April 2, 2020

3384 words 16 mins read

Paper Group ANR 287

Convolutional-Recurrent Neural Networks on Low-Power Wearable Platforms for Cardiac Arrhythmia Detection. Dimension-free convergence rates for gradient Langevin dynamics in RKHS. DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices. Topological Descriptors Help Predict Guest Adsorption …

Convolutional-Recurrent Neural Networks on Low-Power Wearable Platforms for Cardiac Arrhythmia Detection


Title	Convolutional-Recurrent Neural Networks on Low-Power Wearable Platforms for Cardiac Arrhythmia Detection
Authors	Antonino Faraone, Ricard Delgado-Gonzalo
Abstract	Low-power sensing technologies, such as wearables, have emerged in the healthcare domain since they enable continuous and non-invasive monitoring of physiological signals. In order to endow such devices with clinical value, classical signal processing has encountered numerous challenges. However, data-driven methods, such as machine learning, offer attractive accuracies at the expense of being resource and memory demanding. In this paper, we focus on the inference of neural networks running in microcontrollers and low-power processors which wearable sensors and devices are generally equipped with. In particular, we adapted an existing convolutional-recurrent neural network, designed to detect and classify cardiac arrhythmias from a single-lead electrocardiogram, to the low-power embedded System-on-Chip nRF52 from Nordic Semiconductor with an ARM’s Cortex-M4 processing core. We show our implementation in fixed-point precision, using the CMSIS-NN libraries, yields a drop of $F_1$ score from 0.8 to 0.784, from the original implementation, with a memory footprint of 195.6KB, and a throughput of 33.98MOps/s.
Tasks	Arrhythmia Detection
Published	2020-01-08
URL	https://arxiv.org/abs/2001.03538v1
PDF	https://arxiv.org/pdf/2001.03538v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-recurrent-neural-networks-on
Repo
Framework

Dimension-free convergence rates for gradient Langevin dynamics in RKHS


Title	Dimension-free convergence rates for gradient Langevin dynamics in RKHS
Authors	Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki
Abstract	Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracted considerable attention lately, as a way to provide convergence guarantees in a non-convex setting. However, the known rates grow exponentially with the dimension of the space. In this work, we provide a convergence analysis of GLD and SGLD when the optimization space is an infinite dimensional Hilbert space. More precisely, we derive non-asymptotic, dimension-free convergence rates for GLD/SGLD when performing regularized non-convex optimization in a reproducing kernel Hilbert space. Amongst others, the convergence analysis relies on the properties of a stochastic differential equation, its discrete time Galerkin approximation and the geometric ergodicity of the associated Markov chains.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.00306v2
PDF	https://arxiv.org/pdf/2003.00306v2.pdf
PWC	https://paperswithcode.com/paper/dimension-free-convergence-rates-for-gradient
Repo
Framework

DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices


Title	DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices
Authors	Jessica Torres Soto, Euan Ashley
Abstract	Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements like step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist where noise remains an unsolved problem. Here, we develop a multi-task deep learning method to assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation (AF). We train our algorithm on over one million simulated unlabeled physiological signals and fine-tune on a curated dataset of over 500K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that in comparison with a traditional random forest-based approach (precision:0.24, recall:0.58, f1:0.34, auPRC:0.44) and a single task CNN (precision:0.59, recall:0.69, f1:0.64, auPRC:0.68) our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of AF detection in participants at rest (pr:0.94, rc:0.98, f1:0.96, auPRC:0.96). In addition, we validate algorithm performance on a prospectively derived replication cohort of ambulatory subjects using data derived from an independently engineered device. We show that two-stage training can help address the unbalanced data problem common to biomedical applications where large well-annotated datasets are scarce. In conclusion, though a combination of simulation and transfer learning and we develop and apply a multitask architecture to the problem of AF detection from wearable wrist sensors demonstrating high levels of accuracy and a solution for the vexing challenge of mechanical noise.
Tasks	Arrhythmia Detection, Denoising, Heart Rate Variability, Transfer Learning
Published	2020-01-01
URL	https://arxiv.org/abs/2001.00155v2
PDF	https://arxiv.org/pdf/2001.00155v2.pdf
PWC	https://paperswithcode.com/paper/deepbeat-a-multi-task-deep-learning-approach
Repo
Framework

