Physical Adversarial Attacks for Surveillance: A Survey.

Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks-maliciously crafted inputs that are designed to mislead, or trick, models into making incorrect predictions. An adversary can physically change their appearance by wearing adversarial t-shirts, glasses, or hats or by specific behavior, to potentially avoid various forms of detection, tracking, and recognition of surveillance systems; and obtain unauthorized access to secure properties and assets. This poses a severe threat to the security and safety of modern surveillance systems. This article reviews recent attempts and findings in learning and designing physical adversarial attacks for surveillance applications. In particular, we propose a framework to analyze physical adversarial attacks and provide a comprehensive survey of physical adversarial attacks on four key surveillance tasks: detection, identification, tracking, and action recognition under this framework. Furthermore, we review and analyze strategies to defend against physical adversarial attacks and the methods for evaluating the strengths of the defense. The insights in this article present an important step in building resilience within surveillance systems to physical adversarial attacks.

Generalized Generative Deep Learning Models for Biosignal Synthesis and Modality Transfer.

Generative Adversarial Networks (GANs) are a revolutionary innovation in machine learning that enables the generation of artificial data. Artificial data synthesis is valuable especially in the medical field where it is difficult to collect and annotate real data due to privacy issues, limited access to experts, and cost. While adversarial training has led to significant breakthroughs in the computer vision field, biomedical research has not yet fully exploited the capabilities of generative models for data generation, and for more complex tasks such as biosignal modality transfer. We present a broad analysis on adversarial learning on biosignal data. Our study is the first in the machine learning community to focus on synthesizing 1D biosignal data using adversarial models. We consider three types of deep generative adversarial networks: a classical GAN, an adversarial AE, and a modality transfer GAN; individually designed for biosignal synthesis and modality transfer purposes. We evaluate these methods on multiple datasets for different biosignal modalites, including phonocardiogram (PCG), electrocardiogram (ECG), vectorcardiogram and 12-lead electrocardiogram. We follow subject-independent evaluation protocols, by evaluating the proposed models' performance on completely unseen data to demonstrate generalizability. We achieve superior results in generating biosignals, specifically in conditional generation, by synthesizing realistic samples while preserving domain-relevant characteristics. We also demonstrate insightful results in biosignal modality transfer that can generate expanded representations from fewer input-leads, ultimately making the clinical monitoring setting more convenient for the patient. Furthermore our longer duration ECGs generated, maintain clear ECG rhythmic regions, which has been proven using ad-hoc segmentation models.

Robust and Interpretable Temporal Convolution Network for Event Detection in Lung Sound Recordings.

OBJECTIVE: This paper proposes a novel framework for lung sound event detection, segmenting continuous lung sound recordings into discrete events and performing recognition of each event. METHODS: We propose the use of a multi-branch TCN architecture and exploit a novel fusion strategy to combine the resultant features from these branches. This not only allows the network to retain the most salient information across different temporal granularities and disregards irrelevant information, but also allows our network to process recordings of arbitrary length. RESULTS: The proposed method is evaluated on multiple public and in-house benchmarks, containing irregular and noisy recordings of the respiratory auscultation process for the identification of auscultation events including inhalation, crackles, and rhonchi. Moreover, we provide an end-to-end model interpretation pipeline. CONCLUSION: Our analysis of different feature fusion strategies shows that the proposed feature concatenation method leads to better suppression of non-informative features, which drastically reduces the classifier overhead resulting in a robust lightweight network. SIGNIFICANCE: Lung sound event detection is a primary diagnostic step for numerous respiratory diseases. The proposed method provides a cost-effective and efficient alternative to exhaustive manual segmentation, and provides more accurate segmentation than existing methods. The end-to-end model interpretability helps to build the required trust in the system for use in clinical settings.

Geometric Deep Learning for Subject Independent Epileptic Seizure Prediction Using Scalp EEG Signals.

