Driving style detection is an essential real-world requirement in diverse contexts, such as
traffic safety, car insurance and fuel consumption optimization. However, the existing …

Cervical cancer ranks among the most prevalent causes of fatality in women around the
world. Early diagnosis is essential for treating cervical cancer using pap smear slides, but it …

Service-oriented applications commonly involve high-dimensional and sparse (HiDS)
interactions among users and service-related entities, eg, user-item interactions from a …

Stochastic momentum methods are widely used to solve stochastic optimization problems in
machine learning. However, most of the existing theoretical analyses rely on either bounded …

A restoring-force model is a versatile mathematical model that can describe the relationship
between the restoring force and the deformation obtained from a large number of …

Abstract The Convolutional Neural Network (CNN) algorithm is used to classify multispectral
images of labelled EuroSAT data from Sentinel-2 satellite. The main objective of this study to …

Back propagation (BP) is widely used for parameter search of fully-connected layers in many
neural networks. Although BP has the potential of quickly converging to a solution, due to its …

Deep neural networks have achieved remarkable success in various fields. However,
training an effective deep neural network still poses challenges. This paper aims to propose …

In an intelligent transportation system, accurate traffic flow prediction can provide significant
help for travel planning. Even though some methods are proposed to do so, they focus on …

Stochastic adaptive gradient decent algorithms, such as AdaGrad and Adam, are
extensively used to train deep neural networks. However, randomly sampling gradient …