January 29, 2020

3427 words 17 mins read

Paper Group ANR 513

An Application of Generative Adversarial Networks for Super Resolution Medical Imaging. High Speed Cognitive Domain Ontologies for Asset Allocation Using Loihi Spiking Neurons. Towards Monitoring Parkinson’s Disease Following Drug Treatment: CGP Classification of rs-MRI Data. Codes, Functions, and Causes: A Critique of Brette’s Conceptual Analysis …

An Application of Generative Adversarial Networks for Super Resolution Medical Imaging


Title	An Application of Generative Adversarial Networks for Super Resolution Medical Imaging
Authors	Rewa Sood, Binit Topiwala, Karthik Choutagunta, Rohit Sood, Mirabela Rusu
Abstract	Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires the patient to remain still for long periods of time, which causes patient discomfort and increases the probability of motion induced image artifacts. A possible solution is to acquire low resolution (LR) images and to process them with the Super Resolution Generative Adversarial Network (SRGAN) to create an HR version. Acquiring LR images requires a lower scan time than acquiring HR images, which allows for higher patient comfort and scanner throughput. This work applies SRGAN to MR images of the prostate to improve the in-plane resolution by factors of 4 and 8. The term ‘super resolution’ in the context of this paper defines the post processing enhancement of medical images as opposed to ‘high resolution’ which defines native image resolution acquired during the MR acquisition phase. We also compare the SRGAN to three other models: SRCNN, SRResNet, and Sparse Representation. While the SRGAN results do not have the best Peak Signal to Noise Ratio (PSNR) or Structural Similarity (SSIM) metrics, they are the visually most similar to the original HR images, as portrayed by the Mean Opinion Score (MOS) results.
Tasks	Super-Resolution
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09507v1
PDF	https://arxiv.org/pdf/1912.09507v1.pdf
PWC	https://paperswithcode.com/paper/an-application-of-generative-adversarial
Repo
Framework

High Speed Cognitive Domain Ontologies for Asset Allocation Using Loihi Spiking Neurons


Title	High Speed Cognitive Domain Ontologies for Asset Allocation Using Loihi Spiking Neurons
Authors	Chris Yakopcic, Nayim Rahman, Tanvir Atahary, Tarek M. Taha, Alex Beigh, Scott Douglass
Abstract	Cognitive agents are typically utilized in autonomous systems for automated decision making. These systems interact at real time with their environment and are generally heavily power constrained. Thus, there is a strong need for a real time agent running on a low power platform. The agent examined is the Cognitively Enhanced Complex Event Processing (CECEP) architecture. This is an autonomous decision support tool that reasons like humans and enables enhanced agent-based decision-making. It has applications in a large variety of domains including autonomous systems, operations research, intelligence analysis, and data mining. One of the key components of CECEP is the mining of knowledge from a repository described as a Cognitive Domain Ontology (CDO). One problem that is often tasked to CDOs is asset allocation. Given the number of possible solutions in this allocation problem, determining the optimal solution via CDO can be very time consuming. In this work we show that a grid of isolated spiking neurons is capable of generating solutions to this problem very quickly, although some degree of approximation is required to achieve the speedup. However, the approximate spiking approach presented in this work was able to complete all allocation simulations with greater than 99.9% accuracy. To show the feasibility of low power implementation, this algorithm was executed using the Intel Loihi manycore neuromorphic processor. Given the vast increase in speed (greater than 1000 times in larger allocation problems), as well as the reduction in computational requirements, the presented algorithm is ideal for moving asset allocation to low power, portable, embedded hardware.
Tasks	Decision Making
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12338v1
PDF	https://arxiv.org/pdf/1906.12338v1.pdf
PWC	https://paperswithcode.com/paper/high-speed-cognitive-domain-ontologies-for
Repo
Framework

Towards Monitoring Parkinson’s Disease Following Drug Treatment: CGP Classification of rs-MRI Data


