The tasks of semantic web service (discovery, selection, composition, and execution) are supposed to enable seamless interoperation between systems, whereby human intervention is kept at a minimum. In the field of Web service description research, the exploitation of descriptions of services through semantics is a better support for the life-cycle of Web services. The large number of developed ontologies, languages of representations, and integrated frameworks supporting the discovery, composition and invocation of services is a good indicator that research in the field of Semantic Web Services (SWS) has been considerably active. We provide in this paper a detailed classification of the approaches and solutions, indicating their core characteristics and objectives required and provide indicators for the interested reader to follow up further insights and details about these solutions and related software.
A novel methodology for gender classification is presented in this paper. It extracts feature from local region of a face using gray color intensity difference. The facial area is divided into sub-regions and GDP histogram extracted from those regions are concatenated into a single vector to represent the face. The classification accuracy obtained by using support vector machine has outperformed all traditional feature descriptors for gender classification. It is evaluated on the images collected from FERET database and obtained very high accuracy.
This report describes the suicidality prediction models created under the DARPA DCAPS program in association with the Durkheim Project [http://durkheimproject.org/]. The models were built primarily from unstructured text (free-format clinician notes) for several hundred patient records obtained from the Veterans Health Administration (VHA). The models were constructed using a genetic programming algorithm applied to bag-of-words and bag-of-phrases datasets. The influence of additional structured data was explored but was found to be minor. Given the small dataset size, classification between cohorts was high fidelity (98%). Cross-validation suggests these models are reasonably predictive, with an accuracy of 50% to 69% on five rotating folds, with ensemble averages of 58% to 67%. One particularly noteworthy result is that word-pairs can dramatically improve classification accuracy; but this is the case only when one of the words in the pair is already known to have a high predictive value. By contrast, the set of all possible word-pairs does not improve on a simple bag-of-words model.
In recent years, Printed Circuit Boards (PCB) have become the backbone of a large number of consumer electronic devices leading to a surge in their production. This has made it imperative to employ automatic inspection systems to identify manufacturing defects in PCB before they are installed in the respective systems. An important task in this regard is the classification of defects as either true or pseudo defects, which decides if the PCB is to be re-manufactured or not. This work proposes a novel approach to detect most common defects in the PCBs. The problem has been approached by employing highly discriminative features based on multi-scale wavelet transform, which are further boosted by using a kernalized version of the support vector machines (SVM). A real world printed circuit board dataset has been used for quantitative analysis. Experimental results demonstrated the efficacy of the proposed method.
The functional and structural representation of the brain as a complex network is marked by the fact that the comparison of noisy and intrinsically correlated high-dimensional structures between experimental conditions or groups shuns typical mass univariate methods. Furthermore most network estimation methods cannot distinguish between real and spurious correlation arising from the convolution due to nodes' interaction, which thus introduces additional noise in the data. We propose a machine learning pipeline aimed at identifying multivariate differences between brain networks associated to different experimental conditions. The pipeline (1) leverages the deconvolved individual contribution of each edge and (2) maps the task into a sparse classification problem in order to construct the associated "sparse deconvolved predictive network", i.e., a graph with the same nodes of those compared but whose edge weights are defined by their relevance for out of sample predictions in classification. We present an application of the proposed method by decoding the covert attention direction (left or right) based on the single-trial functional connectivity matrix extracted from high-frequency magnetoencephalography (MEG) data. Our results demonstrate how network deconvolution matched with sparse classification methods outperforms typical approaches for MEG decoding.
Combining information from different sources is a common way to improve classification accuracy in Brain-Computer Interfacing (BCI). For instance, in small sample settings it is useful to integrate data from other subjects or sessions in order to improve the estimation quality of the spatial filters or the classifier. Since data from different subjects may show large variability, it is crucial to weight the contributions according to importance. Many multi-subject learning algorithms determine the optimal weighting in a separate step by using heuristics, however, without ensuring that the selected weights are optimal with respect to classification. In this work we apply Multiple Kernel Learning (MKL) to this problem. MKL has been widely used for feature fusion in computer vision and allows to simultaneously learn the classifier and the optimal weighting. We compare the MKL method to two baseline approaches and investigate the reasons for performance improvement.
The Internet has dramatically changed the relationship among people and their relationships with others people and made the valuable information available for the users. Email is the service, which the Internet provides today for its own users; this service has attracted most of the users' attention due to the low cost. Along with the numerous benefits of Email, one of the weaknesses of this service is that the number of received emails is continually being enhanced, thus the ways are needed to automatically filter these disturbing letters. Most of these filters utilize a combination of several techniques such as the Black or white List, using the keywords and so on in order to identify the spam more accurately In this paper, we introduce a new method to classify the spam. We are seeking to increase the accuracy of Email classification by combining the output of several decision trees and the concept of ontology.
