发布求助
文献互助 智能选刊 最新文献

2011 10th International Conference on Machine Learning and Applications and Workshops最新文献

筛选
英文 中文
The DIEGO Lab Graph Based Gene Normalization System 基于DIEGO Lab图的基因归一化系统
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.140
R. Sullivan, Robert Leaman, Graciela Gonzalez
{"title":"The DIEGO Lab Graph Based Gene Normalization System","authors":"R. Sullivan, Robert Leaman, Graciela Gonzalez","doi":"10.1109/ICMLA.2011.140","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.140","url":null,"abstract":"Gene entity normalization, the mapping of a gene mention in free text to a unique identifier, is one of the primary subtasks in the biomedical information extraction pipeline. Gene entity normalization provides many challenges, specifically with the high ambiguity of gene names and the many-to-many relationship between gene names and identifiers. Drawing inspiration from recent work in word sense disambiguation, this paper presents a gene entity normalization system based on entity relationship graphs. This system creates a concept graph from the possible entities and their relationships within a full-text document, and takes advantage of a node ranking algorithm to rank and score each potential candidate entity. This system is a prototype to represent a specific approach to gene normalization, and the results reflect this. However, this system demonstrates that the relationship graph-based approach, an approach grounded in a theoretical basis, can potentially be useful for gene normalization and possibly for the normalization of various biomedical entities.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132051096","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: 6
A Non-parametric Approach to Approximate Dynamic Programming 近似动态规划的一种非参数方法
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.19
Hadrien Glaude, Fadi Akrimi, M. Geist, O. Pietquin
{"title":"A Non-parametric Approach to Approximate Dynamic Programming","authors":"Hadrien Glaude, Fadi Akrimi, M. Geist, O. Pietquin","doi":"10.1109/ICMLA.2011.19","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.19","url":null,"abstract":"Approximate Dynamic Programming (ADP) is a machine learning method aiming at learning an optimal control policy for a dynamic and stochastic system from a logged set of observed interactions between the system and one or several non-optimal controlers. It defines a class of particular Reinforcement Learning (RL) algorithms which is a general paradigm for learning such a control policy from interactions. ADP addresses the problem of systems exhibiting a state space which is too large to be enumerated in the memory of a computer. Because of this, approximation schemes are used to generalize estimates over continuous state spaces. Nevertheless, RL still suffers from a lack of scalability to multidimensional continuous state spaces. In this paper, we propose the use of the Locally Weighted Projection Regression (LWPR) method to handle this scalability problem. We prove the efficacy of our approach on two standard benchmarks modified to exhibit larger state spaces.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130452080","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: 2
De-noising Slap Fingerprint Images for Accurate Slap Fingerprint Segmentation 基于去噪方法的拍打指纹图像分割
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.52
N. P. Ramaiah, C. Mohan
{"title":"De-noising Slap Fingerprint Images for Accurate Slap Fingerprint Segmentation","authors":"N. P. Ramaiah, C. Mohan","doi":"10.1109/ICMLA.2011.52","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.52","url":null,"abstract":"Fingerprints have unique properties like distinctiveness and persistence. Sometimes, fingerprint images can have some noisy data while capturing them using slap fingerprint scanners. This noise causes improper slap fingerprint segmentation due to which the performance of fingerprint matching decreases. The process of eliminating duplicates is called de-duplication which requires the plain quality fingerprints. While doing the segmentation of slap fingerprints, some of the fingerprint images are improperly segmented because of the noise present in the data. In this paper, an attempt is made to remove the noise present in the slap fingerprint data using binarization of slap fingerprint image, and region labeling of desired regions with 8-adjacency neighborhood for accurate slap fingerprint segmentation. Experimental results demonstrate that the fingerprint segmentation rate is improved from 78% to 99%.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126689153","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: 9
Smartphone Interruptibility Using Density-Weighted Uncertainty Sampling with Reinforcement Learning 基于密度加权不确定性采样和强化学习的智能手机可中断性
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.128
Robert W. H. Fisher, R. Simmons
