Browsing by Subject "Supervised learning"

Now showing 1 - 10 of 10

Open Access
Canlı hücre bölütlemesi için gözeticili öğrenme modeli
(IEEE Computer Society, 2014-04) Koyuncu, Can Fahrettin; Durmaz, İrem; Çetin-Atalay, Rengül; Gündüz-Demir, Çiğdem
Automated cell imaging systems have been proposed for faster and more reliable analysis of biological events at the cellular level. The first step of these systems is usually cell segmentation whose success affects the other system steps. Thus, it is critical to implement robust and efficient segmentation algorithms for the design of successful systems. In the literature, the most commonly used methods for cell segmentation are marker controlled watersheds. These watershed algorithms assume that markers one-to-one correspond to cells and identify their boundaries by growing these markers. Thus, it is very important to correctly define the markers for these algorithms. The markers are usually defined by finding local minima/maxima on intensity or gradient values or by applying morphological operations on the corresponding binary image. In this work, we propose a new marker controlled watershed algorithm for live cell segmentation. The main contributions of this algorithm are twofold. First, different than the approaches in the literature, it implements a new supervised learning model for marker detection. In this model, it has been proposed to extract features for each pixel considering its neighbors' intensities and gradients and to decide whether this pixel is a marker pixel or not by a classifier using these extracted features. Second, it has been proposed to group the neighboring pixels based on the direction information and to extract features according to these groups. The experiments on 1954 cells show that the proposed algorithm leads to higher segmentation results compared to other watersheds. © 2014 IEEE.
Open Access
GOOWE-ML: a novel online stacked ensemble for multi-label classification in data streams
(2019-07) Büyükçakır, Alican
As data streams become more prevalent, the necessity for online algorithms that mine this transient and dynamic data becomes clearer. Multi-label data stream classification is a supervised learning problem where each instance in the data stream is classified into one or more pre-defined sets of labels. Many methods have been proposed to tackle this problem, including but not limited to ensemblebased methods. Some of these ensemble-based methods are specifically designed to work with certain multi-label base classifiers; some others employ online bagging schemes to build their ensembles. In this study, we introduce a novel online and dynamically-weighted stacked ensemble for multi-label classification, called GOOWE-ML, that utilizes spatial modeling to assign optimal weights to its component classifiers. Our model can be used with any existing incremental multilabel classification algorithm as its base classifier. We conduct experiments with 4 GOOWE-ML-based multi-label ensembles and 7 baseline models on 7 real-world datasets from diverse areas of interest. Our experiments show that GOOWE-ML ensembles yield consistently better results in terms of predictive performance in almost all of the datasets, with respect to the other prominent ensemble models.
Open Access
Less is more: a comprehensive framework for the number of components of ensemble classifiers
(IEEE, 2019) Bonab, H.; Can, Fazlı
The number of component classifiers chosen for an ensemble greatly impacts the prediction ability. In this paper, we use a geometric framework for a priori determining the ensemble size, which is applicable to most of the existing batch and online ensemble classifiers. There are only a limited number of studies on the ensemble size examining majority voting (MV) and weighted MV (WMV). Almost all of them are designed for batch-mode, hardly addressing online environments. Big data dimensions and resource limitations, in terms of time and memory, make the determination of ensemble size crucial, especially for online environments. For the MV aggregation rule, our framework proves that the more strong components we add to the ensemble, the more accurate predictions we can achieve. For the WMV aggregation rule, our framework proves the existence of an ideal number of components, which is equal to the number of class labels, with the premise that components are completely independent of each other and strong enough. While giving the exact definition for a strong and independent classifier in the context of an ensemble is a challenging task, our proposed geometric framework provides a theoretical explanation of diversity and its impact on the accuracy of predictions. We conduct a series of experimental evaluations to show the practical value of our theorems and existing challenges.
Open Access
Non-incremental classification learning algorithms based on voting feature intervals
(1997-08) Demiröz, Gülşen
Learning is one of the necessary abilities of an intelligent agent. This thesis proposes several learning algorithms for multi-concept descriptions in the form of feature intervals, called Voting Feature Intervals (VFI) algorithms. These algorithms are non-incremental classification learning algorithms, and use feature projection based knowledge representation for the classification knowledge induced from a set of preclassified examples. The concept description learned is a set of intervals constructed separately for each feature. Each interval carries classification information for all classes. The classification of an unseen instance is based on a voting scheme, where each feature distributes its vote among all classes. Empirical evaluation of the VFI algorithms has shown that they are the best performing algorithms among other previously developed feature projection based methods in term of classification accuracy. In order to further improve the accuracy, genetic algorithms are developed to learn the optimum feature weights for any given classifier. Also a new crossover operator, called continuous uniform crossover, to be used in this weight learning genetic algorithm is proposed and developed during this thesis. Since the explanation ability of a learning system is as important as its accuracy, VFI classifiers are supplemented with a facility to convey what they have learned in a comprehensible way to humans.