The ability for an autonomous agent to self-localise is directly proportional to the accuracy and precision with which it can perceive salient features within its local environment. The identification of such features by recognising geometric profile allows robustness against lighting variations, which is necessary in most industrial robotics applications. This paper details a framework by which the random sample consensus (RANSAC) algorithm, often applied to parameter fitting in linear models, can be extended to identify higher-order geometric features. Goalpost identification within humanoid robot soccer is investigated as an application, with the developed system yielding an order-of-magnitude improvement in classification performance relative to a traditional histogramming methodology.
Significant success has been reported recently using deep neural networks for classification. Such large networks can be computationally intensive, even after training is over. Implementing these trained networks in hardware chips with a limited precision of synaptic weights may improve their speed and energy efficiency by several orders of magnitude, thus enabling their integration into small and low-power electronic devices. With this motivation, we develop a computationally efficient learning algorithm for multilayer neural networks with binary weights, assuming all the hidden neurons have a fan-out of one. This algorithm, derived within a Bayesian probabilistic online setting, is shown to work well for both synthetic and real-world problems, performing comparably to algorithms with real-valued weights, while retaining computational tractability.
In this paper, we apply Classification Restricted Boltzmann Machine (ClassRBM) to the problem of predicting breast cancer recurrence. According to the Polish National Cancer Registry, in 2010 only, the breast cancer caused almost 25% of all diagnosed cases of cancer in Poland. We propose how to use ClassRBM for predicting breast cancer return and discovering relevant inputs (symptoms) in illness reappearance. Next, we outline a general probabilistic framework for learning Boltzmann machines with masks, which we refer to as Dropping. The fashion of generating masks leads to different learning methods, i.e., DropOut, DropConnect. We propose a new method called DropPart which is a generalization of DropConnect. In DropPart the Beta distribution instead of Bernoulli distribution in DropConnect is used. At the end, we carry out an experiment using real-life dataset consisting of 949 cases, provided by the Institute of Oncology Ljubljana.
In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical use of the confusion matrix of a classifier as an error measure; this puts our contribution in the line of work aiming at dealing with performance measure that are richer than mere scalar criterion such as the misclassification rate. Thanks to very recent and beautiful results on matrix concentration inequalities, we derive two bounds showing that the true confusion risk of the Gibbs classifier is upper-bounded by its empirical risk plus a term depending on the number of training examples in each class. To the best of our knowledge, this is the first PAC-Bayes bounds based on confusion matrices.
Many researches have been devoted to learn a Mahalanobis distance metric, which can effectively improve the performance of kNN classification. Most approaches are iterative and computational expensive and linear rigidity still critically limits metric learning algorithm to perform better. We proposed a computational economical framework to learn multiple metrics in closed-form.
Analysis of microscopy images is one important tool in many fields of biomedical research, as it allows the quantification of a multitude of parameters at the cellular level. However, manual counting of these images is both tiring and unreliable and ultimately very time-consuming for biomedical researchers. Not only does this slow down the overall research process, it also introduces counting errors due to a lack of objectivity and consistency inherent to the researchers own human nature. This thesis addresses this issue by automatically determining infection indexes of macrophages parasite by Leishmania in microscopy images using computer vision and pattern recognition methodologies. Initially images are submitted to a pre-processing stage that consists in a normalization of illumination conditions. Three algorithms are then applied in parallel to each image. Algorithm A intends to detect macrophage nuclei and consists of segmentation via adaptive multi-threshold, and classification of resulting regions using a set of collected features. Algorithm B intends to detect parasites and is similar to Algorithm A but the adaptive multi-threshold is parameterized with a different constraints vector. Algorithm C intends to detect the macrophages and parasites cytoplasm and consists of a cut-off version of the previous two algorithms, where the classification step is skipped. Regions with multiple nuclei or parasites are processed by a voting system that employs both a Support Vector Machine and a set of region features for determining the number of objects present in each region. The previous vote is then taken into account as the number of mixtures to be used in a Gaussian Mixture Model to decluster the said region. Finally each parasite is assigned to, at most, a single macrophage using minimum Euclidean distance to a cell nucleus, thus quantifying Leishmania infection levels.
Motivated by the increased need for formalized representations of the domain of Data Mining, the success of using Formal Concept Analysis (FCA) and Ontology in several Computer Science fields, we present in this paper a new approach for automatic generation of Fuzzy Ontology of Data Mining (FODM), through the fusion of conceptual clustering, fuzzy logic, and FCA. In our approach, we propose to generate ontology taking in consideration another degree of granularity into the process of generation. Indeed, we suggest to define an ontology between classes resulting from a preliminary classification on the data. We prove that this approach optimize the definition of the ontology, offered a better interpretation of the data and optimized both the space memory and the execution time for exploiting this data.