Recently, researchers in the biomedical community have introduced deep learning-based epileptic seizure prediction models using electroencephalograms (EEGs) that can anticipate an epileptic seizure by differentiating between the pre-ictal and interictal stages of the subject's brain. Despite having the appearance of a typical anomaly detection task, this problem is complicated by subject-specific characteristics in EEG data. Therefore, studies that investigate seizure prediction widely employ subject-specific models. However, this approach is not suitable in situations where a target subject has limited (or no) data for training. Subject-independent models can address this issue by learning to predict seizures from multiple subjects, and therefore are of greater value in practice. In this study, we propose a subject-independent seizure predictor using Geometric Deep Learning (GDL). In the first stage of our GDL-based method we use graphs derived from physical connections in the EEG grid. We subsequently seek to synthesize subject-specific graphs using deep learning. The models proposed in both stages achieve state-of-the-art performance using a one-hour early seizure prediction window on two benchmark datasets (CHB-MIT-EEG: 95.38% with 23 subjects and Siena-EEG: 96.05% with 15 subjects). To the best of our knowledge, this is the first study that proposes synthesizing subject-specific graphs for seizure prediction. Furthermore, through model interpretation we outline how this method can potentially contribute towards Scalp EEG-based seizure localization.

Domain Generalization in Biosignal Classification.

OBJECTIVE: When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is violated when the model is evaluated on another unseen but similar database, even if that database contains the same classes. This problem is caused by domain-shift and can be solved using two approaches: domain adaptation and domain generalization. Simply, domain adaptation methods can access data from unseen domains during training; whereas in domain generalization, the unseen data is not available during training. Hence, domain generalization concerns models that perform well on inaccessible, domain-shifted data. METHOD: Our proposed domain generalization method represents an unseen domain using a set of known basis domains, afterwhich we classify the unseen domain using classifier fusion. To demonstrate our system, we employ a collection of heart sound databases that contain normal and abnormal sounds (classes). RESULTS: Our proposed classifier fusion method achieves accuracy gains of up to 16% for four completely unseen domains. CONCLUSION: Recognizing the complexity induced by the inherent temporal nature of biosignal data, the two-stage method proposed in this study is able to effectively simplify the whole process of domain generalization while demonstrating good results on unseen domains and the adopted basis domains. SIGNIFICANCE: To our best knowledge, this is the first study that investigates domain generalization for biosignal data. Our proposed learning strategy can be used to effectively learn domain-relevant features while being aware of the class differences in the data.

Identification of Children at Risk of Schizophrenia via Deep Learning and EEG Responses.

The prospective identification of children likely to develop schizophrenia is a vital tool to support early interventions that can mitigate the risk of progression to clinical psychosis. Electroencephalographic (EEG) patterns from brain activity and deep learning techniques are valuable resources in achieving this identification. We propose automated techniques that can process raw EEG waveforms to identify children who may have an increased risk of schizophrenia compared to typically developing children. We also analyse abnormal features that remain during developmental follow-up over a period of   âˆ¼ 4 years in children with a vulnerability to schizophrenia initially assessed when aged 9 to 12 years. EEG data from participants were captured during the recording of a passive auditory oddball paradigm. We undertake a holistic study to identify brain abnormalities, first by exploring traditional machine learning algorithms using classification methods applied to hand-engineered features (event-related potential components). Then, we compare the performance of these methods with end-to-end deep learning techniques applied to raw data. We demonstrate via average cross-validation performance measures that recurrent deep convolutional neural networks can outperform traditional machine learning methods for sequence modeling. We illustrate the intuitive salient information of the model with the location of the most relevant attributes of a post-stimulus window. This baseline identification system in the area of mental illness supports the evidence of developmental and disease effects in a pre-prodromal phase of psychosis. These results reinforce the benefits of deep learning to support psychiatric classification and neuroscientific research more broadly.

A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation.

Traditionally, abnormal heart sound classification is framed as a three-stage process. The first stage involves segmenting the phonocardiogram to detect fundamental heart sounds; after which features are extracted and classification is performed. Some researchers in the field argue the segmentation step is an unwanted computational burden, whereas others embrace it as a prior step to feature extraction. When comparing accuracies achieved by studies that have segmented heart sounds before analysis with those who have overlooked that step, the question of whether to segment heart sounds before feature extraction is still open. In this study, we explicitly examine the importance of heart sound segmentation as a prior step for heart sound classification, and then seek to apply the obtained insights to propose a robust classifier for abnormal heart sound detection. Furthermore, recognizing the pressing need for explainable Artificial Intelligence (AI) models in the medical domain, we also unveil hidden representations learned by the classifier using model interpretation techniques. Experimental results demonstrate that the segmentation which can be learned by the model plays an essential role in abnormal heart sound classification. Our new classifier is also shown to be robust, stable and most importantly, explainable, with an accuracy of almost 100% on the widely used PhysioNet dataset.

