Images shared on social media help crisis managers gain situational awareness and assess incurred damages, among other response tasks. As the volume and velocity of such content are typically high, real-time image classification has become an urgent need for a faster disaster response. Recent advances in computer vision and deep neural networks have enabled the development of models for real-time image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of the damage. To develop robust real-time models, it is necessary to understand the capability of the publicly available pre-trained models for these tasks, which remains to be under-explored in the crisis informatics literature. In this study, we address such limitations by investigating ten different network architectures for four different tasks using the largest publicly available datasets for these tasks. We also explore various data augmentation strategies, semi-supervised techniques, and a multitask learning setup. In our extensive experiments, we achieve promising results.
Image classification technology and performance based on Deep Learning have already achieved high standards. Nevertheless, many efforts have conducted to improve the stability of classification via ensembling. However, the existing ensemble method has a limitation in that it requires extra effort including time consumption to find the weight for each model output. In this paper, we propose a simple but improved ensemble method, naming with Self-Weighted Ensemble (SWE), that places the weight of each model via its verification reliability. The proposed ensemble method, SWE, reduces overall efforts for constructing a classification system with varied classifiers. The performance using SWE is 0.033% higher than the conventional ensemble method. Also, the percent of performance superiority to the previous model is up to 73.333% (ratio of 8:22).
Feature generation is an open topic of investigation in graph machine learning. In this paper, we study the use of graph homomorphism density features as a scalable alternative to homomorphism numbers which retain similar theoretical properties and ability to take into account inductive bias. For this, we propose a high-performance implementation of a simple sampling algorithm which computes additive approximations of homomorphism densities. In the context of graph machine learning, we demonstrate in experiments that simple linear models trained on sample homomorphism densities can achieve performance comparable to graph neural networks on standard graph classification datasets. Finally, we show in experiments on synthetic data that this algorithm scales to very large graphs when implemented with Bloom filters.
The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are the ideal clinical research environment for such development because they collect many clinical data and are highly computerized environments. We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36 % of total) and 3503 negative cases classified by two independent physicians using a standardized approach. The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89 % accuracy, 88 % recall, and 89 % precision. This study successfully applied learning representation and machine learning algorithms to detect heart failure from clinical natural language in a single French institution. Further work is needed to use the same methodology in other institutions and other languages.
Chest X-rays are the most commonly performed diagnostic examination to detect cardiopulmonary abnormalities. However, the presence of bony structures such as ribs and clavicles can obscure subtle abnormalities, resulting in diagnostic errors. This study aims to build a deep learning-based bone suppression model that identifies and removes these occluding bony structures in frontal CXRs to assist in reducing errors in radiological interpretation, including DL workflows, related to detecting manifestations consistent with tuberculosis (TB). Several bone suppression models with various deep architectures are trained and optimized using the proposed combined loss function and their performances are evaluated in a cross-institutional test setting. The best-performing model is used to suppress bones in the publicly available Shenzhen and Montgomery TB CXR collections. A VGG-16 model is pretrained on a large collection of publicly available CXRs. The CXR-pretrained model is then fine-tuned individually on the non-bone-suppressed and bone-suppressed CXRs of Shenzhen and Montgomery TB CXR collections to classify them as showing normal lungs or TB manifestations. The performances of these models are compared using several performance metrics, analyzed for statistical significance, and their predictions are qualitatively interpreted through class-selective relevance maps. It is observed that the models trained on bone-suppressed CXRs significantly outperformed (p<0.05) the models trained on the non-bone-suppressed CXRs. Models trained on bone-suppressed CXRs improved detection of TB-consistent findings and resulted in compact clustering of the data points in the feature space signifying that bone suppression improved the model sensitivity toward TB classification.
This paper introduces the Class-wise Principal Component Analysis, a supervised feature extraction method for hyperspectral data. Hyperspectral Imaging (HSI) has appeared in various fields in recent years, including Remote Sensing. Realizing that information extraction tasks for hyperspectral images are burdened by data-specific issues, we identify and address two major problems. Those are the Curse of Dimensionality which occurs due to the high-volume of the data cube and the class imbalance problem which is common in hyperspectral datasets. Dimensionality reduction is an essential preprocessing step to complement a hyperspectral image classification task. Therefore, we propose a feature extraction algorithm for dimensionality reduction, based on Principal Component Analysis (PCA). Evaluations are carried out on the Indian Pines dataset to demonstrate that significant improvements are achieved when using the reduced data in a classification task.
