• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.11
• /
• pp.130-137
• /
• 1992

This paper presents the word recognition method using a neural-fuzzy pattern matching, in order to make a proper speech pattern for a spectrum sequence and to improve a recognition rate. In this method, a frequency variation is reduced by generating binary spectrum patterns through associative memory using a neural network, and a time variation is decreased by measuring the simillarity using a fuzzy pattern matching. For this method using binary spectrum patterns and logic algebraic operations to measure the simillarity, memory capacity and computation requirements are far less than those of DTW using a conventional distortion measure. To show the validity of the recognition performance for this method, word recognition experiments are carried out using 28 DDD city names and compared with DTW and a fuzzy pattern matching. The results show that our presented method is more excellent in the recognition performance than the other methods.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.205-217
• /
• 2024

We propose a bandwidth prediction approach based on deep learning. The approach is intended to accurately predict the bandwidth of various types of mobile networks. We first use a machine learning technique, namely, the gradient boosting algorithm, to recognize the connected mobile network. Second, we apply a handover detection algorithm based on network recognition to account for vertical handover that causes the bandwidth variance. Third, as the communication performance offered by 3G, 4G, and 5G networks varies, we suggest a bidirectional long short-term memory model with time distribution for bandwidth prediction per network. To increase the prediction accuracy, pretraining and fine-tuning are applied for each type of network. We use a dataset collected at University College Cork for network recognition, handover detection, and bandwidth prediction. The performance evaluation indicates that the handover detection algorithm achieves 88.5% accuracy, and the bandwidth prediction model achieves a high accuracy, with a root-mean-square error of only 2.12%.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.6
• /
• pp.61-69
• /
• 1994

For distortion-invariant recognition of Korean characters, a holographic implementation of an optical associative memory system is proposed. The structure of the proposed system is a single-layer neural network employing interconneclion matrix, thresholding and feedback. To provide the interconnection matrix, we use two CGII's which are placed on intermcdiate plane of cascaded Vander Lugt corrclators to form an optical memory loop. The holographic correlator stores reference images in a hologram and retrives them in a coherently illuminated feedback loop. An input image which maybe noisy or incomplete, is applicd to the system and simultaneously correlated optically with all of the stord images. These correlations are throsholed and fed back to the input, where the strongest correlation reinforces the input image. The enhanced image passes arround the loop repeatedly, approaching the stored image more closely on each pass until the system stabilizes on the desired image. The computer simulation results show that the proposed Korean Character recognition algorithm has high discrimination capability and noise immunity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.438-449
• /
• 2022

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.11-18
• /
• 2023

Recently, in the field of Speech Emotion Recognition (SER), many studies have been conducted to improve accuracy using voice features and modeling. In addition to modeling studies to improve the accuracy of existing voice emotion recognition, various studies using voice features are being conducted. This paper, voice files are separated by time interval in a time series method, focusing on the fact that voice emotions are related to time flow. After voice file separation, we propose a model for classifying emotions of speech data by extracting speech features Mel, Chroma, zero-crossing rate (ZCR), root mean square (RMS), and mel-frequency cepstrum coefficients (MFCC) and applying them to a recurrent neural network model used for sequential data processing. As proposed method, voice features were extracted from all files using 'librosa' library and applied to neural network models. The experimental method compared and analyzed the performance of models of recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) using the Interactive emotional dyadic motion capture Interactive Emotional Dyadic Motion Capture (IEMOCAP) english dataset.

• 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.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.11
• /
• pp.63-75
• /
• 1998

Since many co-articulation problems are occurring in continuous spoken Korean language, several researches use words as a basic recognition unit. Though the word unit can solve this problem, it requires much memory and has difficulty fitting an input speech in a word list. In this paper, we propose an hidden Markov model(HMM) based recognition model that is an interconnection network of word HMMs for a syntax of sentences. To match suitably the input sentence into the continuous word list in the network, we use a level building search algorithm. This system represents the large sentence set with a relatively small memory and also has good extensibility. The experimental result of an airplane reservation system shows that it is proper method for a practical recognition system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4664-4681
• /
• 2020

Modulation recognition (MR) plays a key role in cognitive radar, cognitive radio, and some other civilian and military fields. While existing methods can identify the signal modulation type by extracting the signal characteristics, the quality of feature extraction has a serious impact on the recognition results. In this paper, an end-to-end MR method based on long short-term memory (LSTM) and the gated recurrent unit (GRU) is put forward, which can directly predict the modulation type from a sampled signal. Additionally, the sliding window method is applied to fast-changing mixed-modulation signals for which the signal modulation type changes over time. The recognition accuracy on training datasets in different SNR ranges and the proportion of each modulation method in misclassified samples are analyzed, and it is found to be reasonable to select the evenly-distributed and full range of SNR data as the training data. With the improvement of the SNR, the recognition accuracy increases rapidly. When the length of the training dataset increases, the neural network recognition effect is better. The loss function value of the neural network decreases with the increase of the training dataset length, and then tends to be stable. Moreover, when the fast-changing period is less than 20ms, the error rate is as high as 50%. As the fast-changing period is increased to 30ms, the error rates of the GRU and LSTM neural networks are less than 5%.

• Korean Journal of Optics and Photonics
• /
• v.3 no.3
• /
• pp.191-197
• /
• 1992

We have developed a new optical associative memory system hased on the symmetric three layered neural network model, uhing two holograms and a LCIV. In the experiment, four Korean alphabet letters (ㄹ, ㅅ, ㅇ, ㅈ) are used as memory patterns. The results are compared with those of the two layered network and the IIopfield models. The results show that more than 95% recognition ablity is obtained for thc input which has the error rate less than 12%.