2014 13th International Conference on Machine Learning and Applications最新文献

Varying Coefficient Models for Analyzing the Effects of Risk Factors on Pregnant Women's Blood Pressure 危险因素对孕妇血压影响的变系数模型分析

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.14

Wenshuai Cheng, Liying Fang, L. Yang, Han Zhao, Pu Wang, Jianzhuo Yan

{"title":"Varying Coefficient Models for Analyzing the Effects of Risk Factors on Pregnant Women's Blood Pressure","authors":"Wenshuai Cheng, Liying Fang, L. Yang, Han Zhao, Pu Wang, Jianzhuo Yan","doi":"10.1109/ICMLA.2014.14","DOIUrl":"https://doi.org/10.1109/ICMLA.2014.14","url":null,"abstract":"In the study of gestational hypertension, most of studies focused on whether a risk factor is associated with gestational hypertension. However, according to the clinical experience, it is important to know the effects of risk factors on women's blood pressure during pregnancy. Thus, we examined the effects of known risk factors (age, hematocrit, etc.) over gestational age. We also examined whether the effects of known risk factors are different between gestational hypertension group and preeclampsia group. These were studied in 412 pregnant women including 1874 clinical follow-up records. On the longitudinal clinical data of pregnant women, varying coefficient models were applied to study the effects of known risk factors over gestational age. The results showed that the effects of known risk factors varied with gestational age, and the changing processes of known risk factors over gestational age were different between gestational hypertension group and preeclampsia group. In final, we used the relative error as the criterion to assess the accuracy of the estimated varying coefficient model. The relative errors for total clinical data, gestational hypertension group and preeclampsia group were 13.3%, 8.1% and 14.3%, respectively.","PeriodicalId":109606,"journal":{"name":"2014 13th International Conference on Machine Learning and Applications","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116789793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

A Comparison of Supervised Machine Learning Techniques for Predicting Short-Term In-Hospital Length of Stay among Diabetic Patients 有监督机器学习技术预测糖尿病患者短期住院时间的比较

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.76

A. Morton, Eman N. Marzban, G. Giannoulis, Ayush Patel, R. Aparasu, I. Kakadiaris

引用次数: 62

Visualising Singing Style under Common Musical Events Using Pitch-Dynamics Trajectories and Modified TRACLUS Clustering 基于音高动态轨迹和改进TRACLUS聚类的常见音乐事件下的歌唱风格可视化

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.44

Kin Wah Edward Lin, Hans Anderson, Natalie Agus, C. So, Simon Lui

{"title":"Visualising Singing Style under Common Musical Events Using Pitch-Dynamics Trajectories and Modified TRACLUS Clustering","authors":"Kin Wah Edward Lin, Hans Anderson, Natalie Agus, C. So, Simon Lui","doi":"10.1109/ICMLA.2014.44","DOIUrl":"https://doi.org/10.1109/ICMLA.2014.44","url":null,"abstract":"We present a novel method for visualising the singing style of vocalists. To illustrate our method, we take 26 audio recordings of A cappella solo vocal music from two different professional singers and we visualise the performance style of each vocalist in a two-dimensional space of pitch and dynamics. We use our own novel modification of a trajectory clustering algorithm called TRACLUS to generate four representative paths, called trajectories, in that two dimensional space. Each trajectory represents the characteristic style of a vocalist during one of four common musical events: (1) Crescendo, (2) Diminuendo, (3) Ascending Pitches and (4) Descending Pitches. The unique shapes of these trajectories characterize the singing style of each vocalist with respect to each of these events. We present the details of our modified version of the TRACULUS algorithm and demonstrate graphically how the plots produced indicate distinct stylistic differences between singers. Potential applications for this method include: (a) automatic identification of singers and automatic classification of singing styles and (b) automatic retargeting of performance style to add human expression to computer generated vocal performances and allow singing synthesisers to imitate the styles of specific famous professional vocalists.","PeriodicalId":109606,"journal":{"name":"2014 13th International Conference on Machine Learning and Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115026628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Incremental SVD for Insight into Wind Generation 基于增量SVD的风力发电研究

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.77

C. Kamath, Y. Fan

引用次数: 0

Transient Characteristics of DC-DC Converter with PID Parameters Selection and Neural Network Control 基于PID参数选择和神经网络控制的DC-DC变换器暂态特性研究

