• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.567-571
• /
• 2015

Transition-based dependency parsing requires much time and efforts to design and select features from a very large number of possible combinations. Recent studies have successfully applied Multi-Layer Perceptrons (MLP) to find solutions to this problem and to reduce the data sparseness. However, most of these methods have adopted greedy search and can only consider a limited amount of information from the context window. In this study, we use a Recurrent Neural Network to handle long dependencies between sub dependency trees of current state and current transition action. The results indicate that our method provided a higher accuracy (UAS) than an MLP based model.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2789-2791
• /
• 2001

데이터 마이닝을 통해 우리는 숨겨진 지식, 예상되지 않았던 경향 그리고 새로운 법칙들을 방대한 데이터에서 이끌어내고자 한다. 본 논문에서 우리는 사용자의 구매 패턴을 발견하여 사용자가 원하는 상품을 미리 예측하여 추천하는 알고리즘을 소개하고자 한다. 제안하고 있는 item dependency map은 구매된 상품간의 관계를 수식화 하여 행렬의 형태로 표현한 것이다. Item dependency map의 값은 사용자가 A라는 상품을 구매한 후 B상품을 살 확률이다. 이런 정보를 가지고 있는 item dependency map은 홉필드 네트윅(Hopfield network)에서 연상을 위한 패턴 값으로 적용된다. 홉필드 네트웍은 각 노드사이의 연결가중치에 기억하고자 하는 것들을 연상시킨 뒤 어떤 입력을 통해서 전체 네트워크가 어떤 평형상태에 도달하는 방식으로 작동되는 신경망 중의 하나이다. 홉필드 네트웍의 특징 중의 하나는 부분 정보로부터 전체 정보를 추출할 수 있는 것이다. 이러한 특징을 가지고 사용자들의 일반적인 구매패턴을 일부 정보만 가지고 예측할 수 있다. Item dependency map은 홉필드 네트윅에서 사용자들의 그룹별 패턴을 학습하는데 사용된다. 따라서 item dependency map이 얼마나 사용자 구매패턴에 대한 정보를 가지고 있는지에 따라 그 결과가 결정되는 것이다. 본 논문은 정확한 item dependency map을 계산해 내는 알고리즘을 주로 논의하겠다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3C
• /
• pp.115-125
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by insitu test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network (NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. It was already found that NN model can come over the site dependency and prediction accuracy is greatly improved when compared with present theoretical and empirical models. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network (CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. Prediction results of CNN model are compared with those of conventional empirical and theoretical models and multi-layered neural network model, which has the optimized structure. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.5
• /
• pp.343-356
• /
• 1991

An efficient real-time implementation of digital filtering algorithms using a multiprocessor system in a ring network is investigated. The development time and cost for implementing a high speed signal processing system can be considerably reduced because algorithm are implemented in software using commercially available digital signal processors. This method is based on a parallel block processing approach, where a continuously supplied input data is divided into blocks, and the blocks are processed concurrently by being assigned to each processor in the system. This approach not only requires a simple interconnection network but also reduces the number of communications among the processors very much. The data dependency of the blocks to be processed concurrently brings on dependency problems between the processors in the system. A systematic scheduling method has been developed by using a processors which can be used efficiently, the methods for solving dependency problems between the processors are investigated. Implementation procedures and results for FIR, recursive (IIR), and adaptive filtering algorithms are illustrated.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.533-536
• /
• 2019

의존 구문 분석은 문장 구성 성분 간의 의존 관계를 분석하는 태스크로, 자연어 이해의 대표적인 과제 중 하나이다. 본 논문에서는 한국어 의존 구문 분석의 성능 향상을 위해 Deep Bi-Affine Network와 Left to Right Dependency Parser를 적용하고, 새롭게 한국어의 언어적 특징을 반영한 Right to Left Dependency Parser 모델을 제안한다. 3개의 의존 구문 분석 모델에 단어 표현을 생성하는 방법으로 ELMo, BERT 임베딩 방법을 적용하고 여러 종류의 모델을 앙상블하여 세종 의존 구문 분석 데이터에 대해 UAS 94.50, LAS 92.46 성능을 얻을 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.5 no.3
• /
• pp.175-181
• /
• 2005

Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits at a wide range of scales-Self-similarity. Self-similarity is expressed by long term dependency, this is contradictory concept with Poisson model that have relativity short term dependency. Therefore, first of all for design and dimensioning of next generation communication network, traffic model that are reflected burstness and self-similarity is required. Here self-similarity can be characterized by Hurst parameter. In this paper, when different many data traffic being integrated under various environments is arrived to communication network, Hurst Parameter's change is analyzed and compared with simulation results.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.410-415
• /
• 2005

Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits at a wide range of scales - Self-similarity. Self-similarity is expressed by long term dependency, this is contradictory concept with Poisson model that have relativity short term dependency. Therefore, first of all for design and dimensioning of next generation communication network, traffic model that are reflected burstness and self-similarity is required. Here self-similarity can be characterized by Hurst parameter. In this paper, when different many data traffic being integrated under various environments is arrived to communication network, Hurst Parameter's change is analyzed and compared with simulation results.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.8
• /
• pp.367-375
• /
• 2001

In Underwater Flight Vehicle depth control system, the followings must be required. First, it needs robust performance which can get over modeling error, parameter variation and disturbance. Second, it needs accurate performance which have small overshoot phenomenon and steady state error to avoid colliding with ground surface or obstacles. Third, it needs continuous control input to reduce the acoustic noise and propulsion energy consumption. Finally, it needs interpolation method which can sole the speed dependency problem of controller parameters. To solve these problems, we propose a depth control method using Fuzzy Sliding Mode Controller with feedforward control-plane bias term and Neural Network Interpolator. Simulation results show the proposed method has robust and accurate control performance by the continuous control input and has no speed dependency problem.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.316-321
• /
• 2007

We propose a quatitative annotation method for edges in Bayesian networks using given sets of condition-specific data. Bayesian network model has been used widely in various fields to infer probabilistic dependency relationships between entities in target systems. Besides the need for identifying dependency relationships, the annotation of edges in Bayesian networks is required to analyze the meaning of learned Bayesian networks. We assume the training data is composed of several condition-specific data sets. The contribution of each condition-specific data set to each edge in the learned Bayesian network is measured using the ratio of likelihoods between network structures of including and missing the specific edge. The proposed method can be a good approach to make quantitative annotation for learned Bayesian network structures while previous annotation approaches only give qualitative one.