This paper proposes an automatic Chinese text categorization method for solving the emergency event report classification problem. Since bidirectional encoder representations from transformers (BERT) has achieved great success in natural language processing domain, it is employed to derive emergency text features in this study. To overcome the data imbalance problem in the distribution of emergency event categories, a novel loss function is proposed to improve the performance of the BERT-based model. Meanwhile, to avoid the impact of the extreme learning rate, the Adabound optimization algorithm that achieves a gradual smooth transition from Adam to SGD is employed to learn parameters of the model. To verify the feasibility and effectiveness of the proposed method, a Chinese emergency text dataset collected from the Internet is employed. Compared with benchmarking methods, the proposed method has achieved the best performance in terms of accuracy, weighted-precision, weighted-recall, and weighted-F1 values. Therefore, it is promising to employ the proposed method for real applications in smart emergency management systems.
Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to trained models that are unusable for any practical purpose. In this study we explore an unsupervised approach to address these imbalances by leveraging transfer learning from pre-trained image classification models to encoder-based Generative Adversarial Network (eGAN). To the best of our knowledge, this is the first work to tackle this problem using GAN without needing to augment with synthesized fake images. In the proposed approach we use the discriminator network to output a negative or positive score. We classify as minority, test samples with negative scores and as majority those with positive scores. Our approach eliminates epistemic uncertainty in model predictions, as the P(minority) + P(majority) need not sum up to 1. The impact of transfer learning and combinations of different pre-trained image classification models at the generator and discriminator is also explored. Best result of 0.69 F1-score was obtained on CIFAR-10 classification task with imbalance ratio of 1:2500. Our approach also provides a mechanism of thresholding the specificity or sensitivity of our machine learning system. Keywords: Class imbalance, Transfer Learning, GAN, nash equilibrium
Fingerprint capture systems can be fooled by widely accessible methods to spoof the system using fake fingers, known as presentation attacks. As biometric recognition systems become more extensively relied upon at international borders and in consumer electronics, presentation attacks are becoming an increasingly serious issue. A robust solution is needed that can handle the increased variability and complexity of spoofing techniques. This paper demonstrates the viability of utilizing a sensor with time-series and color-sensing capabilities to improve the robustness of a traditional fingerprint sensor and introduces a comprehensive fingerprint dataset with over 36,000 image sequences and a state-of-the-art set of spoofing techniques. The specific sensor used in this research captures a traditional gray-scale static capture and a time-series color capture simultaneously. Two different methods for Presentation Attack Detection (PAD) are used to assess the benefit of a color dynamic capture. The first algorithm utilizes Static-Temporal Feature Engineering on the fingerprint capture to generate a classification decision. The second generates its classification decision using features extracted by way of the Inception V3 CNN trained on ImageNet. Classification performance is evaluated using features extracted exclusively from the static capture, exclusively from the dynamic capture, and on a fusion of the two feature sets. With both PAD approaches we find that the fusion of the dynamic and static feature-set is shown to improve performance to a level not individually achievable.
Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis. Unsurprisingly, those who do text classification are concerned with the run-time of their algorithms, many of which depend on the size of the corpus' vocabulary due to their bag-of-words representation. Although many studies have examined the effect of preprocessing techniques on vocabulary size and accuracy, none have examined how these methods affect a model's run-time. To fill this gap, we provide a comprehensive study that examines how preprocessing techniques affect the vocabulary size, model performance, and model run-time, evaluating ten techniques over four models and two datasets. We show that some individual methods can reduce run-time with no loss of accuracy, while some combinations of methods can trade 2-5% of the accuracy for up to a 65% reduction of run-time. Furthermore, some combinations of preprocessing techniques can even provide a 15% reduction in run-time while simultaneously improving model accuracy.
Deep learning-based automatic modulation classification (AMC) models are susceptible to adversarial attacks. Such attacks inject specifically crafted wireless interference into transmitted signals to induce erroneous classification predictions. Furthermore, adversarial interference is transferable in black box environments, allowing an adversary to attack multiple deep learning models with a single perturbation crafted for a particular classification model. In this work, we propose a novel wireless receiver architecture to mitigate the effects of adversarial interference in various black box attack environments. We begin by evaluating the architecture uncertainty environment, where we show that adversarial attacks crafted to fool specific AMC DL architectures are not directly transferable to different DL architectures. Next, we consider the domain uncertainty environment, where we show that adversarial attacks crafted on time domain and frequency domain features to not directly transfer to the altering domain. Using these insights, we develop our Assorted Deep Ensemble (ADE) defense, which is an ensemble of deep learning architectures trained on time and frequency domain representations of received signals. Through evaluation on two wireless signal datasets under different sources of uncertainty, we demonstrate that our ADE obtains substantial improvements in AMC classification performance compared with baseline defenses across different adversarial attacks and potencies.
