Digital Library[ Search Result ]
A Method for Cancer Prognosis Prediction Using Gene Embedding
http://doi.org/10.5626/JOK.2021.48.7.842
Identifying prognostic genes and using them to predict the prognosis of cancer patients can help provide them with more effective treatments. Many methods have been proposed to identify prognostic genes and predict cancer prognosis, and recent studies have focused on machine learning methods including deep learning. However, applying gene expression data to machine learning methods has the limitations of a small number of samples and a large number of genes. In this study, we additionally use a gene network to generate many random gene paths, which we used for training the model, thereby compensating for the small sample problem. We identified the prognostic genes and predicted the prognosis of patients using the gene expression data and gene networks for five cancer types and confirmed that the proposed method showed better predictive accuracy compared to other existing methods, and good performance on small sample data.
Topic Centric Korean Text Summarization using Attribute Model
Su-Hwan Yoon, A-Yeong Kim, Seong-Bae Park
http://doi.org/10.5626/JOK.2021.48.6.688
Abstractive summarization takes original text as an input and generates a summary containing the core-information about the original text. The abstractive summarization model is mainly designed by the Sequence-to-Sequence model. To improve quality as well as coherence of summary, the topic-centric methods which contain the core information of the original text are recently proposed. However, the previous methods perform additional training steps which make it difficult to take advantage of the pre-trained language model. This paper proposes a topic-centric summarizer that can reflect topic words to a summary as well as retain the characteristics of language model by using PPLM. The proposed method does not require any additional training. To prove the effectiveness of the proposed summarizer, this paper performed summarization experiments with Korean newspaper data.
CRF based Named Entity Recognition Using a Korean Lexical Semantic Network
http://doi.org/10.5626/JOK.2021.48.5.556
Named Entity Recognition(NER) is the process of classifying words with unique meanings that often appear as OOV within sentence into categories of predefined entities. Recently, many researches have been conducted using deep learning to synthesize the words’ embedding via Convolution Neural Network(CNN), Long Short-Term Memory(LSTM) networks or training language models. However, models using these deep learning network or language model require high performance computing power and have low practicality due to slow speed. For practicality, this paper proposes Conditional Random Field(CRF) based NER model using Korean lexical network(UWordMap). By using hypernym, dependence and case particle information as training feature, our model showed 90.54% point of accuracy, 1,461 sentences/sec processing speed.
Improvement in Network Intrusion Detection based on LSTM and Feature Embedding
Hyeokmin Gwon, Chungjun Lee, Rakun Keum, Heeyoul Choi
http://doi.org/10.5626/JOK.2021.48.4.418
Network Intrusion Detection System (NIDS) is an essential tool for network perimeter security. NIDS inspects network traffic packets to detect network intrusions. Most of the existing works have used machine learning techniques for building the system. While the reported works demonstrated the effectiveness of various artificial intelligence algorithms, only a few of them have utilized the time-series information of network traffic data. Also, categorical information of network traffic data has not been included in neural network-based approaches. In this paper, we propose network intrusion detection models based on sequential information using the long short-term memory (LSTM) network and categorical information using the embedding technique. We have conducted experiments using models with UNSW-NB15, which is a comprehensive network traffic dataset. The experiment results confirm that the proposed method improves the performance, with a binary classification accuracy rate of 99.72%.
Conditional Knowledge Distillation for Model Specialization
http://doi.org/10.5626/JOK.2021.48.4.369
Many recent works on model compression in neural networks are based on knowledge distillation (KD). However, since the basic goal of KD is to transfer the entire knowledge set of a teacher model to a student model, the standard KD may not represent the best use of the model’s capacity when a user wishes to classify only a small subset of classes. Also, it is necessary to possess the original teacher model dataset for KD, but for various practical reasons, such as privacy issues, the entire dataset may not be available. Thus, this paper proposes conditional knowledge distillation (CKD), which only distills specialized knowledge corresponding to a given subset of classes, as well as data-free CKD (DF-CKD), which does not require the original data. As a major extension, we devise Joint-CKD, which jointly performs DF-CKD and CKD with only a small additional dataset collected by a client. Our experimental results show that the CKD and DF-CKD methods are superior to standard KD, and also confirm that joint use of CKD and DF-CKD is effective at further improving the overall accuracy of a specialized model.
