This paper presents a new supervised machine learning technique based on distances between points and straight lines segments. Basically, given a training data set, this technique estimates a function where its value is calculated using the distance between points and two sets of straight line segments. A training algorithm has been developed to find these sets of straight line segments that minimize the mean square error. This technique has been applied on two real pattern recognition problems: (1) breast cancer data set to classify tumors as benign or malignant; (2) wine data set to classify wines in one of the three different cultivators from which they could be derived. This technique was also tested with two artificial data sets in order to show its ability to solve approximation function problems. The obtained results show that this technique has a good performance in all of these problems and they indicate that it is a good candidate to be used in machine learning applications
{"title":"A New Machine Learning Technique Based on Straight Line Segments","authors":"J. Ribeiro, R. F. Hashimoto","doi":"10.1109/ICMLA.2006.8","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.8","url":null,"abstract":"This paper presents a new supervised machine learning technique based on distances between points and straight lines segments. Basically, given a training data set, this technique estimates a function where its value is calculated using the distance between points and two sets of straight line segments. A training algorithm has been developed to find these sets of straight line segments that minimize the mean square error. This technique has been applied on two real pattern recognition problems: (1) breast cancer data set to classify tumors as benign or malignant; (2) wine data set to classify wines in one of the three different cultivators from which they could be derived. This technique was also tested with two artificial data sets in order to show its ability to solve approximation function problems. The obtained results show that this technique has a good performance in all of these problems and they indicate that it is a good candidate to be used in machine learning applications","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115268690","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}
Automated or semi-automated gait analysis systems are important in assisting physicians for diagnosis of various diseases. The objective of this study is to discuss ensemble methods for gait classification as a part of preliminary studies of designing a semi-automated diagnosis system. For this purpose gait data is collected from 110 sick subjects (having knee osteoarthritis (OA)) and 91 age-matched normal subjects. A set of multilayer perceptrons (MLPs) is trained by using joint angle and time-distance parameters of gait as features. Large dimensional feature vector is decomposed into feature subsets and the ones selected by gait expert are used to categorize subjects into two classes; healthy and patient. Ensemble of MLPs is built using these distinct feature subsets and diversification of classifiers is analyzed by cross-validation approach and confusion matrices. High diversifications observed in the confusion matrices suggested that using combining methods would help. Indeed, when a proper combining rule is applied to decomposed sets, more accurate results are obtained. The result suggests that ensemble of MLPs could be applied in the automated diagnosis of gait disorders in a clinical context
{"title":"Ensemble Classifiers for Medical Diagnosis of Knee Osteoarthritis Using Gait Data","authors":"Nigar Sen Köktas, N. Yalabik, G. Yavuzer","doi":"10.1109/ICMLA.2006.22","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.22","url":null,"abstract":"Automated or semi-automated gait analysis systems are important in assisting physicians for diagnosis of various diseases. The objective of this study is to discuss ensemble methods for gait classification as a part of preliminary studies of designing a semi-automated diagnosis system. For this purpose gait data is collected from 110 sick subjects (having knee osteoarthritis (OA)) and 91 age-matched normal subjects. A set of multilayer perceptrons (MLPs) is trained by using joint angle and time-distance parameters of gait as features. Large dimensional feature vector is decomposed into feature subsets and the ones selected by gait expert are used to categorize subjects into two classes; healthy and patient. Ensemble of MLPs is built using these distinct feature subsets and diversification of classifiers is analyzed by cross-validation approach and confusion matrices. High diversifications observed in the confusion matrices suggested that using combining methods would help. Indeed, when a proper combining rule is applied to decomposed sets, more accurate results are obtained. The result suggests that ensemble of MLPs could be applied in the automated diagnosis of gait disorders in a clinical context","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123641348","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}