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.78

H. Maruta, D. Mitsutake, F. Kurokawa

{"title":"Transient Characteristics of DC-DC Converter with PID Parameters Selection and Neural Network Control","authors":"H. Maruta, D. Mitsutake, F. Kurokawa","doi":"10.1109/ICMLA.2014.78","DOIUrl":"https://doi.org/10.1109/ICMLA.2014.78","url":null,"abstract":"This paper presents a neural network based PID parameter selection control to improve the transient response of dc-dc converters. In the conventional PID control, parameters of it such as proportional, integral, and differential coefficients are selected as fixed parameters to regulate both transient and steady-state characteristics simultaneously as much as possible. The parameter setting of PID control is not optimal for the improvement of transient-state characteristics since the setting needs to satisfy stable steady-state characteristics. Therefore, the parameter selection for different states is widely applicable from the point of view of the improvement of transient response. In this study, we present a novel parameter selection method for PID control based on the load change prediction of neural network to improve the transient response of dc-dc converter. In the presented method, suitable PID parameters are selected with neural network. This neural network is trained to predict the load change from the output voltage of dc-dc converter in advance. From the predicted result of neural network, PID parameters are changed to optimal ones after the load change occurs. Additionally, the reference modification with another neural network, which is trained to modify the reference value of PID control, is also adopted simultaneously to obtain more effective improvement of transient response. From evaluation results, we confirm that our presented method contributes to obtain an effective improvement of the transient response compared to the conventional PID control.","PeriodicalId":109606,"journal":{"name":"2014 13th International Conference on Machine Learning and Applications","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Modelling Mutual Information between Voiceprint and Optimal Number of Mel-Frequency Cepstral Coefficients in Voice Discrimination 声音识别中声纹互信息与mel -频率倒谱系数最优数的建模

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.9

Kin Wah Edward Lin, Tian Feng, Natalie Agus, C. So, Simon Lui

{"title":"Modelling Mutual Information between Voiceprint and Optimal Number of Mel-Frequency Cepstral Coefficients in Voice Discrimination","authors":"Kin Wah Edward Lin, Tian Feng, Natalie Agus, C. So, Simon Lui","doi":"10.1109/ICMLA.2014.9","DOIUrl":"https://doi.org/10.1109/ICMLA.2014.9","url":null,"abstract":"In this paper, we study the relationship between the voiceprint and the optimal number of Mel-frequency Cepstral Coefficients (MFCCs). The voiceprint is modelled as sub-MFCCs matrix with the first d number of MFCCs. We model the relationship through information theory and formulate it as the mutual information maximization problem subject to the probabilities constraint. The solution of this optimization problem provides the optimal number of MFCCs, D among these d, which yields the highest classification accuracy of the voice discrimination, together with a confidence level. This study is dictated by the need to understand the use of MFCCs, which have proliferated since its invention to discriminate voice. We evaluate our model by comparing the leave-one-out cross validation (LOOCV) results of usual multi-class classifier, the Supervised Learning Gaussian Mixture Model (SLGMM), with a set of spoken words and A capella solo vocal performances. The experimental results show that our model is a more comprehensive feature selection criteria for the MFCCs than the de-facto technique, LOOCV.","PeriodicalId":109606,"journal":{"name":"2014 13th International Conference on Machine Learning and Applications","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114357298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Employing Markov Networks on Curriculum Graphs to Predict Student Performance 利用课程图上的马尔可夫网络预测学生成绩

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.74

Ahmad Slim, G. Heileman, Jarred Kozlick, C. Abdallah

引用次数: 25

Human Action Recognition Based on MOCAP Information Using Convolution Neural Networks 基于动作捕捉信息的卷积神经网络人体动作识别

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.30

Earnest Paul Ijjina, C. Mohan

引用次数: 40

A Hybrid Genetic-Programming Swarm-Optimisation Approach for Examining the Nature and Stability of High Frequency Trading Strategies 研究高频交易策略性质与稳定性的混合遗传规划群优化方法

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.11

Andreea-Ingrid Funie, Mark Salmon, W. Luk

引用次数: 8

Protein Conformation Motion Modeling Using Sep-CMA-ES 基于Sep-CMA-ES的蛋白质构象运动建模

2014 13th International Conference on Machine Learning and Applications Pub Date : 2014-12-03 DOI: 10.1109/ICMLA.2014.12

M. Buzdalov, S. Knyazev, Y. Porozov

引用次数: 1