January 28, 2020

3190 words 15 mins read

Paper Group ANR 1026

A systematic review of human activity recognition using smartphones. Comprehend Medical: a Named Entity Recognition and Relationship Extraction Web Service. On improving learning capability of ELM and an application to brain-computer interface. Document Similarity for Texts of Varying Lengths via Hidden Topics. Training Compact Models for Low Resou …

A systematic review of human activity recognition using smartphones


Title	A systematic review of human activity recognition using smartphones
Authors	Marcin Straczkiewicz, Jukka-Pekka Onnela
Abstract	Smartphones have become a global communication tool and more recently a technology for studying human behavior. Given their numerous built-in sensors, smartphones are able to capture detailed and continuous observations on activities of daily living. However, translation of measurements from these consumer-grade devices into research-grade physical activity patterns remains challenging. Over the years, researchers have proposed various human activity recognition (HAR) systems which vary in algorithmic details and statistical principles. In this paper, we summarize existing approaches to smartphone-based HAR. We systematically screened the literature on Scopus, PubMed, and Web of Science in the areas of data acquisition, data preprocessing, feature extraction, and activity classification. We ultimately identified 72 articles on smartphone-based HAR. To provide an understanding of the literature, we discuss each of these areas separately, identify the most common practices and their alternatives, and propose possible future research directions for this interesting and important field.
Tasks	Activity Recognition, Human Activity Recognition
Published	2019-10-07
URL	https://arxiv.org/abs/1910.03970v1
PDF	https://arxiv.org/pdf/1910.03970v1.pdf
PWC	https://paperswithcode.com/paper/a-systematic-review-of-human-activity
Repo
Framework

Comprehend Medical: a Named Entity Recognition and Relationship Extraction Web Service


Title	Comprehend Medical: a Named Entity Recognition and Relationship Extraction Web Service
Authors	Parminder Bhatia, Busra Celikkaya, Mohammed Khalilia, Selvan Senthivel
Abstract	Comprehend Medical is a stateless and Health Insurance Portability and Accountability Act (HIPAA) eligible Named Entity Recognition (NER) and Relationship Extraction (RE) service launched under Amazon Web Services (AWS) trained using state-of-the-art deep learning models. Contrary to many existing open source tools, Comprehend Medical is scalable and does not require steep learning curve, dependencies, pipeline configurations, or installations. Currently, Comprehend Medical performs NER in five medical categories: Anatomy, Medical Condition, Medications, Protected Health Information (PHI) and Treatment, Test and Procedure (TTP). Additionally, the service provides relationship extraction for the detected entities as well as contextual information such as negation and temporality in the form of traits. Comprehend Medical provides two Application Programming Interfaces (API): 1) the NERe API which returns all the extracted named entities, their traits and the relationships between them and 2) the PHId API which returns just the protected health information contained in the text. Furthermore, Comprehend Medical is accessible through AWS Console, Java and Python Software Development Kit (SDK), making it easier for non-developers and developers to use.
Tasks	Named Entity Recognition
Published	2019-10-15
URL	https://arxiv.org/abs/1910.07419v1
PDF	https://arxiv.org/pdf/1910.07419v1.pdf
PWC	https://paperswithcode.com/paper/comprehend-medical-a-named-entity-recognition
Repo
Framework

On improving learning capability of ELM and an application to brain-computer interface


Title	On improving learning capability of ELM and an application to brain-computer interface
Authors	Apdullah Yayık, Yakup Kutlu, Gökhan Altan
Abstract	As a type of pseudoinverse learning, extreme learning machine (ELM) is able to achieve high performances in a rapid pace on benchmark datasets. However, when it is applied to real life large data, decline related to low-convergence of singular value decomposition (SVD) method occurs. Our study aims to resolve this issue via replacing SVD with theoretically and empirically much efficient 5 number of methods: lower upper triangularization, Hessenberg decomposition, Schur decomposition, modified Gram Schmidt algorithm and Householder reflection. Comparisons were made on electroencephalography based brain-computer interface classification problem to decide which method is the most useful. Results of subject-based classifications suggested that if priority was given to training pace, Hessenberg decomposition method, whereas if priority was given to performances Householder reflection method should be preferred.
Tasks
Published	2019-07-14
URL	https://arxiv.org/abs/1907.06633v1
PDF	https://arxiv.org/pdf/1907.06633v1.pdf
PWC	https://paperswithcode.com/paper/on-improving-learning-capability-of-elm-and
Repo
Framework

