• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• Journal of the Korean Regional Science Association
• /
• v.39 no.2
• /
• pp.47-61
• /
• 2023

Satisfaction on the residential environment is a major factor influencing the choice of residence and migration, and is directly related to the quality of life in the city. As online services of real estate increases, people's evaluation on the residential environment can be easily checked and it is possible to analyze their satisfaction and its determining factors based on their evaluation. This means that a larger amount of evaluation can be used more efficiently than previously used methods such as surveys. This study analyzed the residential environment reviews of about 30,000 apartment residents collected from 'Zigbang', an online real estate service in Seoul. The apartment review of Zigbang consists of an evaluation grade on a 5-point scale and the evaluation content directly described by the dweller. At first, this study labeled apartment reviews as positive and negative based on the scores of recommended reviews that include comprehensive evaluation about apartment. Next, to classify them automatically, developed a model by using Bidirectional Encoder Representations from Transformers(BERT), a deep learning-based natural language processing model. After that, by using SHapley Additive exPlanation(SHAP), extract word tokens that play an important role in the classification of reviews, to derive determining factors of the evaluation of the residential environment. Furthermore, by analyzing related keywords using Word2Vec, priority considerations for improving satisfaction on the residential environment were suggested. This study is meaningful that suggested a model that automatically classifies satisfaction on the residential environment into positive and negative by using apartment review big data and deep learning, which are qualitative evaluation data of residents, so that it's determining factors were derived. The result of analysis can be used as elementary data for improving the satisfaction on the residential environment, and can be used in the future evaluation of the residential environment near the apartment complex, and the design and evaluation of new complexes and infrastructure.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.542-549
• /
• 2017

Sequence-to-sequence models and similar pointer networks suffer from performance degradation when an input is composed of multiple sentences or when the length of the input sentence is long. To solve this problem, this paper proposes a hierarchical pointer network model that uses both the word level and sentence level information to encode input sequences composed of several sentences at the word level and sentence level. We propose a hierarchical pointer network based coreference resolution that performs a coreference resolution for all mentions. The experimental results show that the proposed model has a precision of 87.07%, recall of 65.39% and CoNLL F1 74.61%, which is an improvement of 21.83% compared to an existing rule-based model.

• ETRI Journal
• /
• v.34 no.2
• /
• pp.190-198
• /
• 2012

An adaptive correlation noise model (CNM) construction algorithm is proposed in this paper to increase the efficiency of parity bits for correcting errors of the side information in transform domain Wyner-Ziv (WZ) video coding. The proposed algorithm introduces two techniques to improve the accuracy of the CNM. First, it calculates the mean of direct current (DC) coefficients of the original WZ frame at the encoder and uses it to assist the decoder to calculate the CNM parameters. Second, by considering the statistical property of the transform domain correlation noise and the motion characteristic of the frame, the algorithm adaptively models the DC coefficients of the correlation noise with the Gaussian distribution for the low motion frames and the Laplacian distribution for the high motion frames, respectively. With these techniques, the proposed algorithm is able to make a more accurate approximation to the real distribution of the correlation noise at the expense of a very slight increment to the coding complexity. The simulation results show that the proposed algorithm can improve the average peak signal-to-noise ratio of the decoded WZ frames by 0.5 dB to 1.5 dB.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.433-436
• /
• 2003

The estimation of the position and the orientation for the mobile robot constitutes an important problem in mobile robot navigation. Although the odometry can be used to describe the motions of the mobile robots, there inherently exist the gaps between the real robots and the mathematical model, which may be caused by a number of error sources contaminating the encoder outputs. Hence, applying the standard extended Kalman filter for the nominal model is not supposed to give the satisfactory performance. As a solution to this problem, a new robust extended Kalman filter is proposed based on the Krein space approach. We consider the uncertain discrete time nonlinear model of the mobile robot that contains the uncertainties represented as sum quadratic constraints. The proposed robust filter has the merit of being constructed by the same recursive structure as the standard extended Kalman filter and can, therefore, be easily designed to effectively account for the uncertainties. The simulations will be given to verify the robustness against the parameter variation as veil as the reliable performance of the proposed robust filter.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.