IP-LSSVM: A two-step sparse classifier

We present in this work a two-step sparse classifier called IP-LSSVM which is based on Least Squares Support Vector Machine (LS-SVM). The formulation of LS-SVM aims at solving the learning problem with a system of linear equations. Although this solution is simpler, there is a loss of sparseness in the feature vectors. Many works on LS-SVM are focused on improving support vectors representation in the least squares approach, since they correspond to the only vectors that must be stored for further usage of the machine, which can also be directly used as a reduced subset that represents the initial one. The proposed classifier incorporates the advantages of either SVM and LS-SVM: automatic detection of support vectors and a solution obtained simply by the solution of systems of linear equations. IP-LSSVM was compared with other sparse LS-SVM classifiers from literature, and RRS+LS-SVM. The experiments were performed on four important benchmark databases in Machine Learning and on two artificial databases created to show visually the support vectors detected. The results show that IP-LSSVM represents a viable alternative to SVMs, since both have similar features, supported by literature results and yet IP-LSSVM has a simpler and more understandable formulation.     

Multi-layer sparse coding model-based ship detection for optical remote-sensing images

Ship detection plays an important role in remote-sensing image processing. In this article, we propose a multi-layer sparse coding model-based ship detection (MSCMSD) method, integrating bottom-up and top-down mechanisms, for ship detection with high-resolution remote-sensing images. The multi-layer sparse coding model was designed to reveal the way how information is processed by human visual system. It is adopted in MSCMSD to detect candidate regions containing ships before any further processing. To detect ships from candidate regions, an omnidirectional solution is also proposed for deformable parts model-based ship detection. As demonstrated in the experiments, MSCMSD can detect ships from optical remote-sensing images with a higher accuracy than other state-of-the-art algorithms.     

A sparse nearest mean classifier for high dimensional multi-class problems

The analysis of small datasets in high dimensional spaces is inherently difficult. For two-class classification problems there are a few methods that are able to face the so-called curse of dimensionality. However, for multi-class sparsely sampled datasets there are hardly any specific methods. In this paper, we propose four multi-class classifier alternatives that effectively deal with this type of data. Moreover, these methods implicitly select a feature subset optimized for class separation. Accordingly, they are especially interesting for domains where an explanation of the problem in terms of the original features is desired.In the experiments, we applied the proposed methods to an MDMA powders dataset, where the problem was to recognize the production process. It turns out that the proposed multi-class classifiers perform well, while the few utilized features correspond to known MDMA synthesis ingredients. In addition, to show the general applicability of the methods, we applied them to several other sparse datasets, ranging from bioinformatics to chemometrics datasets having as few as tens of samples in tens to even thousands of dimensions and three to four classes. The proposed methods had the best average performance, while very few dimensions were effectively utilized.     

A sparse Bayesian approach for joint feature selection and classifier learning

In this paper we present a new method for Joint Feature Selection and Classifier Learning using a sparse Bayesian approach. These tasks are performed by optimizing a global loss function that includes a term associated with the empirical loss and another one representing a feature selection and regularization constraint on the parameters. To minimize this function we use a recently proposed technique, the Boosted Lasso algorithm, that follows the regularization path of the empirical risk associated with our loss function. We develop the algorithm for a well known non-parametrical classification method, the relevance vector machine, and perform experiments using a synthetic data set and three databases from the UCI Machine Learning Repository. The results show that our method is able to select the relevant features, increasing in some cases the classification accuracy when feature selection is performed.     

A distributed approach to enabling privacy-preserving model-based classifier training

This paper proposes a novel approach for privacy-preserving distributed model-based classifier training. Our approach is an important step towards supporting customizable privacy modeling and protection. It consists of three major steps. First, each data site independently learns a weak concept model (i.e., local classifier) for a given data pattern or concept by using its own training samples. An adaptive EM algorithm is proposed to select the model structure and estimate the model parameters simultaneously. The second step deals with combined classifier training by integrating the weak concept models that are shared from multiple data sites. To reduce the data transmission costs and the potential privacy breaches, only the weak concept models are sent to the central site and synthetic samples are directly generated from these shared weak concept models at the central site. Both the shared weak concept models and the synthetic samples are then incorporated to learn a reliable and complete global concept model. A computational approach is developed to automatically achieve a good trade off between the privacy disclosure risk, the sharing benefit and the data utility. The third step deals with validating the combined classifier by distributing the global concept model to all these data sites in the collaboration network while at the same time limiting the potential privacy breaches. Our approach has been validated through extensive experiments carried out on four UCI machine learning data sets and two image data sets.

