• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.203-212
• /
• 2021

To eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.633-636
• /
• 2022

The reduction of energy consumption at the base station (BS) has become more important recently. In this paper, we consider the adaptive muting of the antennas based on the predicted future traffic load to reduce the energy consumption where the number of active antennas is adaptively adjusted according to the predicted future traffic load. Given that traffic load is sequential data, three different RNN structures, namely long-short term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (Bi-LSTM) are considered for the future traffic load prediction. Through the performance evaluation based on the actual traffic load collected from the Afghanistan telecom company, we confirm that the traffic load can be estimated accurately and the overall power consumption can also be reduced significantly using the antenna musing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.613-616
• /
• 2018

Sequence tagging is an important task in Natural Language Processing (NLP), in which the Named Entity Recognition (NER) is the key issue. So far the most widely adopted model for NER in NLP is that of combining the neural network of bidirectional long short-term memory (BiLSTM) and the statistical sequence prediction method of Conditional Random Field (CRF). In this work, we improve the prediction accuracy of the BiLSTM by supporting an aligned word representation mechanism. We have performed experiments on multilingual (English, Spanish and Dutch) datasets and confirmed that our proposed model outperformed the existing state-of-the-art models.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.870-878
• /
• 2019

In this paper, we propose an Attention-based BLSTM for predicting the video compression standard of a video. Recently, in NLP, many researches have been studied to predict the next word of sentences, classify and translate sentences by their semantics using the structure of RNN, and they were commercialized as chatbots, AI speakers and translator applications, etc. LSTM is designed to solve the gradient vanishing problem in RNN, and is used in NLP. The proposed algorithm makes video compression standard prediction possible by applying BLSTM and Attention algorithm which focuses on the most important word in a sentence to a bitstream of a video, not an sentence of a natural language.

• Structural Engineering and Mechanics
• /
• v.85 no.4
• /
• pp.469-484
• /
• 2023

A deep recursive bidirectional Cuda Deep Neural Network Long Short Term Memory (Bi-CuDNNLSTM) layer is recruited in this paper to predict the entire force time histories, and the corresponding hysteresis and backbone curves of reinforced concrete (RC) bridge piers using experimental fast and slow cyclic tests. The proposed stacked Bi-CuDNNLSTM layers involve multiple uncertain input variables, including horizontal actuator displacements, vertical actuators axial loads, the effective height of the bridge pier, the moment of inertia, and mass. The functional application programming interface in the Keras Python library is utilized to develop a deep learning model considering all the above various input attributes. To have a robust and reliable prediction, the dataset for both the fast and slow cyclic tests is split into three mutually exclusive subsets of training, validation, and testing (unseen). The whole datasets include 17 RC bridge piers tested experimentally ten for fast and seven for slow cyclic tests. The results bring to light that the mean absolute error, as a loss function, is monotonically decreased to zero for both the training and validation datasets after 5000 epochs, and a high level of correlation is observed between the predicted and the experimentally measured values of the force time histories for all the datasets, more than 90%. It can be concluded that the maximum mean of the normalized error, obtained through Box-Whisker plot and Gaussian distribution of normalized error, associated with unseen data is about 10% and 3% for the fast and slow cyclic tests, respectively. In recapitulation, it brings to an end that the stacked Bi-CuDNNLSTM layer implemented in this study has a myriad of benefits in reducing the time and experimental costs for conducting new fast and slow cyclic tests in the future and results in a fast and accurate insight into hysteretic behavior of bridge piers.

• Earthquakes and Structures
• /
• v.9 no.5
• /
• pp.1091-1114
• /
• 2015

The adequacy of a number of advanced earthquake Intensity Measures (IMs) to predict the structural damage of earthquake resistant 3D R/C buildings is investigated in the present paper. To achieve this purpose three symmetric in plan and three asymmetric 5-storey R/C buildings are analyzed by nonlinear time history analysis using 74 bidirectional earthquake records. The two horizontal accelerograms of each ground motion are applied along the structural axes of the buildings and the structural damage is expressed in terms of the maximum and average interstorey drift as well as the overall structural damage index. For each individual pair of accelerograms the values of the aforementioned seismic damage measures are determined. Then, they are correlated with several strong motion scalar IMs that take into account both earthquake and structural characteristics. The research identified certain IMs which exhibit strong correlation with the seismic damage measures of the studied buildings. However, the degree of correlation between IMs and the seismic damage depends on the damage measure adopted. Furthermore, it is confirmed that the widely used spectral acceleration at the fundamental period of the structure is a relatively good IM for medium rise R/C buildings that possess small structural eccentricity.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.6
• /
• pp.619-630
• /
• 2022

