Time series classification (TSC) is a challenging task that attracted many researchers in the last few years. One main challenge in TSC is the diversity of domains where time series data come from. Thus, there is no "one model that fits all" in TSC. Some algorithms are very accurate in classifying a specific type of time series when the whole series is considered, while some only target the existence/non-existence of specific patterns/shapelets. Yet other techniques focus on the frequency of occurrences of discriminating patterns/features. This paper presents a new classification technique that addresses the inherent diversity problem in TSC using a nature-inspired method. The technique is stimulated by how flies look at the world through "compound eyes" that are made up of thousands of lenses, called ommatidia. Each ommatidium is an eye with its own lens, and thousands of them together create a broad field of vision. The developed technique similarly uses different lenses and representations to look at the time series, and then combines them for broader visibility. These lenses have been created through hyper-parameterisation of symbolic representations (Piecewise Aggregate and Fourier approximations). The algorithm builds a random forest for each lens, then performs soft dynamic voting for classifying new instances using the most confident eyes, i.e, forests. We evaluate the new technique, coined Co-eye, using the recently released extended version of UCR archive, containing more than 100 datasets across a wide range of domains. The results show the benefits of bringing together different perspectives reflecting on the accuracy and robustness of Co-eye in comparison to other state-of-the-art techniques.
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different images are pulled apart. In this paper, through visualizing and diagnosing classification errors, we observe that current contrastive models are ineffective at localizing the foreground object, limiting their ability to extract discriminative high-level features. This is due to the fact that view generation process considers pixels in an image uniformly. To address this problem, we propose a data-driven approach for learning invariance to backgrounds. It first estimates foreground saliency in images and then creates augmentations by copy-and-pasting the foreground onto a variety of backgrounds. The learning still follows the instance discrimination pretext task, so that the representation is trained to disregard background content and focus on the foreground. We study a variety of saliency estimation methods, and find that most methods lead to improvements for contrastive learning. With this approach (DiLo), significant performance is achieved for self-supervised learning on ImageNet classification, and also for object detection on PASCAL VOC and MSCOCO.
Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider multiple sources. Using an unrelated source can result in sub-optimal performance, known as the \emph{negative transfer}. However, it is challenging to select the appropriate source(s) for classifying a given target instance in multi-source unsupervised domain adaptation (UDA). We model source-selection as an attention-learning problem, where we learn attention over sources for a given target instance. For this purpose, we first independently learn source-specific classification models, and a relatedness map between sources and target domains using pseudo-labelled target domain instances. Next, we learn attention-weights over the sources for aggregating the predictions of the source-specific models. Experimental results on cross-domain sentiment classification benchmarks show that the proposed method outperforms prior proposals in multi-source UDA.
Pneumonia is a life-threatening disease, which occurs in the lungs caused by either bacterial or viral infection. It can be life-endangering if not acted upon in the right time and thus an early diagnosis of pneumonia is vital. The aim of this paper is to automatically detect bacterial and viral pneumonia using digital x-ray images. It provides a detailed report on advances made in making accurate detection of pneumonia and then presents the methodology adopted by the authors. Four different pre-trained deep Convolutional Neural Network (CNN)- AlexNet, ResNet18, DenseNet201, and SqueezeNet were used for transfer learning. 5247 Bacterial, viral and normal chest x-rays images underwent preprocessing techniques and the modified images were trained for the transfer learning based classification task. In this work, the authors have reported three schemes of classifications: normal vs pneumonia, bacterial vs viral pneumonia and normal, bacterial and viral pneumonia. The classification accuracy of normal and pneumonia images, bacterial and viral pneumonia images, and normal, bacterial and viral pneumonia were 98%, 95%, and 93.3% respectively. This is the highest accuracy in any scheme than the accuracies reported in the literature. Therefore, the proposed study can be useful in faster-diagnosing pneumonia by the radiologist and can help in the fast airport screening of pneumonia patients.
New results suggest strong limits to the feasibility of classifying human brain activity evoked from image stimuli, as measured through EEG. Considerable prior work suffers from a confound between the stimulus class and the time since the start of the experiment. A prior attempt to avoid this confound using randomized trials was unable to achieve results above chance in a statistically significant fashion when the data sets were of the same size as the original experiments. Here, we again attempt to replicate these experiments with randomized trials on a far larger (20x) dataset of 1,000 stimulus presentations of each of forty classes, all from a single subject. To our knowledge, this is the largest such EEG data collection effort from a single subject and is at the bounds of feasibility. We obtain classification accuracy that is marginally above chance and above chance in a statistically significant fashion, and further assess how accuracy depends on the classifier used, the amount of training data used, and the number of classes. Reaching the limits of data collection without substantial improvement in classification accuracy suggests limits to the feasibility of this enterprise.
Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained to learn the ability of handling classification tasks on extremely large or infinite episodes representing different classification task, each with a small labeled support set and its corresponding query set. In this work, we advance this few-shot classification paradigm by formulating it as a supervised classification learning problem. We further propose multi-episode and cross-way training techniques, which respectively correspond to the minibatch and pretraining in classification problems. Experimental results on a state-of-the-art few-shot classification method (prototypical networks) demonstrate that both the proposed training strategies can highly accelerate the training process without accuracy loss for varying few-shot classification problems on Omniglot and miniImageNet.
We present an adapted single-shot convolutional neural network (YOLOv2) for the real-time localization and classification of particles in optical microscopy. As compared to previous works, we focus on the real-time detection capabilities of the system to allow for manipulation of microscopic objects in large heterogeneous ensembles with the help of feedback control. The network is capable of localizing and classifying several hundreds of microscopic objects even at very low signal-to-noise ratios for images as large as 416x416 pixels with an inference time of about 10 ms. We demonstrate the real-time detection performance by manipulating active particles propelled by laser-induced self-thermophoresis. In order to make our framework readily available for others, we provide all scripts and source code. The network is implemented in Python/Keras using the TensorFlow backend. A C library supporting GPUs is provided for the real-time inference.
Analyzing a huge amount of malware is a major burden for security analysts. Since emerging malware is often a variant of existing malware, automatically classifying malware into known families greatly reduces a part of their burden. Image-based malware classification with deep learning is an attractive approach for its simplicity, versatility, and affinity with the latest technologies. However, the impact of differences in deep learning models and the degree of transfer learning on the classification accuracy of malware variants has not been fully studied. In this paper, we conducted an exhaustive survey of deep learning models using 24 ImageNet pre-trained models and five fine-tuning parameters, totaling 120 combinations, on two platforms. As a result, we found that the highest classification accuracy was obtained by fine-tuning one of the latest deep learning models with a relatively low degree of transfer learning, and we achieved the highest classification accuracy ever in cross-validation on the Malimg and Drebin datasets. We also confirmed that this trend holds true for the recent malware variants using the VirusTotal 2020 Windows and Android datasets. The experimental results suggest that it is effective to periodically explore optimal deep learning models with the latest models and malware datasets by gradually reducing the degree of transfer learning from half.
Cardiac arrhythmia is a prevalent and significant cause of morbidity and mortality among cardiac ailments. Early diagnosis is crucial in providing intervention for patients suffering from cardiac arrhythmia. Traditionally, diagnosis is performed by examination of the Electrocardiogram (ECG) by a cardiologist. This method of diagnosis is hampered by the lack of accessibility to expert cardiologists. For quite some time, signal processing methods had been used to automate arrhythmia diagnosis. However, these traditional methods require expert knowledge and are unable to model a wide range of arrhythmia. Recently, Deep Learning methods have provided solutions to performing arrhythmia diagnosis at scale. However, the black-box nature of these models prohibit clinical interpretation of cardiac arrhythmia. There is a dire need to correlate the obtained model outputs to the corresponding segments of the ECG. To this end, two methods are proposed to provide interpretability to the models. The first method is a novel application of Gradient-weighted Class Activation Map (Grad-CAM) for visualizing the saliency of the CNN model. In the second approach, saliency is derived by learning the input deletion mask for the LSTM model. The visualizations are provided on a model whose competence is established by comparisons against baselines. The results of model saliency not only provide insight into the prediction capability of the model but also aligns with the medical literature for the classification of cardiac arrhythmia.
It is well understood that a system built from individually fair components may not itself be individually fair. In this work, we investigate individual fairness under pipeline composition. Pipelines differ from ordinary sequential or repeated composition in that individuals may drop out at any stage, and classification in subsequent stages may depend on the remaining "cohort" of individuals. As an example, a company might hire a team for a new project and at a later point promote the highest performer on the team. Unlike other repeated classification settings, where the degree of unfairness degrades gracefully over multiple fair steps, the degree of unfairness in pipelines can be arbitrary, even in a pipeline with just two stages. Guided by a panoply of real-world examples, we provide a rigorous framework for evaluating different types of fairness guarantees for pipelines. We show that na\"{i}ve auditing is unable to uncover systematic unfairness and that, in order to ensure fairness, some form of dependence must exist between the design of algorithms at different stages in the pipeline. Finally, we provide constructions that permit flexibility at later stages, meaning that there is no need to lock in the entire pipeline at the time that the early stage is constructed.