Document Similarity for Texts of Varying Lengths via Hidden Topics


Title	Document Similarity for Texts of Varying Lengths via Hidden Topics
Authors	Hongyu Gong, Tarek Sakakini, Suma Bhat, Jinjun Xiong
Abstract	Measuring similarity between texts is an important task for several applications. Available approaches to measure document similarity are inadequate for document pairs that have non-comparable lengths, such as a long document and its summary. This is because of the lexical, contextual and the abstraction gaps between a long document of rich details and its concise summary of abstract information. In this paper, we present a document matching approach to bridge this gap, by comparing the texts in a common space of hidden topics. We evaluate the matching algorithm on two matching tasks and find that it consistently and widely outperforms strong baselines. We also highlight the benefits of incorporating domain knowledge to text matching.
Tasks	Text Matching
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10675v1
PDF	http://arxiv.org/pdf/1903.10675v1.pdf
PWC	https://paperswithcode.com/paper/document-similarity-for-texts-of-varying-1
Repo
Framework

Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models


Title	Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models
Authors	Peter Izsak, Shira Guskin, Moshe Wasserblat
Abstract	Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases there is often an abundance of unlabeled data, while labeled data is scarce or unavailable. Pre-trained language models trained to extract contextual features from text were shown to improve many natural language processing (NLP) tasks, including scarcely labeled tasks, by leveraging transfer learning. However, such models impose a heavy memory and computational burden, making it a challenge to train and deploy such models for inference use. In this work-in-progress we combined the effectiveness of transfer learning provided by pre-trained masked language models with a semi-supervised approach to train a fast and compact model using labeled and unlabeled examples. Preliminary evaluations show that the compact models can achieve competitive accuracy with 36x compression rate when compared with a state-of-the-art pre-trained language model, and run significantly faster in inference, allowing deployment of such models in production environments or on edge devices.
Tasks	Language Modelling, Named Entity Recognition, Transfer Learning
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06294v2
PDF	https://arxiv.org/pdf/1910.06294v2.pdf
PWC	https://paperswithcode.com/paper/training-compact-models-for-low-resource
Repo
Framework

A Robust Roll Angle Estimation Algorithm Based on Gradient Descent


Title	A Robust Roll Angle Estimation Algorithm Based on Gradient Descent
Authors	Rui Fan, Lujia Wang, Ming Liu, Ioannis Pitas
Abstract	This paper presents a robust roll angle estimation algorithm, which is developed from our previously published work, where the roll angle was estimated from a dense disparity map by minimizing a global energy using golden section search algorithm. In this paper, to achieve greater computational efficiency, we utilize gradient descent to optimize the aforementioned global energy. The experimental results illustrate that the proposed roll angle estimation algorithm takes fewer iterations to achieve the same precision as the previous method.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01894v1
PDF	https://arxiv.org/pdf/1906.01894v1.pdf
PWC	https://paperswithcode.com/paper/a-robust-roll-angle-estimation-algorithm
Repo
Framework