{"title":"Smartphone Interruptibility Using Density-Weighted Uncertainty Sampling with Reinforcement Learning","authors":"Robert W. H. Fisher, R. Simmons","doi":"10.1109/ICMLA.2011.128","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.128","url":null,"abstract":"We present the In-Context application for smart-phones, which combines signal processing, active learning, and reinforcement learning to autonomously create a personalized model of interruptibility for incoming phone calls. We empirically evaluate the system, and show that we can obtain an average of 96.12% classification accuracy when predicting interruptibility after a week of training. In contrast to previous work, we leverage density-weighted uncertainty sampling combined with a reinforcement learning framework applied to passively collected data to achieve comparable or superior classification accuracy using many fewer queries issued to the user.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122959456","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: 45
L1 vs. L2 Regularization in Text Classification when Learning from Labeled Features 从标记特征学习时文本分类中的L1与L2正则化
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.85
Sinziana Mazilu, J. Iria
{"title":"L1 vs. L2 Regularization in Text Classification when Learning from Labeled Features","authors":"Sinziana Mazilu, J. Iria","doi":"10.1109/ICMLA.2011.85","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.85","url":null,"abstract":"In this paper we study the problem of building document classifiers using labeled features and unlabeled documents, where not all the features are helpful for the process of learning. This is an important setting, since building classifiers using labeled words has been recently shown to require considerably less human labeling effort than building classifiers using labeled documents. We propose the use of Generalized Expectation (GE) criteria combined with a L1 regularization term for learning from labeled features. This lets the feature labels guide model expectation constraints, while approaching feature selection from a regularization perspective. We show that GE criteria combined with L1 regularization consistently outperforms -- up to 12% increase in accuracy -- the best previously reported results in the literature under the same setting, obtained using L2 regularization. Furthermore, the results obtained with GE criteria and L1 regularizer are competitive to those obtained in the traditional instance-labeling setting, with the same labeling cost.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114111938","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: 9
Exploring Structural Features in Predicting Social Network Evolution 探索预测社会网络演化的结构特征
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.66
Shu Huang, Dongwon Lee
{"title":"Exploring Structural Features in Predicting Social Network Evolution","authors":"Shu Huang, Dongwon Lee","doi":"10.1109/ICMLA.2011.66","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.66","url":null,"abstract":"In this paper, we present a novel approach to incorporate the activity features in measuring the influence of member activities on the social network evolution. Conventional methods analyze social networks and make predictions based on all cumulative members and activities. However, since inactive members do not contribute to the network growth, including them in analysis can lead to less accurate results. Based on this observation, we propose to focus on the active population and explore the influence of member activities. We present a model that can incorporate various activity features and predict the evolution of the social activity. At the same time, an algorithm is adopted to select the most influential activity features. The experiments on two different types of social network show that the activity features can predict the evolution of the social activity accurately and our algorithm is effective to select the most influential features. Additionally, we find that the most significant activity features to determine the network evolution vary among different types of social network.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127743776","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: 9
Using SVD for Segmentation and Classification of Human Hand Actions 基于SVD的手部动作分割与分类
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.155
A. Cavallo
{"title":"Using SVD for Segmentation and Classification of Human Hand Actions","authors":"A. Cavallo","doi":"10.1109/ICMLA.2011.155","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.155","url":null,"abstract":"An automated strategy for decomposing time series into small, elementary subsequences is proposed. This is accomplished in two steps: first the time series must be decomposed into simpler sub-series (segmentation), next each sub series has to be suitably modeled or uniquely characterized (classification). In this paper, an approximation employing the first right singular vector of the data matrix is considered, and two new criteria for segmenting data are proposed and compared. The effectiveness of the proposed strategy is shown on a time series resulting from sensory data on a data-glove when a human picks a tin can. The strategy proves to be simple and reliable, and can be used as a basic ingredient for real-time detection and interpretation of human gestures.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133632665","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: 2
