PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1505.04424

Improved Microaneurysm Detection using Deep Neural Networks

In this work, we propose a novel microaneurysm (MA) detection for early diabetic retinopathy screening using color fundus images. Since MA usually the first lesions to appear as an indicator of diabetic retinopathy, accurate detection of MA is necessary for treatment. Each pixel of the image is classified as either MA or non-MA using a deep neural network with dropout training procedure using maxout activation function. No preprocessing step or manual feature extraction is required. Substantial improvements over standard MA detection method based on the pipeline of preprocessing, feature extraction, classification followed by post processing is achieved. The presented method is evaluated in publicly available Retinopathy Online Challenge (ROC) and Diaretdb1v2 database and achieved state-of-the-art accuracy.

arXiv:1607.06299

Opinion Mining in Online Reviews About Distance Education Programs

The popularity of distance education programs is increasing at a fast pace. En par with this development, online communication in fora, social media and reviewing platforms between students is increasing as well. Exploiting this information to support fellow students or institutions requires to extract the relevant opinions in order to automatically generate reports providing an overview of pros and cons of different distance education programs. We report on an experiment involving distance education experts with the goal to develop a dataset of reviews annotated with relevant categories and aspects in each category discussed in the specific review together with an indication of the sentiment. Based on this experiment, we present an approach to extract general categories and specific aspects under discussion in a review together with their sentiment. We frame this task as a multi-label hierarchical text classification problem and empirically investigate the performance of different classification architectures to couple the prediction of a category with the prediction of particular aspects in this category. We evaluate different architectures and show that a hierarchical approach leads to superior results in comparison to a flat model which makes decisions independently.

arXiv:1607.06190

An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates

This paper primarily addresses a dataset relating to cellular, chemical and physical conditions of patients gathered at the time they are operated upon to remove colorectal tumours. This data provides a unique insight into the biochemical and immunological status of patients at the point of tumour removal along with information about tumour classification and post-operative survival. The relationship between severity of tumour, based on TNM staging, and survival is still unclear for patients with TNM stage 2 and 3 tumours. We ask whether it is possible to predict survival rate more accurately using a selection of machine learning techniques applied to subsets of data to gain a deeper understanding of the relationships between a patient's biochemical markers and survival. We use a range of feature selection and single classification techniques to predict the 5 year survival rate of TNM stage 2 and 3 patients which initially produces less than ideal results. The performance of each model individually is then compared with subsets of the data where agreement is reached for multiple models. This novel method of selective ensembling demonstrates that significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved. Finally we point at a possible method to identify whether a patients prognosis can be accurately predicted or not.

arXiv:1607.06186

Applying Interval Type-2 Fuzzy Rule Based Classifiers Through a Cluster-Based Class Representation

Fuzzy Rule-Based Classification Systems (FRBCSs) have the potential to provide so-called interpretable classifiers, i.e. classifiers which can be introspective, understood, validated and augmented by human experts by relying on fuzzy-set based rules. This paper builds on prior work for interval type-2 fuzzy set based FRBCs where the fuzzy sets and rules of the classifier are generated using an initial clustering stage. By introducing Subtractive Clustering in order to identify multiple cluster prototypes, the proposed approach has the potential to deliver improved classification performance while maintaining good interpretability, i.e. without resulting in an excessive number of rules. The paper provides a detailed overview of the proposed FRBC framework, followed by a series of exploratory experiments on both linearly and non-linearly separable datasets, comparing results to existing rule-based and SVM approaches. Overall, initial results indicate that the approach enables comparable classification performance to non rule-based classifiers such as SVM, while often achieving this with a very small number of rules.

arXiv:1607.06144

Learning the Roots of Visual Domain Shift

In this paper we focus on the spatial nature of visual domain shift, attempting to learn where domain adaptation originates in each given image of the source and target set. We borrow concepts and techniques from the CNN visualization literature, and learn domainnes maps able to localize the degree of domain specificity in images. We derive from these maps features related to different domainnes levels, and we show that by considering them as a preprocessing step for a domain adaptation algorithm, the final classification performance is strongly improved. Combined with the whole image representation, these features provide state of the art results on the Office dataset.

arXiv:1607.06011

On the Modeling of Error Functions as High Dimensional Landscapes for Weight Initialization in Learning Networks