On the Estimation of Network Complexity: Dimension of Graphons


Title	On the Estimation of Network Complexity: Dimension of Graphons
Authors	Yann Issartel
Abstract	Network complexity has been studied for over half a century and has found a wide range of applications. Many methods have been developed to characterize and estimate the complexity of networks. However, there has been little research with statistical guarantees. In this paper, we develop a statistical theory of graph complexity in a general model of random graphs, the so-called graphon model. Given a graphon, we endow the latent space of the nodes with the so-called neighborhood distance that measures the propensity of two nodes to be connected with similar nodes. Our complexity index is then based on the covering number and the Minkowski dimension of (a purified version of) this metric space. Although the latent space is not identifiable, these indices turn out to be identifiable. This notion of complexity has simple interpretations on popular examples of random graphs: it matches the number of communities in stochastic block models; the dimension of the Euclidean space in random geometric graphs; the regularity of the link function in H"older graphon models. From a single observation of the graph, we construct an estimator of the neighborhood-distance and show universal non-asymptotic bounds for its risk, matching minimax lower bounds. Based on this estimated distance, we compute the corresponding covering number and Minkowski dimension and we provide optimal non-asymptotic error bounds for these two plug-in estimators.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02900v1
PDF	https://arxiv.org/pdf/1909.02900v1.pdf
PWC	https://paperswithcode.com/paper/on-the-estimation-of-network-complexity
Repo
Framework

A Comparison Study of Credit Card Fraud Detection: Supervised versus Unsupervised


Title	A Comparison Study of Credit Card Fraud Detection: Supervised versus Unsupervised
Authors	Xuetong Niu, Li Wang, Xulei Yang
Abstract	Credit card has become popular mode of payment for both online and offline purchase, which leads to increasing daily fraud transactions. An Efficient fraud detection methodology is therefore essential to maintain the reliability of the payment system. In this study, we perform a comparison study of credit card fraud detection by using various supervised and unsupervised approaches. Specifically, 6 supervised classification models, i.e., Logistic Regression (LR), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGB), as well as 4 unsupervised anomaly detection models, i.e., One-Class SVM (OCSVM), Auto-Encoder (AE), Restricted Boltzmann Machine (RBM), and Generative Adversarial Networks (GAN), are explored in this study. We train all these models on a public credit card transaction dataset from Kaggle website, which contains 492 frauds out of 284,807 transactions. The labels of the transactions are used for supervised learning models only. The performance of each model is evaluated through 5-fold cross validation in terms of Area Under the Receiver Operating Curves (AUROC). Within supervised approaches, XGB and RF obtain the best performance with AUROC = 0.989 and AUROC = 0.988, respectively. While for unsupervised approaches, RBM achieves the best performance with AUROC = 0.961, followed by GAN with AUROC = 0.954. The experimental results show that supervised models perform slightly better than unsupervised models in this study. Anyway, unsupervised approaches are still promising for credit card fraud transaction detection due to the insufficient annotation and the data imbalance issue in real-world applications.
Tasks	Anomaly Detection, Fraud Detection, Unsupervised Anomaly Detection
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10604v1
PDF	http://arxiv.org/pdf/1904.10604v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-study-of-credit-card-fraud
Repo
Framework

Ancestral causal learning in high dimensions with a human genome-wide application


Title	Ancestral causal learning in high dimensions with a human genome-wide application
Authors	Umberto Noè, Bernd Taschler, Joachim Täger, Peter Heutink, Sach Mukherjee
Abstract	We consider learning ancestral causal relationships in high dimensions. Our approach is driven by a supervised learning perspective, with discrete indicators of causal relationships treated as labels to be learned from available data. We focus on the setting in which some causal (ancestral) relationships are known (via background knowledge or experimental data) and put forward a general approach that scales to large problems. This is motivated by problems in human biology which are characterized by high dimensionality and potentially many latent variables. We present a case study involving interventional data from human cells with total dimension $p ! \sim ! 19{,}000$. Performance is assessed empirically by testing model output against previously unseen interventional data. The proposed approach is highly effective and demonstrably scalable to the human genome-wide setting. We consider sensitivity to background knowledge and find that results are robust to nontrivial perturbations of the input information. We consider also the case, relevant to some applications, where the only prior information available concerns a small number of known ancestral relationships.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11506v1
PDF	https://arxiv.org/pdf/1905.11506v1.pdf
PWC	https://paperswithcode.com/paper/ancestral-causal-learning-in-high-dimensions
Repo
Framework