Topological Descriptors Help Predict Guest Adsorption in Nanoporous Materials


Title	Topological Descriptors Help Predict Guest Adsorption in Nanoporous Materials
Authors	Aditi S. Krishnapriyan, Maciej Haranczyk, Dmitriy Morozov
Abstract	Machine learning has emerged as an attractive alternative to experiments and simulations for predicting material properties. Usually, such an approach relies on specific domain knowledge for feature design: each learning target requires careful selection of features that an expert recognizes as important for the specific task. The major drawback of this approach is that computation of only a few structural features has been implemented so far, and it is difficult to tell a priori which features are important for a particular application. The latter problem has been empirically observed for predictors of guest uptake in nanoporous materials: local and global porosity features become dominant descriptors at low and high pressures, respectively. We investigate a feature representation of materials using tools from topological data analysis. Specifically, we use persistent homology to describe the geometry of nanoporous materials at various scales. We combine our topological descriptor with traditional structural features and investigate the relative importance of each to the prediction tasks. We demonstrate an application of this feature representation by predicting methane adsorption in zeolites, for pressures in the range of 1-200 bar. Our results not only show a considerable improvement compared to the baseline, but they also highlight that topological features capture information complementary to the structural features: this is especially important for the adsorption at low pressure, a task particularly difficult for the traditional features. Furthermore, by investigation of the importance of individual topological features in the adsorption model, we are able to pinpoint the location of the pores that correlate best to adsorption at different pressure, contributing to our atom-level understanding of structure-property relationships.
Tasks	Feature Importance, Topological Data Analysis
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05972v3
PDF	https://arxiv.org/pdf/2001.05972v3.pdf
PWC	https://paperswithcode.com/paper/robust-topological-descriptors-for-machine
Repo
Framework

Comparison of Distal Teacher Learning with Numerical and Analytical Methods to Solve Inverse Kinematics for Rigid-Body Mechanisms


Title	Comparison of Distal Teacher Learning with Numerical and Analytical Methods to Solve Inverse Kinematics for Rigid-Body Mechanisms
Authors	Tim von Oehsen, Alexander Fabisch, Shivesh Kumar, Frank Kirchner
Abstract	Several publications are concerned with learning inverse kinematics, however, their evaluation is often limited and none of the proposed methods is of practical relevance for rigid-body kinematics with a known forward model. We argue that for rigid-body kinematics one of the first proposed machine learning (ML) solutions to inverse kinematics – distal teaching (DT) – is actually good enough when combined with differentiable programming libraries and we provide an extensive evaluation and comparison to analytical and numerical solutions. In particular, we analyze solve rate, accuracy, sample efficiency and scalability. Further, we study how DT handles joint limits, singularities, unreachable poses, trajectories and provide a comparison of execution times. The three approaches are evaluated on three different rigid body mechanisms with varying complexity. With enough training data and relaxed precision requirements, DT has a better solve rate and is faster than state-of-the-art numerical solvers for a 15-DoF mechanism. DT is not affected by singularities while numerical solutions are vulnerable to them. In all other cases numerical solutions are usually better. Analytical solutions outperform the other approaches by far if they are available.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.00225v1
PDF	https://arxiv.org/pdf/2003.00225v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-distal-teacher-learning-with
Repo
Framework

Understanding the Power of Persistence Pairing via Permutation Test


Title	Understanding the Power of Persistence Pairing via Permutation Test
Authors	Chen Cai, Yusu Wang
Abstract	Recently many efforts have been made to incorporate persistence diagrams, one of the major tools in topological data analysis (TDA), into machine learning pipelines. To better understand the power and limitation of persistence diagrams, we carry out a range of experiments on both graph data and shape data, aiming to decouple and inspect the effects of different factors involved. To this end, we also propose the so-called \emph{permutation test} for persistence diagrams to delineate critical values and pairings of critical values. For graph classification tasks, we note that while persistence pairing yields consistent improvement over various benchmark datasets, it appears that for various filtration functions tested, most discriminative power comes from critical values. For shape segmentation and classification, however, we note that persistence pairing shows significant power on most of the benchmark datasets, and improves over both summaries based on merely critical values, and those based on permutation tests. Our results help provide insights on when persistence diagram based summaries could be more suitable.
Tasks	Graph Classification, Topological Data Analysis
Published	2020-01-16
URL	https://arxiv.org/abs/2001.06058v1
PDF	https://arxiv.org/pdf/2001.06058v1.pdf
PWC	https://paperswithcode.com/paper/understanding-the-power-of-persistence
Repo
Framework

