In this paper, we present a new approach to enhance the performance of Bayesian classifiers. Our method relies on the combination of two ideas: pairwise classification on the one hand, and threshold optimization on the other hand. Introducing one threshold per pair of classes increases the expressivity of the model, therefore its performance on complex problems such as cost-sensitive problems increases as well. Indeed a comparison of our algorithm to other cost-sensitive approaches shows that it reduces the total misclassification cost.
{"title":"Pairwise Optimization of Bayesian Classifiers for Multi-class Cost-Sensitive Learning","authors":"Clément Charnay, N. Lachiche, Agnès Braud","doi":"10.1109/ICTAI.2013.80","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.80","url":null,"abstract":"In this paper, we present a new approach to enhance the performance of Bayesian classifiers. Our method relies on the combination of two ideas: pairwise classification on the one hand, and threshold optimization on the other hand. Introducing one threshold per pair of classes increases the expressivity of the model, therefore its performance on complex problems such as cost-sensitive problems increases as well. Indeed a comparison of our algorithm to other cost-sensitive approaches shows that it reduces the total misclassification cost.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121012951","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}
V. Dzyuba, M. Leeuwen, Siegfried Nijssen, L. D. Raedt
Pattern mining provides useful tools for exploratory data analysis. Numerous efficient algorithms exist that are able to discover various types of patterns in large datasets. However, the problem of identifying patterns that are genuinely interesting to a particular user remains challenging. Current approaches generally require considerable data mining expertise or effort and hence cannot be used by typical domain experts. We show that it is possible to resolve this issue by interactive learning of user-specific pattern ranking functions, where a user ranks small sets of patterns and a general ranking function is inferred from this feedback by preference learning techniques. We present a general framework for learning pattern ranking functions and propose a number of active learning heuristics that aim at minimizing the required user effort. In particular we focus on Subgroup Discovery, a specific pattern mining task. We evaluate the capacity of the algorithm to learn a ranking of a subgroup set defined by a complex quality measure, given only reasonably small sample rankings. Experiments demonstrate that preference learning has the capacity to learn accurate rankings and that active learning heuristics help reduce the required user effort. Moreover, using learned ranking functions as search heuristics allows discovering subgroups of substantially higher quality than those in the given set. This shows that active preference learning is potentially an important building block of interactive pattern mining systems.
{"title":"Active Preference Learning for Ranking Patterns","authors":"V. Dzyuba, M. Leeuwen, Siegfried Nijssen, L. D. Raedt","doi":"10.1109/ICTAI.2013.85","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.85","url":null,"abstract":"Pattern mining provides useful tools for exploratory data analysis. Numerous efficient algorithms exist that are able to discover various types of patterns in large datasets. However, the problem of identifying patterns that are genuinely interesting to a particular user remains challenging. Current approaches generally require considerable data mining expertise or effort and hence cannot be used by typical domain experts. We show that it is possible to resolve this issue by interactive learning of user-specific pattern ranking functions, where a user ranks small sets of patterns and a general ranking function is inferred from this feedback by preference learning techniques. We present a general framework for learning pattern ranking functions and propose a number of active learning heuristics that aim at minimizing the required user effort. In particular we focus on Subgroup Discovery, a specific pattern mining task. We evaluate the capacity of the algorithm to learn a ranking of a subgroup set defined by a complex quality measure, given only reasonably small sample rankings. Experiments demonstrate that preference learning has the capacity to learn accurate rankings and that active learning heuristics help reduce the required user effort. Moreover, using learned ranking functions as search heuristics allows discovering subgroups of substantially higher quality than those in the given set. This shows that active preference learning is potentially an important building block of interactive pattern mining systems.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114620143","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 study proposes a distance metric learning method based on a clustering index with neighbor relation that simultaneously evaluates inter-and intra-clusters. Our proposed method optimizes a distance transform matrix based on the Mahalanobis distance by utilizing a self-adaptive differential evolution (jDE) algorithm. Our approach directly improves various clustering indices and in principle requires less auxiliary information compared to conventional metric learning methods. We experimentally validated the search efficiency of jDE and the generalization performance.