Multi-linear Faster RCNN with ELA for Image Tampering Detection


Title	Multi-linear Faster RCNN with ELA for Image Tampering Detection
Authors	Robin Elizabeth Yancey, Norman Matloff, Paul Thompson
Abstract	With technological advances leading to an increase in mechanisms for image tampering, fraud detection methods must continue to be upgraded to match their sophistication. One problem with current methods is that they require prior knowledge of the method of forgery in order to determine which features to extract from the image to localize the region of interest. When a machine learning algorithm is used to learn different types of tampering from a large set of various image types, with a large enough database we can easily classify which images are tampered (by training on the entire image feature map for each image). However, we still are left with the question of which features to train on, and how to localize the manipulation. To solve this, object detection networks such as Faster R-CNN, which combine an RPN (Region Proposal Network) with a CNN, have recently been adapted to fraud detection by utilizing their ability to propose bounding boxes for objects of interest to localize the tampering artifacts. By making use of the computational powers of today’s GPUs this method also achieves a fast run-time and higher accuracy than the top current methods such as noise analysis, ELA (Error Level Analysis), or CFA (Color Filter Array). In this work, a multi-linear Faster RCNN network will be applied similarly but with the second stream having an input of the ELA JPEG compression level mask. This is shown to provide even higher accuracy by adding training features from the segmented image map to the network.
Tasks	Fraud Detection, Object Detection
Published	2019-04-07
URL	https://arxiv.org/abs/1904.08484v2
PDF	https://arxiv.org/pdf/1904.08484v2.pdf
PWC	https://paperswithcode.com/paper/190408484
Repo
Framework

Operational Neural Networks


Title	Operational Neural Networks
Authors	Serkan Kiranyaz, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj
Abstract	Feed-forward, fully-connected Artificial Neural Networks (ANNs) or the so-called Multi-Layer Perceptrons (MLPs) are well-known universal approximators. However, their learning performance varies significantly depending on the function or the solution space that they attempt to approximate. This is mainly because of their homogenous configuration based solely on the linear neuron model. Therefore, while they learn very well those problems with a monotonous, relatively simple and linearly separable solution space, they may entirely fail to do so when the solution space is highly nonlinear and complex. Sharing the same linear neuron model with two additional constraints (local connections and weight sharing), this is also true for the conventional Convolutional Neural Networks (CNNs) and, it is, therefore, not surprising that in many challenging problems only the deep CNNs with a massive complexity and depth can achieve the required diversity and the learning performance. In order to address this drawback and also to accomplish a more generalized model over the convolutional neurons, this study proposes a novel network model, called Operational Neural Networks (ONNs), which can be heterogeneous and encapsulate neurons with any set of operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data. Finally, a novel training method is formulated to back-propagate the error through the operational layers of ONNs. Experimental results over highly challenging problems demonstrate the superior learning capabilities of ONNs even with few neurons and hidden layers.
Tasks
Published	2019-02-15
URL	https://arxiv.org/abs/1902.11106v2
PDF	https://arxiv.org/pdf/1902.11106v2.pdf
PWC	https://paperswithcode.com/paper/operational-neural-networks
Repo
Framework