The concrete mix design and compressive strength evaluation are used as basic data for the durability of sustainable structures. However, the recent diversification of mixing factors has created difficulties in calculating the correct mixing factor or setting the reference value concrete mixing design. The purpose of this study is to design a predictive model of bidirectional analysis that calculates the mixing elements of ternary concrete using deep learning, one of the artificial intelligence techniques. For the DNN-based predictive model for calculating the concrete mixing factor, performance evaluation and comparison were performed using a total of 8 models with the number of layers and the number of hidden neurons as variables. The combination calculation result was output. As a result of the model's performance evaluation, an average error rate of about 1.423% for the concrete compressive strength factor was achieved. and an average MAPE error of 8.22% for the prediction of the ternary concrete mixing factor was satisfied. Through comparing the performance evaluation for each structure of the DNN model, the DNN5L-2048 model showed the highest performance for all compounding factors. Using the learned DNN model, the prediction of the ternary concrete formulation table with the required compressive strength of 30 and 50 MPa was carried out. The verification process through the expansion of the data set for learning and a comparison between the actual concrete mix table and the DNN model output concrete mix table is necessary.

• Earthquakes and Structures
• /
• v.22 no.4
• /
• pp.355-372
• /
• 2022

The study is part of an experimental program on full-scale Un-Reinforced Masonry (URM) wall panels strengthened with Textile reinforced mortars (TRM). Eight brick walls (two with and five without central opening), were tested under the diagonal tension (shear) test method in order to investigate the strengthening system effectiveness on the in-plane behaviour of the walls. All the URM panels consist of the innovative components, named "Orthoblock K300 bricks" with vertical holes and a thin layer mortar. Both of them have great capacity and easy application and can be constructed much more rapidly than the traditional bricks and mortars, increasing productivity, as well as the compressive strength of the masonry walls. Several parameters pertaining to the in-plane shear behaviour of the retrofitted panels were investigated, including shear capacity, failure modes, the number of layers of the external TRM jacket, and the existence of the central opening of the wall. For both the control and retrofitted panels, the experimental shear capacity and failure mode were compared with the predictions of existing prediction models (ACI 2013, TA 2000, Triantafillou 1998, Triantafillou 2016, CNR 2018, CNR 2013, Eurocode 6, Eurocode 8, Thomoglou et al. 2020). The experimental work allowed an evaluation of the shear performance in the case of the bidirectional textile (TRM) system applied on the URM walls. The results have shown that some analytical models present a better accuracy in predicting the shear resistance of all the strengthened masonry walls with TRM systems which can be used in design guidelines for reliable predictions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.710-712
• /
• 2022

Agricultural products take a large part of the wholesale and retail market as a necessity for daily consumption, and the consumption and price of agricultural products affect the supply and demand of agricultural products, consumer spending, and agricultural household income. Therefore, in this study, It was conducted on unit price prediction using LSTM to trade agricultural products, weather observation, import and export performance and fresh food index data. In order to study the supply and demand management of agricultural products and appropriate prices in the wholesale and retail market, unit prices are predicted for garlic, cabbage, and onions with high consumer price index weights among items subject to vegetable price stabilizers.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.292-294
• /
• 2007

Recently, for satisfying many application demands such as coding delay, computing power, transporting channel characteristic, etc, many profiles are supported in video coding standards. Therefore, in transcoding between same standards or between other standards, the functional difference of profiles supported by application occur many problems. In this paper, transcoding MPEG-2 main profile to H.264/AVC baseline profile which has restriction in the number of reference frame is focused. In this case, the bidirectional prediction supported in MPEG-2 main profile is not supported in H.264/AVC baseline profile. Also, in the restriction of reference frame, motion vectors in the MPEG-2 decoder as predictor should be adjusted. In this paper, the proposed algorithm is based on the characteristic of which motion. vector is uniform according to the distance from reference frame. The adaptive search techniques through the determination of the uniformity extremely reduce the computational complexity.