http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Dependency Graph-Based Keyphrase Extraction Method Using Anti-patterns
( Khuyagbaatar Batsuren ),( Erdenebileg Batbaatar ),( Tsendsuren Munkhdalai ),( Meijing Li ),( Oyun-erdene Namsrai ),( Keun Ho Ryu ) 한국정보처리학회 2018 Journal of information processing systems Vol.14 No.5
Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many textmining applications such as document summarization and clustering. In this paper, we propose to use two novel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patterns that aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature set to identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases share very few similar patterns and stylistic features while non-keyphrase candidates often share many similar patterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrence graph that could not connect two words that are syntactically related and placed far from each other in a sentence while the dependency graph can do so. In experiments, we have compared the performances with different settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform the state-of-the-art performances.
A Dependency Graph-Based Keyphrase Extraction Method Using Anti-patterns
Batsuren, Khuyagbaatar,Batbaatar, Erdenebileg,Munkhdalai, Tsendsuren,Li, Meijing,Namsrai, Oyun-Erdene,Ryu, Keun Ho Korea Information Processing Society 2018 Journal of information processing systems Vol.14 No.5
Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many text-mining applications such as document summarization and clustering. In this paper, we propose to use two novel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patterns that aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature set to identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases share very few similar patterns and stylistic features while non-keyphrase candidates often share many similar patterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrence graph that could not connect two words that are syntactically related and placed far from each other in a sentence while the dependency graph can do so. In experiments, we have compared the performances with different settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform the state-of-the-art performances.
Deep Generative Convolutional Variational Autoencoder for Identification of Wafer Map
Ho Sun Shon(손호선),Erdenebileg Batbaatar,Kyung Hee Lee(이경희),Wan-Sup Cho(조완섭),Seong Gon Choi(최성곤) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
In this paper, we develop a novel Variational Autoencoder (VAE) to identify wafer map defect patterns. The Deep Generative Convolutional Network (DGCN) is used as an encoder to approximate distribution for the latent features linked to generative models. And the Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the wafer map defect patterns. Firstly, we pre-trained unsupervised VAE which consists of DGCN and DGDN. Secondly, we fine-tuned DGCN with neural network classification as a predictor. In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features. We present experimental results to show that the VAE trained with our new method outperforms the state-of-the-art in identifying wafer map defect patterns. We also show that our method can learn powerful embeddings of input wafer map images, which can be used to achieve defect pattern manipulation.
최성곤,김경아,손호선,Erdenebileg Batbaatar,차은종,강태건 대한전기학회 2022 전기학회논문지 Vol.71 No.10
Predicting clinical information using gene expression is challenging given the complexity and high dimensionality of gene data. This study propose a deep learning framework for cancer diagnosis through feature extraction and classifier based on various pre-trained autoencoder technologies for kidney cancer. It can be fine-tuned for any tasks and predict clinical information by neural network classifiers. Our model achieved micro and macro F1-scores of 96.2% and 95.8% for gender, 95.8% and 76.3% for race, and 99.8% and 99.6% for sample type predictions, respectively, which is much higher than the values of traditional dimensionality reduction and machine learning techniques. In the results, the conditional variational mutation autoencoder (CVAE) improved the macro F1 score, a difficult race prediction task, by 7.6%. Our results are useful for the prognosis as well as prevention and early diagnosis of kidney cancer.
Li, Dingkun,Park, Hyun Woo,Batbaatar, Erdenebileg,Munkhdalai, Lkhagvadorj,Musa, Ibrahim,Li, Meijing,Ryu, Keun Ho Hindawi Limited 2018 Journal of sensors Vol.2018 No.-
<P>Hadoop is a globally famous framework for big data processing. Data mining (DM) is the key technique for the discovery of the useful information from massive datasets. In our work, we take advantage of both platforms to design a real-time and intelligent mobile health-care system for chronic disease detection based on IoT device data, government-provided public data and user input data. The purpose of our work is the provision of a practical assistant system for self-based patient health care, as well as the design of a complementary system for patient disease diagnosis. This system was only applied to hypertensive disease during the first research stage. Nevertheless, a detailed design, an implementation, a clear overview of the whole system, and a significant guide for further work are provided; the entire step-by-step procedure is depicted. The experiment results show a relatively high accuracy.</P>