• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• KIISE Transactions on Computing Practices
• /
• v.22 no.7
• /
• pp.315-319
• /
• 2016

Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.238-246
• /
• 2021

The rapid rise of the Internet and social media has resulted in a large number of text-based reviews being placed on sites such as social media. In the age of social media, utilizing machine learning technologies to analyze the emotional context of comments aids in the understanding of QoS for any product or service. The classification and analysis of user reviews aids in the improvement of QoS. (Quality of Services). Machine Learning algorithms have evolved into a powerful tool for analyzing user sentiment. Unlike traditional categorization models, which are based on a set of rules. In sentiment categorization, Bidirectional Long Short-Term Memory (BiLSTM) has shown significant results, and Convolution Neural Network (CNN) has shown promising results. Using convolutions and pooling layers, CNN can successfully extract local information. BiLSTM uses dual LSTM orientations to increase the amount of background knowledge available to deep learning models. The suggested hybrid model combines the benefits of these two deep learning-based algorithms. The data source for analysis and classification was user reviews of Indian Railway Services on Twitter. The suggested hybrid model uses the Keras Embedding technique as an input source. The suggested model takes in data and generates lower-dimensional characteristics that result in a categorization result. The suggested hybrid model's performance was compared using Keras and Word2Vec, and the proposed model showed a significant improvement in response with an accuracy of 95.19 percent.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.4
• /
• pp.621-625
• /
• 2018

This paper proposes a method for bridge damage factor recognition from inspection reports using deep learning. Bridge inspection reports contains inspection results including identified damages and causal analysis results. However, collecting such information from inspection reports manually is limited due to their considerable amount. Therefore, this paper proposes a model for recognizing bridge damage factor from inspection reports applying Named Entity Recognition (NER) using deep learning. Named Entity Recognition, Word Embedding, Recurrent Neural Network, one of deep learning methods, were applied to construct the proposed model. Experimental results showed that the proposed model has abilities to 1) recognize damage and damage factor included in a training data, 2) distinguish a specific word as a damage or a damage factor, depending on its context, and 3) recognize new damage words not included in a training data.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.217-223
• /
• 2023

In this paper, we propose a new model for the conditional generation of music, considering key and rhythm, fundamental elements of music. MIDI sheet music is converted into a WAV format, which is then transformed into a Mel Spectrogram using the Short-Time Fourier Transform (STFT). Using this information, key and rhythm details are classified by passing through two Convolutional Neural Networks (CNNs), and this information is again fed into the Music Transformer. The key and rhythm details are combined by differentially multiplying the weights and the embedding vectors of the MIDI events. Several experiments are conducted, including a process for determining the optimal weights. This research represents a new effort to integrate essential elements into music generation and explains the detailed structure and operating principles of the model, verifying its effects and potentials through experiments. In this study, the accuracy for rhythm classification reached 94.7%, the accuracy for key classification reached 92.1%, and the Negative Likelihood based on the weights of the embedding vector resulted in 3.01.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1419-1425
• /
• 2017

The ultimate goal of legal knowledge search is to obtain optimal legal information based on laws and precedent. Text mining research is actively being undertaken to meet the needs of efficient retrieval from large scale data. A typical method is to use a word embedding algorithm based on Neural Net. This paper demonstrates how to search relevant information, applying Korean law information to word embedding. First, we extracts reference laws from precedents in order and takes reference laws as input of Law2Vec. The model learns a law by predicting its surrounding context law. The algorithm then moves over each law in the corpus and repeats the training step. After the training finished, we could infer the relationship between the laws via the embedding method. The search performance was evaluated based on precision and the recall rate which are computed from how closely the results are associated to the search terms. The test result proved that what this paper proposes is much more useful compared to existing systems utilizing only keyword search when it comes to extracting related laws.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.1144-1148
• /
• 1997

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.578-580
• /
• 1995

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time, For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor font mentioned above. The one day ahead forecast errors are about 1.4% of absolute percentage average error.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.835-837
• /
• 1996

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network(Back-propagation) is proposed. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.

• Journal of Advanced Navigation Technology
• /
• v.24 no.5
• /
• pp.430-437
• /
• 2020

The proposed model implements a model that improves the face prediction rate and recognition rate through learning with an artificial neural network using face detection, landmark and face recognition algorithms. After landmarking in the face images of a specific person, the proposed model use the previously learned Caffe model to extract face detection and embedding vector 128D. The learning is learned by building machine learning algorithms such as support vector machine (SVM) and deep neural network (DNN). Face recognition is tested with a face image different from the learned figure using the learned model. As a result of the experiment, the result of learning with DNN rather than SVM showed better prediction rate and recognition rate. However, when the hidden layer of DNN is increased, the prediction rate increases but the recognition rate decreases. This is judged as overfitting caused by a small number of objects to be recognized. As a result of learning by adding a clear face image to the proposed model, it is confirmed that the result of high prediction rate and recognition rate can be obtained. This research will be able to obtain better recognition and prediction rates through effective deep learning establishment by utilizing more face image data.