http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Improved Bimodal Speech Recognition Study Based on Product Hidden Markov Model
Xi, Su Mei,Cho, Young Im Korean Institute of Intelligent Systems 2013 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.13 No.3
Recent years have been higher demands for automatic speech recognition (ASR) systems that are able to operate robustly in an acoustically noisy environment. This paper proposes an improved product hidden markov model (HMM) used for bimodal speech recognition. A two-dimensional training model is built based on dependently trained audio-HMM and visual-HMM, reflecting the asynchronous characteristics of the audio and video streams. A weight coefficient is introduced to adjust the weight of the video and audio streams automatically according to differences in the noise environment. Experimental results show that compared with other bimodal speech recognition approaches, this approach obtains better speech recognition performance.
A New Approach of Domain Dictionary Generation
Xi, Su Mei,Cho, Young-Im,Gao, Qian Korean Institute of Intelligent Systems 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.1
A Domain Dictionary generation algorithm based on pseudo feedback model is presented in this paper. This algorithm can increase the precision of domain dictionary generation algorithm. The generation of Domain Dictionary is regarded as a domain term retrieval process: Assume that top N strings in the original retrieval result set are relevant to C, append these strings into the dictionary, retrieval again. Iterate the process until a predefined number of domain terms have been generated. Experiments upon corpus show that the precision of pseudo feedback model based algorithm is much higher than existing algorithms.
Study of Cross-media Retrieval Technique Based on Ontology
Xi, Su Mei,Cho, Young Im Korean Institute of Intelligent Systems 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.4
With the recent advances in information retrieval, cross-media retrieval has been attracting lot of attention, but several issues remain problems such as constructing effective correlations, calculating similarity between different kinds of media objects. To gain better cross-media retrieval performance, it is crucial to mine the semantic correlations among the heterogeneous multimedia data. This paper introduces a new method for cross-media retrieval which uses ontology to organize different media objects. The experiment results show that the proposed method is effective in cross-media retrieval.
Soy Protein Supplementation Reduces Clinical Indices in Type 2 Diabetes and Metabolic Syndrome
Xi-Mei Zhang,Yun-Bo Zhang,Mei-Hua Chi 연세대학교의과대학 2016 Yonsei medical journal Vol.57 No.3
Purpose: Clinical trials have studied the use of soy protein for treating type 2 diabetes (T2D) and metabolic syndrome (MS). The purpose of this study was to outline evidence on the effects of soy protein supplementation on clinical indices in T2D and MS subjects by performing a meta-analysis of randomized controlled trials (RCTs). Materials and Methods: We searched PubMed, EMBASE, and Cochrane databases up to March 2015 for RCTs. Pooled estimates and 95% confidence intervals (CIs) were calculated by the fixed-and-random-effects model. A total of eleven studies with eleven clinical variables met the inclusion criteria. Results: The meta-analysis showed that fasting plasma glucose (FPG) [weighted mean difference (WMD), -0.207; 95% CI, -0.374 to -0.040; p=0.015], fasting serum insulin (FSI) (WMD, -0.292; 95% CI, -0.496 to -0.088; p=0.005), homeostasis model of assessmentfor insulin resistance index (HOMA-IR) (WMD, -0.346; 95% CI, -0.570 to -0.123; p=0.002), diastolic blood pressure (DBP) (WMD, -0.230; 95% CI, -0.441 to -0.019; p=0.033), low-density lipoprotein cholesterol (LDL-C) (WMD, -0.304; 95% CI, -0.461 to -0.148; p=0.000), total cholesterol (TC) (WMD, -0.386; 95% CI, -0.548 to -0.225; p=0.000), and C-reactive protein (CRP) (WMD, -0.510; 95% CI, -0.722 to -0.299; p=0.000) are significant reduced with soy protein supplementation, compared with a placebo control group, in T2D and MS patients. Furthermore, soy protein supplementation for longer duration (≥6 mo) significantly reducedFPG, LDL-C, and CRP, while that for a shorter duration (<6 mo) significantly reduced FSI and HOMA-IR. Conclusion: Soy protein supplementation could be beneficial for FPG, FSI, HOMA-IR, DBP, LDL-C, TC, and CRP control in plasma.
