Πλοήγηση ανά Θέμα "Features extraction"

A Baselined Gated Attention Recurrent Network for Request Prediction in Ridesharing

Shen J., Tziritas N., Theodoropoulos G. (2022)

Ridesharing has received global popularity due to its convenience and cost efficiency for both drivers and passengers and its strong potential to contribute to the implementation of the UN Sustainable Development Goals. ...

Early Fusion of Visual Representations of Skeletal Data for Human Activity Recognition

Vernikos I., Koutrintzes D., Mathe E., Spyrou E., Mylonas P. (2022)

In this work we present an approach for human activity recognition which is based on skeletal motion, i.e., the motion of skeletal joints in the 3D space. More specifically, we propose the use of 4 well-known image ...

Explainable Classification of Weakly Annotated Wireless Capsule Endoscopy Images Based on a Fuzzy Bag-of-Colour Features Model and Brain Storm Optimization

Vasilakakis M., Sovatzidi G., Iakovidis D.K. (2021)

Wireless capsule endoscopy (WCE) constitutes a medical imaging technology developed for the endoscopic exploration of the gastrointestinal (GI) tract, whereas it provides a more comfortable examination method, in comparison ...

Fuzzy Pooling

Diamantis D.E., Iakovidis D.K. (2021)

Convolutional neural networks (CNNs) are artificial learning systems typically based on two operations: convolution, which implements feature extraction through filtering, and pooling, which implements dimensionality ...

Towards the Interpretation of Convolutional Neural Networks for Image Classification Using Fuzzy Sets

Vasilakakis M., Sovatzidi G., Dimas G., Iakovidis D.K. (2022)

Convolutional Neural Networks (CNNs) have demonstrated an outstanding performance on a range of image classification problems in various domains. However, their major drawback is that they are 'black box' and opaque ...