This text argues for the potential of machine learning infused classification systems as vectors for a technically-engaged and constructive technology critique. The text describes this potential with several experiments in image data creation and neural network based classification. The text considers varying aspects of slippage in classification and considers the potential for discovery - as opposed to disaster - stemming from machine learning systems when they fail to perform as anticipated.
Recent research has shown the great potential of deep learning algorithms in the hyperspectral image (HSI) classification task. Nevertheless, training these models usually requires a large amount of labeled data. Since the collection of pixel-level annotations for HSI is laborious and time-consuming, developing algorithms that can yield good performance in the small sample size situation is of great significance. In this study, we propose a robust self-ensembling network (RSEN) to address this problem. The proposed RSEN consists of two subnetworks including a base network and an ensemble network. With the constraint of both the supervised loss from the labeled data and the unsupervised loss from the unlabeled data, the base network and the ensemble network can learn from each other, achieving the self-ensembling mechanism. To the best of our knowledge, the proposed method is the first attempt to introduce the self-ensembling technique into the HSI classification task, which provides a different view on how to utilize the unlabeled data in HSI to assist the network training. We further propose a novel consistency filter to increase the robustness of self-ensembling learning. Extensive experiments on three benchmark HSI datasets demonstrate that the proposed algorithm can yield competitive performance compared with the state-of-the-art methods. Code is available online (\url{https://github.com/YonghaoXu/RSEN}).
This paper presents DeepI2P: a novel approach for cross-modality registration between an image and a point cloud. Given an image (e.g. from a rgb-camera) and a general point cloud (e.g. from a 3D Lidar scanner) captured at different locations in the same scene, our method estimates the relative rigid transformation between the coordinate frames of the camera and Lidar. Learning common feature descriptors to establish correspondences for the registration is inherently challenging due to the lack of appearance and geometric correlations across the two modalities. We circumvent the difficulty by converting the registration problem into a classification and inverse camera projection optimization problem. A classification neural network is designed to label whether the projection of each point in the point cloud is within or beyond the camera frustum. These labeled points are subsequently passed into a novel inverse camera projection solver to estimate the relative pose. Extensive experimental results on Oxford Robotcar and KITTI datasets demonstrate the feasibility of our approach. Our source code is available at https://github.com/lijx10/DeepI2P
Recently proposed few-shot image classification methods have generally focused on use cases where the objects to be classified are the central subject of images. Despite success on benchmark vision datasets aligned with this use case, these methods typically fail on use cases involving densely-annotated, busy images: images common in the wild where objects of relevance are not the central subject, instead appearing potentially occluded, small, or among other incidental objects belonging to other classes of potential interest. To localize relevant objects, we employ a prototype-based few-shot segmentation model which compares the encoded features of unlabeled query images with support class centroids to produce region proposals indicating the presence and location of support set classes in a query image. These region proposals are then used as additional conditioning input to few-shot image classifiers. We develop a framework to unify the two stages (segmentation and classification) into an end-to-end classification model -- PRoPnet -- and empirically demonstrate that our methods improve accuracy on image datasets with natural scenes containing multiple object classes.
Convolutional Neural Networks (CNN) are used mainly to treat problems with many images characteristic of Deep Learning. In this work, we propose a hybrid image classification model to take advantage of quantum and classical computing. The method will use the potential that convolutional networks have shown in artificial intelligence by replacing classical filters with variational quantum filters. Similarly, this work will compare with other classification methods and the system's execution on different servers. The algorithm's quantum feasibility is modelled and tested on Amazon Braket Notebook instances and experimented on the Pennylane's philosophy and framework.