The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and applications in natural language processing (NLP). The problem, however, is that most such benchmarks are limited to English, which has made it difficult to replicate many of the successes in English NLU for other languages. To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark. CLUE is an open-ended, community-driven project that brings together 9 tasks spanning several well-established single-sentence/sentence-pair classification tasks, as well as machine reading comprehension, all on original Chinese text. To establish results on these tasks, we report scores using an exhaustive set of current state-of-the-art pre-trained Chinese models (9 in total). We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on Chinese NLU. Our benchmark is released at https://www.CLUEbenchmarks.com
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show that adversarial attacks against CNN, LSTM and Transformer-based classification models perform word substitutions that are identifiable through frequency differences between replaced words and their corresponding substitutions. Based on these findings, we propose frequency-guided word substitutions (FGWS), a simple algorithm exploiting the frequency properties of adversarial word substitutions for the detection of adversarial examples. FGWS achieves strong performance by accurately detecting adversarial examples on the SST-2 and IMDb sentiment datasets, with F1 detection scores of up to 91.4% against RoBERTa-based classification models. We compare our approach against a recently proposed perturbation discrimination framework and show that we outperform it by up to 13.0% F1.
The COVID-19 can cause severe pneumonia and is estimated to have a high impact on the healthcare system. The standard image diagnosis tests for pneumonia are chest X-ray (CXR) and computed tomography (CT) scan. CXR are useful in because it is cheaper, faster and more widespread than CT. This study aims to identify pneumonia caused by COVID-19 from other types and also healthy lungs using only CXR images. In order to achieve the objectives, we have proposed a classification schema considering the multi-class and hierarchical perspectives, since pneumonia can be structured as a hierarchy. Given the natural data imbalance in this domain, we also proposed the use of resampling algorithms in order to re-balance the classes distribution. Our classification schema extract features using some well-known texture descriptors and also using a pre-trained CNN model. We also explored early and late fusion techniques in order to leverage the strength of multiple texture descriptors and base classifiers at once. To evaluate the approach, we composed a database, named RYDLS-20, containing CXR images of pneumonia caused by different pathogens as well as CXR images of healthy lungs. The classes distribution follows a real-world scenario in which some pathogens are more common than others. The proposed approach achieved a macro-avg F1-Score of 0.65 using a multi-class approach and a F1-Score of 0.89 for the COVID-19 identification in the hierarchical classification scenario. As far as we know, we achieved the best nominal rate obtained for COVID-19 identification in an unbalanced environment with more than three classes. We must also highlight the novel proposed hierarchical classification approach for this task, which considers the types of pneumonia caused by the different pathogens and lead us to the best COVID-19 recognition rate obtained here.
In a data-scarce field such as healthcare, where models often deliver predictions on patients with rare conditions, the ability to measure the uncertainty of a model's prediction could potentially lead to improved effectiveness of decision support tools and increased user trust. This work advances the understanding of uncertainty estimation for classification and risk prediction on medical tabular data, in a two-fold way. First, we expand and refine the set of heuristics to select an uncertainty estimation technique, introducing tests for clinically-relevant scenarios such as generalization to uncommon pathologies, changes in clinical protocol and simulations of corrupted data. We furthermore differentiate these heuristics depending on the clinical use-case. Second, we observe that ensembles and related techniques perform poorly when it comes to detecting out-of-domain examples, a critical task which is carried out more successfully by auto-encoders. These remarks are enriched by considerations of the interplay of uncertainty estimation with class imbalance, post-modeling calibration and other modeling procedures. Our findings are supported by an array of experiments on toy and real-world data.
