법을 제시한다. 딥러닝을 활용한 분자의 성능을 예측하는 연구는 그동안 레이블이 부족한 분자데이터의 특성에 의해 학습 때 사용된 데이터이외의 분자데이터에 대해 일반화 능력이 떨어지는 어려움을 겪었다. 이 논문에서 제시한 모델은 사전학습(pretraining)을 수행할 때 자기지도학습(self-supervised training)을 사용하여 부족한 레이블에 의한 문제점을 피할 수 있다. 대규모 분자 데이터셋으로부터 학습된 이 모델은 4가지 다운스트림 데이터셋에 대해 모두 우수한 성능을 보여주어 일반화 성능이 뛰어나며 효과적인 분자표현을 얻을 수 있음을 보인다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.400-409
• /
• 2003

Collaborative filtering (CF) recommendation is a knowledge sharing technology for distribution of opinions and facilitating contacts in network society between people with similar interests. The main concerns of the CF algorithm are about prediction accuracy, speed of response time, problem of data sparsity, and scalability. In general, the efforts of improving prediction algorithms and lessening response time are decoupled. We propose a three-step CF recommendation model which is composed of profiling, inferring, and predicting steps while considering prediction accuracy and computing speed simultaneously. This model combines a CF algorithm with two machine learning processes, SOM (Self-Organizing Map) and CBR (Case Based Reasoning) by changing an unsupervised clustering problem into a supervised user preference reasoning problem, which is a novel approach for the CF recommendation field. This paper demonstrates the utility of the CF recommendation based on SOM cluster-indexing CBR with validation against control algorithms through an open dataset of user preference.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.354-359
• /
• 2013

In this paper, we suggested the method for implementation of unsupervised nonlinear classification using Binary Harmony Search (BHS) algorithm, which is known as a optimization algorithm. Various algorithms have been suggested for classification of feature vectors from the process of machine learning for pattern recognition or EEG signal analysis processing. Supervised learning based support vector machine or fuzzy c-mean (FCM) based on unsupervised learning have been used for classification in the field. However, conventional methods were hard to apply nonlinear dataset classification or required prior information for supervised learning. We solved this problems with proposed classification method using heuristic approach which took the minimal Euclidean distance between vectors, then we assumed them as same class and the others were another class. For the comparison, we used FCM, self-organizing map (SOM) based on artificial neural network (ANN). KEEL machine learning datset was used for simulation. We concluded that proposed method was superior than other algorithms.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.15 no.3
• /
• pp.134-141
• /
• 2011

There have been increased economic and societal demands to continuously monitor the integrity and long-term deterioration of civil infrastructures to ensure their safety and adequate performance throughout their life span. However, it is very difficult to continuously monitor the structural condition of the pipeline structures because those are placed underground and connected each other complexly, although pipeline structures are core underground infrastructures which transport primary sources. Moreover, damage can occur at several scales from micro-cracking to buckling or loose bolts in the pipeline structures. In this study, guided wave measurement can be achieved with a self-sensing circuit using a piezoelectric active sensor. In this self sensing system, a specific frequency-induced structural wavelet response is obtained from the self-sensed guided wave measurement. To classify the multiple types of structural damage, supervised learning-based statistical pattern recognition was implemented using the damage indices extracted from the guided wave features. Different types of structural damage artificially inflicted on a pipeline system were investigated to verify the effectiveness of the proposed SHM approach.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.157-181
• /
• 2022

As competition in the airline industry intensifies, effective airline service quality evaluation has become one of the main challenges. In particular, as big data analytics has been touted as a new research paradigm, new research on service quality measurement using online review analysis has been attempted. However, these studies do not use review titles for analysis, relyon supervised learning that requires a lot of human intervention in learning, and do not consider airline characteristics in classifying service quality dimensions.To overcome the limitations of existing studies, this study attempts to measure airlines service quality and to classify it into the AIRQUAL service quality dimension using online review text as well as title based on self-trainingand sentiment analysis. The results show the way of effective extracting service quality dimensions of AIRQUAL from online reviews, and find that each service quality dimension have a significant effect on service satisfaction. Furthermore, the effect of review title on service satisfaction is also found to be significant. This study sheds new light on service quality measurement in airline industry by using an advanced analytical approach to analyze effects of service quality on customer satisfaction. This study also helps managers who want to improve customer satisfaction by providing high quality service in airline industry.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.482-488
• /
• 2014

This paper aims to analyze user's emotion automatically by analyzing Twitter, a representative social network service (SNS). In order to create sentiment analysis models by using machine learning techniques, sentiment labels that represent positive/negative emotions are required. However it is very expensive to obtain sentiment labels of tweets. So, in this paper, we propose a sentiment analysis model by using self-training technique in order to utilize "data without sentiment labels" as well as "data with sentiment labels". Self-training technique is that labels of "data without sentiment labels" is determined by utilizing "data with sentiment labels", and then updates models using together with "data with sentiment labels" and newly labeled data. This technique improves the sentiment analysis performance gradually. However, it has a problem that misclassifications of unlabeled data in an early stage affect the model updating through the whole learning process because labels of unlabeled data never changes once those are determined. Thus, labels of "data without sentiment labels" needs to be carefully determined. In this paper, in order to get high performance using self-training technique, we propose 3 policies for updating "data with sentiment labels" and conduct a comparative analysis. The first policy is to select data of which confidence is higher than a given threshold among newly labeled data. The second policy is to choose the same number of the positive and negative data in the newly labeled data in order to avoid the imbalanced class learning problem. The third policy is to choose newly labeled data less than a given maximum number in order to avoid the updates of large amount of data at a time for gradual model updates. Experiments are conducted using Stanford data set and the data set is classified into positive and negative. As a result, the learned model has a high performance than the learned models by using "data with sentiment labels" only and the self-training with a regular model update policy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.514-517
• /
• 2023

본 연구는 인 컨택스트 러닝 (In-Context Learning)을 오디오-언어 작업에 적용하기 위한 멀티모달 (Multi-Modal) 딥러닝 모델을 다룬다. 해당 모델을 통해 학습 단계에서 오디오와 텍스트의 소통 가능한 형태의 표현 (Representation)을 학습하고 여러가지 오디오-텍스트 작업을 수행할 수 있는 멀티모달 딥러닝 모델을 개발하는 것이 본 연구의 목적이다. 모델은 오디오 인코더와 언어 인코더가 연결된 구조를 가지고 있으며, 언어 모델은 6.7B, 30B 의 파라미터 수를 가진 자동회귀 (Autoregressive) 대형 언어 모델 (Large Language Model)을 사용한다 오디오 인코더는 자기지도학습 (Self-Supervised Learning)을 기반으로 사전학습 된 오디오 특징 추출 모델이다. 언어모델이 상대적으로 대용량이기 언어모델의 파라미터를 고정하고 오디오 인코더의 파라미터만 업데이트하는 프로즌 (Frozen) 방법으로 학습한다. 학습을 위한 과제는 음성인식 (Automatic Speech Recognition)과 요약 (Abstractive Summarization) 이다. 학습을 마친 후 질의응답 (Question Answering) 작업으로 테스트를 진행했다. 그 결과, 정답 문장을 생성하기 위해서는 추가적인 학습이 필요한 것으로 보였으나, 음성인식으로 사전학습 한 모델의 경우 정답과 유사한 키워드를 사용하는 문법적으로 올바른 문장을 생성함을 확인했다.