{"title":"Evolutionary Distance Metric Learning Approach to Semi-supervised Clustering with Neighbor Relations","authors":"Ken-ichi Fukui, S. Ono, Taishi Megano, M. Numao","doi":"10.1109/ICTAI.2013.66","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.66","url":null,"abstract":"This study proposes a distance metric learning method based on a clustering index with neighbor relation that simultaneously evaluates inter-and intra-clusters. Our proposed method optimizes a distance transform matrix based on the Mahalanobis distance by utilizing a self-adaptive differential evolution (jDE) algorithm. Our approach directly improves various clustering indices and in principle requires less auxiliary information compared to conventional metric learning methods. We experimentally validated the search efficiency of jDE and the generalization performance.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114623879","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. Khoshgoftaar, D. Dittman, Randall Wald, Wael Awada
Ensemble classification has been a frequent topic of research in recent years, especially in bioinformatics. The benefits of ensemble classification (less prone to overfitting, increased classification performance, and reduced bias) are a perfect match for a number of issues that plague bioinformatics experiments. This is especially true for DNA microarray data experiments, due to the large amount of data (results from potentially tens of thousands of gene probes per sample) and large levels of noise inherent in the data. This work is a review of the current state of research regarding the applications of ensemble classification for DNA microarrays. We discuss what research thus far has demonstrated, as well as identify the areas where more research is required.
{"title":"A Review of Ensemble Classification for DNA Microarrays Data","authors":"T. Khoshgoftaar, D. Dittman, Randall Wald, Wael Awada","doi":"10.1109/ICTAI.2013.64","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.64","url":null,"abstract":"Ensemble classification has been a frequent topic of research in recent years, especially in bioinformatics. The benefits of ensemble classification (less prone to overfitting, increased classification performance, and reduced bias) are a perfect match for a number of issues that plague bioinformatics experiments. This is especially true for DNA microarray data experiments, due to the large amount of data (results from potentially tens of thousands of gene probes per sample) and large levels of noise inherent in the data. This work is a review of the current state of research regarding the applications of ensemble classification for DNA microarrays. We discuss what research thus far has demonstrated, as well as identify the areas where more research is required.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124058680","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}
Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL considerably outperforms the traditional Single task learning (STL) in terms of prediction accuracy. In this work we develop an MTL based approach for classifying documents that are archived within dual concept hierarchies, namely, DMOZ and Wikipedia. We solve the multi-class classification problem by defining one-versus-rest binary classification tasks for each of the different classes across the two hierarchical datasets. Instead of learning a linear discriminant for each of the different tasks independently, we use a MTL approach with relationships between the different tasks across the datasets established using the non-parametric, lazy, nearest neighbor approach. We also develop and evaluate a transfer learning (TL) approach and compare the MTL (and TL) methods against the standard single task learning and semi-supervised learning approaches. Our empirical results demonstrate the strength of our developed methods that show an improvement especially when there are fewer number of training examples per classification task.
{"title":"Classifying Documents within Multiple Hierarchical Datasets Using Multi-task Learning","authors":"Azad Naik, Anveshi Charuvaka, H. Rangwala","doi":"10.1109/ICTAI.2013.65","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.65","url":null,"abstract":"Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL considerably outperforms the traditional Single task learning (STL) in terms of prediction accuracy. In this work we develop an MTL based approach for classifying documents that are archived within dual concept hierarchies, namely, DMOZ and Wikipedia. We solve the multi-class classification problem by defining one-versus-rest binary classification tasks for each of the different classes across the two hierarchical datasets. Instead of learning a linear discriminant for each of the different tasks independently, we use a MTL approach with relationships between the different tasks across the datasets established using the non-parametric, lazy, nearest neighbor approach. We also develop and evaluate a transfer learning (TL) approach and compare the MTL (and TL) methods against the standard single task learning and semi-supervised learning approaches. Our empirical results demonstrate the strength of our developed methods that show an improvement especially when there are fewer number of training examples per classification task.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130213396","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}
Recently, MaxSAT reasoning has been shown to be powerful in computing upper bounds for the cardinality of a maximum clique of a graph. However, existing upper bounds based on MaxSAT reasoning have two drawbacks: (1)at every node of the search tree, MaxSAT reasoning has to be performed from scratch to compute an upper bound and is time-consuming, (2) due to the NP-hardness of the MaxSAT problem, MaxSAT reasoning generally cannot be complete at anode of a search tree, and may not give an upper bound tight enough for pruning search space. In this paper, we propose an incremental upper bound and combine it with MaxSAT reasoning to remedy the two drawbacks. The new approach is used to develop an efficient branch-and-bound algorithm for MaxClique, called IncMaxCLQ. We conduct experiments to show the complementarity of the incremental upper bound and MaxSAT reasoning and to compare IncMaxCLQ with several state-of-the-art algorithms for MaxClique.