Scalable Similarity Joins of Tokenized Strings


Title	Scalable Similarity Joins of Tokenized Strings
Authors	Ahmed Metwally, Chun-Heng Huang
Abstract	This work tackles the problem of fuzzy joining of strings that naturally tokenize into meaningful substrings, e.g., full names. Tokenized-string joins have several established applications in the context of data integration and cleaning. This work is primarily motivated by fraud detection, where attackers slightly modify tokenized strings, e.g., names on accounts, to create numerous identities that she can use to defraud service providers, e.g., Google, and LinkedIn. To detect such attacks, all the accounts are pair-wise compared, and the resulting similar accounts are considered suspicious and are further investigated. Comparing the tokenized-string features of a large number of accounts requires an intuitive tokenized-string distance that can detect subtle edits introduced by an adversary, and a very scalable algorithm. This is not achievable by existing distance measure that are unintuitive, hard to tune, and whose join algorithms are serial and hence unscalable. We define a novel intuitive distance measure between tokenized strings, Normalized Setwise Levenshtein Distance (NSLD). To the best of our knowledge, NSLD is the first metric proposed for comparing tokenized strings. We propose a scalable distributed framework, Tokenized-String Joiner (TSJ), that adopts existing scalable string-join algorithms as building blocks to perform NSLD-joins. We carefully engineer optimizations and approximations that dramatically improve the efficiency of TSJ. The effectiveness of the TSJ framework is evident from the evaluation conducted on tens of millions of tokenized-string names from Google accounts. The superiority of the tokenized-string-specific TSJ framework over the general-purpose metric-spaces joining algorithms has been established.
Tasks	Fraud Detection
Published	2019-03-21
URL	http://arxiv.org/abs/1903.09238v1
PDF	http://arxiv.org/pdf/1903.09238v1.pdf
PWC	https://paperswithcode.com/paper/scalable-similarity-joins-of-tokenized
Repo
Framework

Recent Advances in End-to-End Spoken Language Understanding


Title	Recent Advances in End-to-End Spoken Language Understanding
Authors	Natalia Tomashenko, Antoine Caubriere, Yannick Esteve, Antoine Laurent, Emmanuel Morin
Abstract	This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. Two SLU tasks are considered: named entity recognition (NER) and semantic slot filling (SF). For these tasks, in order to improve the model performance, we explore various techniques including speaker adaptation, a modification of the connectionist temporal classification (CTC) training criterion, and sequential pretraining.
Tasks	Named Entity Recognition, Slot Filling, Spoken Language Understanding
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13332v1
PDF	https://arxiv.org/pdf/1909.13332v1.pdf
PWC	https://paperswithcode.com/paper/recent-advances-in-end-to-end-spoken-language
Repo
Framework

Attention-Based Structural-Plasticity


Title	Attention-Based Structural-Plasticity
Authors	Soheil Kolouri, Nicholas Ketz, Xinyun Zou, Jeffrey Krichmar, Praveen Pilly
Abstract	Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several efforts towards overcoming catastrophic forgetting in neural networks. Here, we propose a biologically inspired method toward overcoming catastrophic forgetting. Specifically, we define an attention-based selective plasticity of synapses based on the cholinergic neuromodulatory system in the brain. We define synaptic importance parameters in addition to synaptic weights and then use Hebbian learning in parallel with backpropagation algorithm to learn synaptic importances in an online and seamless manner. We test our proposed method on benchmark tasks including the Permuted MNIST and the Split MNIST problems and show competitive performance compared to the state-of-the-art methods.
Tasks
Published	2019-03-02
URL	http://arxiv.org/abs/1903.06070v1
PDF	http://arxiv.org/pdf/1903.06070v1.pdf
PWC	https://paperswithcode.com/paper/attention-based-structural-plasticity
Repo
Framework

Adversarial Examples to Fool Iris Recognition Systems


Title	Adversarial Examples to Fool Iris Recognition Systems
Authors	Sobhan Soleymani, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
Abstract	Adversarial examples have recently proven to be able to fool deep learning methods by adding carefully crafted small perturbation to the input space image. In this paper, we study the possibility of generating adversarial examples for code-based iris recognition systems. Since generating adversarial examples requires back-propagation of the adversarial loss, conventional filter bank-based iris-code generation frameworks cannot be employed in such a setup. Therefore, to compensate for this shortcoming, we propose to train a deep auto-encoder surrogate network to mimic the conventional iris code generation procedure. This trained surrogate network is then deployed to generate the adversarial examples using the iterative gradient sign method algorithm. We consider non-targeted and targeted attacks through three attack scenarios. Considering these attacks, we study the possibility of fooling an iris recognition system in white-box and black-box frameworks.
Tasks	Code Generation, Iris Recognition
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09300v2
PDF	https://arxiv.org/pdf/1906.09300v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-examples-to-fool-iris-recognition
Repo
Framework