A. Grasso, J. Willamowski, Victor Ciriza, Yves Hoppenot
To face ongoing global warming issues and in general to promote sustainable development, a number of tools have been developed that help people to assess the impact of their behavior on the environment. In this paper we present the Personal Assessment Tool, a system that observes print behavior and aggregates information in ways meant to promote more conscious use of the shared printing resources.
{"title":"The Personal Assessment Tool: A System Providing Environmental Feedback to Users of Shared Printers for Providing Environmental Feedback","authors":"A. Grasso, J. Willamowski, Victor Ciriza, Yves Hoppenot","doi":"10.1109/ICMLA.2010.108","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.108","url":null,"abstract":"To face ongoing global warming issues and in general to promote sustainable development, a number of tools have been developed that help people to assess the impact of their behavior on the environment. In this paper we present the Personal Assessment Tool, a system that observes print behavior and aggregates information in ways meant to promote more conscious use of the shared printing resources.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115469007","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}
Feature selection has become the essential step in many data mining applications. Using a single feature subset selection method may generate local optima. Ensembles of feature selection methods attempt to combine multiple feature selection methods instead of using a single one. We present a comprehensive empirical study examining 17 different ensembles of feature ranking techniques (rankers) including six commonly-used feature ranking techniques, the signal-to-noise filter technique, and 11 threshold-based feature ranking techniques. This study utilized 16 real-world software measurement data sets of different sizes and built 13,600 classification models. Experimental results indicate that ensembles of very few rankers are very effective and even better than ensembles of many or all rankers.
{"title":"A Comparative Study of Ensemble Feature Selection Techniques for Software Defect Prediction","authors":"Huanjing Wang, T. Khoshgoftaar, Amri Napolitano","doi":"10.1109/ICMLA.2010.27","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.27","url":null,"abstract":"Feature selection has become the essential step in many data mining applications. Using a single feature subset selection method may generate local optima. Ensembles of feature selection methods attempt to combine multiple feature selection methods instead of using a single one. We present a comprehensive empirical study examining 17 different ensembles of feature ranking techniques (rankers) including six commonly-used feature ranking techniques, the signal-to-noise filter technique, and 11 threshold-based feature ranking techniques. This study utilized 16 real-world software measurement data sets of different sizes and built 13,600 classification models. Experimental results indicate that ensembles of very few rankers are very effective and even better than ensembles of many or all rankers.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"30 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127098978","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}
In this paper, we propose a dynamic technique for selecting the most informative samples in classification problems as coming in two stages: the first stage conducts sample selection in batch off-line mode based on unsupervised criteria extracted from cluster partitions, the second phase proposes an active learning scheme during on-line adaptation of classifiers in non-stationary environments. This is based on the reliability of the classifiers in their output responses (confidences in their predictions). Both approaches contribute to a reduction of the annotation effort for operators, as operators only have to label/give feedback on a subset of the off-line/online. At the same time they are able to keep the accuracy on almost the same level as when the classifiers would have been trained on all samples. This will be verified based on real-world data sets from two image classification problems used in on-line surface inspection scenarios.
{"title":"On Dynamic Selection of the Most Informative Samples in Classification Problems","authors":"E. Lughofer","doi":"10.1109/ICMLA.2010.89","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.89","url":null,"abstract":"In this paper, we propose a dynamic technique for selecting the most informative samples in classification problems as coming in two stages: the first stage conducts sample selection in batch off-line mode based on unsupervised criteria extracted from cluster partitions, the second phase proposes an active learning scheme during on-line adaptation of classifiers in non-stationary environments. This is based on the reliability of the classifiers in their output responses (confidences in their predictions). Both approaches contribute to a reduction of the annotation effort for operators, as operators only have to label/give feedback on a subset of the off-line/online. At the same time they are able to keep the accuracy on almost the same level as when the classifiers would have been trained on all samples. This will be verified based on real-world data sets from two image classification problems used in on-line surface inspection scenarios.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123557870","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}
T. Damoulas, S. Henry, Andrew Farnsworth, Michael Lanzone, C. Gomes
In this paper we propose a probabilistic classification algorithm with a novel Dynamic Time Warping (DTW) kernel to automatically recognize flight calls of different species of birds. The performance of the method on a real world dataset of warbler (Parulidae) flight calls is competitive to human expert recognition levels and outperforms other classifiers trained on a variety of feature extraction approaches. In addition we offer a novel and intuitive DTW kernel formulation which is positive semi-definite in contrast with previous work. Finally we obtain promising results with a larger dataset of multiple species that we can handle efficiently due to the explicit multiclass probit likelihood of the proposed approach.
