In a large-scale collaborative filtering system, pair wise similarity between users is usually measured by users' ratings on the whole set of items. However, this measurement may not be well defined due to the sparsity problem, i.e., the lack of adequate ratings on items for calculating accurate predictions. In fact, most correlated users have similar ratings only on a subset of items. In this paper, we consider a kernel-based classification approach for collaborative filtering and propose several kernel matrix construction methods by using biclusters to capture pair wise similarity between users. In order to characterize accurate correlation among users, we embed both local information and global information into the similarity matrix. However, this similarity matrix may not be a kernel matrix. Our solution is to approximate it with the matrix close to it and use low rank constraints to control the complexity of the matrix.
{"title":"Kernel-based Approaches for Collaborative Filtering","authors":"Zhonghang Xia, Wenke Zhang, Manghui Tu, I. Yen","doi":"10.1109/ICMLA.2010.41","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.41","url":null,"abstract":"In a large-scale collaborative filtering system, pair wise similarity between users is usually measured by users' ratings on the whole set of items. However, this measurement may not be well defined due to the sparsity problem, i.e., the lack of adequate ratings on items for calculating accurate predictions. In fact, most correlated users have similar ratings only on a subset of items. In this paper, we consider a kernel-based classification approach for collaborative filtering and propose several kernel matrix construction methods by using biclusters to capture pair wise similarity between users. In order to characterize accurate correlation among users, we embed both local information and global information into the similarity matrix. However, this similarity matrix may not be a kernel matrix. Our solution is to approximate it with the matrix close to it and use low rank constraints to control the complexity of the matrix.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"1 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":"125459368","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}
As a famous game in the domain of game theory, both pervasive empirical studies as well as intensive theoretical analysis have been conducted and performed worldwide to research different public goods game scenarios. At the same time, computer game simulators are utilized widely for better research of game theory by providing easy but powerful visualization and statistics functionalities. However, although solutions of public goods game have been widely discussed with empirical studies or theoretical approaches, no computational and automatic simulation approaches has been adopted. For this reason, we have implemented a computer simulator with reinforcement learning agents module for public goods game, and we have utilized this simulator to further study the characteristics of public goods game. Furthermore, in this article, we have also presented a bunch of interesting experimental results with respect to the strategies that agents used and the profits they earned.
{"title":"Public Goods Game Simulator with Reinforcement Learning Agents","authors":"U. ManChon, Z. Li","doi":"10.1109/ICMLA.2010.14","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.14","url":null,"abstract":"As a famous game in the domain of game theory, both pervasive empirical studies as well as intensive theoretical analysis have been conducted and performed worldwide to research different public goods game scenarios. At the same time, computer game simulators are utilized widely for better research of game theory by providing easy but powerful visualization and statistics functionalities. However, although solutions of public goods game have been widely discussed with empirical studies or theoretical approaches, no computational and automatic simulation approaches has been adopted. For this reason, we have implemented a computer simulator with reinforcement learning agents module for public goods game, and we have utilized this simulator to further study the characteristics of public goods game. Furthermore, in this article, we have also presented a bunch of interesting experimental results with respect to the strategies that agents used and the profits they earned.","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":"133461732","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}
Hybrid intelligent systems which take advantage of the Bayesian/Fuzzy collaboration have been explored in the literature in the last years. Such collaboration can play an important role mainly in real intelligent systems applications, where accuracy and comprehensibility are crucial aspects to be considered. This paper further explore the Bayes Fuzzy method proposing a classification method specially designed to be used in intelligent systems for data analysis. The main idea is to enhance comprehensibility while maintaining accuracy by decreasing the number of fuzzy rules used to explain a Bayesian Classifier (BC). The proposed Pruned Bayes Fuzzy 2 (PBF2) method is based on a new feature selection method named Selection by Markov Blanket Relation Strength (SMBRS). In the performed experiments, PBF2 is empirically applied to a real world police records problem in order to extract a comprehensible and accurate set of rules which can help in crime prevention. The obtained results show PBF2, when used with proper parameters, brings better precision and comprehensibility compared to other Bayesian/Fuzzy-based methods and to C4.5 algorithm.