Title	Towards Monitoring Parkinson’s Disease Following Drug Treatment: CGP Classification of rs-MRI Data
Authors	Amir Dehsarvi, Jennifer Kay South Palomares, Stephen Leslie Smith
Abstract	Background and Objective: It is commonly accepted that accurate monitoring of neurodegenerative diseases is crucial for effective disease management and delivery of medication and treatment. This research develops automatic clinical monitoring techniques for PD, following treatment, using the novel application of EAs. Specifically, the research question addressed was: Can accurate monitoring of PD be achieved using EAs on rs-fMRI data for patients prescribed Modafinil (typically prescribed for PD patients to relieve physical fatigue)? Methods: This research develops novel clinical monitoring tools using data from a controlled experiment where participants were administered Modafinil versus placebo, examining the novel application of EAs to both map and predict the functional connectivity in participants using rs-fMRI data. Specifically, CGP was used to classify DCM analysis and timeseries data. Results were validated with two other commonly used classification methods (ANN and SVM) and via k-fold cross-validation. Results: Findings revealed a maximum accuracy of 74.57% for CGP. Furthermore, CGP provided comparable performance accuracy relative to ANN and SVM. Nevertheless, EAs enable us to decode the classifier, in terms of understanding the data inputs that are used, more easily than in ANN and SVM. Conclusions: These findings underscore the applicability of both DCM analyses for classification and CGP as a novel classification technique for brain imaging data with medical implications for medication monitoring. Furthermore, classification of fMRI data for research typically involves statistical modelling techniques being often hypothesis driven, whereas EAs use data-driven explanatory modelling methods resulting in numerous benefits. DCM analysis is novel for classification and advantageous as it provides information on the causal links between different brain regions.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.03439v1
PDF	https://arxiv.org/pdf/1911.03439v1.pdf
PWC	https://paperswithcode.com/paper/towards-monitoring-parkinsons-disease
Repo
Framework

Codes, Functions, and Causes: A Critique of Brette’s Conceptual Analysis of Coding


Title	Codes, Functions, and Causes: A Critique of Brette’s Conceptual Analysis of Coding
Authors	David Barack, Andrew Jaegle
Abstract	In a recent article, Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette’s conceptual analysis mischaracterizes the structure of causal claims in coding and other forms of analysis-by-decomposition. We argue that analyses of this form are permissible, conceptually coherent, and offer essential tools for building and developing models of neurocognitive systems like the brain.
Tasks
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08873v1
PDF	http://arxiv.org/pdf/1904.08873v1.pdf
PWC	https://paperswithcode.com/paper/codes-functions-and-causes-a-critique-of
Repo
Framework

Verification of data-aware workflows via reachability: formalisation and experiments


Title	Verification of data-aware workflows via reachability: formalisation and experiments
Authors	Riccardo De Masellis, Chiara Di Francescomarino, Chiara Ghidini, Sergio Tessaris
Abstract	The growing adoption of IT-systems for the modelling and execution of (business) processes or services has thrust the scientific investigation towards techniques and tools which support complex forms of process analysis. These techniques rely on observation of past (tracked and logged) process executions but typically: (i) only consider activities, lacking the ability to take into account the data objects manipulated by these activities and (ii) assume complete observations of terminated process executions. In many real cases, however, only incomplete log information is available. This paper tackles these two shortcomings by proposing an approach to exploit reachability to reason on imperative data-aware process models and possibly incomplete process executions. The contribution of this paper is twofold: first, it formulates the trace completion as a reachability problem over data-aware models and second, it provides a rigorous mapping between our data-aware models and three important paradigms for reasoning about dynamic systems, namely Action Languages, Classical Planning, and Model-Checking. This allows us to exploit and extensively evaluate the available tools for the above paradigms to solve the trace repair problem. The rigorous encoding of our data-aware models, based on a common interpretation of the semantics of Action Languages, Classical Planning, and Model-Checking in terms of transition systems, paired with a first comprehensive assessment of the performances of their tools in computing reachability for data-aware workflow net languages, provide a solid contribution to advancing the state-of-the-art on the concrete exploitation of formal verification techniques on business processes.
Tasks
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12738v1
PDF	https://arxiv.org/pdf/1909.12738v1.pdf
PWC	https://paperswithcode.com/paper/verification-of-data-aware-workflows-via
Repo
Framework

