arXiv subjects

Puneet Sharma

Publications and source records attributed to Puneet Sharma.

At least 55 records · Page 3Linked to original sources

arXiv2020

A DICOM Framework for Machine Learning Pipelines against Real-Time Radiology Images

Executing machine learning (ML) pipelines in real-time on radiology images is hard due to the limited computing resources in clinical environments and the lack of efficient data transfer capabilities to run them on research clusters. We propose Niffler, an integrated framework that enables the execution of ML pipelines at research clusters by efficiently querying and retrieving radiology images from the Picture Archiving and Communication Systems (PACS) of the hospitals. Niffler uses the Digital Imaging and Communications in Medicine (DICOM) protocol to fetch and store imaging data and provides metadata extraction capabilities and Application programming interfaces (APIs) to apply filters on the images. Niffler further enables the sharing of the outcomes from the ML pipelines in a de-identified manner. Niffler has been running stable for more than 19 months and has supported several research projects at the department. In this paper, we present its architecture and three of its use cases: an inferior vena cava (IVC) filter detection from the images in real-time, identification of scanner utilization, and scanner clock calibration. Evaluations on the Niffler prototype highlight its feasibility and efficiency in facilitating the ML pipelines on the images and metadata in real-time and retrospectively.

eess.IV↗

arXiv2020

Assertion Detection in Multi-Label Clinical Text using Scope Localization

Multi-label sentences (text) in the clinical domain result from the rich description of scenarios during patient care. The state-of-theart methods for assertion detection mostly address this task in the setting of a single assertion label per sentence (text). In addition, few rules based and deep learning methods perform negation/assertion scope detection on single-label text. It is a significant challenge extending these methods to address multi-label sentences without diminishing performance. Therefore, we developed a convolutional neural network (CNN) architecture to localize multiple labels and their scopes in a single stage end-to-end fashion, and demonstrate that our model performs atleast 12% better than the state-of-the-art on multi-label clinical text.

cs.LG↗

arXiv2020

PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing

The global health threat from COVID-19 has been controlled in a number of instances by large-scale testing and contact tracing efforts. We created this document to suggest three functionalities on how we might best harness computing technologies to supporting the goals of public health organizations in minimizing morbidity and mortality associated with the spread of COVID-19, while protecting the civil liberties of individuals. In particular, this work advocates for a third-party free approach to assisted mobile contact tracing, because such an approach mitigates the security and privacy risks of requiring a trusted third party. We also explicitly consider the inferential risks involved in any contract tracing system, where any alert to a user could itself give rise to de-anonymizing information. More generally, we hope to participate in bringing together colleagues in industry, academia, and civil society to discuss and converge on ideas around a critical issue rising with attempts to mitigate the COVID-19 pandemic.

cs.CR↗

arXiv2020

Multi-boundary entanglement in Chern-Simons theory with finite gauge groups

We study the multi-boundary entanglement structure of the states prepared in (1+1) and (2+1) dimensional Chern-Simons theory with finite discrete gauge group $G$. The states in (1+1)-$d$ are associated with Riemann surfaces of genus $g$ with multiple $S^1$ boundaries and we use replica trick to compute the entanglement entropy for such states. In (2+1)-$d$, we focus on the states associated with torus link complements which live in the tensor product of Hilbert spaces associated with multiple $T^2$. We present a quantitative analysis of the entanglement structure for both abelian and non-abelian groups. For all the states considered in this work, we find that the entanglement entropy for direct product of groups is the sum of entropy for individual groups, i.e. $\text{EE}(G_1 \times G_2) = \text{EE}(G_1)+\text{EE}(G_2)$. Moreover, the reduced density matrix obtained by tracing out a subset of the total Hilbert space has a positive semidefinite partial transpose on any bi-partition of the remaining Hilbert space.

hep-th↗

arXiv2019

Multidimensional Shifts And Finite Matrices

Let $X$ be a $2$-dimensional subshift of finite type generated by a finite set of forbidden blocks (of finite size). We give an algorithm for generating the elements of the shift space using sequence of finite matrices (of increasing size). We prove that the sequence generated yields precisely the elements of the shift space $X$ and hence characterizes the elements of the shift space $X$. We extend our investigations to a general $d$-dimensional shift of finite type. In the process, we prove that that elements of $d$-dimensional shift of finite type can be characterized by a sequence of finite matrices (of increasing size).