{"title":"Intelligent Classification System Using a Pruned Bayes Fuzzy Rule Set","authors":"I. Yin, Estevam Hruschka, H. Camargo","doi":"10.1109/ICMLA.2010.98","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.98","url":null,"abstract":"Hybrid intelligent systems which take advantage of the Bayesian/Fuzzy collaboration have been explored in the literature in the last years. Such collaboration can play an important role mainly in real intelligent systems applications, where accuracy and comprehensibility are crucial aspects to be considered. This paper further explore the Bayes Fuzzy method proposing a classification method specially designed to be used in intelligent systems for data analysis. The main idea is to enhance comprehensibility while maintaining accuracy by decreasing the number of fuzzy rules used to explain a Bayesian Classifier (BC). The proposed Pruned Bayes Fuzzy 2 (PBF2) method is based on a new feature selection method named Selection by Markov Blanket Relation Strength (SMBRS). In the performed experiments, PBF2 is empirically applied to a real world police records problem in order to extract a comprehensible and accurate set of rules which can help in crime prevention. The obtained results show PBF2, when used with proper parameters, brings better precision and comprehensibility compared to other Bayesian/Fuzzy-based methods and to C4.5 algorithm.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"36 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":"132592279","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}
Many machine learning algorithms require a single value per feature per record for modeling. However, there are applications, in the medical domain particularly, where a single record may have multiple observations for the same feature. For example, a patient could have the same gene analyzed in multiple tissue slides of a biopsy, or could have the same genetic test performed on multiple subsequent biopsies. The challenge in these applications is how to integrate multiple observations of the same predictor feature per record. In this paper, two data aggregation methods are compared, one method is a simple median aggregation of feature values, while the other is a novel method which constructs intervals of values for each feature. The aggregated features are passed as input to a novel support vector regression method for modeling survival data in a prostate cancer setting. The performance of both methods was similar in predicting prostate cancer progression on three data cohorts.
{"title":"Aggregating Multiple Biological Measurements Per Patient","authors":"V. Zubek, F. Khan","doi":"10.1109/ICMLA.2010.120","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.120","url":null,"abstract":"Many machine learning algorithms require a single value per feature per record for modeling. However, there are applications, in the medical domain particularly, where a single record may have multiple observations for the same feature. For example, a patient could have the same gene analyzed in multiple tissue slides of a biopsy, or could have the same genetic test performed on multiple subsequent biopsies. The challenge in these applications is how to integrate multiple observations of the same predictor feature per record. In this paper, two data aggregation methods are compared, one method is a simple median aggregation of feature values, while the other is a novel method which constructs intervals of values for each feature. The aggregated features are passed as input to a novel support vector regression method for modeling survival data in a prostate cancer setting. The performance of both methods was similar in predicting prostate cancer progression on three data cohorts.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"230 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":"115751914","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 binocular framework for face liveness verification under unconstrained localization. The proposed framework contains two components: the first component localizes imbalanced points in face regions of an input pair of stereo images and the second component detects whether an imaging face is a 2D object or a 3D object. We test the propose framework on a publicly available stereo face database, which demonstrated its potential.
{"title":"A Binocular Framework for Face Liveness Verification under Unconstrained Localization","authors":"Qi Li, Zhonghang Xia, Guangming Xing","doi":"10.1109/ICMLA.2010.37","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.37","url":null,"abstract":"In this paper, we propose a binocular framework for face liveness verification under unconstrained localization. The proposed framework contains two components: the first component localizes imbalanced points in face regions of an input pair of stereo images and the second component detects whether an imaging face is a 2D object or a 3D object. We test the propose framework on a publicly available stereo face database, which demonstrated its potential.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"161 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":"115996449","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}
Modern compilers provide optimization options to obtain better performance for a given program. Effective selection of optimization options is a challenging task. Recent work has shown that machine learning can be used to select the best compiler optimization options for a given program. Machine learning techniques rely upon selecting features which represent a program in the best way. The quality of these features is critical to the performance of machine learning techniques. Previous work on feature selection for program representation is based on code size, mostly executed parts, parallelism and memory access patterns with-in a program. Spatial based information–how instructions are distributed with-in a program–has never been studied to generate features for the best compiler options selection using machine learning techniques. In this paper, we present a framework that address how to capture the spatial information with-in a program and transform it to features for machine learning techniques. An extensive experimentation is done using the SPEC2006 and MiBench benchmark applications. We compare our work with the IBM Milepost-gcc framework. The Milepost work gives a comprehensive set of features for using machine learning techniques for the best compiler options selection problem. Results show that the performance of machine learning techniques using spatial based features is better than the performance using the Milepost framework. With 66 available compiler options, we are also able to achieve 70% of the potential speed up obtained through an iterative compilation.