Protein-protein interaction is essential to cellular functions. In this work, we describe a simple, novel approach to improve the accuracy of predicting protein-protein interaction by incorporating the binding site information. First, we assess the importance of the seven attributes that are used by Bradford et. al (2005) for predicting protein binding sites. The leave-one-out cross validation experiments and principal component analysis indicate that some attributes such as residue propensity and hydrophobicity are more important than other attributes such as curvedness and shape index in differentiating a binding patch from nonbinding patch. Second, we incorporate those attributes to predict protein-protein interaction by simple concatenation of the attribute vectors of candidate interacting partners. A support vector machine is trained to predict the interacting partners. This is combined with using the attributes directly derived from the primary sequence at the binding sites. The results from the leave-one-out cross validation experiments show significant improvement in prediction accuracy by incorporating the structural information at the binding sites
{"title":"Information of Binding Sites Improves Prediction of Protein-Protein Interaction","authors":"Tapan P. Patel, Manoj Pillay, Rahul Jawa, Li Liao","doi":"10.1109/ICMLA.2006.29","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.29","url":null,"abstract":"Protein-protein interaction is essential to cellular functions. In this work, we describe a simple, novel approach to improve the accuracy of predicting protein-protein interaction by incorporating the binding site information. First, we assess the importance of the seven attributes that are used by Bradford et. al (2005) for predicting protein binding sites. The leave-one-out cross validation experiments and principal component analysis indicate that some attributes such as residue propensity and hydrophobicity are more important than other attributes such as curvedness and shape index in differentiating a binding patch from nonbinding patch. Second, we incorporate those attributes to predict protein-protein interaction by simple concatenation of the attribute vectors of candidate interacting partners. A support vector machine is trained to predict the interacting partners. This is combined with using the attributes directly derived from the primary sequence at the binding sites. The results from the leave-one-out cross validation experiments show significant improvement in prediction accuracy by incorporating the structural information at the binding sites","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121421936","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}
E. Marchiori, W. Pirovano, J. Heringa, K. Feenstra
Multiple sequence alignments are often used to reveal functionally important residues within a protein family. In particular, they can be very useful for identification of key residues that determine functional differences between protein subclasses (subtype specific sites). This paper proposes a new algorithm for selecting subtype specific sites from a set of aligned protein sequences. The algorithm combines a feature selection technique with neighbor position information for selecting and ranking a set of putative relevant sites. The algorithm is applied to a dataset of protein sequences from the MH2 domain of the SMAD family of transcriptor factors. Validation of the results on the basis of the known interaction and function of the sites shows that the algorithm successfully identifies the known (from literature) subtype specific sites and new putative ones
{"title":"A Feature Selection Algorithm for Detecting Subtype Specific Functional Sites from Protein Sequences for Smad Receptor Binding","authors":"E. Marchiori, W. Pirovano, J. Heringa, K. Feenstra","doi":"10.1109/ICMLA.2006.7","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.7","url":null,"abstract":"Multiple sequence alignments are often used to reveal functionally important residues within a protein family. In particular, they can be very useful for identification of key residues that determine functional differences between protein subclasses (subtype specific sites). This paper proposes a new algorithm for selecting subtype specific sites from a set of aligned protein sequences. The algorithm combines a feature selection technique with neighbor position information for selecting and ranking a set of putative relevant sites. The algorithm is applied to a dataset of protein sequences from the MH2 domain of the SMAD family of transcriptor factors. Validation of the results on the basis of the known interaction and function of the sites shows that the algorithm successfully identifies the known (from literature) subtype specific sites and new putative ones","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126720852","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}
Sergiy Fefilatyev, Volha Smarodzinava, L. Hall, Dmitry Goldgof
Detecting a horizon in an image is an important part of many image related applications such as detecting ships on the horizon, flight control, and port security. Most of the existing solutions for the problem only use image processing methods to identify a horizon line in an image. This results in good accuracy for many cases and is fast in computation. However, for some images with difficult environmental conditions like a foggy or cloudy sky these image processing methods are inherently inaccurate in identifying the correct horizon. This paper investigates how to detect the horizon line in a set of images using a machine learning approach. The performance of the SVM, J48, and naive Bayes classifiers, used for the problem, has been compared. Accuracy of 90-99% in identifying horizon was achieved on image data set of 20 images