Next generation deep neural networks for classification hosted on embedded platforms will rely on fast, efficient, and accurate learning algorithms. Initialization of weights in learning networks has a great impact on the classification accuracy. In this paper we focus on deriving good initial weights by modeling the error function of a deep neural network as a high-dimensional landscape. We observe that due to the inherent complexity in its algebraic structure, such an error function may conform to general results of the statistics of large systems. To this end we apply some results from Random Matrix Theory to analyse these functions. We model the error function in terms of a Hamiltonian in N-dimensions and derive some theoretical results about its general behavior. These results are further used to make better initial guesses of weights for the learning algorithm.

arXiv:1607.05969

4D Cardiac Ultrasound Standard Plane Location by Spatial-Temporal Correlation

Echocardiography plays an important part in diagnostic aid in cardiac diseases. A critical step in echocardiography-aided diagnosis is to extract the standard planes since they tend to provide promising views to present different structures that are benefit to diagnosis. To this end, this paper proposes a spatial-temporal embedding framework to extract the standard view planes from 4D STIC (spatial-temporal image corre- lation) volumes. The proposed method is comprised of three stages, the frame smoothing, spatial-temporal embedding and final classification. In first stage, an L 0 smoothing filter is used to preprocess the frames that removes the noise and preserves the boundary. Then a compact repre- sentation is learned via embedding spatial and temporal features into a latent space in the supervised scheme considering both standard plane information and diagnosis result. In last stage, the learned features are fed into support vector machine to identify the standard plane. We eval- uate the proposed method on a 4D STIC volume dataset with 92 normal cases and 93 abnormal cases in three standard planes. It demonstrates that our method outperforms the baselines in both classification accuracy and computational efficiency.

arXiv:1607.05913

Optimising Rule-Based Classification in Temporal Data

This study optimises manually derived rule-based expert system classification of objects according to changes in their properties over time. One of the key challenges that this study tries to address is how to classify objects that exhibit changes in their behaviour over time, for example how to classify companies' share price stability over a period of time or how to classify students' preferences for subjects while they are progressing through school. A specific case the paper considers is the strategy of players in public goods games (as common in economics) across multiple consecutive games. Initial classification starts from expert definitions specifying class allocation for players based on aggregated attributes of the temporal data. Based on these initial classifications, the optimisation process tries to find an improved classifier which produces the best possible compact classes of objects (players) for every time point in the temporal data. The compactness of the classes is measured by a cost function based on internal cluster indices like the Dunn Index, distance measures like Euclidean distance or statistically derived measures like standard deviation. The paper discusses the approach in the context of incorporating changing player strategies in the aforementioned public good games, where common classification approaches so far do not consider such changes in behaviour resulting from learning or in-game experience. By using the proposed process for classifying temporal data and the actual players' contribution during the games, we aim to produce a more refined classification which in turn may inform the interpretation of public goods game data.

arXiv:1607.05909

Supervised Anomaly Detection in Uncertain Pseudoperiodic Data Streams

Uncertain data streams have been widely generated in many Web applications. The uncertainty in data streams makes anomaly detection from sensor data streams far more challenging. In this paper, we present a novel framework that supports anomaly detection in uncertain data streams. The proposed framework adopts an efficient uncertainty pre-processing procedure to identify and eliminate uncertainties in data streams. Based on the corrected data streams, we develop effective period pattern recognition and feature extraction techniques to improve the computational efficiency. We use classification methods for anomaly detection in the corrected data stream. We also empirically show that the proposed approach shows a high accuracy of anomaly detection on a number of real datasets.

arXiv:1607.05832

Personalization Effect on Emotion Recognition from Physiological Data: An Investigation of Performance on Different Setups and Classifiers

This paper addresses the problem of emotion recognition from physiological signals. Features are extracted and ranked based on their effect on classification accuracy. Different classifiers are compared. The inter-subject variability and the personalization effect are thoroughly investigated, through trial-based and subject-based cross-validation. Finally, a personalized model is introduced, that would allow for enhanced emotional state prediction, based on the physiological data of subjects that exhibit a certain degree of similarity, without the requirement of further feedback.

arXiv:1607.05709

Multi-category Angle-based Classifier Refit

Classification is an important statistical learning tool. In real application, besides high prediction accuracy, it is often desirable to estimate class conditional probabilities for new observations. For traditional problems where the number of observations is large, there exist many well developed approaches. Recently, high dimensional low sample size problems are becoming increasingly popular. Margin-based classifiers, such as logistic regression, are well established methods in the literature. On the other hand, in terms of probability estimation, it is known that for binary classifiers, the commonly used methods tend to under-estimate the norm of the classification function. This can lead to biased probability estimation. Remedy approaches have been proposed in the literature. However, for the simultaneous multicategory classification framework, much less work has been done. We fill the gap in this paper. In particular, we give theoretical insights on why heavy regularization terms are often needed in high dimensional applications, and how this can lead to bias in probability estimation. To overcome this difficulty, we propose a new refit strategy for multicategory angle-based classifiers. Our new method only adds a small computation cost to the problem, and is able to attain prediction accuracy that is as good as the regular margin-based classifiers. On the other hand, the improvement of probability estimation can be very significant. Numerical results suggest that the new refit approach is highly competitive.