{"title":"Combining MaxSAT Reasoning and Incremental Upper Bound for the Maximum Clique Problem","authors":"Chu Min Li, Zhiwen Fang, Ke Xu","doi":"10.1109/ICTAI.2013.143","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.143","url":null,"abstract":"Recently, MaxSAT reasoning has been shown to be powerful in computing upper bounds for the cardinality of a maximum clique of a graph. However, existing upper bounds based on MaxSAT reasoning have two drawbacks: (1)at every node of the search tree, MaxSAT reasoning has to be performed from scratch to compute an upper bound and is time-consuming, (2) due to the NP-hardness of the MaxSAT problem, MaxSAT reasoning generally cannot be complete at anode of a search tree, and may not give an upper bound tight enough for pruning search space. In this paper, we propose an incremental upper bound and combine it with MaxSAT reasoning to remedy the two drawbacks. The new approach is used to develop an efficient branch-and-bound algorithm for MaxClique, called IncMaxCLQ. We conduct experiments to show the complementarity of the incremental upper bound and MaxSAT reasoning and to compare IncMaxCLQ with several state-of-the-art algorithms for MaxClique.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134005653","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}
Arunprasath Shankar, B. Singh, F. Wolff, C. Papachristou
In a component based engineering approach, a system can be envisioned as an assembly of reusable and independently developed components. In order to produce automated tools to support the selection and assembly of components, precise selection and retrieval strategies based on product specifications are needed. Conventional approaches use keyword based models for automatically retrieving specification documents that match a set of requirements. These approaches typically fail to mine relationships and spotlight excessively on injective matching. In this paper, we propose a Neuro-fuzzy Concept based Inference System (NEFCIS) which is a novel hybrid expert system approach targeted to extract concepts and retrieve relevant information using the excerpted concepts rather than only keywords. By infusing fuzzy logic into our model, we can process the queries with greater precision and produce deeper knowledge inferences. We describe the basic principles of the proposed methodology and illustrate it with example scenarios.
{"title":"NEFCIS: Neuro-fuzzy Concept Based Inference System for Specification Mining","authors":"Arunprasath Shankar, B. Singh, F. Wolff, C. Papachristou","doi":"10.1109/ICTAI.2013.58","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.58","url":null,"abstract":"In a component based engineering approach, a system can be envisioned as an assembly of reusable and independently developed components. In order to produce automated tools to support the selection and assembly of components, precise selection and retrieval strategies based on product specifications are needed. Conventional approaches use keyword based models for automatically retrieving specification documents that match a set of requirements. These approaches typically fail to mine relationships and spotlight excessively on injective matching. In this paper, we propose a Neuro-fuzzy Concept based Inference System (NEFCIS) which is a novel hybrid expert system approach targeted to extract concepts and retrieve relevant information using the excerpted concepts rather than only keywords. By infusing fuzzy logic into our model, we can process the queries with greater precision and produce deeper knowledge inferences. We describe the basic principles of the proposed methodology and illustrate it with example scenarios.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"86 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132788429","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}
Laurie Serrano, M. Bouzid, Thierry Charnois, S. Brunessaux, B. Grilhères
Due to the considerable increase of freely available data, the discovery of relevant information from textual content is a critical challenge. The work presented here takes part in ongoing researches to develop a global knowledge gathering system. It aims at building knowledge sheets summarizing all the pieces of information we know about events extracted from text. For this sake, we define a global process bringing together different methods and components from multiple domains of research.
{"title":"Events Extraction and Aggregation for Open Source Intelligence: From Text to Knowledge","authors":"Laurie Serrano, M. Bouzid, Thierry Charnois, S. Brunessaux, B. Grilhères","doi":"10.1109/ICTAI.2013.83","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.83","url":null,"abstract":"Due to the considerable increase of freely available data, the discovery of relevant information from textual content is a critical challenge. The work presented here takes part in ongoing researches to develop a global knowledge gathering system. It aims at building knowledge sheets summarizing all the pieces of information we know about events extracted from text. For this sake, we define a global process bringing together different methods and components from multiple domains of research.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133431128","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}
Solving Constraint Satisfaction Problems (CSPs) through Boolean Satisfiability (SAT) requires suitable encodings for translating CSPs to equivalent SAT instances that can not only be efficiently generated, but also efficiently solved by SAT solvers. In this paper we investigate hierarchical and hybrid encodings, as proposed by Velev, namely a previously studied log-direct encoding, and a new combination, the log-order encoding. Experiments on different domain problems with these hierarchical encodings demonstrate their significant promise in practice. Our experiments show that the log-direct encoding significantly outperforms the direct encoding (typically by one or two orders of magnitude) taking advantage not only of the more concise representation, but also of the better capability of the log-direct encoding to represent interval variables. We also show that the log-order encoding is competitive with the order encoding, although more studies are required to understand the tradeoff between the fewer variables and longer clauses in the former, when expressing complex CSP constraints.
