Audio-based music classification and tagging is typically based on categorical supervised learning with a fixed set of labels. This intrinsically cannot handle unseen labels such as newly added music genres or semantic words that users arbitrarily choose for music retrieval. Zero-shot learning can address this problem by leveraging an additional semantic space of labels where side information about the labels is used to unveil the relationship between each other. In this work, we investigate the zero-shot learning in the music domain and organize two different setups of side information. One is using human-labeled attribute information based on Free Music Archive and OpenMIC-2018 datasets. The other is using general word semantic information based on Million Song Dataset and Last.fm tag annotations. Considering a music track is usually multi-labeled in music classification and tagging datasets, we also propose a data split scheme and associated evaluation settings for the multi-label zero-shot learning. Finally, we report experimental results and discuss the effectiveness and new possibilities of zero-shot learning in the music domain.
This paper describes our DKU replay detection system for the ASVspoof 2019 challenge. The goal is to develop spoofing countermeasure for automatic speaker recognition in physical access scenario. We leverage the countermeasure system pipeline from four aspects, including the data augmentation, feature representation, classification, and fusion. First, we introduce an utterance-level deep learning framework for anti-spoofing. It receives the variable-length feature sequence and outputs the utterance-level scores directly. Based on the framework, we try out various kinds of input feature representations extracted from either the magnitude spectrum or phase spectrum. Besides, we also perform the data augmentation strategy by applying the speed perturbation on the raw waveform. Our best single system employs a residual neural network trained by the speed-perturbed group delay gram. It achieves EER of 1.04% on the development set, as well as EER of 1.08% on the evaluation set. Finally, using the simple average score from several single systems can further improve the performance. EER of 0.24% on the development set and 0.66% on the evaluation set is obtained for our primary system.
Suffering from the multi-view data diversity and complexity for semi-supervised classification, most of existing graph convolutional networks focus on the networks architecture construction or the salient graph structure preservation, and ignore the the complete graph structure for semi-supervised classification contribution. To mine the more complete distribution structure from multi-view data with the consideration of the specificity and the commonality, we propose structure fusion based on graph convolutional networks (SF-GCN) for improving the performance of semi-supervised classification. SF-GCN can not only retain the special characteristic of each view data by spectral embedding, but also capture the common style of multi-view data by distance metric between multi-graph structures. Suppose the linear relationship between multi-graph structures, we can construct the optimization function of structure fusion model by balancing the specificity loss and the commonality loss. By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as adjacent matrix to input graph convolutional networks for semi-supervised classification. Experiments demonstrate that the performance of SF-GCN outperforms that of the state of the arts on three challenging datasets, which are Cora,Citeseer and Pubmed in citation networks.
Mental illness affects a significant portion of the worldwide population. Online mental health forums can provide a supportive environment for those afflicted and also generate a large amount of data which can be mined to predict mental health states using machine learning methods. We benchmark multiple methods of text feature representation for social media posts and compare their downstream use with automated machine learning (AutoML) tools to triage content for moderator attention. We used 1588 labeled posts from the CLPsych 2017 shared task collected from the Reachout.com forum (Milne et al., 2019). Posts were represented using lexicon based tools including VADER, Empath, LIWC and also used pre-trained artificial neural network models including DeepMoji, Universal Sentence Encoder, and GPT-1. We used TPOT and auto-sklearn as AutoML tools to generate classifiers to triage the posts. The top-performing system used features derived from the GPT-1 model, which was finetuned on over 150,000 unlabeled posts from Reachout.com. Our top system had a macro averaged F1 score of 0.572, providing a new state-of-the-art result on the CLPsych 2017 task. This was achieved without additional information from meta-data or preceding posts. Error analyses revealed that this top system often misses expressions of hopelessness. We additionally present visualizations that aid understanding of the learned classifiers. We show that transfer learning is an effective strategy for predicting risk with relatively little labeled data. We note that finetuning of pretrained language models provides further gains when large amounts of unlabeled text is available.