Sentiment polarity classification is perhaps the most widely studied topic. It classifies an opinionated document as expressing a positive or negative opinion. In this paper, using movie review dataset, we perform a comparative study with different single kind linguistic features and the combinations of these features. We find that the classic topic-based classifier(Naive Bayes and Support Vector Machine) do not perform as well on sentiment polarity classification. And we find that with some combination of different linguistic features, the classification accuracy can be boosted a lot. We give some reasonable explanations about these boosting outcomes.
We consider the problem of learning a vector-valued function f in an online learning setting. The function f is assumed to lie in a reproducing Hilbert space of operator-valued kernels. We describe two online algorithms for learning f while taking into account the output structure. A first contribution is an algorithm, ONORMA, that extends the standard kernel-based online learning algorithm NORMA from scalar-valued to operator-valued setting. We report a cumulative error bound that holds both for classification and regression. We then define a second algorithm, MONORMA, which addresses the limitation of pre-defining the output structure in ONORMA by learning sequentially a linear combination of operator-valued kernels. Our experiments show that the proposed algorithms achieve good performance results with low computational cost.
The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifier design because the error must be estimated using the same data from which the classifier has been designed. Use of prior knowledge, in the form of a prior distribution on an uncertainty class of feature-label distributions to which the true, but unknown, feature-distribution belongs, can facilitate accurate error estimation (in the mean-square sense) in circumstances where accurate completely model-free error estimation is impossible. This paper provides analytic asymptotically exact finite-sample approximations for various performance metrics of the resulting Bayesian Minimum Mean-Square-Error (MMSE) error estimator in the case of linear discriminant analysis (LDA) in the multivariate Gaussian model. These performance metrics include the first, second, and cross moments of the Bayesian MMSE error estimator with the true error of LDA, and therefore, the Root-Mean-Square (RMS) error of the estimator. We lay down the theoretical groundwork for Kolmogorov double-asymptotics in a Bayesian setting, which enables us to derive asymptotic expressions of the desired performance metrics. From these we produce analytic finite-sample approximations and demonstrate their accuracy via numerical examples. Various examples illustrate the behavior of these approximations and their use in determining the necessary sample size to achieve a desired RMS. The Supplementary Material contains derivations for some equations and added figures.
In imbalanced multi-class classification problems, the misclassification rate as an error measure may not be a relevant choice. Several methods have been developed where the performance measure retained richer information than the mere misclassification rate: misclassification costs, ROC-based information, etc. Following this idea of dealing with alternate measures of performance, we propose to address imbalanced classification problems by using a new measure to be optimized: the norm of the confusion matrix. Indeed, recent results show that using the norm of the confusion matrix as an error measure can be quite interesting due to the fine-grain informations contained in the matrix, especially in the case of imbalanced classes. Our first contribution then consists in showing that optimizing criterion based on the confusion matrix gives rise to a common background for cost-sensitive methods aimed at dealing with imbalanced classes learning problems. As our second contribution, we propose an extension of a recent multi-class boosting method --- namely AdaBoost.MM --- to the imbalanced class problem, by greedily minimizing the empirical norm of the confusion matrix. A theoretical analysis of the properties of the proposed method is presented, while experimental results illustrate the behavior of the algorithm and show the relevancy of the approach compared to other methods.
Several methods to identify plants have been proposed by several researchers. Commonly, the methods did not capture color information, because color was not recognized as an important aspect to the identification. In this research, shape and vein, color, and texture features were incorporated to classify a leaf. In this case, a neural network called Probabilistic Neural network (PNN) was used as a classifier. The experimental result shows that the method for classification gives average accuracy of 93.75% when it was tested on Flavia dataset, that contains 32 kinds of plant leaves. It means that the method gives better performance compared to the original work.
Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks. The framework is based on encoding information on sparse pathways and recognizing the correct pathway at inference time. Elaborating further on this insight, we propose a novel deep network architecture, called "channel-out" network, which takes a much better advantage of sparse pathway encoding. In channel-out networks, pathways are not only formed a posteriori, but they are also actively selected according to the inference outputs from the lower layers. From a mathematical perspective, channel-out networks can represent a wider class of piece-wise continuous functions, thereby endowing the network with more expressive power than that of maxout networks. We test our channel-out networks on several well-known image classification benchmarks, setting new state-of-the-art performance on CIFAR-100 and STL-10, which represent some of the "harder" image classification benchmarks.