math.DS↗

arXiv2018

Deep Neural Networks for ECG-free Cardiac Phase and End-Diastolic Frame Detection on Coronary Angiographies

Invasive coronary angiography (ICA) is the gold standard in Coronary Artery Disease (CAD) imaging. Detection of the end-diastolic frame (EDF) and, in general, cardiac phase detection on each temporal frame of a coronary angiography acquisition is of significant importance for the anatomical and non-invasive functional assessment of CAD. This task is generally performed via manual frame selection or semi-automated selection based on simultaneously acquired ECG signals - thus introducing the requirement of simultaneous ECG recordings. We evaluate the performance of a purely image based workflow based on deep neural networks for fully automated cardiac phase and EDF detection on coronary angiographies. A first deep neural network (DNN), trained to detect coronary arteries, is employed to preselect a subset of frames in which coronary arteries are well visible. A second DNN predicts cardiac phase labels for each frame. Only in the training and evaluation phases for the second DNN, ECG signals are used to provide ground truth labels for each angiographic frame. The networks were trained on 17800 coronary angiographies from 3900 patients and evaluated on 27900 coronary angiographies from 6250 patients. No exclusion criteria related to patient state, previous interventions, or pathology were formulated. Cardiac phase detection had an accuracy of 97.6%, a sensitivity of 97.6% and a specificity of 97.5% on the evaluation set. EDF prediction had a precision of 97.4% and a recall of 96.9%. Several sub-group analyses were performed, indicating that the cardiac phase detection performance is largely independent from acquisition angles and the heart rate of the patient. The average execution time of cardiac phase detection for one angiographic series was on average less than five seconds on a standard workstation.

cs.CV↗

arXiv2018

Dynamics Of Finitely Generated Non-Autonomous Systems

In this paper, we discuss dynamical behavior of a non-autonomous system generated by a finite family $\mathbb{F}$. In the process, we relate the dynamical behavior of the non-autonomous system generated by the family $\mathbb{F}=\{f_1,f_2,\ldots,f_k\}$ with the dynamical behavior of the system $(X,f_k\circ f_{k-1}\circ\ldots\circ f_1)$. We discuss properties like minimality, equicontinuity, proximality and various forms of sensitivities for the two systems. We derive conditions under which the dynamical behavior of $(X,f_k\circ f_{k-1}\circ\ldots\circ f_1)$ is carried forward to $(X,\mathbb{F})$ (and vice-versa). We also give examples to illustrate the necessity of the conditions imposed.

math.DS↗

arXiv2018

Select, Attend, and Transfer: Light, Learnable Skip Connections

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients. They equip encoder-decoder-like networks with richer feature representations, but at the cost of higher memory usage, computation, and possibly resulting in transferring non-discriminative feature maps. In this paper, we focus on improving skip connections used in segmentation networks (e.g., U-Net, V-Net, and The One Hundred Layers Tiramisu (DensNet) architectures). We propose light, learnable skip connections which learn to first select the most discriminative channels and then attend to the most discriminative regions of the selected feature maps. The output of the proposed skip connections is a unique feature map which not only reduces the memory usage and network parameters to a high extent, but also improves segmentation accuracy. We evaluate the proposed method on three different 2D and volumetric datasets and demonstrate that the proposed light, learnable skip connections can outperform the traditional heavy skip connections in terms of segmentation accuracy, memory usage, and number of network parameters.

cs.CV↗

arXiv2017

Alterations And Rearrangements Of A Non-Autonomous Dynamical System

In this paper, we discuss the dynamics of alterations and rearrangements of a non-autonomous dynamical system generated by the family $\mathbb{F}$. We prove that while insertion/deletion of a map in the family $\mathbb{F}$ can disturb the dynamics of a system, the dynamics of the system does not change if the map inserted/deleted is feeble open. In the process, we prove that if the inserted/deleted map is feeble open, the altered system exhibits any form of mixing/sensitivity if and only if the original system exhibits the same. We extend our investigations to properties like equicontinuity, minimality and proximality for the two systems. We prove that any finite rearrangement of a non-autonomous dynamical system preserves the dynamics of original system if the family $\mathbb{F}$ is feeble open. We also give examples to show that the dynamical behavior of a system need be not be preserved under infinite rearrangement.

