May 6, 2019

3041 words 15 mins read

Paper Group ANR 417

Developing an ICU scoring system with interaction terms using a genetic algorithm. Susceptibility of texture measures to noise: an application to lung tumor CT images. Argumentation Models for Cyber Attribution. Multiple Instance Hyperspectral Target Characterization. American Sign Language fingerspelling recognition from video: Methods for unrestr …

Developing an ICU scoring system with interaction terms using a genetic algorithm


Title	Developing an ICU scoring system with interaction terms using a genetic algorithm
Authors	Chee Chun Gan, Gerard Learmonth
Abstract	ICU mortality scoring systems attempt to predict patient mortality using predictive models with various clinical predictors. Examples of such systems are APACHE, SAPS and MPM. However, most such scoring systems do not actively look for and include interaction terms, despite physicians intuitively taking such interactions into account when making a diagnosis. One barrier to including such terms in predictive models is the difficulty of using most variable selection methods in high-dimensional datasets. A genetic algorithm framework for variable selection with logistic regression models is used to search for two-way interaction terms in a clinical dataset of adult ICU patients, with separate models being built for each category of diagnosis upon admittance to the ICU. The models had good discrimination across all categories, with a weighted average AUC of 0.84 (>0.90 for several categories) and the genetic algorithm was able to find several significant interaction terms, which may be able to provide greater insight into mortality prediction for health practitioners. The GA selected models had improved performance against stepwise selection and random forest models, and provides greater flexibility in terms of variable selection by being able to optimize over any modeler-defined model performance metric instead of a specific variable importance metric.
Tasks	Mortality Prediction
Published	2016-04-22
URL	http://arxiv.org/abs/1604.06730v1
PDF	http://arxiv.org/pdf/1604.06730v1.pdf
PWC	https://paperswithcode.com/paper/developing-an-icu-scoring-system-with
Repo
Framework

Susceptibility of texture measures to noise: an application to lung tumor CT images


Title	Susceptibility of texture measures to noise: an application to lung tumor CT images
Authors	O. S. Al-Kadi, D. Watson
Abstract	Five different texture methods are used to investigate their susceptibility to subtle noise occurring in lung tumor Computed Tomography (CT) images caused by acquisition and reconstruction deficiencies. Noise of Gaussian and Rayleigh distributions with varying mean and variance was encountered in the analyzed CT images. Fisher and Bhattacharyya distance measures were used to differentiate between an original extracted lung tumor region of interest (ROI) with a filtered and noisy reconstructed versions. Through examining the texture characteristics of the lung tumor areas by five different texture measures, it was determined that the autocovariance measure was least affected and the gray level co-occurrence matrix was the most affected by noise. Depending on the selected ROI size, it was concluded that the number of extracted features from each texture measure increases susceptibility to noise.
Tasks	Computed Tomography (CT)
Published	2016-01-02
URL	http://arxiv.org/abs/1601.00210v1
PDF	http://arxiv.org/pdf/1601.00210v1.pdf
PWC	https://paperswithcode.com/paper/susceptibility-of-texture-measures-to-noise
Repo
Framework

Argumentation Models for Cyber Attribution


Title	Argumentation Models for Cyber Attribution
Authors	Eric Nunes, Paulo Shakarian, Gerardo I. Simari, Andrew Ruef
Abstract	A major challenge in cyber-threat analysis is combining information from different sources to find the person or the group responsible for the cyber-attack. It is one of the most important technical and policy challenges in cyber-security. The lack of ground truth for an individual responsible for an attack has limited previous studies. In this paper, we take a first step towards overcoming this limitation by building a dataset from the capture-the-flag event held at DEFCON, and propose an argumentation model based on a formal reasoning framework called DeLP (Defeasible Logic Programming) designed to aid an analyst in attributing a cyber-attack. We build models from latent variables to reduce the search space of culprits (attackers), and show that this reduction significantly improves the performance of classification-based approaches from 37% to 62% in identifying the attacker.
Tasks
Published	2016-07-07
URL	http://arxiv.org/abs/1607.02171v1
PDF	http://arxiv.org/pdf/1607.02171v1.pdf
PWC	https://paperswithcode.com/paper/argumentation-models-for-cyber-attribution
Repo
Framework

