Boosting text segmentation via progressive classification

A novel approach for reconciling tuples stored as free text into an existing attribute schema is proposed. The basic idea is to subject the available text to progressive classification, i.e., a multi-stage classification scheme where, at each intermediate stage, a classifier is learnt that analyzes the textual fragments not reconciled at the end of the previous steps. Classification is accomplished by an ad hoc exploitation of traditional association mining algorithms, and is supported by a data transformation scheme which takes advantage of domain-specific dictionaries/ontologies. A key feature is the capability of progressively enriching the available ontology with the results of the previous stages of classification, thus significantly improving the overall classification accuracy. An extensive experimental evaluation shows the effectiveness of our approach.     

Conceptual equivalence for contrast mining in classification learning

Learning often occurs through comparing. In classification learning, in order to compare data groups, most existing methods compare either raw instances or learned classification rules against each other. This paper takes a different approach, namely conceptual equivalence, that is, groups are equivalent if their underlying concepts are equivalent while their instance spaces do not necessarily overlap and their rule sets do not necessarily present the same appearance. A new methodology of comparing is proposed that learns a representation of each group’s underlying concept and respectively cross-exams one group’s instances by the other group’s concept representation. The innovation is fivefold. First, it is able to quantify the degree of conceptual equivalence between two groups. Second, it is able to retrace the source of discrepancy at two levels: an abstract level of underlying concepts and a specific level of instances. Third, it applies to numeric data as well as categorical data. Fourth, it circumvents direct comparisons between (possibly a large number of) rules that demand substantial effort. Fifth, it reduces dependency on the accuracy of employed classification algorithms. Empirical evidence suggests that this new methodology is effective and yet simple to use in scenarios such as noise cleansing and concept-change learning.     

Automatic Construction and Verification of Isotopy Invariants

We extend our previous study of the automatic construction of isomorphic classification theorems for algebraic domains by considering the isotopy equivalence relation. Isotopism is an important generalisation of isomorphism, and is studied by mathematicians in domains such as loop theory. This extension was not straightforward, and we had to solve two major technical problems, namely, generating and verifying isotopy invariants. Concentrating on the domain of loop theory, we have developed three novel techniques for generating isotopic invariants, by using the notion of universal identities and by using constructions based on subblocks. In addition, given the complexity of the theorems that verify that a conjunction of the invariants form an isotopy class, we have developed ways of simplifying the problem of proving these theorems. Our techniques employ an interplay of computer algebra, model generation, theorem proving, and satisfiability-solving methods. To demonstrate the power of the approach, we generate isotopic classification theorems for loops of size 6 and 7, which extend the previously known enumeration results. This work was previously beyond the capabilities of automated reasoning techniques. The author’s work was supported by EPSRC MathFIT grant GR/S31099.     

A knowledge-based approach to manage information systems interoperability

Interoperability is a key property of enterprise applications, which is hard to achieve due to the large number of interoperating components and semantic heterogeneity. The inherent complexity of interoperability problems implies that there exists no silver bullet to solve them. Rather, the knowledge about how to solve wicked interoperability problems is hidden in the application cases that expose those problems. The paper addresses the question of how to organise and use method knowledge to resolve interoperability problems. We propose the structure of a knowledge-based system that can deliver situation-specific solutions, called method chunks. Situational Method Engineering promotes modularisation and formalisation of method knowledge in the form of reusable method chunks, which can be combined to compose a situation-specific method. The method chunks are stored in a method chunk repository. In order to cater for management and retrieval, we introduce an Interoperability Classification Framework, which is used to classify and tag method chunks and to assess the project situation in which they are to be used. The classification framework incorporates technical as well as business and organisational aspects of interoperability. This is an important feature as interoperability problems typically are multifaceted spanning multiple aspects. We have applied the approach to analyse an industry case from the insurance sector to identify and classify a set of method chunks.     

Rollout sampling approximate policy iteration

Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car.     

