• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.88.4-88
• /
• 2001

In this paper, we propose a solver for differential equations, using a multi-layer neural network. The multi-layer neural network is a transformer function originally where the function is differential and the explicit representation has been developed. The learning determines the response of neural networks; however, the response is not equal to the output values. The differential relations are also the response. The differential conditions can be also set as teaching data; therefore, there is a possibility to reach a new solver for the differential equations. Since it is unknown how to define the input data for the neural network solver during long terms, we could not derive the expressions. Recently, the analogue type neural network is known and it transforms any vector to another The "any" must be...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.43.3-43
• /
• 2001

In conventional RBF network, the activation functions of hidden layers generally are symmetric functions like gaussian function. This has been considered to be one of the limiting factors for the network to speed up learning of actuately describing a given function. To avoid this criticism, we propose a pseudo gaussian function (PGF) whose deviation is changed according to the direction of incoming pattern. This property helps to estimate the given function more effectively with a minimal number of centers because of its flexibility of functional representation. A level set method is used to describe the asymmetric shape of deviation of the pseudo gaussian function. To demonstrate the performance of the proposed network ...

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.8-13
• /
• 2019

Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.717-723
• /
• 2019

Smart systems and services aim to facilitate growing urban populations and their prospects of virtual-real social behaviors, gig economies, factory automation, knowledge-based workforce, integrated societies, modern living, among many more. To satisfy these objectives, smart systems and services must comprises of a complex set of features such as security, ease of use and user friendliness, manageability, scalability, adaptivity, intelligent behavior, and personalization. Recently, artificial intelligence (AI) is realized as a data-driven technology to provide an efficient knowledge representation, semantic modeling, and can support a cognitive behavior aspect of the system. In this paper, an integration of AI with the smart systems and services is presented to mitigate the existing challenges. Several novel researches work in terms of frameworks, architectures, paradigms, and algorithms are discussed to provide possible solutions against the existing challenges in the AI-based smart systems and services. Such novel research works involve efficient shape image retrieval, speech signal processing, dynamic thermal rating, advanced persistent threat tactics, user authentication, and so on.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.45-46
• /
• 2018

This paper focuses on human activities monitoring problem using onboard smartphone sensors as data generator. Monitoring such activities can be very important to detect anomalies and prevent disease from patients. Machine learning (ML) algorithms appear to be ideal approaches to use for processing data from smartphone to get sense of how to classify human activities. ML algorithms depend on quality, the quantity and even more important, the properties or features, that can be learnt from data. This paper proposes a mobile virtual reality visualization system that helps to view data representation in a very immersive way so that its quality and discriminative characteristics may be evaluated and improved. The proposed system comes as well with a handy data collecting application that can be accessed directly by the VR visualization part.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.33-39
• /
• 2019

In this paper, we propose deep convolutional neural network(CNN) with bottleneck structure which improves the performance of earthquake classification. In order to address all possible forms of earthquakes including micro-earthquakes and artificial-earthquakes as well as large earthquakes, we need a representation and classifier that can effectively discriminate seismic waveforms in adverse conditions. In particular, to robustly classify seismic waveforms even in low snr, a deep CNN with 1x1 convolution bottleneck structure is proposed in raw seismic waveforms. The representative experimental results show that the proposed method is effective for noisy seismic waveforms and outperforms the previous state-of-the art methods on domestic earthquake database.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.721-739
• /
• 2023

Rating prediction is an important issue in recommender systems, and its accuracy affects the experience of the user and the revenue of the company. Traditional recommender systems use Factorization Machinesfor rating predictions and each feature is selected with the same weight. Thus, there are problems with inaccurate ratings and limited data representation. This study proposes a deep recommendation model based on self-attention Factorization (SAFMR) to solve these problems. This model uses Convolutional Neural Networks to extract features from user and item reviews. The obtained features are fed into self-attention mechanism Factorization Machines, where the self-attention network automatically learns the dependencies of the features and distinguishes the weights of the different features, thereby reducing the prediction error. The model was experimentally evaluated using six classes of dataset. We compared MSE, NDCG and time for several real datasets. The experiment demonstrated that the SAFMR model achieved excellent rating prediction results and recommendation correlations, thereby verifying the effectiveness of the model.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.111-114
• /
• 2019

BERT는 자연어처리 여러 응용 분야(task)에서 우수한 성능을 보여줬으나, BERT 사전학습 모델을 학습하기 위해서는 많은 학습 시간과 학습 자원이 요구된다. 본 논문에서는 빠른 학습을 위한 한국어 BERT 학습 방법을 제안한다. 본 논문에서는 다음과 같은 세 가지 학습 방법을 적용했다. 교착어인 한국어 특성을 반영하기 위해 형태소 분석 기반의 사전을 사용하였으며, 단어 간 상대적 위치 표현을 추가하여, 상대적 위치 정보를 학습했다. 또한 BERT 베이스 모델의 12-레이어 중 3-레이어만을 사용하여, 모델을 경량화시켰다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.71-75
• /
• 2020

오픈북 질의응답 문제는 올바른 정답을 고르기 위해 사람들끼리 공유하고 있는 상식정보가 필요한 질의로 이루어져있다. 기계가 사람과 달리 상식 정보를 이용하여 결론을 도출하는 상식 추론을 하기 위해서는 적절한 상식 정보를 논리적으로 사용하여야 한다. 본 연구에서는 적절한 상식정보의 선택과 논리적 추론을 위하여, 질의에 대한 Abstract Meaning Representation (AMR) 그래프를 이용하여 적절한 상식 정보를 선택하고 그의 해석을 용이하게 만들었다. 본 연구에서 제안한 상식 그래프 경로 학습 모델은 오픈북 질의응답 문제에서 대표적 언어모델인 BERT의 성능보다 약 7%p 높은 55.02%의 정확도를 달성하였다.