At the heart of text based neural models lay word representations, which are powerful but occupy a lot of memory making it challenging to deploy to devices with memory constraints such as mobile phones, watches and IoT. To surmount these challenges, we introduce ProFormer -- a projection based transformer architecture that is faster and lighter making it suitable to deploy to memory constraint devices and preserve user privacy. We use LSH projection layer to dynamically generate word representations on-the-fly without embedding lookup tables leading to significant memory footprint reduction from O(V.d) to O(T), where V is the vocabulary size, d is the embedding dimension size and T is the dimension of the LSH projection representation. We also propose a local projection attention (LPA) layer, which uses self-attention to transform the input sequence of N LSH word projections into a sequence of N/K representations reducing the computations quadratically by O(K^2). We evaluate ProFormer on multiple text classification tasks and observed improvements over prior state-of-the-art on-device approaches for short text classification and comparable performance for long text classification tasks. In comparison with a 2-layer BERT model, ProFormer reduced the embedding memory footprint from 92.16 MB to 1.3 KB and requires 16 times less computation overhead, which is very impressive making it the fastest and smallest on-device model.
This paper attempts to analyze the Korean sentence classification system for a chatbot. Sentence classification is the task of classifying an input sentence based on predefined categories. However, spelling or space error contained in the input sentence causes problems in morphological analysis and tokenization. This paper proposes a novel approach of Integrated Eojeol (Korean syntactic word separated by space) Embedding to reduce the effect that poorly analyzed morphemes may make on sentence classification. It also proposes two noise insertion methods that further improve classification performance. Our evaluation results indicate that the proposed system classifies erroneous sentences more accurately than the baseline system by 17%p.0
Binary image based classification and retrieval of documents of an intellectual nature is a very challenging problem. Variations in the binary image generation mechanisms which are subject to the document artisan designer including drawing style, view-point, inclusion of multiple image components are plausible causes for increasing the complexity of the problem. In this work, we propose a method suitable to binary images which bridges some of the successes of deep learning (DL) to alleviate the problems introduced by the aforementioned variations. The method consists on extracting the shape of interest from the binary image and applying a non-Euclidean geometric neural-net architecture to learn the local and global spatial relationships of the shape. Empirical results show that our method is in some sense invariant to the image generation mechanism variations and achieves results outperforming existing methods in a patent image dataset benchmark.
Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within a sentence or document. However, their ability of capturing the global information about the vocabulary of a language is more limited. This latter is the strength of Graph Convolutional Networks (GCN). In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN). Local information and global information interact through different layers of BERT, allowing them to influence mutually and to build together a final representation for classification. In our experiments on several text classification datasets, our approach outperforms BERT and GCN alone, and achieve higher effectiveness than that reported in previous studies.
In 5G networks, the Cloud Radio Access Network (C-RAN) is considered a promising future architecture in terms of minimizing energy consumption and allocating resources efficiently by providing real-time cloud infrastructures, cooperative radio, and centralized data processing. Recently, given their vulnerability to malicious attacks, the security of C-RAN networks has attracted significant attention. Among various anomaly-based intrusion detection techniques, the most promising one is the machine learning-based intrusion detection as it learns without human assistance and adjusts actions accordingly. In this direction, many solutions have been proposed, but they show either low accuracy in terms of attack classification or they offer just a single layer of attack detection. This research focuses on deploying a multi-stage machine learning-based intrusion detection (ML-IDS) in 5G C-RAN that can detect and classify four types of jamming attacks: constant jamming, random jamming, deceptive jamming, and reactive jamming. This deployment enhances security by minimizing the false negatives in C-RAN architectures. The experimental evaluation of the proposed solution is carried out using WSN-DS (Wireless Sensor Networks DataSet), which is a dedicated wireless dataset for intrusion detection. The final classification accuracy of attacks is 94.51\% with a 7.84\% false negative rate.
The proliferation and application of machine learning based Intrusion Detection Systems (IDS) have allowed for more flexibility and efficiency in the automated detection of cyber attacks in Industrial Control Systems (ICS). However, the introduction of such IDSs has also created an additional attack vector; the learning models may also be subject to cyber attacks, otherwise referred to as Adversarial Machine Learning (AML). Such attacks may have severe consequences in ICS systems, as adversaries could potentially bypass the IDS. This could lead to delayed attack detection which may result in infrastructure damages, financial loss, and even loss of life. This paper explores how adversarial learning can be used to target supervised models by generating adversarial samples using the Jacobian-based Saliency Map attack and exploring classification behaviours. The analysis also includes the exploration of how such samples can support the robustness of supervised models using adversarial training. An authentic power system dataset was used to support the experiments presented herein. Overall, the classification performance of two widely used classifiers, Random Forest and J48, decreased by 16 and 20 percentage points when adversarial samples were present. Their performances improved following adversarial training, demonstrating their robustness towards such attacks.