In this paper, we propose a new experimental protocol and use it to benchmark the data efficiency --- performance as a function of training set size --- of two deep learning algorithms, convolutional neural networks (CNNs) and hierarchical information-preserving graph-based slow feature analysis (HiGSFA), for tasks in classification and transfer learning scenarios. The algorithms are trained on different-sized subsets of the MNIST and Omniglot data sets. HiGSFA outperforms standard CNN networks when the models are trained on 50 and 200 samples per class for MNIST classification. In other cases, the CNNs perform better. The results suggest that there are cases where greedy, locally optimal bottom-up learning is equally or more powerful than global gradient-based learning.
Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models trained for sound event classification. Four of the models use mel-spectrogram input and one model uses raw audio input. The models represent standard architectures such as convolutional, recurrent and dense networks. The dataset used for training is the Freesound dataset released for task 2 of the DCASE 2018 challenge and the models used are from participants of the challenge who open sourced their code. Our experiments show that adversarial attacks can be generated with high confidence and low perturbation. In addition, we show that the adversarial attacks are very effective across the different models.
An approach for computing unique gait signature using measurements collected from body-worn inertial measurement units (IMUs) is proposed. The gait signature represents one full cycle of the human gait, and is suitable for off-line or on-line classification of the gait mode. The signature can also be used to jointly classify the gait mode and the device mode. The device mode identifies how the IMU-equipped device is being carried by the user. The method is based on precise segmentation and resampling of the measured IMU signal, as an initial step, further tuned by minimizing the variability of the obtained signature within each gait cycle. Finally, a Fourier series expansion of the gait signature is introduced which provides a low-dimensional feature vector well suited for classification purposes. The proposed method is evaluated on a large dataset involving several subjects, each one containing two different gait modes and four different device modes. The gait signatures enable a high classification rate for each step cycle.
Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. However, ESC often suffers from the semantically irrelevant frames and silent frames. In order to deal with this, we employ a frame-level attention model to focus on the semantically relevant frames and salient frames. Specifically, we first propose an convolutional recurrent neural network to learn spectro-temporal features and temporal correlations. Then, we extend our convolutional RNN model with a frame-level attention mechanism to learn discriminative feature representations for ESC. Experiments were conducted on ESC-50 and ESC-10 datasets. Experimental results demonstrated the effectiveness of the proposed method and achieved the state-of-the-art performance in terms of classification accuracy.
Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x,y (and also z in 3D images) dimensions. However often only labels of the whole images are annotated, and localized ROIs are unavailable; and 3) ROIs in medical images often appear in varying sizes (scales). We approach these three challenges with a Multi-Instance Multi-Scale (MIMS) CNN: 1) We propose a multi-scale convolutional layer, which extracts patterns of different receptive fields with a shared set of convolutional kernels, so that scale-invariant patterns are captured by this compact set of kernels. As this layer contains only a small number of parameters, training on small datasets becomes feasible; 2) We propose a "top-k pooling" to aggregate the feature maps in varying scales from multiple spatial dimensions, allowing the model to be trained using weak annotations within the multiple instance learning (MIL) framework. Our method is shown to perform well on three classification tasks involving two 3D and two 2D medical image datasets.
Convolutional Neural Networks (CNNs) have had great success in many machine vision as well as machine audition tasks. Many image recognition network architectures have consequently been adapted for audio processing tasks. However, despite some successes, the performance of many of these did not translate from the image to the audio domain. For example, very deep architectures such as ResNet and DenseNet, which significantly outperform VGG in image recognition, do not perform better in audio processing tasks such as Acoustic Scene Classification (ASC). In this paper, we investigate the reasons why such powerful architectures perform worse in ASC compared to simpler models (e.g., VGG). To this end, we analyse the receptive field (RF) of these CNNs and demonstrate the importance of the RF to the generalization capability of the models. Using our receptive field analysis, we adapt both ResNet and DenseNet, achieving state-of-the-art performance and eventually outperforming the VGG-based models. We introduce systematic ways of adapting the RF in CNNs, and present results on three data sets that show how changing the RF over the time and frequency dimensions affects a model's performance. Our experimental results show that very small or very large RFs can cause performance degradation, but deep models can be made to generalize well by carefully choosing an appropriate RF size within a certain range.