Optimal Feature Manipulation Attacks Against Linear Regression


Title	Optimal Feature Manipulation Attacks Against Linear Regression
Authors	Fuwei Li, Lifeng Lai, Shuguang Cui
Abstract	In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points. Given the energy budget, we first provide the closed-form solution of the optimal poisoning data point when our target is modifying one designated regression coefficient. We then extend the analysis to the more challenging scenario where the attacker aims to change one particular regression coefficient while making others to be changed as small as possible. For this scenario, we introduce a semidefinite relaxation method to design the best attack scheme. Finally, we study a more powerful adversary who can perform a rank-one modification on the feature matrix. We propose an alternating optimization method to find the optimal rank-one modification matrix. Numerical examples are provided to illustrate the analytical results obtained in this paper.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.00177v1
PDF	https://arxiv.org/pdf/2003.00177v1.pdf
PWC	https://paperswithcode.com/paper/optimal-feature-manipulation-attacks-against
Repo
Framework

Unsupervised non-parametric change point detection in quasi-periodic signals


Title	Unsupervised non-parametric change point detection in quasi-periodic signals
Authors	Nikolay Shvetsov, Nazar Buzun, Dmitry V. Dylov
Abstract	We propose a new unsupervised and non-parametric method to detect change points in intricate quasi-periodic signals. The detection relies on optimal transport theory combined with topological analysis and the bootstrap procedure. The algorithm is designed to detect changes in virtually any harmonic or a partially harmonic signal and is verified on three different sources of physiological data streams. We successfully find abnormal or irregular cardiac cycles in the waveforms for the six of the most frequent types of clinical arrhythmias using a single algorithm. The validation and the efficiency of the method are shown both on synthetic and on real time series. Our unsupervised approach reaches the level of performance of the supervised state-of-the-art techniques. We provide conceptual justification for the efficiency of the method and prove the convergence of the bootstrap procedure theoretically.
Tasks	Change Point Detection, Time Series
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02717v1
PDF	https://arxiv.org/pdf/2002.02717v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-non-parametric-change-point
Repo
Framework

Scalable Hybrid HMM with Gaussian Process Emission for Sequential Time-series Data Clustering


Title	Scalable Hybrid HMM with Gaussian Process Emission for Sequential Time-series Data Clustering
Authors	Yohan Jung, Jinkyoo Park
Abstract	Hidden Markov Model (HMM) combined with Gaussian Process (GP) emission can be effectively used to estimate the hidden state with a sequence of complex input-output relational observations. Especially when the spectral mixture (SM) kernel is used for GP emission, we call this model as a hybrid HMM-GPSM. This model can effectively model the sequence of time-series data. However, because of a large number of parameters for the SM kernel, this model can not effectively be trained with a large volume of data having (1) long sequence for state transition and 2) a large number of time-series dataset in each sequence. This paper proposes a scalable learning method for HMM-GPSM. To effectively train the model with a long sequence, the proposed method employs a Stochastic Variational Inference (SVI) approach. Also, to effectively process a large number of data point each time-series data, we approximate the SM kernel using Reparametrized Random Fourier Feature (R-RFF). The combination of these two techniques significantly reduces the training time. We validate the proposed learning method in terms of its hidden-sate estimation accuracy and computation time using large-scale synthetic and real data sets with missing values.
Tasks	Time Series
Published	2020-01-07
URL	https://arxiv.org/abs/2001.01917v1
PDF	https://arxiv.org/pdf/2001.01917v1.pdf
PWC	https://paperswithcode.com/paper/scalable-hybrid-hmm-with-gaussian-process
Repo
Framework