Neural Memory Networks for Seizure Type Classification.

Classification of seizure type is a key step in the clinical process for evaluating an individual who presents with seizures. It determines the course of clinical diagnosis and treatment, and its impact stretches beyond the clinical domain to epilepsy research and the development of novel therapies. Automated identification of seizure type may facilitate understanding of the disease, and seizure detection and prediction have been the focus of recent research that has sought to exploit the benefits of machine learning and deep learning architectures. Nevertheless, there is not yet a definitive solution for automating the classification of seizure type, a task that must currently be performed by an expert epileptologist. Inspired by recent advances in neural memory networks (NMNs), we introduce a novel approach for the classification of seizure type using electrophysiological data. We first explore the performance of traditional deep learning techniques which use convolutional and recurrent neural networks, and enhance these architectures by using external memory modules with trainable neural plasticity. We show that our model achieves a state-of-the-art weighted F1 score of 0.945 for seizure type classification on the TUH EEG Seizure Corpus with the IBM TUSZ preprocessed data. This work highlights the potential of neural memory networks to support the field of epilepsy research, along with biomedical research and signal analysis more broadly.

Corticosteroids for alopecia areata in children.

Question In my family practice, several children have presented with alopecia areata. Families are worried about the ongoing hair loss and have been trying several natural health products. I understand that corticosteroids are also considered to treat this condition. Which corticosteroid treatments can I consider and how beneficial are they?Answer Alopecia areata is a source of considerable distress to those affected, and although there are many treatment options available, none have been clinically proven to be consistently effective. Steroids are commonly prescribed and can result in hair regrowth. Topical steroids are most commonly used in children, but intralesional, oral, and even intravenous steroids are available, with varying levels of efficacy.

Les corticostéroïdes pour l'alopécie areata chez les enfants.

Question Quelques enfants atteints d'alopécie areata se sont présentés à ma clinique de pratique familiale. Les familles s'inquiètent de la perte continuelle de cheveux et ont essayé divers produits de santé naturels. Je sais que les corticostéroïdes sont aussi envisagés pour traiter ce problème. Quels sont les traitements aux corticostéroïdes à considérer, et dans quelle mesure sont-ils bénéfiques?Réponse L'alopécie areata cause une détresse considérable aux personnes affectées et, même s'il y a de nombreux choix de traitements, aucun n'a été cliniquement éprouvé comme étant uniformément efficace. Les stéroïdes sont communément prescrits et peuvent favoriser la repousse des cheveux. Les stéroïdes topiques sont les plus souvent utilisés chez les enfants, mais ils sont aussi offerts sous forme intralésionelle, orale et même intraveineuse, et leur degré d'efficacité est variable.

Neural memory plasticity for medical anomaly detection.

In the domain of machine learning, Neural Memory Networks (NMNs) have recently achieved impressive results in a variety of application areas including visual question answering, trajectory prediction, object tracking, and language modelling. However, we observe that the attention based knowledge retrieval mechanisms used in current NMNs restrict them from achieving their full potential as the attention process retrieves information based on a set of static connection weights. This is suboptimal in a setting where there are vast differences among samples in the data domain; such as anomaly detection where there is no consistent criteria for what constitutes an anomaly. In this paper, we propose a plastic neural memory access mechanism which exploits both static and dynamic connection weights in the memory read, write and output generation procedures. We demonstrate the effectiveness and flexibility of the proposed memory model in three challenging anomaly detection tasks in the medical domain: abnormal EEG identification, MRI tumour type classification and schizophrenia risk detection in children. In all settings, the proposed approach outperforms the current state-of-the-art. Furthermore, we perform an in-depth analysis demonstrating the utility of neural plasticity for the knowledge retrieval process and provide evidence on how the proposed memory model generates sparse yet informative memory outputs.

Heart Sound Segmentation Using Bidirectional LSTMs With Attention.

