• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.1
• /
• pp.39-49
• /
• 2013

This paper presents a method of improving the performance of a day-ahead 24-h load curve and peak load forecasting. The next-day load curve is forecasted using radial basis function (RBF) neural network models built using the best design parameters. To improve the forecasting accuracy, the load curve forecasted using the RBF network models is corrected by the weighted sum of both the error of the current prediction and the change in the errors between the current and the previous prediction. The optimal weights (called "gains" in the error correction) are identified by differential evolution. The peak load forecasted by the RBF network models is also corrected by combining the load curve outputs of the RBF models by linear addition with 24 coefficients. The optimal coefficients for reducing both the forecasting mean absolute percent error (MAPE) and the sum of errors are also identified using differential evolution. The proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange. Simulation results reveal satisfactory forecasts: 1.230% MAPE for daily peak load and 1.128% MAPE for daily load curve.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.688-701
• /
• 2023

The conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.540-543
• /
• 2021

In this paper, we present an experimental comparative study of recurrent neural network based techniques for trajectory prediction of flight vehicles. We defined and investigated various relationships between input and output under the same experimental setup. In particular, we proposed a relationship based on the relative positions of flight vehicles. Furthermore, we conducted an ablation study on the network architectures and hyperparameters. We believe that this comprehensive comparative study serves as a reference point and guide for developers in choosing an appropriate recurrent neural network based techniques for building (flight) vehicle trajectory prediction systems.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.5
• /
• pp.780-790
• /
• 2022

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.

• Journal of Korean Society of Transportation
• /
• v.21 no.1
• /
• pp.91-102
• /
• 2003

There are two goals in this paper. The one is development of existing CA(Cellular Automata) model to explain more realistic deceleration process to stop. The other is the application of the updated CA model to forecasting simulation to predict short term link travel time that takes a key rule in finding the shortest path of route guidance system of ITS. Car following theory of CA models don't makes not response to leading vehicle's velocity but gap or distance between leading vehicles and following vehicles. So a following vehicle running at free flow speed must meet steeply sudden deceleration to avoid back collision within unrealistic braking distance. To tackle above unrealistic deceleration rule, “Slow-to-stop” rule is integrated into NaSch model. For application to interrupted traffic flow, this paper applies “Slow-to-stop” rule to both normal traffic light and random traffic light. And vehicle packet method is used to simulate a large-scale network on the desktop. Generally, time series data analysis methods such as neural network, ARIMA, and Kalman filtering are used for short term link travel time prediction that is crucial to find an optimal dynamic shortest path. But those methods have time-lag problems and are hard to capture traffic flow mechanism such as spill over and spill back etc. To address above problems. the CA model built in this study is used for forecasting simulation to predict short term link travel time in Kangnam district network And it's turned out that short term prediction simulation method generates novel results, taking a crack of time lag problems and considering interrupted traffic flow mechanism.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.57-64
• /
• 2019

In this paper, we construct a Korean text-to-speech system using the Merlin toolkit which is an open source system for speech synthesis. In the text-to-speech system, the HMM-based statistical parametric speech synthesis method is widely used, but it is known that the quality of synthesized speech is degraded due to limitations of the acoustic modeling scheme that includes context factors. In this paper, we propose an acoustic modeling architecture that uses deep neural network technique, which shows excellent performance in various fields. Fully connected deep feedforward neural network (DNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional LSTM (BLSTM) are included in the architecture. Experimental results have shown that the performance is improved by including sequence modeling in the architecture, and the architecture with LSTM or BLSTM shows the best performance. It has been also found that inclusion of delta and delta-delta components in the acoustic feature parameters is advantageous for performance improvement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1275-1281
• /
• 2019

The automatic modulation recognition of a radio signal is a major task of an intelligent receiver, with various civilian and military applications. In this paper, we propose a method to recognize the modulation of radio signals in wireless communication based on the deep neural network. We classify the modulation pattern of radio signal by using the LSTM model, which can catch the long-term pattern for the sequential data as the input data of the deep neural network. The amplitude and phase of the modulated signal, the in-phase carrier, and the quadrature-phase carrier are used as input data in the LSTM model. In order to verify the performance of the proposed learning method, we use a large dataset for training and test, including the ten types of modulation signal under various signal-to-noise ratios.

• ETRI Journal
• /
• v.41 no.3
• /
• pp.371-382
• /
• 2019

Machine reading comprehension is the task of understanding a given context and finding the correct response in that context. A simple recurrent unit (SRU) is a model that solves the vanishing gradient problem in a recurrent neural network (RNN) using a neural gate, such as a gated recurrent unit (GRU) and long short-term memory (LSTM); moreover, it removes the previous hidden state from the input gate to improve the speed compared to GRU and LSTM. A self-matching network, used in R-Net, can have a similar effect to coreference resolution because the self-matching network can obtain context information of a similar meaning by calculating the attention weight for its own RNN sequence. In this paper, we construct a dataset for Korean machine reading comprehension and propose an $S^2-Net$ model that adds a self-matching layer to an encoder RNN using multilayer SRU. The experimental results show that the proposed $S^2-Net$ model has performance of single 68.82% EM and 81.25% F1, and ensemble 70.81% EM, 82.48% F1 in the Korean machine reading comprehension test dataset, and has single 71.30% EM and 80.37% F1 and ensemble 73.29% EM and 81.54% F1 performance in the SQuAD dev dataset.