Multiple Instance Hyperspectral Target Characterization


Title	Multiple Instance Hyperspectral Target Characterization
Authors	Alina Zare, Changzhe Jiao, Taylor Glenn
Abstract	In this paper, two methods for multiple instance target characterization, MI-SMF and MI-ACE, are presented. MI-SMF and MI-ACE estimate a discriminative target signature from imprecisely-labeled and mixed training data. In many applications, such as sub-pixel target detection in remotely-sensed hyperspectral imagery, accurate pixel-level labels on training data is often unavailable and infeasible to obtain. Furthermore, since sub-pixel targets are smaller in size than the resolution of a single pixel, training data is comprised only of mixed data points (in which target training points are mixtures of responses from both target and non-target classes). Results show improved, consistent performance over existing multiple instance concept learning methods on several hyperspectral sub-pixel target detection problems.
Tasks
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06354v3
PDF	http://arxiv.org/pdf/1606.06354v3.pdf
PWC	https://paperswithcode.com/paper/multiple-instance-hyperspectral-target
Repo
Framework

American Sign Language fingerspelling recognition from video: Methods for unrestricted recognition and signer-independence


Title	American Sign Language fingerspelling recognition from video: Methods for unrestricted recognition and signer-independence
Authors	Taehwan Kim
Abstract	In this thesis, we study the problem of recognizing video sequences of fingerspelled letters in American Sign Language (ASL). Fingerspelling comprises a significant but relatively understudied part of ASL, and recognizing it is challenging for a number of reasons: It involves quick, small motions that are often highly coarticulated; it exhibits significant variation between signers; and there has been a dearth of continuous fingerspelling data collected. In this work, we propose several types of recognition approaches, and explore the signer variation problem. Our best-performing models are segmental (semi-Markov) conditional random fields using deep neural network-based features. In the signer-dependent setting, our recognizers achieve up to about 8% letter error rates. The signer-independent setting is much more challenging, but with neural network adaptation we achieve up to 17% letter error rates.
Tasks
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08339v1
PDF	http://arxiv.org/pdf/1608.08339v1.pdf
PWC	https://paperswithcode.com/paper/american-sign-language-fingerspelling-1
Repo
Framework

HMM and DTW for evaluation of therapeutical gestures using kinect


Title	HMM and DTW for evaluation of therapeutical gestures using kinect
Authors	Carlos Palma, Augusto Salazar, Francisco Vargas
Abstract	Automatic recognition of the quality of movement in human beings is a challenging task, given the difficulty both in defining the constraints that make a movement correct, and the difficulty in using noisy data to determine if these constraints were satisfied. This paper presents a method for the detection of deviations from the correct form in movements from physical therapy routines based on Hidden Markov Models, which is compared to Dynamic Time Warping. The activities studied include upper an lower limbs movements, the data used comes from a Kinect sensor. Correct repetitions of the activities of interest were recorded, as well as deviations from these correct forms. The ability of the proposed approach to detect these deviations was studied. Results show that a system based on HMM is much more likely to determine if a certain movement has deviated from the specification.
Tasks
Published	2016-02-11
URL	http://arxiv.org/abs/1602.03742v1
PDF	http://arxiv.org/pdf/1602.03742v1.pdf
PWC	https://paperswithcode.com/paper/hmm-and-dtw-for-evaluation-of-therapeutical
Repo
Framework

Hypervolume-based Multi-objective Bayesian Optimization with Student-t Processes


Title	Hypervolume-based Multi-objective Bayesian Optimization with Student-t Processes
Authors	Joachim van der Herten, Ivo Couckuyt, Tom Dhaene
Abstract	Student-$t$ processes have recently been proposed as an appealing alternative non-parameteric function prior. They feature enhanced flexibility and predictive variance. In this work the use of Student-$t$ processes are explored for multi-objective Bayesian optimization. In particular, an analytical expression for the hypervolume-based probability of improvement is developed for independent Student-$t$ process priors of the objectives. Its effectiveness is shown on a multi-objective optimization problem which is known to be difficult with traditional Gaussian processes.
Tasks	Gaussian Processes
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00393v1
PDF	http://arxiv.org/pdf/1612.00393v1.pdf
PWC	https://paperswithcode.com/paper/hypervolume-based-multi-objective-bayesian
Repo
Framework