Deep learning velocity signals allows to quantify turbulence intensity


Title	Deep learning velocity signals allows to quantify turbulence intensity
Authors	Alessandro Corbetta, Vlado Menkovski, Roberto Benzi, Federico Toschi
Abstract	Turbulence, the ubiquitous and chaotic state of fluid motions, is characterized by strong and statistically non-trivial fluctuations of the velocity field, over a wide range of length- and time-scales, and it can be quantitatively described only in terms of statistical averages. Strong non-stationarities hinder the possibility to achieve statistical convergence, making it impossible to define the turbulence intensity and, in particular, its basic dimensionless estimator, the Reynolds number. Here we show that by employing Deep Neural Networks (DNN) we can accurately estimate the Reynolds number within $15%$ accuracy, from a statistical sample as small as two large-scale eddy-turnover times. In contrast, physics-based statistical estimators are limited by the rate of convergence of the central limit theorem, and provide, for the same statistical sample, an error at least $100$ times larger. Our findings open up new perspectives in the possibility to quantitatively define and, therefore, study highly non-stationary turbulent flows as ordinarily found in nature as well as in industrial processes.
Tasks
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05718v2
PDF	https://arxiv.org/pdf/1911.05718v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-velocity-signals-allows-to
Repo
Framework

Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement


Title	Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement
Authors	Soumi Maiti, Michael I Mandel
Abstract	Traditional speech enhancement systems produce speech with compromised quality. Here we propose to use the high quality speech generation capability of neural vocoders for better quality speech enhancement. We term this parametric resynthesis (PR). In previous work, we showed that PR systems generate high quality speech for a single speaker using two neural vocoders, WaveNet and WaveGlow. Both these vocoders are traditionally speaker dependent. Here we first show that when trained on data from enough speakers, these vocoders can generate speech from unseen speakers, both male and female, with similar quality as seen speakers in training. Next using these two vocoders and a new vocoder LPCNet, we evaluate the noise reduction quality of PR on unseen speakers and show that objective signal and overall quality is higher than the state-of-the-art speech enhancement systems Wave-U-Net, Wavenet-denoise, and SEGAN. Moreover, in subjective quality, multiple-speaker PR out-performs the oracle Wiener mask.
Tasks	Speech Enhancement
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06266v1
PDF	https://arxiv.org/pdf/1911.06266v1.pdf
PWC	https://paperswithcode.com/paper/speaker-independence-of-neural-vocoders-and
Repo
Framework

Efficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR


Title	Efficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR
Authors	Jesus Zarzar, Silvio Giancola, Bernard Ghanem
Abstract	Tracking vehicles in LIDAR point clouds is a challenging task due to the sparsity of the data and the dense search space. The lack of structure in point clouds impedes the use of convolution and correlation filters usually employed in 2D object tracking. In addition, structuring point clouds is cumbersome and implies losing fine-grained information. As a result, generating proposals in 3D space is expensive and inefficient. In this paper, we leverage the dense and structured Bird Eye View (BEV) representation of LIDAR point clouds to efficiently search for objects of interest. We use an efficient Region Proposal Network and generate a small number of object proposals in 3D. Successively, we refine our selection of 3D object candidates by exploiting the similarity capability of a 3D Siamese network. We regularize the latter 3D Siamese network for shape completion to enhance its discrimination capability. Our method attempts to solve both for an efficient search space in the BEV space and a meaningful selection using 3D LIDAR point cloud. We show that the Region Proposal in the BEV outperforms Bayesian methods such as Kalman and Particle Filters in providing proposal by a significant margin and that such candidates are suitable for the 3D Siamese network. By training our method end-to-end, we outperform the previous baseline in vehicle tracking by 12% / 18% in Success and Precision when using only 16 candidates.
Tasks	Object Tracking
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10168v1
PDF	http://arxiv.org/pdf/1903.10168v1.pdf
PWC	https://paperswithcode.com/paper/efficient-tracking-proposals-using-2d-3d
Repo
Framework

A Bad Arm Existence Checking Problem


Title	A Bad Arm Existence Checking Problem
Authors	Koji Tabata, Atsuyoshi Nakamura, Junya Honda, Tamiki Komatsuzaki
Abstract	We study a bad arm existing checking problem in which a player’s task is to judge whether a positive arm exists or not among given K arms by drawing as small number of arms as possible. Here, an arm is positive if its expected loss suffered by drawing the arm is at least a given threshold. This problem is a formalization of diagnosis of disease or machine failure. An interesting structure of this problem is the asymmetry of positive and negative (non-positive) arms’ roles; finding one positive arm is enough to judge existence while all the arms must be discriminated as negative to judge non-existence. We propose an algorithms with arm selection policy (policy to determine the next arm to draw) and stopping condition (condition to stop drawing arms) utilizing this asymmetric problem structure and prove its effectiveness theoretically and empirically.
Tasks
Published	2019-01-31
URL	http://arxiv.org/abs/1901.11200v1
PDF	http://arxiv.org/pdf/1901.11200v1.pdf
PWC	https://paperswithcode.com/paper/a-bad-arm-existence-checking-problem
Repo
Framework