Evaluation of tile–wall bonding integrity based on impact acoustics and support vector machine

It is well recognized that the impact-acoustic emissions contain information that can indicate the presence of the adhesive defects in the bonding structures. In our previous papers, artificial neural network (ANN) was adopted to assess the bonding integrity of the tile–walls with the feature extracted from the power spectral density (PSD) of the impact-acoustic signals acting as the input of classifier. However, in addition to the inconvenience posed by the general drawbacks such as long training time and large number of training samples needed, the performance of the classic ANN classifier is deteriorated by the similar spectral characteristics between different bonding status caused by abnormal impacts. In this paper our previous works was developed by the employment of the least-squares support vector machine (LS-SVM) classifier instead of the ANN to derive a bonding integrity recognition approach with better reliability and enhanced immunity to surface roughness. With the help of the specially designed artificial sample slabs, experiments results obtained with the proposed method are provided and compared with that using the ANN classifier, demonstrating the effectiveness of the present strategy.     

Learning traversability models for autonomous mobile vehicles

Autonomous mobile robots need to adapt their behavior to the terrain over which they drive, and to predict the traversability of the terrain so that they can effectively plan their paths. Such robots usually make use of a set of sensors to investigate the terrain around them and build up an internal representation that enables them to navigate. This paper addresses the question of how to use sensor data to learn properties of the environment and use this knowledge to predict which regions of the environment are traversable. The approach makes use of sensed information from range sensors (stereo or ladar), color cameras, and the vehicle’s navigation sensors. Models of terrain regions are learned from subsets of pixels that are selected by projection into a local occupancy grid. The models include color and texture as well as traversability information obtained from an analysis of the range data associated with the pixels. The models are learned without supervision, deriving their properties from the geometry and the appearance of the scene. The models are used to classify color images and assign traversability costs to regions. The classification does not use the range or position information, but only color images. Traversability determined during the model-building phase is stored in the models. This enables classification of regions beyond the range of stereo or ladar using the information in the color images. The paper describes how the models are constructed and maintained, how they are used to classify image regions, and how the system adapts to changing environments. Examples are shown from the implementation of this algorithm in the DARPA Learning Applied to Ground Robots (LAGR) program, and an evaluation of the algorithm against human-provided ground truth is presented.

Integration of independent component analysis and neural networks for ECG beat classification

In this paper, we propose a scheme to integrate independent component analysis (ICA) and neural networks for electrocardiogram (ECG) beat classification. The ICA is used to decompose ECG signals into weighted sum of basic components that are statistically mutual independent. The projections on these components, together with the RR interval, then constitute a feature vector for the following classifier. Two neural networks, including a probabilistic neural network (PNN) and a back-propagation neural network (BPNN), are employed as classifiers. ECG samples attributing to eight different beat types were sampled from the MIT-BIH arrhythmia database for experiments. The results show high classification accuracy of over 98% with either of the two classifiers. Between them, the PNN shows a slightly better performance than BPNN in terms of accuracy and robustness to the number of ICA-bases. The impressive results prove that the integration of independent component analysis and neural networks, especially PNN, is a promising scheme for the computer-aided diagnosis of heart diseases based on ECG.     

An efficient bit-based feature selection method

Feature selection is about finding useful (relevant) features to describe an application domain. Selecting relevant and enough features to effectively represent and index the given dataset is an important task to solve the classification and clustering problems intelligently. This task is, however, quite difficult to carry out since it usually needs a very time-consuming search to get the features desired. This paper proposes a bit-based feature selection method to find the smallest feature set to represent the indexes of a given dataset. The proposed approach originates from the bitmap indexing and rough set techniques. It consists of two-phases. In the first phase, the given dataset is transformed into a bitmap indexing matrix with some additional data information. In the second phase, a set of relevant and enough features are selected and used to represent the classification indexes of the given dataset. After the relevant and enough features are selected, they can be judged by the domain expertise and the final feature set of the given dataset is thus proposed. Finally, the experimental results on different data sets also show the efficiency and accuracy of the proposed approach.     

基于IPC知识结构的专利自动分类方法

基于国际专利分类号的层次结构,利用自身的类别描述信息,建立了不同层次的类别特征向量,结合现有专利进行修正训练,分别在各层次上采用经典的KNN算法实现专利的自动分类。实验结果表明：该方法的分类效果在部、大类、小类层次上表现较好。经过修正训练后的分类性能有所提高。