A Spiking Network that Learns to Extract Spike Signatures from Speech Signals


Title	A Spiking Network that Learns to Extract Spike Signatures from Speech Signals
Authors	Amirhossein Tavanaei, Anthony S Maida
Abstract	Spiking neural networks (SNNs) with adaptive synapses reflect core properties of biological neural networks. Speech recognition, as an application involving audio coding and dynamic learning, provides a good test problem to study SNN functionality. We present a simple, novel, and efficient nonrecurrent SNN that learns to convert a speech signal into a spike train signature. The signature is distinguishable from signatures for other speech signals representing different words, thereby enabling digit recognition and discrimination in devices that use only spiking neurons. The method uses a small, nonrecurrent SNN consisting of Izhikevich neurons equipped with spike timing dependent plasticity (STDP) and biologically realistic synapses. This approach introduces an efficient and fast network without error-feedback training, although it does require supervised training. The new simulation results produce discriminative spike train patterns for spoken digits in which highly correlated spike trains belong to the same category and low correlated patterns belong to different categories. The proposed SNN is evaluated using a spoken digit recognition task where a subset of the Aurora speech dataset is used. The experimental results show that the network performs well in terms of accuracy rate and complexity.
Tasks	Speech Recognition
Published	2016-06-02
URL	http://arxiv.org/abs/1606.00802v3
PDF	http://arxiv.org/pdf/1606.00802v3.pdf
PWC	https://paperswithcode.com/paper/a-spiking-network-that-learns-to-extract
Repo
Framework

Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration


Title	Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration
Authors	Abhishek Gupta, Clemens Eppner, Sergey Levine, Pieter Abbeel
Abstract	Dexterous multi-fingered hands can accomplish fine manipulation behaviors that are infeasible with simple robotic grippers. However, sophisticated multi-fingered hands are often expensive and fragile. Low-cost soft hands offer an appealing alternative to more conventional devices, but present considerable challenges in sensing and actuation, making them difficult to apply to more complex manipulation tasks. In this paper, we describe an approach to learning from demonstration that can be used to train soft robotic hands to perform dexterous manipulation tasks. Our method uses object-centric demonstrations, where a human demonstrates the desired motion of manipulated objects with their own hands, and the robot autonomously learns to imitate these demonstrations using reinforcement learning. We propose a novel algorithm that allows us to blend and select a subset of the most feasible demonstrations to learn to imitate on the hardware, which we use with an extension of the guided policy search framework to use multiple demonstrations to learn generalizable neural network policies. We demonstrate our approach on the RBO Hand 2, with learned motor skills for turning a valve, manipulating an abacus, and grasping.
Tasks
Published	2016-03-21
URL	http://arxiv.org/abs/1603.06348v3
PDF	http://arxiv.org/pdf/1603.06348v3.pdf
PWC	https://paperswithcode.com/paper/learning-dexterous-manipulation-for-a-soft
Repo
Framework

Convolutional Neural Networks for Attribute-based Active Authentication on Mobile Devices


Title	Convolutional Neural Networks for Attribute-based Active Authentication on Mobile Devices
Authors	Pouya Samangouei, Rama Chellappa
Abstract	We present a Deep Convolutional Neural Network (DCNN) architecture for the task of continuous authentication on mobile devices. To deal with the limited resources of these devices, we reduce the complexity of the networks by learning intermediate features such as gender and hair color instead of identities. We present a multi-task, part-based DCNN architecture for attribute detection that performs better than the state-of-the-art methods in terms of accuracy. As a byproduct of the proposed architecture, we are able to explore the embedding space of the attributes extracted from different facial parts, such as mouth and eyes, to discover new attributes. Furthermore, through extensive experimentation, we show that the attribute features extracted by our method outperform the previously presented attribute-based method and a baseline LBP method for the task of active authentication. Lastly, we demonstrate the effectiveness of the proposed architecture in terms of speed and power consumption by deploying it on an actual mobile device.
Tasks
Published	2016-04-29
URL	http://arxiv.org/abs/1604.08865v2
PDF	http://arxiv.org/pdf/1604.08865v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-attribute
Repo
Framework

