about.jpg

Filter by

Lvlnet: Lightweight left ventricle localizer using encoder-decoder neural network

Automatic localization of the left ventricle (LV) is an important preprocessing step in any further analysis or quantification of LV function. Also, LV localization is usually done manually by MRI operator to plan Cardiac Magnetic Resonance Imaging (Cardiac MR) acquisition which can be standardized and automated to reduce the operator's error. In this study, we propose LVLNET; an automatic left

Depth Augmented Semantic Segmentation Networks for Automated Driving

In this paper, we explore the augmentation of depth maps to improve the performance of semantic segmentation motivated by the geometric structure in automotive scenes. Typically depth is already computed in an automotive system to localize objects and path planning and thus can be leveraged for semantic segmentation. We construct two networks that serve as a baseline for comparison which are “RGB

Welcome Messages

[No abstract available]

Enhanced Proactive Caching Through Content Recommendation

The mismatch between user demand and service supply creates a congestion in mobile wireless networks. Taking advantage of user demand predictability, Service Providers (SPs) apply proactive caching to smooth out the network load. However, the performance of applied caching strategy depends on the content popularity information. This paper studies the effect of recommendation on empowering the

Review on Dark Energy Models

Based on quantum mechanics and general relativity, Karolyhazy proposed a generalization to the well-known Heisenberg uncertainty relation in which the energy density of quantum fluctuations of space-time plays a crucial role. Later on, various holographic DE models were suggested, in which the Hubble scale (size) and the age of the universe were assumed as measures for the largest infrared cutoff

Particle yields and ratios within equilibrium and non-equilibrium statistics

In characterizing the various yields and ratios of well-identified particles in the ALICE experiment, we utilize extensive additive thermal approaches, to which various missing states of the hadron resonances are taken into consideration as well. Despite some non-equilibrium conditions that are slightly driving this statistical approach away from equilibrium, the approaches are and remain additive

Out-Of-Equilibrium Transverse Momentum Spectra of Pions at LHC Energies

In order to characterize the transverse momentum spectra (pT) of positive pions measured in the ALICE experiment, two thermal approaches are utilized; one is based on degeneracy of nonperfect Bose-Einstein gas and the other imposes an ad hoc finite pion chemical potential. The inclusion of missing hadron states and the out-of-equilibrium contribute greatly to the excellent characterization of pion

Biologically Inspired Optimization Algorithms for Fractional-Order Bioimpedance Models Parameters Extraction

This chapter introduces optimization algorithms for parameter extractions of three fractional-order circuits that model bioimpedance. The Cole-impedance model is investigated; it is considered one of the most commonly used models providing the best fit with the measured data. Two new models are introduced: the fractional Hayden model and the fractional-order double-shell model. Both models are the

Artificial Intelligence
Circuit Theory and Applications

FPGA Implementation of Fractional-Order Chaotic Systems

This chapter introduces two FPGA implementations of the fractional-order operators: the Caputo and the Grünwald-Letnikov (GL) derivatives. First, the Caputo derivative is realized using nonuniform segmentation to reduce the size of the Look-Up Table. The Caputo implementation introduced can generate derivatives of previously defined functions only. Generic and complete hardware architecture of the

Circuit Theory and Applications

Nonlinear fractional order boundary-value problems with multiple solutions

It is well-known that discovering and then calculating all branches of solutions of fractional order nonlinear differential equations with boundary conditions can be difficult even by numerical methods. To overcome this difficulty, in this chapter two semianalytic methods are presented to predict and obtain multiple solutions of nonlinear boundary value problems. These methods are based on the

Artificial Intelligence
Circuit Theory and Applications