Deep learning neural network for driver drowsiness detection using eyes recognition
MK Gatea, SK Gharghan, AH Ali - AIP Conference Proceedings, 2023 - pubs.aip.org
Driver drowsiness and fatigue are two of the most common causes of automobile accidents.
Yearly, the number of deaths in addition to fatalities rises dramatically owing to a variety of …
Yearly, the number of deaths in addition to fatalities rises dramatically owing to a variety of …
The celerity high-level api: C++ 20 for accelerator clusters
P Thoman, F Tischler, P Salzmann… - International Journal of …, 2022 - Springer
Providing convenient APIs and notations for data parallelism which remain accessible for
programmers while still providing good performance has been a long-term goal of …
programmers while still providing good performance has been a long-term goal of …
Evolving messy gates for fault tolerance: some preliminary findings
JF Miller, M Hartmann - Proceedings Third NASA/DoD …, 2001 - ieeexplore.ieee.org
We investigate a preliminary model of gate-like components with added random noise. We
refer to these types of components as messy. The principal idea behind messy gates is that …
refer to these types of components as messy. The principal idea behind messy gates is that …
A new SIMD iterative connected component labeling algorithm
This paper presents a new multi-pass iterative algorithm for Connected Component
Labeling. The performance of this algorithm is compared to those of State-of-the-Art two …
Labeling. The performance of this algorithm is compared to those of State-of-the-Art two …
Metaprogramming dense linear algebra solvers applications to multi and many-core architectures
The increasing complexity of new parallel architectures has widened the gap between
adaptability and efficiency of the codes. As high performance numerical libraries tend to …
adaptability and efficiency of the codes. As high performance numerical libraries tend to …
Rapid prototyping of embedded vision systems: Embedding computer vision applications into low-power heterogeneous architectures
S Aldegheri, N Bombieri - 2018 International Symposium on …, 2018 - ieeexplore.ieee.org
Embedded vision is a disruptive new technology in the vision industry. It is a revolutionary
concept with far reaching implications, and it is opening up new applications and shaping …
concept with far reaching implications, and it is opening up new applications and shaping …
Comprehensive performance analysis of C++ smart pointers
B Babati, N Pataki - Pollack Periodica, 2017 - akjournals.com
Smart pointers play an important role in bypassing memory leaks in C++. Since C++ 11
standard the smart pointers have become widely-used tools because they let the …
standard the smart pointers have become widely-used tools because they let the …
Meta-programming and Multi-stage Programming for GPGPUs
GPGPUs and other accelerators are becoming a mainstream asset for high-performance
computing. Raising the programmability of such hardware is essential to enable users to …
computing. Raising the programmability of such hardware is essential to enable users to …
High level data structures for GPGPU programming in a statically typed language
M Bourgoin, E Chailloux, JL Lamotte - International Journal of Parallel …, 2017 - Springer
To increase software performance, it is now common to use hardware accelerators.
Currently, GPUs are the most widespread accelerators that can handle general …
Currently, GPUs are the most widespread accelerators that can handle general …
Kiwaku, a C++ 20 library for multidimensional arrays. Application to ACTS tracking
S Joube, H Grasland, D Chamont… - EPJ Web of …, 2024 - epj-conferences.org
C++ is a vital part of particle physics as it allows for high level abstractions while offering
state of the art performance. In this article we will first introduce the C++ 20 concepts, a major …
state of the art performance. In this article we will first introduce the C++ 20 concepts, a major …