24   Artículos

 
en línea
Kenneth Lange    
The current paper proposes and tests algorithms for finding the diameter of a compact convex set and the farthest point in the set to another point. For these two nonconvex problems, I construct Frank?Wolfe and projected gradient ascent algorithms. Altho... ver más
Revista: Algorithms    Formato: Electrónico

 
en línea
William Villegas-Ch, Angel Jaramillo-Alcázar and Sergio Luján-Mora    
This study evaluated the generation of adversarial examples and the subsequent robustness of an image classification model. The attacks were performed using the Fast Gradient Sign method, the Projected Gradient Descent method, and the Carlini and Wagner ... ver más
Revista: Big Data and Cognitive Computing    Formato: Electrónico

 
en línea
Kenneth Lange    
The Hausdorff distance between two closed sets has important theoretical and practical applications. Yet apart from finite point clouds, there appear to be no generic algorithms for computing this quantity. Because many infinite sets are defined by algeb... ver más
Revista: Algorithms    Formato: Electrónico

 
en línea
Sapdo Utomo, Adarsh Rouniyar, Hsiu-Chun Hsu and Pao-Ann Hsiung    
Smart city applications that request sensitive user information necessitate a comprehensive data privacy solution. Federated learning (FL), also known as privacy by design, is a new paradigm in machine learning (ML). However, FL models are susceptible to... ver más
Revista: Future Internet    Formato: Electrónico

 
en línea
Yuanhong Li, Jiapeng Liao, Jing Wang, Yangfan Luo and Yubin Lan    
The automated harvesting of clustered fruits relies on fast and accurate visual perception. However, the obscured stem diameters via leaf occlusion lack any discernible texture patterns. Nevertheless, our human visual system can often judge the position ... ver más
Revista: Agronomy    Formato: Electrónico

 
en línea
Weimin Zhao, Sanaa Alwidian and Qusay H. Mahmoud    
Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms. Adversarial training is one of the methods used to defend against the thr... ver más
Revista: Algorithms    Formato: Electrónico

 
en línea
Abdul Haseeb Azizi and Yoshihiro Asaoka    
Projected snow cover and river flows are important for planning and managing water resources in snow-dominated basins of the Himalayas. To quantify the impacts of climate change in the data scarce Panjshir River basin of Afghanistan, this study simulated... ver más
Revista: Hydrology    Formato: Electrónico

 
en línea
Dandan Yan, Zhaoqing Luan, Dandan Xu, Yuanyuan Xue and Dan Shi    
Water level fluctuations resulting from natural and anthropogenic factors have been projected to affect the functions and structures of wetland vegetation communities. Therefore, it is important to assess the impact of the hydrological gradient on wetlan... ver más
Revista: Water    Formato: Electrónico

 
en línea
Ende Wang, Jinlei Jiao, Jingchao Yang, Dongyi Liang and Jiandong Tian    
Keypoint matching is of fundamental importance in computer vision applications. Fish-eye lenses are convenient in such applications that involve a very wide angle of view. However, their use has been limited by the lack of an effective matching algorithm... ver más
Revista: Information    Formato: Electrónico

 
en línea
Esteve Codina, Francisca Rosell, Luís Cadarso, Ángel Marín     Pág. 615 - 624
This paper focuses on a mathematical programming based model for setting the schedule of a given number of services on a public transportation network. The structure of the model is that of a time-expanded or diachronic network, where origin to destinati... ver más
Revista: Transportation Research Procedia    Formato: Electrónico

« Anterior     Página: 1 de 2     Siguiente »