OBJECTIVE: This paper proposes a novel framework for the segmentation of phonocardiogram (PCG) signals into heart states, exploiting the temporal evolution of the PCG as well as considering the salient information that it provides for the detection of the heart state. METHODS: We propose the use of recurrent neural networks and exploit recent advancements in attention based learning to segment the PCG signal. This allows the network to identify the most salient aspects of the signal and disregard uninformative information. RESULTS: The proposed method attains state-of-the-art performance on multiple benchmarks including both human and animal heart recordings. Furthermore, we empirically analyse different feature combinations including envelop features, wavelet and Mel Frequency Cepstral Coefficients (MFCC), and provide quantitative measurements that explore the importance of different features in the proposed approach. CONCLUSION: We demonstrate that a recurrent neural network coupled with attention mechanisms can effectively learn from irregular and noisy PCG recordings. Our analysis of different feature combinations shows that MFCC features and their derivatives offer the best performance compared to classical wavelet and envelop features. SIGNIFICANCE: Heart sound segmentation is a crucial pre-processing step for many diagnostic applications. The proposed method provides a cost effective alternative to labour extensive manual segmentation, and provides a more accurate segmentation than existing methods. As such, it can improve the performance of further analysis including the detection of murmurs and ejection clicks. The proposed method is also applicable for detection and segmentation of other one dimensional biomedical signals.

Management of gastroesophageal reflux disease in pediatric patients with cerebral palsy.

Question As a family physician who provides care to a large pediatric population in the community, I see children with various neurologic impairments, many with cerebral palsy (CP), presenting with gastroesophageal reflux disease (GERD). What are the current recommendations to manage GERD in pediatric patients with CP?Answer A variety of lifestyle modifications can be used to manage GERD in pediatric patients with CP, including raising the head of the patient's bed, reducing patient weight, limiting exposure to smoke, and avoiding caffeine, spicy foods, fatty foods, and chocolate. The primary pharmacologic treatments currently recommended are histamine-2 receptor antagonists and proton pump inhibitors. Surgical treatments for GERD, like the Nissen fundoplication, might result in complications, so there is ongoing research looking at the benefits of using high-pectin diets, baclofen, and prokinetic agents like mosapride instead.

Prise en charge du reflux gastro-œsophagien chez les enfants atteints de paralysie cérébrale.

Question En tant que médecin de famille qui dispense des soins à une vaste population pédiatrique de la communauté, je vois des enfants atteints de diverses déficiences neurologiques, dont beaucoup de cas de paralysie cérébrale (PC), qui présentent un reflux gastro-œsophagien (RGO). Quelles sont les recommandations actuelles de prise en charge du RGO chez les enfants atteints de PC?Réponse Diverses modifications du mode de vie sont utiles pour prendre en charge le RGO chez les enfants atteints de PC, notamment soulever la tête du lit du patient, faire maigrir le patient, limiter l'exposition à la fumée, et éviter la caféine, les aliments épicés, les aliments gras et le chocolat. Les traitements pharmacologiques recommandés à l'heure actuelle sont les antagonistes des récepteurs de l'histamine H2 et les inhibiteurs de la pompe à protons. Le traitement chirurgical du RGO, comme la fundoplicature de Nissen, pourrait entraîner des complications, alors la recherche se poursuit sur les bienfaits liés aux régimes riches en pectine, au baclofène et aux agents stimulant la motilité gastrique, comme le mosapride, à titre de solution de rechange.

An Improved Method for Measuring Absolute Metabolite Concentrations in Small Biofluid or Tissue Samples.

The measurement of absolute metabolite concentrations in small samples remains a significant analytical challenge. This is particularly the case when the sample volume is only a few microliters or less and cannot be determined accurately via direct measurement. We previously developed volume determination with two standards (VDTS) as a method to address this challenge for biofluids. As a proof-of-principle, we applied VDTS to NMR spectra of polar metabolites in the hemolymph (blood) of the tiny yet powerful genetic model Drosophila melanogaster. This showed that VDTS calculation of absolute metabolite concentrations in fed versus starved Drosophila larvae is more accurate than methods utilizing normalization to total spectral signal. Here, we introduce paired VDTS (pVDTS), an improved VDTS method for biofluids and solid tissues that implements the statistical power of paired control and experimental replicates. pVDTS utilizes new equations that also include a correction for dilution errors introduced by the variable surface wetness of solid samples. We then show that metabolite concentrations in Drosophila larvae are more precisely determined and logically consistent using pVDTS than using the original VDTS method. The refined pVDTS workflow described in this study is applicable to a wide range of different tissues and biofluids.