math.DS↗

arXiv2017

On Dynamics Generated by a Uniformly Convergent Sequence of Maps

In this paper, we study the dynamics of a non-autonomous dynamical system $(X,\mathbb{F})$ generated by a sequence $(f_n)$ of continuous self maps converging uniformly to $f$. We relate the dynamics of the non-autonomous system $(X,\mathbb{F})$ with the dynamics of $(X,f)$. We prove that if the family $\mathbb{F}$ commutes with $f$ and $(f_n)$ converges to $f$ at a "sufficiently fast rate", many of the dynamical properties for the systems $(X,\mathbb{F})$ and $(X,f)$ coincide. In the procees we establish equivalence of properties like equicontinuity, minimality and denseness of proximal pairs (cells) for the two systems. In addition, if $\mathbb{F}$ is feeble open, we establish equivalence of properties like transitivity, weak mixing and various forms of sensitivities. We prove that feeble openness of $\mathbb{F}$ is sufficient to establish equivalence of topological mixing for the two systems. We prove that if $\mathbb{F}$ is feeble open, dynamics of the non-autonomous system on a compact interval exhibits any form of mixing if and only if $(X,f)$ exhibits identical form of mixing. We also investigate dense periodicity for the two systems. We give examples to investigate sufficiency/necessity of the conditions imposed. In the process we derive weaker conditions under which the established dynamical relation (between the two systems $(X,\mathbb{F})$ and $(X,f)$) is preserved.

math.DS↗

arXiv2017

Induced Dynamics of Non-Autonomous Discrete Dynamical Systems

In this paper, we investigate the dynamics on the hyperspace induced by a non-autonomous dynamical system $(X,\mathbb{F})$, where the non-autonomous system is generated by a sequence $(f_n)$ of continuous self maps on $X$. We relate the dynamical behavior of the induced system on the hyperspace with the dynamical behavior of the original system $(X,\mathbb{F})$. We derive conditions under which the dynamical behavior of the non-autonomous system extends to its induced counterpart(and vice-versa). In the process, we discuss properties like transitivity, weak mixing, topological mixing, topological entropy and various forms of sensitivities. We also discuss properties like equicontinuity, dense periodicity and Li-Yorke chaoticity for the two systems. We also give examples when a dynamical notion of a system cannot be extended to its induced counterpart (and vice-versa).

math.DS↗

arXiv2017

Dynamics of the Induced Shift Map

In this article, we compare the dynamics of the shift map and its induced counterpart on the hyperspace of the shift space. We show that many of the properties of induced shift map can be easily demonstrated by appropriate sequences of symbols. We compare the dynamics of the shift system $(Ω, σ)$ with its induced counterpart $(\mathcal{K}(Ω),\overlineσ)$, where $\mathcal{K}(Ω)$ is the hyperspace of all nonempty compact subsets of $Ω$. Recently, such comparisons have been studied a lot for general spaces. We continue the same study in case of shift spaces, and bring out the significance of such a study in terms of sequences. We compare the mixing properties, denseness of periodic points, various forms of sensitivity and expansivity of the shift map and its induced counterpart. In particular, we show their equivalence in case of the full shift. We also look into the special case of subshifts of finite type, and in particular prove that the properties of weakly mixing, mixing and sensitivity are equivalent in both systems. And in the case of any general subshift, we show that the concept of cofinite sensitivity is equivalent in both systems and for transitive subshifts, cofinite sensitivity is equivalent to syndectic sensitivity. In the process we prove that all sturmian subshifts are cofinitely sensitive.

math.DS↗

arXiv2016

Stringer: Balancing Latency and Resource Usage in Service Function Chain Provisioning

Network Functions Virtualization, or NFV, enables telecommunications infrastructure providers to replace special-purpose networking equipment with commodity servers running virtualized network functions (VNFs). A service provider utilizing NFV technology faces the SFC provisioning problem of assigning VNF instances to nodes in the physical infrastructure (e.g., a datacenter), and routing Service Function Chains (sequences of functions required by customers, a.k.a. SFCs) in the physical network. In doing so, the provider must balance between various competing goals of performance and resource usage. We present an approach for SFC provisioning, consisting of three elements. The first element is a fast, scalable round-robin heuristic. The second element is a Mixed Integer Programming (MIP) based approach. The third element is a queueing-theoretic model to estimate the average latency associated with any SFC provisioning solution. Combined, these elements create an approach that generates a set of SFC provisioning solutions, reflecting different tradeoffs between resource usage and performance.