On-line Learning with Evolutionary Algorithms towards Adaptation of Underwater Vehicle Missions to Dynamic Ocean Environments 基于进化算法的水下航行器任务适应动态海洋环境的在线学习
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.110
M. Seto
{"title":"On-line Learning with Evolutionary Algorithms towards Adaptation of Underwater Vehicle Missions to Dynamic Ocean Environments","authors":"M. Seto","doi":"10.1109/ICMLA.2011.110","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.110","url":null,"abstract":"Autonomous underwater vehicles (AUV) are tasked to ever longer deployments so energy management issues are timely and relevant. Energy shortages can occur due to dynamic ocean conditions that vary temporally and spatially in unpredictable ways. This is compounded by underwater communication challenges. Proposed, is an on-going energy evaluation that assesses the AUV ability to complete the mission through an agent that considers the AUV on-line states, non-linear dynamics, recent learned history, and past history to project an energy shortage. When a shortage occurs an onboard knowledge-based agent re-plans the AUV survey mission using on-line learning with a genetic algorithm given the energy budget, mission duration, and the remaining survey area dimensions. The validated agent is especially effective in the case studied for an energy shortfall resulting from increasing the surveyed area by a factor of 2, for a factor of 2 drop in energy. An agent that effectively monitors and re-plans optimal missions with energy considerations, especially for side scan sonars, is quite novel and increases the operational options of AUVs on long deployments.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132113379","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: 6
Collaborative Filtering with CCAM 协同过滤与CCAM
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.47
Meng-Lun Wu, Chia-Hui Chang, Rui-Zhe Liu
{"title":"Collaborative Filtering with CCAM","authors":"Meng-Lun Wu, Chia-Hui Chang, Rui-Zhe Liu","doi":"10.1109/ICMLA.2011.47","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.47","url":null,"abstract":"Recommender system has become an important research topic since the high interest of academia and industry. As a branch of recommender systems, collaborative filtering (CF) systems take its roots from sharing opinions with others and have been shown to be very effective for generating high quality recommendations. However, CF often confronts a problem of sparsity which is caused by relevantly less number of ratings against the unknowns that need to be predicted. In this paper, we consider a hybrid approach which combines the content-based approach with collaborative filtering under a unified model called Co-Clustering with Augmented data Matrix (CCAM). CCAM is based on information-theoretic co-clustering but further considers augmented data matrix like user profile and item description. By presenting results on a better error of prediction, we show that our algorithm is more effective in addressing sparsity through optimizing the co-cluster in mutual information loss between multiple tabular data than algorithm with single data and algorithms do not consider mutual information loss or co-clustering in our prediction framework.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133781273","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
Learning Recognition of Ambiguous Proper Names in Hindi 印地语歧义专名识别的学习
2011 10th International Conference on Machine Learning and Applications and Workshops Pub Date : 2011-12-18 DOI: 10.1109/ICMLA.2011.87
R. Sinha
{"title":"Learning Recognition of Ambiguous Proper Names in Hindi","authors":"R. Sinha","doi":"10.1109/ICMLA.2011.87","DOIUrl":"https://doi.org/10.1109/ICMLA.2011.87","url":null,"abstract":"An ambiguous proper name is a name which is also a valid dictionary word with a meaning of its own when used in the text. For example in English, the word 'bush' in 'Mr. Bush' is a proper name whereas in 'a dense bush' it is a lexical entity. Almost all proper names in Hindi have a meaning and find an entry in the dictionary. Recognition of named entities finds wide application in MT, IR and several other NLP tasks. While there have been a number of investigations on Hindi NER in general, no work has been reported exclusively on ambiguous proper nouns which are more difficult to deal with. This paper presents a methodology for recognizing ambiguous proper names in Hindi using hybridization of a rule-base and statistical CRF based machine learning using morphological and context features. The methodology yields a F-score of 71.6%.","PeriodicalId":439926,"journal":{"name":"2011 10th International Conference on Machine Learning and Applications and Workshops","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130292493","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信