{"title":"Application of Hierarchical Hybrid Encodings to Efficient Translation of CSPs to SAT","authors":"Van-Hau Nguyen, M. Velev, P. Barahona","doi":"10.1109/ICTAI.2013.154","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.154","url":null,"abstract":"Solving Constraint Satisfaction Problems (CSPs) through Boolean Satisfiability (SAT) requires suitable encodings for translating CSPs to equivalent SAT instances that can not only be efficiently generated, but also efficiently solved by SAT solvers. In this paper we investigate hierarchical and hybrid encodings, as proposed by Velev, namely a previously studied log-direct encoding, and a new combination, the log-order encoding. Experiments on different domain problems with these hierarchical encodings demonstrate their significant promise in practice. Our experiments show that the log-direct encoding significantly outperforms the direct encoding (typically by one or two orders of magnitude) taking advantage not only of the more concise representation, but also of the better capability of the log-direct encoding to represent interval variables. We also show that the log-order encoding is competitive with the order encoding, although more studies are required to understand the tradeoff between the fewer variables and longer clauses in the former, when expressing complex CSP constraints.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133783799","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}
Tianxia Gong, Nengli Lim, Li Cheng, Hwee Kuan Lee, Bolan Su, C. Tan, Shimiao Li, C. Lim, B. Pang, C. Lee
Computer aided diagnosis (CAD) in medical imaging is of growing interest in recent years. Our proposed CAD system aims to enhance diagnosis and prognosis of traumatic brain injury (TBI) patients with hematomas. Hematoma caused by blood vessel rupture is the major lesion in TBI cases and is usually assessed using head computed tomography (CT). In our CAD system, we segment the hematoma region from each slice of a CT series, extract features from the hematoma segments, and automatically classify the hematoma types using machine learning methods. We propose two sets of shape based features for each segmented hematoma region. The first set contains primitive features describing the overall shape of a hematoma region. The features in the second set are based on the dissimilarities of the shapes of hematoma regions measured by geodesic distances. After feature extraction, we classify the hematoma regions into three types -- epidural hematoma, sub-dural hematoma, and intracerebral hematoma, using random forest. Each tree of the random forest votes one class for each hematoma, and the random forest takes the class label with the majority votes for the hematoma. As hematomas are volumetric in nature, some hematomas are observed across several consecutive slices in the same CT series. For each class, we add the votes from each hematoma slice that comprises the volumetric hematoma in that class, then we take the class with the majority of the summed votes as the class label for that volumetric hematoma. The overall classification accuracies for hematoma region from each CT slice are 80.7%, 81.3%, and 81.1% using primitive features only, geodesic distance features only, or both sets of features, respectively. For volumetric hematoma classification, the overall accuracies are 80.9%, 81.5%, and 81.5% respectively. The results are promising to radiologists and neurosurgeons specialized in this field of research.
{"title":"Finding Distinctive Shape Features for Automatic Hematoma Classification in Head CT Images from Traumatic Brain Injuries","authors":"Tianxia Gong, Nengli Lim, Li Cheng, Hwee Kuan Lee, Bolan Su, C. Tan, Shimiao Li, C. Lim, B. Pang, C. Lee","doi":"10.1109/ICTAI.2013.45","DOIUrl":"https://doi.org/10.1109/ICTAI.2013.45","url":null,"abstract":"Computer aided diagnosis (CAD) in medical imaging is of growing interest in recent years. Our proposed CAD system aims to enhance diagnosis and prognosis of traumatic brain injury (TBI) patients with hematomas. Hematoma caused by blood vessel rupture is the major lesion in TBI cases and is usually assessed using head computed tomography (CT). In our CAD system, we segment the hematoma region from each slice of a CT series, extract features from the hematoma segments, and automatically classify the hematoma types using machine learning methods. We propose two sets of shape based features for each segmented hematoma region. The first set contains primitive features describing the overall shape of a hematoma region. The features in the second set are based on the dissimilarities of the shapes of hematoma regions measured by geodesic distances. After feature extraction, we classify the hematoma regions into three types -- epidural hematoma, sub-dural hematoma, and intracerebral hematoma, using random forest. Each tree of the random forest votes one class for each hematoma, and the random forest takes the class label with the majority votes for the hematoma. As hematomas are volumetric in nature, some hematomas are observed across several consecutive slices in the same CT series. For each class, we add the votes from each hematoma slice that comprises the volumetric hematoma in that class, then we take the class with the majority of the summed votes as the class label for that volumetric hematoma. The overall classification accuracies for hematoma region from each CT slice are 80.7%, 81.3%, and 81.1% using primitive features only, geodesic distance features only, or both sets of features, respectively. For volumetric hematoma classification, the overall accuracies are 80.9%, 81.5%, and 81.5% respectively. The results are promising to radiologists and neurosurgeons specialized in this field of research.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133856660","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：