基于级联稀疏表示分类器的人脸识别算法

针对基于稀疏表示的分类器算法复杂度高、识别速度较慢的问题,提出了基于级联稀疏表示分类器的人脸识别算法。该算法采用级联的思想,通过多次重复使用基于稀疏表示的分类器,逐级精确确定待分类样本所在的类,降低了计算复杂度和识别难度,达到了识别率高、鲁棒性强、识别速度快的目标。     

Aggregative model-based classifier ensemble for improving land-use/cover classification of Landsat TM Images

This article proposes a new approach to improve the classification performance of remotely sensed images with an aggregative model based on classifier ensemble (AMCE). AMCE is a multi-classifier system with two procedures, namely ensemble learning and predictions combination. Two ensemble algorithms (Bagging and AdaBoost.M1) were used in the ensemble learning process to stabilize and improve the performance of single classifiers (i.e. maximum likelihood classifier, minimum distance classifier, back propagation neural network, classification and regression tree, and support vector machine (SVM)). Prediction results from single classifiers were integrated according to a diversity measurement with an averaged double-fault indicator and different combination strategies (i.e. weighted vote, Bayesian product, logarithmic consensus, and behaviour knowledge space). The suitability of the AMCE model was examined using a Landsat Thematic Mapper (TM) image of Dongguan city (Guangdong, China), acquired on 2 January 2009. Experimental results show that the proposed model was significantly better than the most accurate single classification (i.e. SVM) in terms of classification accuracy (i.e. from 88.83% to 92.45%) and kappa coefficient (i.e. from 0.8624 to 0.9088). A stepwise comparison illustrates that both ensemble learning and predictions combination with the AMCE model improved classification.     

Vision for Robotics: a tool for model-based object tracking

Vision for Robotics (V4R) is a software package for tracking rigid objects in unknown surroundings. Its output is the 3-D pose of the target object, which can be further used as an input to control, e.g., the end effector of a robot. The major goals are tracking at camera frame rate and robustness. The latter is achieved by performing cue integration in order to compensate for weaknesses of individual cues. Therefore, features such as lines and ellipses are not only extracted from 2-D images, but the 3-D model and the pose of the object are exploited also.     

Wodel-Test: a model-based framework for language-independent mutation testing

Software and Systems Modeling - Mutation testing (MT) targets the assessment of test cases by measuring their efficiency to detect faults. This technique involves modifying the program under test...     

Learning classifier systems: a survey

Learning classifier systems (LCSs) are rule- based systems that automatically build their ruleset. At the origin of Holland’s work, LCSs were seen as a model of the emergence of cognitive abilities thanks to adaptive mechanisms, particularly evolutionary processes. After a renewal of the field more focused on learning, LCSs are now considered as sequential decision problem-solving systems endowed with a generalization property. Indeed, from a Reinforcement Learning point of view, LCSs can be seen as learning systems building a compact representation of their problem thanks to generalization. More recently, LCSs have proved efficient at solving automatic classification tasks. The aim of the present contribution is to describe the state-of- the-art of LCSs, emphasizing recent developments, and focusing more on the sequential decision domain than on automatic classification.     

Decision rules for a hierarchical classifier

Two hierarchical classifier strategies which minimize the global and local probabilities of misclassification, respectively are presented. The modified version of the k-NN rule for a hierarchical classifier is proposed. Numerical examples are given.     

