In the previous episodes of this AI on Edge journey, we have done something exciting. We built real applications directly on our smartphones. We created image classification apps. We implemented ...

LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Recently, many works project the point cloud onto the 2D image ...

Medical image segmentation is vital for accurate diagnosis. While U-Net-based models are effective, they struggle to capture long-range dependencies in complex anatomy. We propose GH-UNet, a ...

University project of the Parallel Computing course. There are two challenges that are solved using parallel computing techniques and two famous frameworks: OpenMP and CUDA.

Abstract: Finding oil spills in the ocean is one of the most crucial tasks in preserving our ecosystem. Using satellite or aerial photographs as input to a deep learning model that makes use of 2D CNN ...

To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the ...

Abstract: The Electrocardiogram (ECG) signal is increasing in popularity as a biometric modality due to its useful properties in developing trustworthy identification systems. However, one of the ...

Convolution filters are a fundamental building block in image processing and computer vision. They are used to extract specific features from an image by applying a small matrix of numbers, called the ...

Generative Adversarial Networks (GAN) are becoming an alternative to Multiple-point Statistics (MPS) techniques to generate stochastic fields from training images. But a difficulty for all the ...

Recently, the use of deep neural networks in solving scientific problems has increased, such as for finding exotic particles in high-energy physics 1 and predicting the sequence specificities of DNA ...