Histidine is selectively required for the growth of Myc-dependent dedifferentiation tumours in the Drosophila CNS.

Rewired metabolism of glutamine in cancer has been well documented, but less is known about other amino acids such as histidine. Here, we use Drosophila cancer models to show that decreasing the concentration of histidine in the diet strongly inhibits the growth of mutant clones induced by loss of Nerfin-1 or gain of Notch activity. In contrast, changes in dietary histidine have much less effect on the growth of wildtype neural stem cells and Prospero neural tumours. The reliance of tumours on dietary histidine and also on histidine decarboxylase (Hdc) depends upon their growth requirement for Myc. We demonstrate that Myc overexpression in nerfin-1 tumours is sufficient to switch their mode of growth from histidine/Hdc sensitive to resistant. This study suggests that perturbations in histidine metabolism selectively target neural tumours that grow via a dedifferentiation process involving large cell size increases driven by Myc.

Soft + Hardwired attention: An LSTM framework for human trajectory prediction and abnormal event detection.

As humans we possess an intuitive ability for navigation which we master through years of practice; however existing approaches to model this trait for diverse tasks including monitoring pedestrian flow and detecting abnormal events have been limited by using a variety of hand-crafted features. Recent research in the area of deep-learning has demonstrated the power of learning features directly from the data; and related research in recurrent neural networks has shown exemplary results in sequence-to-sequence problems such as neural machine translation and neural image caption generation. Motivated by these approaches, we propose a novel method to predict the future motion of a pedestrian given a short history of their, and their neighbours, past behaviour. The novelty of the proposed method is the combined attention model which utilises both "soft attention" as well as "hard-wired" attention in order to map the trajectory information from the local neighbourhood to the future positions of the pedestrian of interest. We illustrate how a simple approximation of attention weights (i.e. hard-wired) can be merged together with soft attention weights in order to make our model applicable for challenging real world scenarios with hundreds of neighbours. The navigational capability of the proposed method is tested on two challenging publicly available surveillance databases where our model outperforms the current-state-of-the-art methods. Additionally, we illustrate how the proposed architecture can be directly applied for the task of abnormal event detection without handcrafting the features.

A hierarchical multimodal system for motion analysis in patients with epilepsy.

During seizures, a myriad of clinical manifestations may occur. The analysis of these signs, known as seizure semiology, gives clues to the underlying cerebral networks involved. When patients with drug-resistant epilepsy are monitored to assess their suitability for epilepsy surgery, semiology is a vital component to the presurgical evaluation. Specific patterns of facial movements, head motions, limb posturing and articulations, and hand and finger automatisms may be useful in distinguishing between mesial temporal lobe epilepsy (MTLE) and extratemporal lobe epilepsy (ETLE). However, this analysis is time-consuming and dependent on clinical experience and training. Given this limitation, an automated analysis of semiological patterns, i.e., detection, quantification, and recognition of body movement patterns, has the potential to help increase the diagnostic precision of localization. While a few single modal quantitative approaches are available to assess seizure semiology, the automated quantification of patients' behavior across multiple modalities has seen limited advances in the literature. This is largely due to multiple complicated variables commonly encountered in the clinical setting, such as analyzing subtle physical movements when the patient is covered or room lighting is inadequate. Semiology encompasses the stepwise/temporal progression of signs that is reflective of the integration of connected neuronal networks. Thus, single signs in isolation are far less informative. Taking this into account, here, we describe a novel modular, hierarchical, multimodal system that aims to detect and quantify semiologic signs recorded in 2D monitoring videos. Our approach can jointly learn semiologic features from facial, body, and hand motions based on computer vision and deep learning architectures. A dataset collected from an Australian quaternary referral epilepsy unit analyzing 161 seizures arising from the temporal (n = 90) and extratemporal (n = 71) brain regions has been used in our system to quantitatively classify these types of epilepsy according to the semiology detected. A leave-one-subject-out (LOSO) cross-validation of semiological patterns from the face, body, and hands reached classification accuracies ranging between 12% and 83.4%, 41.2% and 80.1%, and 32.8% and 69.3%, respectively. The proposed hierarchical multimodal system is a potential stepping-stone towards developing a fully automated semiology analysis system to support the assessment of epilepsy.