arXiv:1607.05691

Information-theoretical label embeddings for large-scale image classification

We present a method for training multi-label, massively multi-class image classification models, that is faster and more accurate than supervision via a sigmoid cross-entropy loss (logistic regression). Our method consists in embedding high-dimensional sparse labels onto a lower-dimensional dense sphere of unit-normed vectors, and treating the classification problem as a cosine proximity regression problem on this sphere. We test our method on a dataset of 300 million high-resolution images with 17,000 labels, where it yields considerably faster convergence, as well as a 7% higher mean average precision compared to logistic regression.

arXiv:1607.05523

Dendritic Spine Shape Analysis: A Clustering Perspective

Functional properties of neurons are strongly coupled with their morphology. Changes in neuronal activity alter morphological characteristics of dendritic spines. First step towards understanding the structure-function relationship is to group spines into main spine classes reported in the literature. Shape analysis of dendritic spines can help neuroscientists understand the underlying relationships. Due to unavailability of reliable automated tools, this analysis is currently performed manually which is a time-intensive and subjective task. Several studies on spine shape classification have been reported in the literature, however, there is an on-going debate on whether distinct spine shape classes exist or whether spines should be modeled through a continuum of shape variations. Another challenge is the subjectivity and bias that is introduced due to the supervised nature of classification approaches. In this paper, we aim to address these issues by presenting a clustering perspective. In this context, clustering may serve both confirmation of known patterns and discovery of new ones. We perform cluster analysis on two-photon microscopic images of spines using morphological, shape, and appearance based features and gain insights into the spine shape analysis problem. We use histogram of oriented gradients (HOG), disjunctive normal shape models (DNSM), morphological features, and intensity profile based features for cluster analysis. We use x-means to perform cluster analysis that selects the number of clusters automatically using the Bayesian information criterion (BIC). For all features, this analysis produces 4 clusters and we observe the formation of at least one cluster consisting of spines which are difficult to be assigned to a known class. This observation supports the argument of intermediate shape types.

arXiv:1607.05440

Collaborative Layer-wise Discriminative Learning in Deep Neural Networks

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples of different complexities. For example, if a training sample has already been correctly classified at a specific layer with high confidence, we argue that it is unnecessary to enforce rest layers to classify this sample correctly and a better strategy is to encourage those layers to focus on other samples. In this paper, we propose a layer-wise discriminative learning method to enhance the discriminative capability of a deep network by allowing its layers to work collaboratively for classification. Towards this target, we introduce multiple classifiers on top of multiple layers. Each classifier not only tries to correctly classify the features from its input layer, but also coordinates with other classifiers to jointly maximize the final classification performance. Guided by the other companion classifiers, each classifier learns to concentrate on certain training examples and boosts the overall performance. Allowing for end-to-end training, our method can be conveniently embedded into state-of-the-art deep networks. Experiments with multiple popular deep networks, including Network in Network, GoogLeNet and VGGNet, on scale-various object classification benchmarks, including CIFAR100, MNIST and ImageNet, and scene classification benchmarks, including MIT67, SUN397 and Places205, demonstrate the effectiveness of our method. In addition, we also analyze the relationship between the proposed method and classical conditional random fields models.

arXiv:1604.03073

Reservoir computing for spatiotemporal signal classification without trained output weights

Reservoir computing is a recently introduced machine learning paradigm that has been shown to be well-suited for the processing of spatiotemporal data. Rather than training the network node connections and weights via backpropagation in traditional recurrent neural networks, reservoirs instead have fixed connections and weights among the `hidden layer' nodes, and traditionally only the weights to the output layer of neurons are trained using linear regression. We claim that for signal classification tasks one may forgo the weight training step entirely and instead use a simple supervised clustering method based upon principal components of norms of reservoir states. The proposed method is mathematically analyzed and explored through numerical experiments on real-world data. The examples demonstrate that the proposed may outperform the traditional trained output weight approach in terms of classification accuracy and sensitivity to reservoir parameters.

arXiv:1602.00490

I Know What You Saw Last Minute - Encrypted HTTP Adaptive Video Streaming Title Classification

Desktops and laptops can be maliciously exploited to violate privacy. There are two main types of attack scenarios: active and passive. In this paper, we consider the passive scenario where the adversary does not interact actively with the device, but he is able to eavesdrop on the network traffic of the device from the network side. Most of the Internet traffic is encrypted and thus passive attacks are challenging. Previous research has shown that information can be extracted from encrypted multimedia streams. This includes video title classification of non HTTP adaptive streams (non-HAS). This paper presents an algorithm for encrypted HTTP adaptive video streaming title classification. We show that an external attacker can identify the video title from video HTTP adaptive streams (HAS) sites such as YouTube. To the best of our knowledge, this is the first work that shows this. We provide a large data set of 10000 YouTube video streams of 100 popular video titles (each title downloaded 100 times) as examples for this task. The dataset was collected under real-world network conditions. We present several machine algorithms for the task and run a through set of experiments, which shows that our classification accuracy is more than 95%. We also show that our algorithms are able to classify video titles that are not in the training set as unknown and some of the algorithms are also able to eliminate false prediction of video titles and instead report unknown. Finally, we evaluate our algorithms robustness to delays and packet losses at test time and show that a solution that uses SVM is the most robust against these changes given enough training data. We provide the dataset and the crawler for future research.

arXiv:1607.07384

Identifying Depression on Twitter

Social media has recently emerged as a premier method to disseminate information online. Through these online networks, tens of millions of individuals communicate their thoughts, personal experiences, and social ideals. We therefore explore the potential of social media to predict, even prior to onset, Major Depressive Disorder (MDD) in online personas. We employ a crowdsourced method to compile a list of Twitter users who profess to being diagnosed with depression. Using up to a year of prior social media postings, we utilize a Bag of Words approach to quantify each tweet. Lastly, we leverage several statistical classifiers to provide estimates to the risk of depression. Our work posits a new methodology for constructing our classifier by treating social as a text-classification problem, rather than a behavioral one on social media platforms. By using a corpus of 2.5M tweets, we achieved an 81% accuracy rate in classification, with a precision score of .86. We believe that this method may be helpful in developing tools that estimate the risk of an individual being depressed, can be employed by physicians, concerned individuals, and healthcare agencies to aid in diagnosis, even possibly enabling those suffering from depression to be more proactive about recovering from their mental health.

arXiv:1607.06988공식 코드 · Papers with Code

Interactive Learning from Multiple Noisy Labels

Interactive learning is a process in which a machine learning algorithm is provided with meaningful, well-chosen examples as opposed to randomly chosen examples typical in standard supervised learning. In this paper, we propose a new method for interactive learning from multiple noisy labels where we exploit the disagreement among annotators to quantify the easiness (or meaningfulness) of an example. We demonstrate the usefulness of this method in estimating the parameters of a latent variable classification model, and conduct experimental analyses on a range of synthetic and benchmark datasets. Furthermore, we theoretically analyze the performance of perceptron in this interactive learning framework.

arXiv:1607.06525공식 코드 · Papers with Code

CGMOS: Certainty Guided Minority OverSampling

Handling imbalanced datasets is a challenging problem that if not treated correctly results in reduced classification performance. Imbalanced datasets are commonly handled using minority oversampling, whereas the SMOTE algorithm is a successful oversampling algorithm with numerous extensions. SMOTE extensions do not have a theoretical guarantee during training to work better than SMOTE and in many instances their performance is data dependent. In this paper we propose a novel extension to the SMOTE algorithm with a theoretical guarantee for improved classification performance. The proposed approach considers the classification performance of both the majority and minority classes. In the proposed approach CGMOS (Certainty Guided Minority OverSampling) new data points are added by considering certainty changes in the dataset. The paper provides a proof that the proposed algorithm is guaranteed to work better than SMOTE for training data. Further experimental results on 30 real-world datasets show that CGMOS works better than existing algorithms when using 6 different classifiers.

arXiv:1606.07908

Label Tree Embeddings for Acoustic Scene Classification

We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels. Given a set of class labels, a category taxonomy is automatically learned by collectively optimizing a clustering of the labels into multiple meta-classes in a tree structure. An acoustic scene instance is then embedded into a low-dimensional feature representation which consists of the likelihoods that it belongs to the meta-classes. We demonstrate state-of-the-art results on two different datasets for the acoustic scene classification task, including the DCASE 2013 and LITIS Rouen datasets.