Effective Context and Fragment Feature Usage for Named Entity Recognition


Title	Effective Context and Fragment Feature Usage for Named Entity Recognition
Authors	Nargiza Nosirova, Mingbin Xu, Hui Jiang
Abstract	In this paper, we explore a new approach to named entity recognition (NER) with the goal of learning from context and fragment features more effectively, contributing to the improvement of overall recognition performance. We use the recent fixed-size ordinally forgetting encoding (FOFE) method to fully encode each sentence fragment and its left-right contexts into a fixed-size representation. Next, we organize the context and fragment features into groups, and feed each feature group to dedicated fully-connected layers. Finally, we merge each group’s final dedicated layers and add a shared layer leading to a single output. The outcome of our experiments show that, given only tokenized text and trained word embeddings, our system outperforms our baseline models, and is competitive to the state-of-the-arts of various well-known NER tasks.
Tasks	Named Entity Recognition, Word Embeddings
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03305v2
PDF	http://arxiv.org/pdf/1904.03305v2.pdf
PWC	https://paperswithcode.com/paper/effective-context-and-fragment-feature-usage
Repo
Framework

DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition


Title	DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
Authors	Zheng Shou, Xudong Lin, Yannis Kalantidis, Laura Sevilla-Lara, Marcus Rohrbach, Shih-Fu Chang, Zhicheng Yan
Abstract	Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation. To remedy these issues, we propose a lightweight generator network, which reduces noises in motion vectors and captures fine motion details, achieving a more Discriminative Motion Cue (DMC) representation. Since optical flow is a more accurate motion representation, we train the DMC generator to approximate flow using a reconstruction loss and a generative adversarial loss, jointly with the downstream action classification task. Extensive evaluations on three action recognition benchmarks (HMDB-51, UCF-101, and a subset of Kinetics) confirm the effectiveness of our method. Our full system, consisting of the generator and the classifier, is coined as DMC-Net which obtains high accuracy close to that of using flow and runs two orders of magnitude faster than using optical flow at inference time.
Tasks	Action Classification, Optical Flow Estimation, Temporal Action Localization, Video Understanding
Published	2019-01-11
URL	https://arxiv.org/abs/1901.03460v3
PDF	https://arxiv.org/pdf/1901.03460v3.pdf
PWC	https://paperswithcode.com/paper/dmc-net-generating-discriminative-motion-cues
Repo
Framework

Neural Constituency Parsing of Speech Transcripts


Title	Neural Constituency Parsing of Speech Transcripts
Authors	Paria Jamshid Lou, Yufei Wang, Mark Johnson
Abstract	This paper studies the performance of a neural self-attentive parser on transcribed speech. Speech presents parsing challenges that do not appear in written text, such as the lack of punctuation and the presence of speech disfluencies (including filled pauses, repetitions, corrections, etc.). Disfluencies are especially problematic for conventional syntactic parsers, which typically fail to find any EDITED disfluency nodes at all. This motivated the development of special disfluency detection systems, and special mechanisms added to parsers specifically to handle disfluencies. However, we show here that neural parsers can find EDITED disfluency nodes, and the best neural parsers find them with an accuracy surpassing that of specialized disfluency detection systems, thus making these specialized mechanisms unnecessary. This paper also investigates a modified loss function that puts more weight on EDITED nodes. It also describes tree-transformations that simplify the disfluency detection task by providing alternative encodings of disfluencies and syntactic information.
Tasks	Constituency Parsing
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08535v3
PDF	https://arxiv.org/pdf/1904.08535v3.pdf
PWC	https://paperswithcode.com/paper/neural-constituency-parsing-of-speech
Repo
Framework

Learning Multimorbidity Patterns from Electronic Health Records Using Non-negative Matrix Factorisation


