• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.703-709
• /
• 2019

This paper proposes speech recognition systems employing Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) structures combined with Hidden Markov Moldel (HMM) to effectively recognize the speech of VeloPharyngeal Insufficiency (VPI) patients, and compares the recognition performance of the systems to the Gaussian Mixture Model (GMM-HMM) and fully-connected Deep Neural Network (DNNHMM) based speech recognition systems. In this paper, the initial model is trained using normal speakers' speech and simulated VPI speech is used for generating a prior model for speaker adaptation. For VPI speaker adaptation, selected layers are trained in the CNN-HMM based model, and dropout regulatory technique is applied in the LSTM-HMM based model, showing 3.68 % improvement in recognition accuracy. The experimental results demonstrate that the proposed LSTM-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM and fully-connected DNN-HMM system.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.681-692
• /
• 2019

In this paper, a hybrid deep learning model, called 2D convolution with bidirectional long short-term memory (2DCBLSTM), is presented that can effectively combine both spatial and temporal features for crop classification. In the proposed model, 2D convolution operators are first applied to extract spatial features of crops and the extracted spatial features are then used as inputs for a bidirectional LSTM model that can effectively process temporal features. To evaluate the classification performance of the proposed model, a case study of crop classification was carried out using multi-temporal unmanned aerial vehicle images acquired in Anbandegi, Korea. For comparison purposes, we applied conventional deep learning models including two-dimensional convolutional neural network (CNN) using spatial features, LSTM using temporal features, and three-dimensional CNN using spatio-temporal features. Through the impact analysis of hyper-parameters on the classification performance, the use of both spatial and temporal features greatly reduced misclassification patterns of crops and the proposed hybrid model showed the best classification accuracy, compared to the conventional deep learning models that considered either spatial features or temporal features. Therefore, it is expected that the proposed model can be effectively applied to crop classification owing to its ability to consider spatio-temporal features of crops.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.148-158
• /
• 2024

We investigate Autism Spectrum Disorder (ASD), which is typified by deficits in social interaction, repetitive behaviors, limited vocabulary, and cognitive delays. Traditional diagnostic methodologies, reliant on expert evaluations, frequently result in deferred detection and intervention, particularly in South Korea, where there is a dearth of qualified professionals and limited public awareness. In this study, we employ advanced deep learning algorithms to enhance early ASD screening through automated video analysis. Utilizing architectures such as Convolutional Long Short-Term Memory (ConvLSTM), Long-term Recurrent Convolutional Network (LRCN), and Convolutional Neural Networks with Gated Recurrent Units (CNN+GRU), we analyze video data from platforms like YouTube and TikTok to identify stereotypic behaviors (arm flapping, head banging, spinning). Our results indicate that the LRCN model exhibited superior performance with 79.61% accuracy on the augmented platform video dataset and 79.37% on the original SSBD dataset. The ConvLSTM and CNN+GRU models also achieved higher accuracy than the original SSBD dataset. Through this research, we underscore AI's potential in early ASD detection by automating the identification of stereotypic behaviors, thereby enabling timely intervention. We also emphasize the significance of utilizing expanded datasets from social media platform videos in augmenting model accuracy and robustness, thus paving the way for more accessible diagnostic methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• Geomechanics and Engineering
• /
• v.37 no.4
• /
• pp.395-418
• /
• 2024

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (R_e), maximum fault distance (R_f), or maximum hypocentral distance (R_h), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (R_e, R_f, or R_h) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.411-412
• /
• 2023

Speech emotion recognition(SER) is one of the interesting topics in the machine learning field. By developing SER, we can get numerous benefits. By using a convolutional neural network and Long Short Term Memory (LSTM ) method as a part of Artificial intelligence, the SER system can be built.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.427-428
• /
• 2021

정보통신기술의 발달로 전자상거래의 증가와 소비자들의 제품에 대한 경험과 지식의 공유가 활발하게 진행됨에 따라 소비자는 제품을 구매하기 위한 자료수집, 활용을 진행하고 있다. 따라서 기업은 다양한 기능들을 반영한 제품이 치열하게 경쟁하고 있는 현 시장에서 우위를 점하고자 소비자 리뷰를 분석하여 소비자의 정확한 소비자의 요구사항을 분석하여 제품기획 프로세스에 반영하고자 텍스트마이닝(Text Mining) 기술과 딥러닝(Deep Learning) 기술을 통한 연구가 이루어지고 있다. 본 논문의 기초자료가 되는 데이터셋은 포털사이트의 구매사이트와 오픈마켓 사이트의 소비자 리뷰를 웹크롤링하고 자연어처리하여 진행한다. 감성분석은 딥러닝기술 중 CNN(Convolutional Neural Network), LSTM(Long Short Term Memory) 조합의 모델을 구현한다. 이는 딥러닝을 이용한 제품기획 프로세스로 소비자 요구사항 반영, 경제적인 측면, 제품기획 시간단축 등 긍정적인 영향을 미칠 것으로 기대한다.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.