{"title":"Spatial Based Feature Generation for Machine Learning Based Optimization Compilation","authors":"A. Malik","doi":"10.1109/ICMLA.2010.147","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.147","url":null,"abstract":"Modern compilers provide optimization options to obtain better performance for a given program. Effective selection of optimization options is a challenging task. Recent work has shown that machine learning can be used to select the best compiler optimization options for a given program. Machine learning techniques rely upon selecting features which represent a program in the best way. The quality of these features is critical to the performance of machine learning techniques. Previous work on feature selection for program representation is based on code size, mostly executed parts, parallelism and memory access patterns with-in a program. Spatial based information–how instructions are distributed with-in a program–has never been studied to generate features for the best compiler options selection using machine learning techniques. In this paper, we present a framework that address how to capture the spatial information with-in a program and transform it to features for machine learning techniques. An extensive experimentation is done using the SPEC2006 and MiBench benchmark applications. We compare our work with the IBM Milepost-gcc framework. The Milepost work gives a comprehensive set of features for using machine learning techniques for the best compiler options selection problem. Results show that the performance of machine learning techniques using spatial based features is better than the performance using the Milepost framework. With 66 available compiler options, we are also able to achieve 70% of the potential speed up obtained through an iterative compilation.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"91 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":"117231964","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}
Hui Li, Chunmei Liu, Xumin Liu, M. Diakite, L. Burge, A. Yakubu, W. Southerland
Identifying the ion types for a mass spectrum is essential for interpreting the spectrum and deriving its peptide sequence. In this paper, we proposed a novel method for identifying ion types and deriving matched peptide sequences for tandem mass spectra. We first divided our dataset into a training set and a testing set and then preprocessed the data using a Support Vector Machine and a 5-fold cross validation based dual denoting model. Then we constructed a syntax tree and generated a rule set to match the mass values from experimental mass spectra with the mass spectral values from corresponding theoretical mass spectra. Finally we applied the proposed algorithm to a tandem mass spectral dataset consisting of 2656 spectra from yeast. Compared with other methods, the experimental results showed that the proposed method can effectively filter noise and successfully derive peptide sequences.
{"title":"Peptide Sequence Tag-Based Blind Identification-based SVM Model","authors":"Hui Li, Chunmei Liu, Xumin Liu, M. Diakite, L. Burge, A. Yakubu, W. Southerland","doi":"10.1109/ICMLA.2010.156","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.156","url":null,"abstract":"Identifying the ion types for a mass spectrum is essential for interpreting the spectrum and deriving its peptide sequence. In this paper, we proposed a novel method for identifying ion types and deriving matched peptide sequences for tandem mass spectra. We first divided our dataset into a training set and a testing set and then preprocessed the data using a Support Vector Machine and a 5-fold cross validation based dual denoting model. Then we constructed a syntax tree and generated a rule set to match the mass values from experimental mass spectra with the mass spectral values from corresponding theoretical mass spectra. Finally we applied the proposed algorithm to a tandem mass spectral dataset consisting of 2656 spectra from yeast. Compared with other methods, the experimental results showed that the proposed method can effectively filter noise and successfully derive peptide sequences.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"10 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":"129629517","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}
Drausin Wulsin, Justin A. Blanco, R. Mani, B. Litt
Clinical electroencephalography (EEG) is routinely used to monitor brain function in critically ill patients, and specific EEG waveforms are recognized by clinicians as signatures of abnormal brain. These pathologic EEG waveforms, once detected, often necessitate accute clinincal interventions, but these events are typically rare, highly variable between patients, and often hard to separate from background, making them difficult to reliably detect. We show that Deep Belief Nets (DBNs), a type of multi-layer generative neural network, can be used effectively for such EEG anomaly detection. We compare this technique to the state-of-the-art, a one-class Support Vector Machine (SVM), showing that the DBN outperforms the SVM by the F1 measure for our EEG dataset. We also show how the outputs of a DBN-based detector can be used to aid visualization of anomalies in large EEG data sets and propose a method for using DBNs to gain insight into which features of signals are characteristically anomalous. These findings show that Deep Belief Nets can facilitate human review of large amounts of clinical EEG as well as mining new EEG features that may be indicators of unusual activity.