{"title":"Horizon Detection Using Machine Learning Techniques","authors":"Sergiy Fefilatyev, Volha Smarodzinava, L. Hall, Dmitry Goldgof","doi":"10.1109/ICMLA.2006.25","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.25","url":null,"abstract":"Detecting a horizon in an image is an important part of many image related applications such as detecting ships on the horizon, flight control, and port security. Most of the existing solutions for the problem only use image processing methods to identify a horizon line in an image. This results in good accuracy for many cases and is fast in computation. However, for some images with difficult environmental conditions like a foggy or cloudy sky these image processing methods are inherently inaccurate in identifying the correct horizon. This paper investigates how to detect the horizon line in a set of images using a machine learning approach. The performance of the SVM, J48, and naive Bayes classifiers, used for the problem, has been compared. Accuracy of 90-99% in identifying horizon was achieved on image data set of 20 images","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116940782","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}
Most machine learning and data mining algorithms for time series datasets need a suitable distance measure. In addition to classic p-norm distance, numerous other distance measures exist and the most popular is dynamic time warping. Here we propose a new distance measure, called adaptable time warping (ATW), which generalizes all previous time warping distances. We present a learning process using a genetic algorithm that adapts ATW in a locally optimal way, according to the current classification issue we have to resolve. It's possible to prove that ATW with optimal parameters is at least equivalent or at best superior to the other time warping distances for all classification problems. We show this assertion by performing comparative tests on two real datasets. The originality of this work is that we propose a whole learning process directly based on the distance measure rather than on the time series themselves
{"title":"An Adaptable Time Warping Distance for Time Series Learning","authors":"R. Gaudin, N. Nicoloyannis","doi":"10.1109/ICMLA.2006.12","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.12","url":null,"abstract":"Most machine learning and data mining algorithms for time series datasets need a suitable distance measure. In addition to classic p-norm distance, numerous other distance measures exist and the most popular is dynamic time warping. Here we propose a new distance measure, called adaptable time warping (ATW), which generalizes all previous time warping distances. We present a learning process using a genetic algorithm that adapts ATW in a locally optimal way, according to the current classification issue we have to resolve. It's possible to prove that ATW with optimal parameters is at least equivalent or at best superior to the other time warping distances for all classification problems. We show this assertion by performing comparative tests on two real datasets. The originality of this work is that we propose a whole learning process directly based on the distance measure rather than on the time series themselves","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122987834","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 work presents an intelligent automatic fingerprint identification and verification system based on artificial neural networks. In this work, the design processes of the system have been presented step by step. In order to make the system automatic, software was developed for fingerprint identification and verification processes. 100 fingerprint images were used to test and evaluate the system. The results have shown that the task was achieved with high accuracy
{"title":"An Intelligent Automatic Fingerprint Recognition System Design","authors":"Necla Özkaya, Ş. Sağiroğlu, M. Wani","doi":"10.1109/ICMLA.2006.15","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.15","url":null,"abstract":"This work presents an intelligent automatic fingerprint identification and verification system based on artificial neural networks. In this work, the design processes of the system have been presented step by step. In order to make the system automatic, software was developed for fingerprint identification and verification processes. 100 fingerprint images were used to test and evaluate the system. The results have shown that the task was achieved with high accuracy","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132457769","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 user preference prediction mechanism, recommendation techniques have been widely used to support personalized information filtering in current e-commerce applications. We build a recommendation tool into the existing Xerox printing workflow configuration system in order to provide new users with a number of solutions that are possibly of their interests. Such solution recommendations can significantly improve the system efficiency and accuracy by reducing workflow generation overhead and helping users quickly identify their needs. In our work, the main challenge is the high sparsity inherent to our application data - most fields have missing values due to a customer's lack of background or uncertainty on their specific needs. We address this problem by using latent semantic indexing (LSI) to merge original sparse data records into dense and semantic records. The generated dense data are then grouped into clusters based on their correlations. These clusters, together with their user patterns and representative workflows, are used to support efficient online workflow recommendation. Our implemented tool is able to achieve 83% accuracy on a dataset of 4569 case logs with 91% average sparseness