Finding Quantum Critical Points with Neural-Network Quantum States


Title	Finding Quantum Critical Points with Neural-Network Quantum States
Authors	Remmy Zen, Long My, Ryan Tan, Frederic Hebert, Mario Gattobigio, Christian Miniatura, Dario Poletti, Stephane Bressan
Abstract	Finding the precise location of quantum critical points is of particular importance to characterise quantum many-body systems at zero temperature. However, quantum many-body systems are notoriously hard to study because the dimension of their Hilbert space increases exponentially with their size. Recently, machine learning tools known as neural-network quantum states have been shown to effectively and efficiently simulate quantum many-body systems. We present an approach to finding the quantum critical points of the quantum Ising model using neural-network quantum states, analytically constructed innate restricted Boltzmann machines, transfer learning and unsupervised learning. We validate the approach and evaluate its efficiency and effectiveness in comparison with other traditional approaches.
Tasks	Transfer Learning
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02618v1
PDF	https://arxiv.org/pdf/2002.02618v1.pdf
PWC	https://paperswithcode.com/paper/finding-quantum-critical-points-with-neural
Repo
Framework

PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks


Title	PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks
Authors	Junfeng Guo, Zelun Kong, Cong Liu
Abstract	The black-box nature of deep neural networks (DNNs) facilitates attackers to manipulate the behavior of DNN through data poisoning. Being able to detect and mitigate poisoning attacks, typically categorized into backdoor and adversarial poisoning (AP), is critical in enabling safe adoption of DNNs in many application domains. Although recent works demonstrate encouraging results on detection of certain backdoor attacks, they exhibit inherent limitations which may significantly constrain the applicability. Indeed, no technique exists for detecting AP attacks, which represents a harder challenge given that such attacks exhibit no common and explicit rules while backdoor attacks do (i.e., embedding backdoor triggers into poisoned data). We believe the key to detect and mitigate AP attacks is the capability of observing and leveraging essential poisoning-induced properties within an infected DNN model. In this paper, we present PoisHygiene, the first effective and robust detection and mitigation framework against AP attacks. PoisHygiene is fundamentally motivated by Dr. Ernest Rutherford’s story (i.e., the 1908 Nobel Prize winner), on observing the structure of atom through random electron sampling.
Tasks	data poisoning
Published	2020-03-24
URL	https://arxiv.org/abs/2003.11110v1
PDF	https://arxiv.org/pdf/2003.11110v1.pdf
PWC	https://paperswithcode.com/paper/poishygiene-detecting-and-mitigating
Repo
Framework

Gated Mechanism for Attention Based Multimodal Sentiment Analysis


Title	Gated Mechanism for Attention Based Multimodal Sentiment Analysis
Authors	Ayush Kumar, Jithendra Vepa
Abstract	Multimodal sentiment analysis has recently gained popularity because of its relevance to social media posts, customer service calls and video blogs. In this paper, we address three aspects of multimodal sentiment analysis; 1. Cross modal interaction learning, i.e. how multiple modalities contribute to the sentiment, 2. Learning long-term dependencies in multimodal interactions and 3. Fusion of unimodal and cross modal cues. Out of these three, we find that learning cross modal interactions is beneficial for this problem. We perform experiments on two benchmark datasets, CMU Multimodal Opinion level Sentiment Intensity (CMU-MOSI) and CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) corpus. Our approach on both these tasks yields accuracies of 83.9% and 81.1% respectively, which is 1.6% and 1.34% absolute improvement over current state-of-the-art.
Tasks	Multimodal Sentiment Analysis, Sentiment Analysis
Published	2020-02-21
URL	https://arxiv.org/abs/2003.01043v1
PDF	https://arxiv.org/pdf/2003.01043v1.pdf
PWC	https://paperswithcode.com/paper/gated-mechanism-for-attention-based
Repo
Framework