Predicting Glaucoma Visual Field Loss by Hierarchically Aggregating Clustering-based Predictors


Title	Predicting Glaucoma Visual Field Loss by Hierarchically Aggregating Clustering-based Predictors
Authors	Motohide Higaki, Kai Morino, Hiroshi Murata, Ryo Asaoka, Kenji Yamanishi
Abstract	This study addresses the issue of predicting the glaucomatous visual field loss from patient disease datasets. Our goal is to accurately predict the progress of the disease in individual patients. As very few measurements are available for each patient, it is difficult to produce good predictors for individuals. A recently proposed clustering-based method enhances the power of prediction using patient data with similar spatiotemporal patterns. Each patient is categorized into a cluster of patients, and a predictive model is constructed using all of the data in the class. Predictions are highly dependent on the quality of clustering, but it is difficult to identify the best clustering method. Thus, we propose a method for aggregating cluster-based predictors to obtain better prediction accuracy than from a single cluster-based prediction. Further, the method shows very high performances by hierarchically aggregating experts generated from several cluster-based methods. We use real datasets to demonstrate that our method performs significantly better than conventional clustering-based and patient-wise regression methods, because the hierarchical aggregating strategy has a mechanism whereby good predictors in a small community can thrive.
Tasks
Published	2016-03-23
URL	http://arxiv.org/abs/1603.07094v1
PDF	http://arxiv.org/pdf/1603.07094v1.pdf
PWC	https://paperswithcode.com/paper/predicting-glaucoma-visual-field-loss-by
Repo
Framework

Saliency Detection combining Multi-layer Integration algorithm with background prior and energy function


Title	Saliency Detection combining Multi-layer Integration algorithm with background prior and energy function
Authors	Hanling Zhang, Chenxing Xia
Abstract	In this paper, we propose an improved mechanism for saliency detection. Firstly,based on a neoteric background prior selecting four corners of an image as background,we use color and spatial contrast with each superpixel to obtain a salinecy map(CBP). Inspired by reverse-measurement methods to improve the accuracy of measurement in Engineering,we employ the Objectness labels as foreground prior based on part of information of CBP to construct a map(OFP).Further,an original energy function is applied to optimize both of them respectively and a single-layer saliency map(SLP)is formed by merging the above twos.Finally,to deal with the scale problem,we obtain our multi-layer map(MLP) by presenting an integration algorithm to take advantage of multiple saliency maps. Quantitative and qualitative experiments on three datasets demonstrate that our method performs favorably against the state-of-the-art algorithm.
Tasks	Saliency Detection
Published	2016-03-05
URL	http://arxiv.org/abs/1603.01684v1
PDF	http://arxiv.org/pdf/1603.01684v1.pdf
PWC	https://paperswithcode.com/paper/saliency-detection-combining-multi-layer
Repo
Framework