Title	Learning Multimorbidity Patterns from Electronic Health Records Using Non-negative Matrix Factorisation
Authors	Abdelaali Hassaine, Dexter Canoy, Jose Roberto Ayala Solares, Yajie Zhu, Shishir Rao, Yikuan Li, Mariagrazia Zottoli, Kazem Rahimi, Gholamreza Salimi-Khorshidi
Abstract	Multimorbidity, or the presence of several medical conditions in the same individual, has been increasing in the population, both in absolute and relative terms. However, multimorbidity remains poorly understood, and the evidence from existing research to describe its burden, determinants and consequences has been limited. Previous studies attempting to understand multimorbidity patterns are often cross-sectional and do not explicitly account for multimorbidity patterns’ evolution over time; some of them are based on small datasets and/or use arbitrary and narrow age ranges; and those that employed advanced models, usually lack appropriate benchmarking and validations. In this study, we (1) introduce a novel approach for using Non-negative Matrix Factorisation (NMF) for temporal phenotyping (i.e., simultaneously mining disease clusters and their trajectories); (2) provide quantitative metrics for the evaluation of disease clusters from such studies; and (3) demonstrate how the temporal characteristics of the disease clusters that result from our model can help mine multimorbidity networks and generate new hypotheses for the emergence of various multimorbidity patterns over time. We trained and evaluated our models on one of the world’s largest electronic health records (EHR), with 7 million patients, from which over 2 million where relevant to this study.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08577v2
PDF	https://arxiv.org/pdf/1907.08577v2.pdf
PWC	https://paperswithcode.com/paper/learning-multimorbidity-patterns-from
Repo
Framework

Obfuscation for Privacy-preserving Syntactic Parsing


Title	Obfuscation for Privacy-preserving Syntactic Parsing
Authors	Zhifeng Hu, Serhii Havrylov, Ivan Titov, Shay B. Cohen
Abstract	The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural language data, inspired by homomorphic encryption. Our primary tool is {\em obfuscation}, relying on the properties of natural language. Specifically, a given text is obfuscated using a neural model that aims to preserve the syntactic relationships of the original sentence so that the obfuscated sentence can be parsed instead of the original one. The model works at the word level, and learns to obfuscate each word separately by changing it into a new word that has a similar syntactic role. The text encrypted by our model leads to better performance on three syntactic parsers (two dependency and one constituency parsers) in comparison to a strong random baseline. The substituted words have similar syntactic properties, but different semantic content, compared to the original words.
Tasks
Published	2019-04-21
URL	http://arxiv.org/abs/1904.09585v1
PDF	http://arxiv.org/pdf/1904.09585v1.pdf
PWC	https://paperswithcode.com/paper/obfuscation-for-privacy-preserving-syntactic
Repo
Framework

Weakly Supervised Prostate TMA Classification via Graph Convolutional Networks


Title	Weakly Supervised Prostate TMA Classification via Graph Convolutional Networks
Authors	Jingwen Wang, Richard J. Chen, Ming Y. Lu, Alexander Baras, Faisal Mahmood
Abstract	Histology-based grade classification is clinically important for many cancer types in stratifying patients distinct treatment groups. In prostate cancer, the Gleason score is a grading system used to measure the aggressiveness of prostate cancer from the spatial organization of cells and the distribution of glands. However, the subjective interpretation of Gleason score often suffers from large interobserver and intraobserver variability. Previous work in deep learning-based objective Gleason grading requires manual pixel-level annotation. In this work, we propose a weakly-supervised approach for grade classification in tissue micro-arrays (TMA) using graph convolutional networks (GCNs), in which we model the spatial organization of cells as a graph to better capture the proliferation and community structure of tumor cells. As node-level features in our graph representation, we learn the morphometry of each cell using a contrastive predictive coding (CPC)-based self-supervised approach. We demonstrate that on a five-fold cross validation our method can achieve $0.9659\pm0.0096$ AUC using only TMA-level labels. Our method demonstrates a 39.80% improvement over standard GCNs with texture features and a 29.27% improvement over GCNs with VGG19 features. Our proposed pipeline can be used to objectively stratify low and high risk cases, reducing inter- and intra-observer variability and pathologist workload.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13328v2
PDF	https://arxiv.org/pdf/1910.13328v2.pdf
PWC	https://paperswithcode.com/paper/191013328
Repo
Framework