Zobrazeno 1 - 10
of 159
pro vyhledávání: '"Shokoufandeh, Ali"'
Developments in touch-sensitive textiles have enabled many novel interactive techniques and applications. Our digitally-knitted capacitive active sensors can be manufactured at scale with little human intervention. Their sensitive areas are created f
Externí odkaz:
http://arxiv.org/abs/2303.10336
It has been argued by Thom and Palm that sparsely-connected neural networks (SCNs) show improved performance over fully-connected networks (FCNs). Super-regular networks (SRNs) are neural networks composed of a set of stacked sparse layers of (epsilo
Externí odkaz:
http://arxiv.org/abs/2201.01363
Autor:
Shortell, Thomas, Shokoufandeh, Ali
In this paper, a secure Convolutional Neural Network classifier is proposed using Fully Homomorphic Encryption (FHE). The secure classifier provides a user with the ability to out-source the computations to a powerful cloud server and/or setup a serv
Externí odkaz:
http://arxiv.org/abs/1808.03819
Autor:
Haag, Scott, Shokoufandeh, Ali
In this paper we propose an algorithm and associated data model for creating a watershed boundary using a 2D Flow Direction Grid. Flow Direction Grids (FDGs) are common abstractions for hydrodynamic models and are utilized for delineating physical sy
Externí odkaz:
http://arxiv.org/abs/1708.00354
Autor:
Shortell, Thomas, Shokoufandeh, Ali
Cloud computing is an important part of today's world because offloading computations is a method to reduce costs. In this paper, we investigate computing the Speeded Up Robust Features (SURF) using Fully Homomorphic Encryption (FHE). Performing SURF
Externí odkaz:
http://arxiv.org/abs/1707.05905
Autor:
Rajanna, Arjun Raj, Aryafar, Kamelia, Ramchandran, Rajeev, Sisson, Christye, Shokoufandeh, Ali, Ptucha, Raymond
Widespread outreach programs using remote retinal imaging have proven to decrease the risk from diabetic retinopathy, the leading cause of blindness in the US. However, this process still requires manual verification of image quality and grading of i
Externí odkaz:
http://arxiv.org/abs/1612.03961
Autor:
Shortell, Thomas, Shokoufandeh, Ali
Secure signal processing is becoming a de facto model for preserving privacy. We propose a model based on the Fully Homomorphic Encryption (FHE) technique to mitigate security breaches. Our framework provides a method to perform a Fast Fourier Transf
Externí odkaz:
http://arxiv.org/abs/1611.08769
Autor:
Haag, Scott, Shokoufandeh, Ali
A data model to store and retrieve surface watershed boundaries using graph theoretic approaches is proposed. This data model integrates output from a standard digital elevation models (DEM) derived stream catchment boundaries, and vector representat
Externí odkaz:
http://arxiv.org/abs/1611.09131
Online retail is a visual experience- Shoppers often use images as first order information to decide if an item matches their personal style. Image characteristics such as color, simplicity, scene composition, texture, style, aesthetics and overall q
Externí odkaz:
http://arxiv.org/abs/1605.03663
We study downlink delay minimization within the context of cellular user association policies that map mobile users to base stations. We note the delay minimum user association problem fits within a broader class of network utility maximization and c
Externí odkaz:
http://arxiv.org/abs/1501.02419