Minimally Supervised Written-to-Spoken Text Normalization


Title	Minimally Supervised Written-to-Spoken Text Normalization
Authors	Ke Wu, Kyle Gorman, Richard Sproat
Abstract	In speech-applications such as text-to-speech (TTS) or automatic speech recognition (ASR), \emph{text normalization} refers to the task of converting from a \emph{written} representation into a representation of how the text is to be \emph{spoken}. In all real-world speech applications, the text normalization engine is developed—in large part—by hand. For example, a hand-built grammar may be used to enumerate the possible ways of saying a given token in a given language, and a statistical model used to select the most appropriate pronunciation in context. In this study we examine the tradeoffs associated with using more or less language-specific domain knowledge in a text normalization engine. In the most data-rich scenario, we have access to a carefully constructed hand-built normalization grammar that for any given token will produce a set of all possible verbalizations for that token. We also assume a corpus of aligned written-spoken utterances, from which we can train a ranking model that selects the appropriate verbalization for the given context. As a substitute for the carefully constructed grammar, we also consider a scenario with a language-universal normalization \emph{covering grammar}, where the developer merely needs to provide a set of lexical items particular to the language. As a substitute for the aligned corpus, we also consider a scenario where one only has the spoken side, and the corresponding written side is “hallucinated” by composing the spoken side with the inverted normalization grammar. We investigate the accuracy of a text normalization engine under each of these scenarios. We report the results of experiments on English and Russian.
Tasks	Speech Recognition
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06649v1
PDF	http://arxiv.org/pdf/1609.06649v1.pdf
PWC	https://paperswithcode.com/paper/minimally-supervised-written-to-spoken-text
Repo
Framework

Impact of Physical Activity on Sleep:A Deep Learning Based Exploration


Title	Impact of Physical Activity on Sleep:A Deep Learning Based Exploration
Authors	Aarti Sathyanarayana, Shafiq Joty, Luis Fernandez-Luque, Ferda Ofli, Jaideep Srivastava, Ahmed Elmagarmid, Shahrad Taheri, Teresa Arora
Abstract	The importance of sleep is paramount for maintaining physical, emotional and mental wellbeing. Though the relationship between sleep and physical activity is known to be important, it is not yet fully understood. The explosion in popularity of actigraphy and wearable devices, provides a unique opportunity to understand this relationship. Leveraging this information source requires new tools to be developed to facilitate data-driven research for sleep and activity patient-recommendations. In this paper we explore the use of deep learning to build sleep quality prediction models based on actigraphy data. We first use deep learning as a pure model building device by performing human activity recognition (HAR) on raw sensor data, and using deep learning to build sleep prediction models. We compare the deep learning models with those build using classical approaches, i.e. logistic regression, support vector machines, random forest and adaboost. Secondly, we employ the advantage of deep learning with its ability to handle high dimensional datasets. We explore several deep learning models on the raw wearable sensor output without performing HAR or any other feature extraction. Our results show that using a convolutional neural network on the raw wearables output improves the predictive value of sleep quality from physical activity, by an additional 8% compared to state-of-the-art non-deep learning approaches, which itself shows a 15% improvement over current practice. Moreover, utilizing deep learning on raw data eliminates the need for data pre-processing and simplifies the overall workflow to analyze actigraphy data for sleep and physical activity research.
Tasks	Activity Recognition, Human Activity Recognition, Sleep Quality, Sleep Quality Prediction
Published	2016-07-24
URL	http://arxiv.org/abs/1607.07034v1
PDF	http://arxiv.org/pdf/1607.07034v1.pdf
PWC	https://paperswithcode.com/paper/impact-of-physical-activity-on-sleepa-deep
Repo
Framework

Efficient Document Indexing Using Pivot Tree


Title	Efficient Document Indexing Using Pivot Tree
Authors	Gaurav Singh, Benjamin Piwowarski
Abstract	We present a novel method for efficiently searching top-k neighbors for documents represented in high dimensional space of terms based on the cosine similarity. Mostly, documents are stored as bag-of-words tf-idf representation. One of the most used ways of computing similarity between a pair of documents is cosine similarity between the vector representations, but cosine similarity is not a metric distance measure as it doesn’t follow triangle inequality, therefore most metric searching methods can not be applied directly. We propose an efficient method for indexing documents using a pivot tree that leads to efficient retrieval. We also study the relation between precision and efficiency for the proposed method and compare it with a state of the art in the area of document searching based on inner product.
Tasks
Published	2016-05-21
URL	http://arxiv.org/abs/1605.06693v1
PDF	http://arxiv.org/pdf/1605.06693v1.pdf
PWC	https://paperswithcode.com/paper/efficient-document-indexing-using-pivot-tree
Repo
Framework