Zobrazeno 1 - 10
of 3 887
pro vyhledávání: '"Enayati, A. A."'
Safe Reinforcement Learning (Safe RL) is one of the prevalently studied subcategories of trial-and-error-based methods with the intention to be deployed on real-world systems. In safe RL, the goal is to maximize reward performance while minimizing co
Externí odkaz:
http://arxiv.org/abs/2408.07962
Multi-object tracking (MOT) is a prominent task in computer vision with application in autonomous driving, responsible for the simultaneous tracking of multiple object trajectories. Detection-based multi-object tracking (DBT) algorithms detect object
Externí odkaz:
http://arxiv.org/abs/2404.03110
Publikováno v:
2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) Page(s): 1839 - 1844
This paper addresses the challenge of geometric quality assurance in manufacturing, particularly when human assessment is required. It proposes using Blender, an open-source simulation tool, to create synthetic datasets for machine learning (ML) mode
Externí odkaz:
http://arxiv.org/abs/2405.14877
Autor:
Karpichev, Yehor, Charter, Todd, Hong, Jayden, Enayati, Amir M. Soufi, Honari, Homayoun, Tamizi, Mehran Ghafarian, Najjaran, Homayoun
The rise of automation has provided an opportunity to achieve higher efficiency in manufacturing processes, yet it often compromises the flexibility required to promptly respond to evolving market needs and meet the demand for customization. Human-ro
Externí odkaz:
http://arxiv.org/abs/2403.14597
Autor:
Nasibeh Zanjirani Farahani, PhD, Mateo Alzate Aguirre, MD, Vanessa Karlinski Vizentin, MD, Moein Enayati, PhD, J. Martijn Bos, MD, PhD, Andredi Pumarejo Medina, MD, Kathryn F. Larson, MD, Kalyan S. Pasupathy, PhD, Christopher G. Scott, MS, April L. Zacher, MS, Eduard Schlechtinger, MS, Bruce K. Daniels, RDCS, Vinod C. Kaggal, MS, Jeffrey B. Geske, MD, Patricia A. Pellikka, MD, Jae K. Oh, MD, Steve R. Ommen, MD, Garvan C. Kane, MD, Michael J. Ackerman, MD, PhD, Adelaide M. Arruda-Olson, MD, PhD
Publikováno v:
Mayo Clinic Proceedings: Digital Health, Vol 2, Iss 4, Pp 564-573 (2024)
Objective: To develop machine learning tools for automated hypertrophic cardiomyopathy (HCM) case recognition from echocardiographic metrics, aiming to identify HCM from standard echocardiographic data with high performance. Patients and Methods: Fou
Externí odkaz:
https://doaj.org/article/6ddece60adbe4ec0872121c1ca8a7c1c
Autor:
Seyed-Mahmood Seyed-Khorami, Ehsan Mostafavi, Sepideh Gerdooei, Seyed Marzieh Sajadi, Laya Farhan Asadi, Tahmineh Jalali, Mohammad Hassan Pouriayevali, Fatemeh Nikpour, Abdolreza Mirolyaei, Ahmad Raeisi, Shahnam Arshi, Mohammad Mehdi Gouya, Ahmadali Enayati, Morteza Zaim, Mostafa Salehi-Vaziri
Publikováno v:
Virology Journal, Vol 21, Iss 1, Pp 1-9 (2024)
Abstract Aim Dengue virus (DENV) and Chikungunya virus (CHIKV) are the most common arthropod-borne viruses (Arboviruses) globally. So far, no autochthonous cases of DENV and CHIKV infections have been reported in Iran. Nevertheless, due to the recent
Externí odkaz:
https://doaj.org/article/1564f99af06e4806a32500fbe098c4b9
Reinforcement learning (RL) for motion planning of multi-degree-of-freedom robots still suffers from low efficiency in terms of slow training speed and poor generalizability. In this paper, we propose a novel RL-based robot motion planning framework
Externí odkaz:
http://arxiv.org/abs/2307.16062
We elaborate the definition and properties of "massive" elementary systems in the $(1+3)$-dimensional Anti-de Sitter (AdS$_4$) spacetime, on both classical and quantum levels. We fully exploit the symmetry group {isomorphic to} Sp$(4,R)$, that is, th
Externí odkaz:
http://arxiv.org/abs/2307.06690
Finding an efficient way to adapt robot trajectory is a priority to improve overall performance of robots. One approach for trajectory planning is through transferring human-like skills to robots by Learning from Demonstrations (LfD). The human demon
Externí odkaz:
http://arxiv.org/abs/2304.05703
Reinforcement learning demonstrates significant potential in automatically building control policies in numerous domains, but shows low efficiency when applied to robot manipulation tasks due to the curse of dimensionality. To facilitate the learning
Externí odkaz:
http://arxiv.org/abs/2304.06055