{"title":"A Printing Workflow Recommendation Tool--Exploiting Correlations between Highly Sparse Case Logs","authors":"Ming Zhong, Tong Sun","doi":"10.1109/ICMLA.2006.10","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.10","url":null,"abstract":"As a user preference prediction mechanism, recommendation techniques have been widely used to support personalized information filtering in current e-commerce applications. We build a recommendation tool into the existing Xerox printing workflow configuration system in order to provide new users with a number of solutions that are possibly of their interests. Such solution recommendations can significantly improve the system efficiency and accuracy by reducing workflow generation overhead and helping users quickly identify their needs. In our work, the main challenge is the high sparsity inherent to our application data - most fields have missing values due to a customer's lack of background or uncertainty on their specific needs. We address this problem by using latent semantic indexing (LSI) to merge original sparse data records into dense and semantic records. The generated dense data are then grouped into clusters based on their correlations. These clusters, together with their user patterns and representative workflows, are used to support efficient online workflow recommendation. Our implemented tool is able to achieve 83% accuracy on a dataset of 4569 case logs with 91% average sparseness","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123198754","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}
Most partitional clustering algorithms require the number of desired clusters to be set a priori. Not only is this somewhat counter-intuitive, it is also difficult except in the simplest of situations. By contrast, hierarchical clustering may create partitions with varying numbers of clusters. The actual final partition depends on a threshold placed on the similarity measure used. Given a cluster quality metric, one can efficiently discover an appropriate threshold through a form of semi-supervised learning. This paper shows one such solution for complete-link hierarchical agglomerative clustering using the F-measure and a small subset of labeled examples. Empirical evaluation demonstrates promise
{"title":"Learning the Threshold in Hierarchical Agglomerative Clustering","authors":"K. Daniels, C. Giraud-Carrier","doi":"10.1109/ICMLA.2006.33","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.33","url":null,"abstract":"Most partitional clustering algorithms require the number of desired clusters to be set a priori. Not only is this somewhat counter-intuitive, it is also difficult except in the simplest of situations. By contrast, hierarchical clustering may create partitions with varying numbers of clusters. The actual final partition depends on a threshold placed on the similarity measure used. Given a cluster quality metric, one can efficiently discover an appropriate threshold through a form of semi-supervised learning. This paper shows one such solution for complete-link hierarchical agglomerative clustering using the F-measure and a small subset of labeled examples. Empirical evaluation demonstrates promise","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115405305","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}
Market mechanism design research is playing an important role in computational economics for resolving multi-agent allocation problems. A genetic algorithm was used to design auction mechanisms in order to automatically generate a desired market mechanism in agent based E-markets. In previous research, a hybrid market was studied, in which the probability that buyers rather than sellers are able to quote on a given time step, this probability was adapted by the GA which attempted to minimise Smith's coefficient of convergence. However, in previous experiments, all trading agents involved are of the same type or have identical preferences. This assumption does not hold in real-world markets which are always populated with heterogeneous agents. In this paper, the research of using evolutionary computing methods for auction designs is extended by using heterogeneous trading agents
{"title":"Market Mechanism Designs with Heterogeneous Trading Agents","authors":"Zengchang Qin","doi":"10.1109/ICMLA.2006.34","DOIUrl":"https://doi.org/10.1109/ICMLA.2006.34","url":null,"abstract":"Market mechanism design research is playing an important role in computational economics for resolving multi-agent allocation problems. A genetic algorithm was used to design auction mechanisms in order to automatically generate a desired market mechanism in agent based E-markets. In previous research, a hybrid market was studied, in which the probability that buyers rather than sellers are able to quote on a given time step, this probability was adapted by the GA which attempted to minimise Smith's coefficient of convergence. However, in previous experiments, all trading agents involved are of the same type or have identical preferences. This assumption does not hold in real-world markets which are always populated with heterogeneous agents. In this paper, the research of using evolutionary computing methods for auction designs is extended by using heterogeneous trading agents","PeriodicalId":297071,"journal":{"name":"2006 5th International Conference on Machine Learning and Applications (ICMLA'06)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121635829","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：