Preventing organizations from Cyber exploits needs timely intelligence about Cyber vulnerabilities and attacks, referred as threats. Cyber threat intelligence can be extracted from various sources including social media platforms where users publish the threat information in real time. Gathering Cyber threat intelligence from social media sites is a time consuming task for security analysts that can delay timely response to emerging Cyber threats. We propose a framework for automatically gathering Cyber threat intelligence from Twitter by using a novelty detection model. Our model learns the features of Cyber threat intelligence from the threat descriptions published in public repositories such as Common Vulnerabilities and Exposures (CVE) and classifies a new unseen tweet as either normal or anomalous to Cyber threat intelligence. We evaluate our framework using a purpose-built data set of tweets from 50 influential Cyber security related accounts over twelve months (in 2018). Our classifier achieves the F1-score of 0.643 for classifying Cyber threat tweets and outperforms several baselines including binary classification models. Our analysis of the classification results suggests that Cyber threat relevant tweets on Twitter do not often include the CVE identifier of the related threats. Hence, it would be valuable to collect these tweets and associate them with the related CVE identifier for cyber security applications.
Transposable Elements (TEs) or jumping genes are the DNA sequences that have an intrinsic capability to move within a host genome from one genomic location to another. Studies show that the presence of a TE within or adjacent to a functional gene may alter its expression. TEs can also cause an increase in the rate of mutation and can even mediate duplications and large insertions and deletions in the genome, promoting gross genetic rearrangements. Thus, the proper classification of the identified jumping genes is essential to understand their genetic and evolutionary effects in the genome. While computational methods have been developed that perform either binary classification or multi-label classification of TEs, few studies have focused on their hierarchical classification. The state-of-the-art machine learning classification method utilizes a Multi-Layer Perceptron (MLP), a class of neural network, for hierarchical classification of TEs. However, the existing methods have limited accuracy in classifying TEs. A more effective classifier, which can explain the role of TEs in germline and somatic evolution, is needed. In this study, we examine the performance of a variety of machine learning (ML) methods. And eventually, propose a robust approach for the hierarchical classification of TEs, with higher accuracy, using Support Vector Machines (SVM).
Central venous catheters (CVCs) are commonly used in critical care settings for monitoring body functions and administering medications. They are often described in radiology reports by referring to their presence, identity and placement. In this paper, we address the problem of automatic detection of their presence and identity through automated segmentation using deep learning networks and classification based on their intersection with previously learned shape priors from clinician annotations of CVCs. The results not only outperform existing methods of catheter detection achieving 85.2% accuracy at 91.6% precision, but also enable high precision (95.2%) classification of catheter types on a large dataset of over 10,000 chest X-rays, presenting a robust and practical solution to this problem.
The growing prosperity of social networks has brought great challenges to the sentimental tendency mining of users. As more and more researchers pay attention to the sentimental tendency of online users, rich research results have been obtained based on the sentiment classification of explicit texts. However, research on the implicit sentiment of users is still in its infancy. Aiming at the difficulty of implicit sentiment classification, a research on implicit sentiment classification model based on deep neural network is carried out. Classification models based on DNN, LSTM, Bi-LSTM and CNN were established to judge the tendency of the user's implicit sentiment text. Based on the Bi-LSTM model, the classification model of word-level attention mechanism is studied. The experimental results on the public dataset show that the established LSTM series classification model and CNN classification model can achieve good sentiment classification effect, and the classification effect is significantly better than the DNN model. The Bi-LSTM based attention mechanism classification model obtained the optimal R value in the positive category identification.
While most heart arrhythmias are not immediately harmful, they can lead to severe complications. In particular, atrial fibrillation, the most common arrhythmia, is characterized by fast and irregular heart beats and increases the risk of suffering a stroke. To detect such abnormal heart conditions, we propose a system composed of two main parts: a smart vest with two cooperative sensors to collect ECG data and a neural network architecture to classify heart rhythms. The smart vest uses two dry bi-electrodes to record a single lead ECG signal. The biopotential signal is then streamed via a gateway to the cloud where a neural network detects and classifies the heart arrhythmias. We selected an architecture that combines convolutional and recurrent layers. The convolutional layers extract relevant features from sliding windows of ECG and the recurrent layer aggregates them for a final softmax layer that performs the classification. Our neural network achieves an accuracy of 87.50% on the dataset of the challenge of Computing in Cardiology 2017.