{"title":"Semi-Supervised Anomaly Detection for EEG Waveforms Using Deep Belief Nets","authors":"Drausin Wulsin, Justin A. Blanco, R. Mani, B. Litt","doi":"10.1109/ICMLA.2010.71","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.71","url":null,"abstract":"Clinical electroencephalography (EEG) is routinely used to monitor brain function in critically ill patients, and specific EEG waveforms are recognized by clinicians as signatures of abnormal brain. These pathologic EEG waveforms, once detected, often necessitate accute clinincal interventions, but these events are typically rare, highly variable between patients, and often hard to separate from background, making them difficult to reliably detect. We show that Deep Belief Nets (DBNs), a type of multi-layer generative neural network, can be used effectively for such EEG anomaly detection. We compare this technique to the state-of-the-art, a one-class Support Vector Machine (SVM), showing that the DBN outperforms the SVM by the F1 measure for our EEG dataset. We also show how the outputs of a DBN-based detector can be used to aid visualization of anomalies in large EEG data sets and propose a method for using DBNs to gain insight into which features of signals are characteristically anomalous. These findings show that Deep Belief Nets can facilitate human review of large amounts of clinical EEG as well as mining new EEG features that may be indicators of unusual activity.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"25 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":"127475327","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}
Metagenomics deals with the study of micro-organisms such as prokaryotes that are found in samples from natural environments. The samples obtained from the environment may contain DNA from many different species of micro-organisms including bacteria and archea. Micro-organisms are responsible for most of the symbiotic activity on earth. They are also responsible for the complex chemical reactions which take place on the surface of the earth, which help maintain earth’s ecological balance. With the increase in genome sequencing projects there has been a considerable increase in the amount of assembled sequencing data. In this article, we apply supervised learners namely decision trees, Bayesian networks and decision tables to see how the performance degrades when the number of species present in the metagenomic sample increases. We also try to see how the performance of the metagenomic sample changes as the percentage of unknown sequences in the metagenomic sample is varied.
{"title":"On the Scalability of Supervised Learners in Metagenomics","authors":"U. ManChon, Vasim Mahamuda, K. Rasheed","doi":"10.1109/ICMLA.2010.123","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.123","url":null,"abstract":"Metagenomics deals with the study of micro-organisms such as prokaryotes that are found in samples from natural environments. The samples obtained from the environment may contain DNA from many different species of micro-organisms including bacteria and archea. Micro-organisms are responsible for most of the symbiotic activity on earth. They are also responsible for the complex chemical reactions which take place on the surface of the earth, which help maintain earth’s ecological balance. With the increase in genome sequencing projects there has been a considerable increase in the amount of assembled sequencing data. In this article, we apply supervised learners namely decision trees, Bayesian networks and decision tables to see how the performance degrades when the number of species present in the metagenomic sample increases. We also try to see how the performance of the metagenomic sample changes as the percentage of unknown sequences in the metagenomic sample is varied.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"58 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":"129150593","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}
We present a simple method for image denoising called power iteration denoising (PID). PID finds a low dimensional embedding of the image data using a truncated power iteration on a normalized pair-wise similarity matrix generated from the image. This embedding turns out to be an effective denoising algorithm outperforming the widely used non-local means algorithm. We apply this method to the denoising of noisy digital camera images producing visually pleasing results.
{"title":"Power Iteration Denoising","authors":"Panganai Gomo, Mike Spann","doi":"10.1109/ICMLA.2010.131","DOIUrl":"https://doi.org/10.1109/ICMLA.2010.131","url":null,"abstract":"We present a simple method for image denoising called power iteration denoising (PID). PID finds a low dimensional embedding of the image data using a truncated power iteration on a normalized pair-wise similarity matrix generated from the image. This embedding turns out to be an effective denoising algorithm outperforming the widely used non-local means algorithm. We apply this method to the denoising of noisy digital camera images producing visually pleasing results.","PeriodicalId":336514,"journal":{"name":"2010 Ninth International Conference on Machine Learning and Applications","volume":"33 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":"130626034","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：