cs.NI↗

arXiv2016

Comparative Advantage Driven Resource Allocation for Virtual Network Functions

As Communication Service Providers (CSPs) adopt the Network Function Virtualization (NFV) paradigm, they need to transition their network function capacity to a virtualized infrastructure with different Network Functions running on a set of heterogeneous servers. This abstract describes a novel technique for allocating server resources (compute, storage and network) for a given set of Virtual Network Function (VNF) requirements. Our approach helps the telco providers decide the most effective way to run several VNFs on servers with different performance characteristics. Our analysis of prior VNF performance characterization on heterogeneous/different server resource allocations shows that the ability to arbitrarily create many VNFs among different servers' resource allocations leads to a comparative advantage among servers. We propose a VNF resource allocation method called COMPARE that maximizes the total throughput of the system by formulating this resource allocation problem as a comparative advantage problem among heterogeneous servers. There several applications for using the VNF resource allocation from COMPARE including transitioning current Telco deployments to NFV based solutions and providing initial VNF placement for Service Function Chain (SFC) provisioning.

cs.NI↗

arXiv2016

Induced Dynamics on the Hyperspaces

In this paper, we study the dynamics induced by finite commutative relation. We prove that the dynamics generated by such a non-trivial collection cannot be transitive/super-transitive and hence cannot exhibit higher degrees of mixing. As a consequence we establish that the dynamics induced by such a collection on the hyperspace endowed with any admissible hit and miss topology cannot be transitive and hence cannot exhibit any form of mixing. We also prove that if the system is generated by such a commutative collection, under suitable conditions the induced system cannot have dense set of periodic points. In the end we give example to show that the induced dynamics in this case may or may not be sensitive.

math.DS↗

arXiv2016

Matrix Characterization of Multidimensional Subshifts of Finite Type

Let $X\subset A^{Z^d}$ be a $2$-dimensional subshift of finite type. We prove that any $2$-dimensional multidimensional subshift of finite type can be characterized by a square matrix of infinite dimension. We extend our result to a general $d$-dimensional case. We prove that the multidimensional shift space is non-empty if and only if the matrix obtained is of positive dimension. In the process, we give an alternative view of the necessary and sufficient conditions obtained for the non-emptiness of the multidimensional shift space. We also give sufficient conditions for the shift space $X$ to exhibit periodic points.

math.DS↗

arXiv2016

Dynamics of Nonautonomous Discrete Dynamical Systems

In this paper we study the dynamics of a general non-autonomous dynamical system generated by a family of continuous self maps on a compact space $X$. We derive necessary and sufficient conditions for the system to exhibit complex dynamical behavior. In the process we discuss properties like transitivity, weakly mixing, topologically mixing, minimality, sensitivity, topological entropy and Li-Yorke chaoticity for the non-autonomous system. We also give examples to prove that the dynamical behavior of the non-autonomous system in general cannot be characterized in terms of the dynamical behavior of its generating functions.

math.DS↗

arXiv2013

Efficient Image Retargeting for High Dynamic Range Scenes

Most of the real world scenes have a very high dynamic range (HDR). The mobile phone cameras and the digital cameras available in markets are limited in their capability in both the range and spatial resolution. Same argument can be posed about the limited dynamic range display devices which also differ in the spatial resolution and aspect ratios. In this paper, we address the problem of displaying the high contrast low dynamic range (LDR) image of a HDR scene in a display device which has different spatial resolution compared to that of the capturing digital camera. The optimal solution proposed in this work can be employed with any camera which has the ability to shoot multiple differently exposed images of a scene. Further, the proposed solutions provide the flexibility in the depiction of entire contrast of the HDR scene as a LDR image with an user specified spatial resolution. This task is achieved through an optimized content aware retargeting framework which preserves salient features along with the algorithm to combine multi-exposure images. We show the proposed approach performs exceedingly well in the generation of high contrast LDR image of varying spatial resolution compared to an alternate approach.

cs.CV↗