Open Access
Non-uniformly sampled sequential data processing
(2019-09) Şahin, Safa Onur
We study classification and regression for variable length sequential data, which is either non-uniformly sampled or contains missing samples. In most sequential data processing studies, one considers data sequence is uniformly sampled and complete, i.e., does not contain missing input values. However, non-uniformly sampled sequences and the missing data problem appear in a wide range of fields such as medical imaging and financial data. To resolve these problems, certain preprocessing techniques, statistical assumptions and imputation methods are usually employed. However, these approaches suffer since the statistical assumptions do not hold in general and the imputation of artificially generated and unrelated inputs deteriorate the model. To mitigate these problems, in chapter 2, we introduce a novel Long Short-Term Memory (LSTM) architecture. In particular, we extend the classical LSTM network with additional time gates, which incorporate the time information as a nonlinear scaling factor on the conventional gates. We also provide forward pass and backward pass update equations for the proposed LSTM architecture. We show that our approach is superior to the classical LSTM architecture, when there is correlation between time samples. In chapter 3, we investigate regression for variable length sequential data containing missing samples and introduce a novel tree architecture based on the Long Short-Term Memory (LSTM) networks. In our architecture, we employ a variable number of LSTM networks, which use only the existing inputs in the sequence, in a tree-like architecture without any statistical assumptions or imputations on the missing data. In particular, we incorporate the missingness information by selecting a subset of these LSTM networks based on presence-pattern of a certain number of previous inputs.
Open Access
A novel online stacked ensemble for multi-label stream classification
(ACM, 2018) Büyükçakır, Alican; Bonab, H.; Can, Fazlı
As data streams become more prevalent, the necessity for online algorithms that mine this transient and dynamic data becomes clearer. Multi-label data stream classification is a supervised learning problem where each instance in the data stream is classified into one or more pre-defined sets of labels. Many methods have been proposed to tackle this problem, including but not limited to ensemble-based methods. Some of these ensemble-based methods are specifically designed to work with certain multi-label base classifiers; some others employ online bagging schemes to build their ensembles. In this study, we introduce a novel online and dynamically-weighted stacked ensemble for multi-label classification, called GOOWE-ML, that utilizes spatial modeling to assign optimal weights to its component classifiers. Our model can be used with any existing incremental multi-label classification algorithm as its base classifier. We conduct experiments with 4 GOOWE-ML-based multi-label ensembles and 7 baseline models on 7 real-world datasets from diverse areas of interest. Our experiments show that GOOWE-ML ensembles yield consistently better results in terms of predictive performance in almost all of the datasets, with respect to the other prominent ensemble models.
Open Access
Online learning under adverse settings
(2015-05) Özkan, Hüseyin
We present novel solutions for contemporary real life applications that generate data at unforeseen rates in unpredictable forms including non-stationarity, corruptions, missing/mixed attributes and high dimensionality. In particular, we introduce novel algorithms for online learning, where the observations are received sequentially and processed only once without being stored, under adverse settings: i) no or limited assumptions can be made about the data source, ii) the observations can be corrupted and iii) the data is to be processed at extremely fast rates. The introduced algorithms are highly effective and efficient with strong mathematical guarantees; and are shown, through the presented comprehensive real life experiments, to significantly outperform the competitors under such adverse conditions. We develop a novel highly dynamical ensemble method without any stochastic assumptions on the data source. The presented method is asymptotically guaranteed to perform as well as, i.e., competitive against, the best expert in the ensemble, where the competitor, i.e., the best expert, itself is also specifically designed to continuously improve over time in a completely data adaptive manner. In addition, our algorithm achieves a significantly superior modeling power (hence, a significantly superior prediction performance) through a hierarchical and self-organizing approach while mitigating over training issues by combining (taking finite unions of) low-complexity methods. On the contrary, the state-of-the-art ensemble techniques are heavily dependent on static and unstructured expert ensembles. In this regard, we rigorously solve the resulting issues such as the over sensitivity to source statistics as well as the incompatibility between the modeling power and the computational load/precision. Our results uniformly hold for every possible input stream in the deterministic sense regardless of the stationary or non-stationary source statistics. Furthermore, we directly address the data corruptions by developing novel versatile imputation methods and thoroughly demonstrate that the anomaly detection -in addition to being stand alone an important learning problem- is extremely effective for corruption detection/imputation purposes. To that end, as the first time in the literature, we develop the online implementation of the Neyman-Pearson characterization for anomalies in stationary or non-stationary fast streaming temporal data. The introduced anomaly detection algorithm maximizes the detection power at a specified controllable constant false alarm rate with no parameter tuning in a truly online manner. Our algorithms can process any streaming data at extremely fast rates without requiring a training phase or a priori information while bearing strong performance guarantees. Through extensive experiments over real/synthetic benchmark data sets, we also show that our algorithms significantly outperform the state-of-the-art as well as the most recently proposed techniques in the literature with remarkable adaptation capabilities to non-stationarity.