The increasing success of Machine Learning (ML) and Deep Learning (DL) has recently re-sparked interest towards traffic classification. While classification of known traffic is a well investigated subject with supervised classification tools (such as ML and DL models) are known to provide satisfactory performance, detection of unknown (or zero-day) traffic is more challenging and typically handled by unsupervised techniques (such as clustering algorithms). In this paper, we share our experience on a commercial-grade DL traffic classification engine that is able to (i) identify known applications from encrypted traffic, as well as (ii) handle unknown zero-day applications. In particular, our contribution for (i) is to perform a thorough assessment of state of the art traffic classifiers in commercial-grade settings comprising few thousands of very fine grained application labels, as opposite to the few tens of classes generally targeted in academic evaluations. Additionally, we contribute to the problem of (ii) detection of zero-day applications by proposing a novel technique, tailored for DL models, that is significantly more accurate and light-weight than the state of the art. Summarizing our main findings, we gather that (i) while ML and DL models are both equally able to provide satisfactory solution for classification of known traffic, however (ii) the non-linear feature extraction process of the DL backbone provides sizeable advantages for the detection of unknown classes.
Current limitations in boosted tree modelling prevent the effective scaling to datasets with a large feature number, particularly when investigating the magnitude and directionality of various features on classification. We present a novel methodology, Hollow-tree Super (HOTS), to resolve and visualize feature importance in boosted tree models involving a large number of features. Further, HOTS allows for investigation of the directionality and magnitude various features have on classification. Using the Iris dataset, we first compare HOTS to Gini Importance, Partial Dependence Plots, and Permutation Importance, and demonstrate how HOTS resolves the weaknesses present in these methods. We then show how HOTS can be utilized in high dimensional neuroscientific data, by taking 60 Schizophrenic subjects and applying the method to determine which brain regions were most important for classification of schizophrenia as determined by the PANSS. HOTS effectively replicated and supported the findings of Gini importance, Partial Dependence Plots and Permutation importance within the Iris dataset. When applied to the schizophrenic brain dataset, HOTS was able to resolve the top 10 most important features for classification, as well as their directionality for classification and magnitude compared to other features. Cross-validation supported that these same 10 features were consistently used in the decision-making process across multiple trees, and these features were localised primarily to the occipital and parietal cortices, commonly disturbed brain regions in those with Schizophrenia. It is imperative that a methodology is developed that is able to handle the demands of working with large datasets that contain a large number of features. HOTS represents a unique way to investigate both the directionality and magnitude of feature importance when working at scale with boosted-tree modelling.
This paper introduces the Diabetic Foot Ulcers dataset (DFUC2021) for analysis of pathology, focusing on infection and ischaemia. We describe the data preparation of DFUC2021 for ground truth annotation, data curation and data analysis. The final release of DFUC2021 consists of 15,683 DFU patches, with 5,955 training, 5,734 for testing and 3,994 unlabeled DFU patches. The ground truth labels are four classes, i.e. control, infection, ischaemia and both conditions. We curate the dataset using image hashing techniques and analyse the separability using UMAP projection. We benchmark the performance of five key backbones of deep learning, i.e. VGG16, ResNet101, InceptionV3, DenseNet121 and EfficientNet on DFUC2021. We report the optimised results of these key backbones with different strategies. Based on our observations, we conclude that EfficientNetB0 with data augmentation and transfer learning provided the best results for multi-class (4-class) classification with macro-average Precision, Recall and F1-score of 0.57, 0.62 and 0.55, respectively. In ischaemia and infection recognition, when trained on one-versus-all, EfficientNetB0 achieved comparable results with the state of the art. Finally, we interpret the results with statistical analysis and Grad-CAM visualisation.
Manual labelling of training examples is common practice in supervised learning. When the labelling task is of non-trivial difficulty, the supplied labels may not be equal to the ground-truth labels, and label noise is introduced into the training dataset. If the manual annotation is carried out by multiple experts, the same training example can be given different class assignments by different experts, which is indicative of label noise. In the framework of model-based classification, a simple, but key observation is that when the manual labels are sampled using the posterior probabilities of class membership, the noisy labels are as valuable as the ground-truth labels in terms of statistical information. A relaxation of this process is a random effects model for imperfect labelling by a group that uses approximate posterior probabilities of class membership. The relative efficiency of logistic regression using the noisy labels compared to logistic regression using the ground-truth labels can then be derived. The main finding is that logistic regression can be robust to label noise when label noise and classification difficulty are positively correlated. In particular, when classification difficulty is the only source of label errors, multiple sets of noisy labels can supply more information for the estimation of a classification rule compared to the single set of ground-truth labels.