VILO: a rapid learning nearest-neighbor classifier for malware triage

VILO is a lazy learner system designed for malware classification and triage. It implements a nearest neighbor (NN) algorithm with similarities computed over Term Frequency $\times $ Inverse Document Frequency (TFIDF) weighted opcode mnemonic permutation features (N-perms). Being an NN-classifier, VILO makes minimal structural assumptions about class boundaries, and thus is well suited for the constantly changing malware population. This paper presents an extensive study of application of VILO in malware analysis. Our experiments demonstrate that (a) VILO is a rapid learner of malware families, i.e., VILO’s learning curve stabilizes at high accuracies quickly (training on less than 20 variants per family is sufficient); (b) similarity scores derived from TDIDF weighted features should primarily be treated as ordinal measurements; and (c) VILO with N-perm feature vectors outperforms traditional N-gram feature vectors when used to classify real-world malware into their respective families.     

Reflectance from images: a model-based approach for human faces

In this paper, we present an image-based framework that acquires the reflectance properties of a human face. A range scan of the face is not required. Based on a morphable face model, the system estimates the 3D shape and establishes point-to-point correspondence across images taken from different viewpoints and across different individuals' faces. This provides a common parameterization of all reconstructed surfaces that can be used to compare and transfer BRDF data between different faces. Shape estimation from images compensates deformations of the face during the measurement process, such as facial expressions. In the common parameterization, regions of homogeneous materials on the face surface can be defined a priori. We apply analytical BRDF models to express the reflectance properties of each region and we estimate their parameters in a least-squares fit from the image data. For each of the surface points, the diffuse component of the BRDF is locally refined, which provides high detail. We present results for multiple analytical BRDF models, rendered at novel orientations and lighting conditions.     

When sparse coding meets ranking: a joint framework for learning sparse codes and ranking scores

Neural Computing and Applications - Sparse coding, which represents a data point as a sparse reconstruction code with regard to a dictionary, has been a popular data representation method....     

Co-eye: a multi-resolution ensemble classifier for symbolically approximated time series

Machine Learning - Time series classification (TSC) is a challenging task that attracted many researchers in the last few years. One main challenge in TSC is the diversity of domains where time...     

Test case prioritization techniques for model-based testing: a replicated study

Recently, several test case prioritization (TCP) techniques have been proposed to order test cases for achieving a goal during test execution, particularly, revealing faults sooner. In the model-based testing (MBT) context, such techniques are usually based on heuristics related to structural elements of the model and derived test cases. In this sense, techniques’ performance may vary due to a number of factors. While empirical studies comparing the performance of TCP techniques have already been presented in literature, there is still little knowledge, particularly in the MBT context, about which factors may influence the outcomes suggested by a TCP technique. In a previous family of empirical studies focusing on labeled transition systems, we identified that the model layout, i.e., amount of branches, joins, and loops in the model, alone may have little influence on the effectiveness of TCP techniques investigated, whereas characteristics of test cases that actually fail definitely influences this aspect. However, we considered only synthetic artifacts in the study, which reduced the ability of representing properly the reality. In this paper, we present a replication of one of these studies, now with a larger and more representative selection of techniques and considering test suites from industrial systems as experimental objects. Our objective is to find out whether the results remain while increasing the validity in comparison to the original study. Results reinforce that there is no best performer among the investigated techniques and characteristics of test cases that fail represent an important factor, although adaptive random-based techniques are less affected by it.     

Teallach: a model-based user interface development environment for object databases

Model-based user interface development environments show promise for improving the productivity of user interface developers, and possibly for improving the quality of developed interfaces. While model-based techniques have previously been applied to the area of database interfaces, they have not been specifically targeted at the important area of object database applications. Such applications make use of models that are semantically richer than their relational counterparts in terms of both data structures and application functionality. In general, model-based techniques have not addressed how the information referenced in such applications is manifested within the described models, and is utilised within the generated interface itself. This lack of experience with such systems has led to many model-based projects providing minimal support for certain features that are essential to such data intensive applications, and has prevented object database interface developers in particular from benefiting from model-based techniques. This paper presents the Teallach model-based user interface development environment for object databases, describing the models it supports, the relationships between these models, the tool used to construct interfaces using the models and the generation of Java programs from the declarative models. Distinctive features of Teallach include comprehensive facilities for linking models, a flexible development method, an open architecture, and the generation of running applications based on the models constructed by designers.