Open Access
Spatio-temporal forecasting over graphs with deep learning
(2020-12) Ceyani, Emir
We study spatiotemporal forecasting of high-dimensional rectangular grid graph structured data, which exhibits both complex spatial and temporal dependencies. In most high-dimensional spatiotemporal forecasting scenarios, deep learningbased methods are widely used. However, deep learning algorithms are overconfident in their predictions, and this overconfidence causes problems in the human-in-the-loop domains such as medical diagnosis and many applications of 5 th generation wireless networks. We propose spatiotemporal extensions to variational autoencoders for regularization, robustness against out-of data distribution, and incorporating uncertainty in predictions to resolve overconfident predictions. However, variational inference methods are prone to biased posterior approximations due to using explicit exponential family densities and mean-field assumption in their posterior factorizations. To mitigate these problems, we utilize variational inference & learning with semi-implicit distributions and apply this inference scheme into convolutional long-short term memory networks(ConvLSTM) for the first time in the literature. In chapter 3, we propose variational autoencoders with convolutional long-short term memory networks, called VarConvLSTM. In chapter 4, we improve our algorithm via semi-implicit & doubly semi-implicit variational inference to model multi-modalities in the data distribution . In chapter 5, we demonstrate that proposed algorithms are applicable for spatiotemporal forecasting tasks, including space-time mobile traffic forecasting over Turkcell base station networks.
Open Access
Supervised approaches for explicit search result diversification
(Elsevier, 2020) Yiğit-Sert, S.; Altıngövde, İ. S.; Macdonald, C.; Ounis, I.; Ulusoy, Özgür
Diversification of web search results aims to promote documents with diverse content (i.e., covering different aspects of a query) to the top-ranked positions, to satisfy more users, enhance fairness and reduce bias. In this work, we focus on the explicit diversification methods, which assume that the query aspects are known at the diversification time, and leverage supervised learning methods to improve their performance in three different frameworks with different features and goals. First, in the LTRDiv framework, we focus on applying typical learning to rank (LTR) algorithms to obtain a ranking where each top-ranked document covers as many aspects as possible. We argue that such rankings optimize various diversification metrics (under certain assumptions), and hence, are likely to achieve diversity in practice. Second, in the AspectRanker framework, we apply LTR for ranking the aspects of a query with the goal of more accurately setting the aspect importance values for diversification. As features, we exploit several pre- and post-retrieval query performance predictors (QPPs) to estimate how well a given aspect is covered among the candidate documents. Finally, in the LmDiv framework, we cast the diversification problem into an alternative fusion task, namely, the supervised merging of rankings per query aspect. We again use QPPs computed over the candidate set for each aspect, and optimize an objective function that is tailored for the diversification goal. We conduct thorough comparative experiments using both the basic systems (based on the well-known BM25 matching function) and the best-performing systems (with more sophisticated retrieval methods) from previous TREC campaigns. Our findings reveal that the proposed frameworks, especially AspectRanker and LmDiv, outperform both non-diversified rankings and two strong diversification baselines (i.e., xQuAD and its variant) in terms of various effectiveness metrics.
Open Access
Weakly supervised object localization with multi-fold multiple instance learning
(IEEE Computer Society, 2017) Cinbis, R. G.; Verbeek, J.; Schmid, C.
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when using high-dimensional representations, such as Fisher vectors and convolutional neural network features. We also propose a window refinement method, which improves the localization accuracy by incorporating an objectness prior. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset, which verifies the effectiveness of our approach. © 2016 IEEE.