Ultrasound tongue imaging (UTI) provides a convenient way to visualize the vocal tract during speech production. UTI is increasingly being used for speech therapy, making it important to develop automatic methods to assist various time-consuming manual tasks currently performed by speech therapists. A key challenge is to generalize the automatic processing of ultrasound tongue images to previously unseen speakers. In this work, we investigate the classification of phonetic segments (tongue shapes) from raw ultrasound recordings under several training scenarios: speaker-dependent, multi-speaker, speaker-independent, and speaker-adapted. We observe that models underperform when applied to data from speakers not seen at training time. However, when provided with minimal additional speaker information, such as the mean ultrasound frame, the models generalize better to unseen speakers.
In the recent years, there is a growing interest in semi-supervised learning, since, in many learning tasks, there is a plentiful supply of unlabeled data, but insufficient labeled ones. Hence, Semi-Supervised learning models can benefit from both types of data to improve the obtained performance. Also, it is important to develop methods that are easy to parameterize in a way that is robust to the different characteristics of the data at hand. This article presents a new method based on Self-Organizing Map (SOM) for clustering and classification, called Adaptive Local Thresholds Semi-Supervised Self-Organizing Map (ALTSS-SOM). It can dynamically switch between two forms of learning at training time, according to the availability of labels, as in previous models, and can automatically adjust itself to the local variance observed in each data cluster. The results show that the ALTSS-SOM surpass the performance of other semi-supervised methods in terms of classification, and other pure clustering methods when there are no labels available, being also less sensitive than previous methods to the parameters values.
There has been an increasing interest in semi-supervised learning in the recent years because of the great number of datasets with a large number of unlabeled data but only a few labeled samples. Semi-supervised learning algorithms can work with both types of data, combining them to obtain better performance for both clustering and classification. Also, these datasets commonly have a high number of dimensions. This article presents a new semi-supervised method based on self-organizing maps (SOMs) for clustering and classification, called Semi-Supervised Self-Organizing Map (SS-SOM). The method can dynamically switch between supervised and unsupervised learning during the training according to the availability of the class labels for each pattern. Our results show that the SS-SOM outperforms other semi-supervised methods in conditions in which there is a low amount of labeled samples, also achieving good results when all samples are labeled.
The Algonauts challenge requires to construct a multi-subject encoder of images to brain activity. Deep networks such as ResNet-50 and AlexNet trained for image classification are known to produce feature representations along their intermediate stages which closely mimic the visual hierarchy. However the challenges introduced in the Algonauts project, including combining data from multiple subjects, relying on very few similarity data points, solving for various ROIs, and multi-modality, require devising a flexible framework which can efficiently accommodate them. Here we build upon a recent state-of-the-art classification network (SE-ResNeXt-50) and construct an adaptive combination of its intermediate representations. While the pretrained network serves as a backbone of our model, we learn how to aggregate feature representations along five stages of the network. During learning, our method enables to modulate and screen outputs from each stage along the network as governed by the optimized objective. We applied our method to the Algonauts2019 fMRI and MEG challenges. Using the combined fMRI and MEG data, our approach was rated among the leading five for both challenges. Surprisingly we find that for both the lower and higher order areas (EVC and IT) the adaptive aggregation favors features stemming at later stages of the network.
Symmetry is a key feature observed in nature (from flowers and leaves, to butterflies and birds) and in human-made objects (from paintings and sculptures, to manufactured objects and architectural design). Rotational, translational, and especially reflectional symmetries, are also important in drawings of graphs. Detecting and classifying symmetries can be very useful in algorithms that aim to create symmetric graph drawings and in this paper we present a machine learning approach for these tasks. Specifically, we show that deep neural networks can be used to detect reflectional symmetries with 92% accuracy. We also build a multi-class classifier to distinguish between reflectional horizontal, reflectional vertical, rotational, and translational symmetries. Finally, we make available a collection of images of graph drawings with specific symmetric features that can be used in machine learning systems for training, testing and validation purposes. Our datasets, best trained ML models, source code are available online.