Study of Cross-media Retrieval Technique Based on Ontology
Su Mei Xi,Young Im Cho 한국지능시스템학회 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.4
With the recent advances in information retrieval, cross-media retrieval has been attracting lot of attention, but several issues remain problems such as constructing effective correlations, calculating similarity between different kinds of media objects. To gain better cross-media retrieval performance, it is crucial to mine the semantic correlations among the heterogeneous multimedia data. This paper introduces a new method for cross-media retrieval which uses ontology to organize different media objects. The experiment results show that the proposed method is effective in cross-media retrieval.
Image Caption Automatic Generation Method Based on Weighted Feature
Su Mei Xi,Young Im Cho 제어로봇시스템학회 2013 제어로봇시스템학회 국제학술대회 논문집 Vol.2013 No.10
For people to use numerous images effectively on the web, technologies must be able to explain image contents and must be capable of searching for data that users need. Moreover, images must be described with natural sentences based not only on the names of objects contained in an image but also on their mutual relations. We propose a novel system which generates sentential annotations for general images. Firstly, a weighted feature clustering algorithm is employed on the semantic concept clusters of the image regions. For a given cluster, we determine relevant features based on their statistical distribution and assign greater weights to relevant features as compared to less relevant features. In this way the computing of clustering algorithm can avoid dominated by trivial relevant or irrelevant features. Then, the relationship between clustering regions and semantic concepts is established according to the labeled images in the training set. Under the condition of the new unlabeled image regions, we calculate the conditional probability of each semantic keyword and annotate the new images with maximal conditional probability. Experiments on the Corel image set show the effectiveness of the new algorithm.
Improved Bimodal Speech Recognition Study Based on Product Hidden Markov Model
Su Mei Xi,Young Im Cho 한국지능시스템학회 2013 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.13 No.3
Recent years have been higher demands for automatic speech recognition (ASR) systems that are able to operate robustly in an acoustically noisy environment. This paper proposes an improved product hidden markov model (HMM) used for bimodal speech recognition. A two-dimensional training model is built based on dependently trained audio-HMM and visual-HMM, reflecting the asynchronous characteristics of the audio and video streams. A weight coefficient is introduced to adjust the weight of the video and audio streams automatically according to differences in the noise environment. Experimental results show that compared with other bimodal speech recognition approaches, this approach obtains better speech recognition performance.
Comparison of Application Effect of Natural Language Processing Techniques for Information Retrieval
Su Mei Xi,Young Im Cho(조영임) 제어로봇시스템학회 2012 제어·로봇·시스템학회 논문지 Vol.18 No.11
In this paper, some applications of natural language processing techniques for information retrieval have been introduced, but the results are known not to be satisfied. In order to find the roles of some classical natural language processing techniques in information retrieval and to find which one is better we compared the effects with the various natural language techniques for information retrieval precision, and the experiment results show that basic natural language processing techniques with small calculated consumption and simple implementation help a small for information retrieval. Senior high complexity of natural language processing techniques with high calculated consumption and low precision can not help the information retrieval precision even harmful to it, so the role of natural language understanding may be larger in the question answering system, automatic abstract and information extraction.
A New Approach of Domain Dictionary Generation
Su mei Xi,Young Im Cho,Qian Gao 한국지능시스템학회 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.1
A Domain Dictionary generation algorithm based on pseudo feedback model is presented in this paper. This algorithm can increase the precision of domain dictionary generation algorithm. The generation of Domain Dictionary is regarded as a domain term retrieval process: Assume that top N strings in the original retrieval result set are relevant to C, append these strings into the dictionary, retrieval again. Iterate the process until a predefined number of domain terms have been generated. Experiments upon corpus show that the precision of pseudo feedback model based algorithm is much higher than existing algorithms.