{"title":"Bayesian Classification of Flight Calls with a Novel Dynamic Time Warping Kernel","authors":"T. Damoulas, S. Henry, Andrew Farnsworth, Michael Lanzone, C. Gomes","doi":"10.1109/ICMLA.2010.69","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.69","url":null,"abstract":"In this paper we propose a probabilistic classification algorithm with a novel Dynamic Time Warping (DTW) kernel to automatically recognize flight calls of different species of birds. The performance of the method on a real world dataset of warbler (Parulidae) flight calls is competitive to human expert recognition levels and outperforms other classifiers trained on a variety of feature extraction approaches. In addition we offer a novel and intuitive DTW kernel formulation which is positive semi-definite in contrast with previous work. Finally we obtain promising results with a larger dataset of multiple species that we can handle efficiently due to the explicit multiclass probit likelihood of the proposed approach.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123697113","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}
In this paper we analyse one of the most challenging problems in natural language processing: domain adaptation in sentiment classification. In particular, we look for generic features by making use of linguistic patterns as an alternative to the commonly feature vectors based on ngrams. The experimentation conducted shows how sentiment classification is highly sensitive to the domain from which the training data are extracted. However, the results of the experimentation also show how a model constructed around linguistic patterns is a plausible alternative for sentiment classification over some domains.
{"title":"Domain Adaptation in Sentiment Classification","authors":"Diego Uribe","doi":"10.1109/ICMLA.2010.133","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.133","url":null,"abstract":"In this paper we analyse one of the most challenging problems in natural language processing: domain adaptation in sentiment classification. In particular, we look for generic features by making use of linguistic patterns as an alternative to the commonly feature vectors based on ngrams. The experimentation conducted shows how sentiment classification is highly sensitive to the domain from which the training data are extracted. However, the results of the experimentation also show how a model constructed around linguistic patterns is a plausible alternative for sentiment classification over some domains.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123743468","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}
Co-clustering has been defined as a way to organize simultaneously subsets of instances and subsets of features in order to improve the clustering of both of them. In previous work, we proposed an efficient co-similarity measure allowing to simultaneously compute two similarity matrices between objects and features, each built on the basis of the other. Here we propose a generalization of this approach by introducing a notion of pseudo-norm and a pruning algorithm. Our experiments show that this new algorithm significantly improves the accuracy of the results when using either supervised or unsupervised feature selection data and that it outperforms other algorithms on various corpora.
{"title":"An Improved Co-Similarity Measure for Document Clustering","authors":"Syed Fawad Hussain, G. Bisson, Clément Grimal","doi":"10.1109/ICMLA.2010.35","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.35","url":null,"abstract":"Co-clustering has been defined as a way to organize simultaneously subsets of instances and subsets of features in order to improve the clustering of both of them. In previous work, we proposed an efficient co-similarity measure allowing to simultaneously compute two similarity matrices between objects and features, each built on the basis of the other. Here we propose a generalization of this approach by introducing a notion of pseudo-norm and a pruning algorithm. Our experiments show that this new algorithm significantly improves the accuracy of the results when using either supervised or unsupervised feature selection data and that it outperforms other algorithms on various corpora.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129951793","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}
Christophe Rodrigues, Pierre Gérard, C. Rouveirol, H. Soldano
In the Relational Reinforcement learning framework, we propose an algorithm that learns an action model allowing to predict the resulting state of each action in any given situation. The system incrementally learns a set of first order rules: each time an example contradicting the current model (a counter-example) is encountered, the model is revised to preserve coherence and completeness, by using data-driven generalization and specialization mechanisms. The system is proved to converge by storing counter-examples only, and experiments on RRL benchmarks demonstrate its good performance w.r.t state of the art RRL systems.