Evaluating of Korean Machine Reading Comprehension Generalization Performance via Cross-, Blind and Open-Domain QA Dataset Assessment
http://doi.org/10.5626/JOK.2021.48.3.275
Machine reading comprehension (MRC) entails identification of the correct answer in a paragraph when a natural language question and paragraph are provided. Recently, fine-tuning based on a pre-trained language model yields the best performance. In this study, we evaluated the ability of machine-reading comprehension method to generalize question and paragraph pairs, rather than similar training sets. Towards this end, the cross-evaluation between datasets and blind evaluation was performed. The results showed a correlation between generalization performance and datasets such as answer length and overlap ratio between question and paragraph. As a result of blind evaluation, the evaluation dataset with the long answer and low lexical overlap between the questions and paragraphs resulted in less than 80% performance. Finally, the generalized performance of the MRC model under the open domain QA environment was evaluated, and the performance of the MRC using the searched paragraph was found to be degraded. According to the MRC task characteristics, the difficulty and differences in generalization performance depend on the relationship between the question and the answer, suggesting the need for analysis of different evaluation sets.
Predicting Chemical Structure of Drugs Using Deep Learning
Soohyun Ko, Chihyun Park, Jaegyoon Ahn
http://doi.org/10.5626/JOK.2021.48.2.234
Numerous computer-based methods have been investigated in attempts to reduce the time and cost of drug development. In particular, with the recent development of deep learning techniques, various generation models for generating the chemical formulas of candidate compounds and reinforcement learning models to generate chemical formulas that satisfy specific conditions have been presented. In this paper, we propose a reinforcement learning model that exploits predicted binding affinity information between specific proteins and generated compounds. More specifically, the generative model used in this paper is Stack-RNN, and reinforcement learning is implemented by using Stack-RNN as a policy to ensure that the generated formula has specific chemical properties and high binding affinity with specific proteins. The proposed model generates paper, we generated the chemical formulas of compounds that are similar to three anti-cancer drugs (Sorafenib, Sunitinib, and Dasatinib) by using the target protein information of these three anti-cancer drugs.
Autoencoder-based Learning Contribution Measurement Method for Training Data Selection
Yuna Jeong, Myunggwon Hwang, Wonkyung Sung
http://doi.org/10.5626/JOK.2021.48.2.195
Despite recent significant performance improvements, the iterative process of machine-learning algorithms makes development and utilization difficult and time-consuming. In this paper, we present a data-selection method that reduces the time required by providing an approximate solution . First, data are mapped to a feature vector in latent space based on an Autoencoder, with high weight given to data with high learning contribution that are relatively difficult to learn. Finally, data are ranked and selected based on weight and used for training. Experimental results showed that the proposed method selected data that achieve higher performance than random sampling.
A Method for Training Data Selection based on LSTRf
Myunggwon Hwang, Yuna Jeong, Wonkyung Sung
http://doi.org/10.5626/JOK.2020.47.12.1192
This paper presents a data selection method that has a positive effect on learning for an efficient human-in-the-loop (HITL) process required for automated and intelligent artificial intelligence (AI) development. Our method first maps the training data onto a 2D distribution based on similarity, and then grids are laid out with a fixed ratio. By applying Least Slack Time Rate first (LSTRf) techniques, the data are selected based on the distribution consistency of the same class data within each grid. The finally selected data are used as convolutional neural network (CNN)-based classifiers to evaluate the performance. We carried out experiments on the CIFAR-10 dataset, and evaluated the effect of grid size and the number of data selected in one operation. The selected training data were compared to randomly selected data of the same size. The results verified that the smaller the grid size (0.008 and 0.005) and the greater the number selected in the single operation, the better the learning performance.
Korean Semantic Role Labeling with BERT
Jangseong Bae, Changki Lee, Soojong Lim, Hyunki Kim
http://doi.org/10.5626/JOK.2020.47.11.1021
Semantic role labeling is an application of natural language processing to identify relationships such as "who, what, how and why" with in a sentence. The semantic role labeling study mainly uses machine learning algorithms and the end-to-end method that excludes feature information. Recently, a language model called BERT (Bidirectional Encoder Representations from Transformers) has emerged in the natural language processing field, performing better than the state-of- the-art models in the natural language processing field. The performance of the semantic role labeling study using the end-to-end method is mainly influenced by the structure of the machine learning model or the pre-trained language model. Thus, in this paper, we apply BERT to the Korean semantic role labeling to improve the Korean semantic role labeling performance. As a result, the performance of the Korean semantic role labeling model using BERT is 85.77%, which is better than the existing Korean semantic role labeling model.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr