PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1903.09588공식 코드 · Papers with Code

Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence

Aspect-based sentiment analysis (ABSA), which aims to identify fine-grained opinion polarity towards a specific aspect, is a challenging subtask of sentiment analysis (SA). In this paper, we construct an auxiliary sentence from the aspect and convert ABSA to a sentence-pair classification task, such as question answering (QA) and natural language inference (NLI). We fine-tune the pre-trained model from BERT and achieve new state-of-the-art results on SentiHood and SemEval-2014 Task 4 datasets.

arXiv:1903.09030

Generative Models For Deep Learning with Very Scarce Data

The goal of this paper is to deal with a data scarcity scenario where deep learning techniques use to fail. We compare the use of two well established techniques, Restricted Boltzmann Machines and Variational Auto-encoders, as generative models in order to increase the training set in a classification framework. Essentially, we rely on Markov Chain Monte Carlo (MCMC) algorithms for generating new samples. We show that generalization can be improved comparing this methodology to other state-of-the-art techniques, e.g. semi-supervised learning with ladder networks. Furthermore, we show that RBM is better than VAE generating new samples for training a classifier with good generalization capabilities.

arXiv:1903.09022

Subgraph Networks with Application to Structural Feature Space Expansion

Real-world networks exhibit prominent hierarchical and modular structures, with various subgraphs as building blocks. Most existing studies simply consider distinct subgraphs as motifs and use only their numbers to characterize the underlying network. Although such statistics can be used to describe a network model, or even to design some network algorithms, the role of subgraphs in such applications can be further explored so as to improve the results. In this paper, the concept of subgraph network (SGN) is introduced and then applied to network models, with algorithms designed for constructing the 1st-order and 2nd-order SGNs, which can be easily extended to build higher-order ones. Furthermore, these SGNs are used to expand the structural feature space of the underlying network, beneficial for network classification. Numerical experiments demonstrate that the network classification model based on the structural features of the original network together with the 1st-order and 2nd-order SGNs always performs the best as compared to the models based only on one or two of such networks. In other words, the structural features of SGNs can complement that of the original network for better network classification, regardless of the feature extraction method used, such as the handcrafted, network embedding and kernel-based methods.

arXiv:1903.09012

Towards a Forensic Event Ontology to Assist Video Surveillance-based Vandalism Detection

The detection and representation of events is a critical element in automated surveillance systems. We present here an ontology for representing complex semantic events to assist video surveillance-based vandalism detection. The ontology contains the definition of a rich and articulated event vocabulary that is aimed at aiding forensic analysis to objectively identify and represent complex events. Our ontology has then been applied in the context of London Riots, which took place in 2011. We report also on the experiments conducted to support the classification of complex criminal events from video data.

arXiv:1903.08901

Transferability of Operational Status Classification Models Among Different Wind Turbine Typesq

A detailed understanding of wind turbine performance status classification can improve operations and maintenance in the wind energy industry. Due to different engineering properties of wind turbines, the standard supervised learning models used for classification do not generalize across data sets obtained from different wind sites. We propose two methods to deal with the transferability of the trained models: first, data normalization in the form of power curve alignment, and second, a robust method based on convolutional neural networks and feature-space extension. We demonstrate the success of our methods on real-world data sets with industrial applications.

arXiv:1903.08864

Convolutional neural network for detection and classification of seizures in clinical data

Epileptic seizure detection and classification in clinical electroencephalogram data still is a challenge, and only low sensitivity with a high rate of false positives has been achieved with commercially available seizure detection tools, which usually are patient non-specific. Epilepsy patients suffer from severe detrimental effects like physical injury or depression due to unpredictable seizures. However, even in hospitals due to the high rate of false positives, the seizure alert systems are of poor help for patients as tools of seizure detection are mostly trained on unrealistically clean data, containing little noise and obtained under controlled laboratory conditions, where patient groups are homogeneous, e.g. in terms of age or type of seizures. In this study authors present the approach for detection and classification of a seizure using clinical data of electroencephalograms and a convolutional neural network trained on features of brain synchronisation and power spectrum. Various deep learning methods were applied, and the network was trained on a very heterogeneous clinical electroencephalogram dataset. In total, eight different types of seizures were considered, and the patients were of various ages, health conditions and they were observed under clinical conditions. Despite this, the classifier presented in this paper achieved sensitivity and specificity equal to 0.68 and 0.67, accordingly, which is a significant improvement as compared to the known results for clinical data.

arXiv:1903.08858

Classification of EEG-Based Brain Connectivity Networks in Schizophrenia Using a Multi-Domain Connectome Convolutional Neural Network

We exploit altered patterns in brain functional connectivity as features for automatic discriminative analysis of neuropsychiatric patients. Deep learning methods have been introduced to functional network classification only very recently for fMRI, and the proposed architectures essentially focused on a single type of connectivity measure. We propose a deep convolutional neural network (CNN) framework for classification of electroencephalogram (EEG)-derived brain connectome in schizophrenia (SZ). To capture complementary aspects of disrupted connectivity in SZ, we explore combination of various connectivity features consisting of time and frequency-domain metrics of effective connectivity based on vector autoregressive model and partial directed coherence, and complex network measures of network topology. We design a novel multi-domain connectome CNN (MDC-CNN) based on a parallel ensemble of 1D and 2D CNNs to integrate the features from various domains and dimensions using different fusion strategies. Hierarchical latent representations learned by the multiple convolutional layers from EEG connectivity reveal apparent group differences between SZ and healthy controls (HC). Results on a large resting-state EEG dataset show that the proposed CNNs significantly outperform traditional support vector machine classifiers. The MDC-CNN with combined connectivity features further improves performance over single-domain CNNs using individual features, achieving remarkable accuracy of $93.06\%$ with a decision-level fusion. The proposed MDC-CNN by integrating information from diverse brain connectivity descriptors is able to accurately discriminate SZ from HC. The new framework is potentially useful for developing diagnostic tools for SZ and other disorders.

arXiv:1903.08847

Parametic Classification of Handvein Patterns Based on Texture Features

In this paper, we have developed Biometric recognition system adopting hand based modality Handvein, which has the unique pattern for each individual and it is impossible to counterfeit and fabricate as it is an internal feature. We have opted in choosing feature extraction algorithms such as LBP-visual descriptor ,LPQ-blur insensitive texture operator, Log-Gabor-Texture descriptor. We have chosen well known classifiers such as KNN and SVM for classification. We have experimented and tabulated results of single algorithm recognition rate for Handvein under different distance measures and kernel options. The feature level fusion is carried out which increased the performance level.

arXiv:1903.08808

Bidirectional Recurrent Models for Offensive Tweet Classification

In this paper we propose four deep recurrent architectures to tackle the task of offensive tweet detection as well as further classification into targeting and subject of said targeting. Our architectures are based on LSTMs and GRUs, we present a simple bidirectional LSTM as a baseline system and then further increase the complexity of the models by adding convolutional layers and implementing a split-process-merge architecture with LSTM and GRU as processors. Multiple pre-processing techniques were also investigated. The validation F1-score results from each model are presented for the three subtasks as well as the final F1-score performance on the private competition test set. It was found that model complexity did not necessarily yield better results. Our best-performing model was also the simplest, a bidirectional LSTM; closely followed by a two-branch bidirectional LSTM and GRU architecture.

arXiv:1903.08689

Implicit Generation and Generalization in Energy-Based Models

Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks, and we show its success on the high-dimensional data domains of ImageNet32x32, ImageNet128x128, CIFAR-10, and robotic hand trajectories, achieving better samples than other likelihood models and nearing the performance of contemporary GAN approaches, while covering all modes of the data. We highlight some unique capabilities of implicit generation such as compositionality and corrupt image reconstruction and inpainting. Finally, we show that EBMs are useful models across a wide variety of tasks, achieving state-of-the-art out-of-distribution classification, adversarially robust classification, state-of-the-art continual online class learning, and coherent long term predicted trajectory rollouts.

arXiv:1809.03395

A Markov-Switching Model Approach to Heart Sound Segmentation and Classification

Objective: This paper considers challenges in developing algorithms for accurate segmentation and classification of heart sound (HS) signals. Methods: We propose an approach based on Markov switching autoregressive model (MSAR) to segmenting the HS into four fundamental components each with distinct second-order structure. The identified boundaries are then utilized for automated classification of pathological HS using the continuous density hidden Markov model (CD-HMM). The MSAR formulated in a state-space form is able to capture simultaneously both the continuous hidden dynamics in HS, and the regime switching in the dynamics using a discrete Markov chain. This overcomes the limitation of HMM which uses a single-layer of discrete states. We introduce three schemes for model estimation: (1.) switching Kalman filter (SKF); (2.) refined SKF; (3.) fusion of SKF and the duration-dependent Viterbi algorithm (SKF-Viterbi). Results: The proposed methods are evaluated on Physionet/CinC Challenge 2016 database. The SKF-Viterbi significantly outperforms SKF by improvement of segmentation accuracy from 71% to 84.2%. The use of CD-HMM as a classifier and Mel-frequency cepstral coefficients (MFCCs) as features can characterize not only the normal and abnormal morphologies of HS signals but also morphologies considered as unclassifiable (denoted as X-Factor). It gives classification rates with best gross F1 score of 90.19 (without X-Factor) and 82.7 (with X-Factor) for abnormal beats. Conclusion: The proposed MSAR approach for automatic localization and detection of pathological HS shows a noticeable performance on large HS dataset. Significance: It has potential applications in heart monitoring systems to assist cardiologists for pre-screening of heart pathologies.

arXiv:1903.08478

Deep Octonion Networks

Deep learning is a research hot topic in the field of machine learning. Real-value neural networks (Real NNs), especially deep real networks (DRNs), have been widely used in many research fields. In recent years, the deep complex networks (DCNs) and the deep quaternion networks (DQNs) have attracted more and more attentions. The octonion algebra, which is an extension of complex algebra and quaternion algebra, can provide more efficient and compact expression. This paper constructs a general framework of deep octonion networks (DONs) and provides the main building blocks of DONs such as octonion convolution, octonion batch normalization and octonion weight initialization; DONs are then used in image classification tasks for CIFAR-10 and CIFAR-100 data sets. Compared with the DRNs, the DCNs, and the DQNs, the proposed DONs have better convergence and higher classification accuracy. The success of DONs is also explained by multi-task learning.

arXiv:1903.08289

GANs for Semi-Supervised Opinion Spam Detection

Online reviews have become a vital source of information in purchasing a service (product). Opinion spammers manipulate reviews, affecting the overall perception of the service. A key challenge in detecting opinion spam is obtaining ground truth. Though there exists a large set of reviews online, only a few of them have been labeled spam or non-spam. In this paper, we propose spamGAN, a generative adversarial network which relies on limited set of labeled data as well as unlabeled data for opinion spam detection. spamGAN improves the state-of-the-art GAN based techniques for text classification. Experiments on TripAdvisor dataset show that spamGAN outperforms existing spam detection techniques when limited labeled data is used. Apart from detecting spam reviews, spamGAN can also generate reviews with reasonable perplexity.

arXiv:1903.08268

Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems

With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component which, in turn, consists of two tasks - Intent Classification (IC) and Slot Labeling (SL). Generally, these two tasks are modeled together jointly to achieve best performance. However, this joint modeling adds to model obfuscation. In this work, we first design framework for a modularization of joint IC-SL task to enhance architecture transparency. Then, we explore a number of self-attention, convolutional, and recurrent models, contributing a large-scale analysis of modeling paradigms for IC+SL across two datasets. Finally, using this framework, we propose a class of 'label-recurrent' models that otherwise non-recurrent, with a 10-dimensional representation of the label history, and show that our proposed systems are easy to interpret, highly accurate (achieving over 30% error reduction in SL over the state-of-the-art on the Snips dataset), as well as fast, at 2x the inference and 2/3 to 1/2 the training time of comparable recurrent models, thus giving an edge in critical real-world systems.

arXiv:1903.07749

Galaxy classification: A machine learning analysis of GAMA catalogue data

We present a machine learning analysis of five labelled galaxy catalogues from the Galaxy And Mass Assembly (GAMA): The SersicCatVIKING and SersicCatUKIDSS catalogues containing morphological features, the GaussFitSimple catalogue containing spectroscopic features, the MagPhys catalogue including physical parameters for galaxies, and the Lambdar catalogue, which contains photometric measurements. Extending work previously presented at the ESANN 2018 conference - in an analysis based on Generalized Relevance Matrix Learning Vector Quantization and Random Forests - we find that neither the data from the individual catalogues nor a combined dataset based on all 5 catalogues fully supports the visual-inspection-based galaxy classification scheme employed to categorise the galaxies. In particular, only one class, the Little Blue Spheroids, is consistently separable from the other classes. To aid further insight into the nature of the employed visual-based classification scheme with respect to physical and morphological features, we present the galaxy parameters that are discriminative for the achieved class distinctions.

arXiv:1903.08100

Residual Deep Convolutional Neural Network for EEG Signal Classification in Epilepsy

Epilepsy is the fourth most common neurological disorder, affecting about 1% of the population at all ages. As many as 60% of people with epilepsy experience focal seizures which originate in a certain brain area and are limited to part of one cerebral hemisphere. In focal epilepsy patients, a precise surgical removal of the seizure onset zone can lead to effective seizure control or even a seizure-free outcome. Thus, correct identification of the seizure onset zone is essential. For clinical evaluation purposes, electroencephalography (EEG) recordings are commonly used. However, their interpretation is usually done manually by physicians and is time-consuming and error-prone. In this work, we propose an automated epileptic signal classification method based on modern deep learning methods. In contrast to previous approaches, the network is trained directly on the EEG recordings, avoiding hand-crafted feature extraction and selection procedures. This exploits the ability of deep neural networks to detect and extract relevant features automatically, that may be too complex or subtle to be noticed by humans. The proposed network structure is based on a convolutional neural network with residual connections. We demonstrate that our network produces state-of-the-art performance on two benchmark data sets, a data set from Bonn University and the Bern-Barcelona data set. We conclude that modern deep learning approaches can reach state-of-the-art performance on epileptic EEG classification and automated seizure onset zone identification tasks when trained on raw EEG data. This suggests that such approaches have potential for improving clinical practice.

arXiv:1903.07994

An Evaluation of Bitcoin Address Classification based on Transaction History Summarization

Bitcoin is a cryptocurrency that features a distributed, decentralized and trustworthy mechanism, which has made Bitcoin a popular global transaction platform. The transaction efficiency among nations and the privacy benefiting from address anonymity of the Bitcoin network have attracted many activities such as payments, investments, gambling, and even money laundering in the past decade. Unfortunately, some criminal behaviors which took advantage of this platform were not identified. This has discouraged many governments to support cryptocurrency. Thus, the capability to identify criminal addresses becomes an important issue in the cryptocurrency network. In this paper, we propose new features in addition to those commonly used in the literature to build a classification model for detecting abnormality of Bitcoin network addresses. These features include various high orders of moments of transaction time (represented by block height) which summarizes the transaction history in an efficient way. The extracted features are trained by supervised machine learning methods on a labeling category data set. The experimental evaluation shows that these features have improved the performance of Bitcoin address classification significantly. We evaluate the results under eight classifiers and achieve the highest Micro-F1/Macro-F1 of 87%/86% with LightGBM.

arXiv:1903.07873

Pose-Invariant Object Recognition for Event-Based Vision with Slow-ELM

Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose.

arXiv:1903.07836

Non-negative representation based discriminative dictionary learning for face recognition

In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification. In contrast to traditional dictionary learning methods, NRDL investigates the use of non-negative representation (NR), which contributes to learning discriminative dictionary atoms. In order to make the learned dictionary more suitable for classification, NRDL seamlessly incorporates nonnegative representation constraint, discriminative dictionary learning and linear classifier training into a unified model. Specifically, NRDL introduces a positive constraint on representation matrix to find distinct atoms from heterogeneous training samples, which results in sparse and discriminative representation. Moreover, a discriminative dictionary encouraging function is proposed to enhance the uniqueness of class-specific sub-dictionaries. Meanwhile, an inter-class incoherence constraint and a compact graph based regularization term are constructed to respectively improve the discriminability of learned classifier. Experimental results on several benchmark face data sets verify the advantages of our NRDL algorithm over the state-of-the-art dictionary learning methods.