{"title":"Incremental Learning of Relational Action Rules","authors":"Christophe Rodrigues, Pierre Gérard, C. Rouveirol, H. Soldano","doi":"10.1109/ICMLA.2010.73","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.73","url":null,"abstract":"In the Relational Reinforcement learning framework, we propose an algorithm that learns an action model allowing to predict the resulting state of each action in any given situation. The system incrementally learns a set of first order rules: each time an example contradicting the current model (a counter-example) is encountered, the model is revised to preserve coherence and completeness, by using data-driven generalization and specialization mechanisms. The system is proved to converge by storing counter-examples only, and experiments on RRL benchmarks demonstrate its good performance w.r.t state of the art RRL systems.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124663862","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}
Shobeir Fakhraei, H. Soltanian-Zadeh, F. Fotouhi, K. Elisevich
Development of a feature ranking method based upon the discriminative power of features and unbiased towards classifiers is of interest. We have studied a consensus feature ranking method, based on multiple classifiers, and have shown its superiority to well known statistical ranking methods. In a target environment such as a medical dataset, missing values and an unbalanced distribution of data must be taken into consideration in the ranking and evaluation phases in order to legitimately apply a feature ranking method. In a comparison study, a Performance Index (PI) is proposed that takes into account both the number of features and the number of samples involved in the classification.
{"title":"Consensus Feature Ranking in Datasets with Missing Values","authors":"Shobeir Fakhraei, H. Soltanian-Zadeh, F. Fotouhi, K. Elisevich","doi":"10.1109/ICMLA.2010.117","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.117","url":null,"abstract":"Development of a feature ranking method based upon the discriminative power of features and unbiased towards classifiers is of interest. We have studied a consensus feature ranking method, based on multiple classifiers, and have shown its superiority to well known statistical ranking methods. In a target environment such as a medical dataset, missing values and an unbalanced distribution of data must be taken into consideration in the ranking and evaluation phases in order to legitimately apply a feature ranking method. In a comparison study, a Performance Index (PI) is proposed that takes into account both the number of features and the number of samples involved in the classification.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126670679","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}
This paper demonstrates the effectiveness of Linear Support Vector Machines (SVM) when applied to non-sparse datasets with a large number of instances. Two linear SVM algorithms are compared. The coordinate descent method (LibLinear) trains a linear SVM with the L2-loss function versus the cutting-plane algorithm (SVMperf), which uses a L1-loss function. Four Geographical Information System (GIS) datasets with over a million instances were used for this study. Each dataset consists of seven independent variables and a class label which denotes the urban areas versus the rural areas.
{"title":"A Comparison of Linear Support Vector Machine Algorithms on Large Non-Sparse Datasets","authors":"A. Lazar","doi":"10.1109/ICMLA.2010.137","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.137","url":null,"abstract":"This paper demonstrates the effectiveness of Linear Support Vector Machines (SVM) when applied to non-sparse datasets with a large number of instances. Two linear SVM algorithms are compared. The coordinate descent method (LibLinear) trains a linear SVM with the L2-loss function versus the cutting-plane algorithm (SVMperf), which uses a L1-loss function. Four Geographical Information System (GIS) datasets with over a million instances were used for this study. Each dataset consists of seven independent variables and a class label which denotes the urban areas versus the rural areas.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127021154","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}
Learning is one way to determine how agents should act, but learning in multi-agent systems is more difficult than in single-agent systems because other learning agents modify their behavior. We introduce a particle-based algorithm called MMM-PHC. MMM-PHC promotes convergence to Nash equilibria in matrix games using the ideas of maxim in strategies and partial commitment. Partial commitment is implemented by restricting policies to a simplex. Simulations show that MMM-PHC performs on a larger class of games than WoLFPHC.
{"title":"MMM-PHC: A Particle-Based Multi-Agent Learning Algorithm","authors":"Philip R. Cook, M. Goodrich","doi":"10.1109/ICMLA.2010.15","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.15","url":null,"abstract":"Learning is one way to determine how agents should act, but learning in multi-agent systems is more difficult than in single-agent systems because other learning agents modify their behavior. We introduce a particle-based algorithm called MMM-PHC. MMM-PHC promotes convergence to Nash equilibria in matrix games using the ideas of maxim in strategies and partial commitment. Partial commitment is implemented by restricting policies to a simplex. Simulations show that MMM-PHC performs on a larger class of games than WoLFPHC.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123626255","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：