Learning End-to-End Lossy Image Compression: A Benchmark


Title	Learning End-to-End Lossy Image Compression: A Benchmark
Authors	Yueyu Hu, Wenhan Yang, Zhan Ma, Jiaying Liu
Abstract	Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline by handcrafted tuning. Later, tremendous contributions were made, especially when data-driven methods revitalized the domain with their excellent modeling capacities and flexibility in incorporating newly designed modules and constraints. Despite great progress, a systematic benchmark and comprehensive analysis of end-to-end learned image compression methods are lacking. In this paper, we first conduct a comprehensive literature survey of learned image compression methods. The literature is organized based on several aspects to jointly optimize the rate-distortion performance with a neural network, i.e., network architecture, entropy model and rate control. We describe milestones in cutting-edge learned image-compression methods, review a broad range of existing works, and provide insights into their historical development routes. With this survey, the main challenges of image compression methods are revealed, along with opportunities to address the related issues with recent advanced learning methods. This analysis provides an opportunity to take a further step towards higher-efficiency image compression. By introducing a coarse-to-fine hyperprior model for entropy estimation and signal reconstruction, we achieve improved rate-distortion performance, especially on high-resolution images. Extensive benchmark experiments demonstrate the superiority of our model in coding efficiency and the potential for acceleration by large-scale parallel computing devices.
Tasks	Image Compression
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03711v2
PDF	https://arxiv.org/pdf/2002.03711v2.pdf
PWC	https://paperswithcode.com/paper/learning-end-to-end-lossy-image-compression-a
Repo
Framework

Learning from Positive and Unlabeled Data by Identifying the Annotation Process


Title	Learning from Positive and Unlabeled Data by Identifying the Annotation Process
Authors	Naji Shajarisales, Peter Spirtes, Kun Zhang
Abstract	In binary classification, Learning from Positive and Unlabeled data (LePU) is semi-supervised learning but with labeled elements from only one class. Most of the research on LePU relies on some form of independence between the selection process of annotated examples and the features of the annotated class, known as the Selected Completely At Random (SCAR) assumption. Yet the annotation process is an important part of the data collection, and in many cases it naturally depends on certain features of the data (e.g., the intensity of an image and the size of the object to be detected in the image). Without any constraints on the model for the annotation process, classification results in the LePU problem will be highly non-unique. So proper, flexible constraints are needed. In this work we incorporate more flexible and realistic models for the annotation process than SCAR, and more importantly, offer a solution for the challenging LePU problem. On the theory side, we establish the identifiability of the properties of the annotation process and the classification function, in light of the considered constraints on the data-generating process. We also propose an inference algorithm to learn the parameters of the model, with successful experimental results on both simulated and real data. We also propose a novel real-world dataset forLePU, as a benchmark dataset for future studies.
Tasks
Published	2020-03-02
URL	https://arxiv.org/abs/2003.01067v1
PDF	https://arxiv.org/pdf/2003.01067v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-positive-and-unlabeled-data-by
Repo
Framework

Machine learning approaches for identifying prey handling activity in otariid pinnipeds


Title	Machine learning approaches for identifying prey handling activity in otariid pinnipeds
Authors	Rita Pucci, Alessio Micheli, Stefano Chessa, Jane Hunter
Abstract	Systems developed in wearable devices with sensors onboard are widely used to collect data of humans and animals activities with the perspective of an on-board automatic classification of data. An interesting application of these systems is to support animals’ behaviour monitoring gathered by sensors’ data analysis. This is a challenging area and in particular with fixed memories capabilities because the devices should be able to operate autonomously for long periods before being retrieved by human operators, and being able to classify activities onboard can significantly improve their autonomy. In this paper, we focus on the identification of prey handling activity in seals (when the animal start attaching and biting the prey), which is one of the main movement that identifies a successful foraging activity. Data taken into consideration are streams of 3D accelerometers and depth sensors values collected by devices attached directly on seals. To analyse these data, we propose an automatic model based on Machine Learning (ML) algorithms. In particular, we compare the performance (in terms of accuracy and F1score) of three ML algorithms: Input Delay Neural Networks, Support Vector Machines, and Echo State Networks. We attend to the final aim of developing an automatic classifier on-board. For this purpose, in this paper, the comparison is performed concerning the performance obtained by each ML approach developed and its memory footprint. In the end, we highlight the advantage of using an ML algorithm, in terms of feasibility in wild animals’ monitoring.
Tasks
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03866v1
PDF	https://arxiv.org/pdf/2002.03866v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-approaches-for-identifying
Repo
Framework