Search results for "deep learning"

Deep-Learning-Enabled Fast Optical Identification and Characterization of 2D Materials.

2020

© 2020 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim Advanced microscopy and/or spectroscopy tools play indispensable roles in nanoscience and nanotechnology research, as they provide rich information about material processes and properties. However, the interpretation of imaging data heavily relies on the “intuition” of experienced researchers. As a result, many of the deep graphical features obtained through these tools are often unused because of difficulties in processing the data and finding the correlations. Such challenges can be well addressed by deep learning. In this work, the optical characterization of 2D materials is used as a case study, and a neural-network-based algorithm is de…

Hydropower Optimization Using Deep Learning

2019

This paper demonstrates how deep learning can be used to find optimal reservoir operating policies in hydropower river systems. The method that we propose is based on the implicit stochastic optimization (ISO) framework, using direct policy search methods combined with deep neural networks (DNN). The findings from a real-world two-reservoir hydropower system in southern Norway suggest that DNNs can learn how to map input (price, inflow, starting reservoir levels) to the optimal production pattern directly. Due to the speed of evaluating the DNN, this approach is from an operational standpoint computationally inexpensive and may potentially address the long-standing problem of high dimension…

Deep Learning Models Performance For NDVI Time Series Prediction: A Case Study On North West Tunisia

2020

The main goal of this paper is to analyze the performance of two deep learning models Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM) network for non-stationary Normalized Difference Vegetation Index (NDVI) time-series prediction. Both methods have provided good performances in the different time series. The BiLSTM has shown the best agreement with the lowest root mean square error (RMSE) and the highest Pearson correlation coefficient (R) of 0.034 and 0.93, respectively.

DeepSRE: Identification of sterol responsive elements and nuclear transcription factors Y proximity in human DNA by Convolutional Neural Network anal…

2021

SREBP1 and 2, are cholesterol sensors able to modulate cholesterol-related gene expression responses. SREBPs binding sites are characterized by the presence of multiple target sequences as SRE, NFY and SP1, that can be arranged differently in different genes, so that it is not easy to identify the binding site on the basis of direct DNA sequence analysis. This paper presents a complete workflow based on a one-dimensional Convolutional Neural Network (CNN) model able to detect putative SREBPs binding sites irrespective of target elements arrangements. The strategy is based on the recognition of SRE linked (less than 250 bp) to NFY sequences according to chromosomal localization derived from …

A Survey on Microaneurysms Detection in Color Fundus Images

2020

Early Detection of Microaneurysms (MA) plays a vital role in preventing the blindness caused by diabetic retinopathy (DR). DR is preventable yet a serious diabetic problem. Treatment at an earlier stage reduces the risk of blindness. Microaneurysm is the first sign of DR found in fundus images while doing screening. Detection of MA is a challenging task mainly because of its size. MA appears as a tiny red spot ranging from 15µm to 60µm size. The most common way to detect the MA from a colour fundus image is by classification/segmentation through machine learning and deep learning approaches. The FROC-based performance evaluation shows that the existing methods can reach only up to 80% of se…

Geometric Calculus Applications to Medical Imaging: Status and Perspectives

2021

Medical imaging data coming from different acquisition modalities requires automatic tools to extract useful information and support clinicians in the formulation of accurate diagnoses. Geometric Calculus (GC) offers a powerful mathematical and computational model for the development of effective medical imaging algorithms. The practical use of GC-based methods in medical imaging requires fast and efficient implementations to meet real-time processing constraints as well as accuracy and robustness requirements. The purpose of this article is to present the state of the art of the GC-based techniques for medical image analysis and processing. The use of GC-based paradigms in Radiomics and De…

Study and identification of new molecular descriptors, finalized to the development of Virtual Screening techniques through the use of deep neural ne…

2022

Using deep neural networks for kinematic analysis: Challenges and opportunities

2020

Kinematic analysis is often performed in a lab using optical cameras combined with reflective markers.\ud With the advent of artificial intelligence techniques such as deep neural networks, it is now possible\ud to perform such analyses without markers, making outdoor applications feasible. In this paper I summarise\ud 2D markerless approaches for estimating joint angles, highlighting their strengths and limitations.\ud In computer science, so-called ‘‘pose estimation” algorithms have existed for many years. These methods\ud involve training a neural network to detect features (e.g. anatomical landmarks) using a process called\ud supervised learning, which requires ‘‘training” images to be …

Depth Attention for Scene Understanding

2022

Deep learning models can nowadays teach a machine to realize a number of tasks, even with better precision than human beings. Among all the modules of an intelligent machine, perception is the most essential part without which all other action modules have difficulties in safely and precisely realizing the target task under complex scenes. Conventional perception systems are based on RGB images which provide rich texture information about the 3D scene. However, the quality of RGB images highly depends on environmental factors, which further influence the performance of deep learning models. Therefore, in this thesis, we aim to improve the performance and robustness of RGB models with comple…

Analyse et fusion d’images multimodales pour la navigation autonome

2021

Robust semantic scene understanding is challenging due to complex object types, as well as environmental changes caused by varying illumination and weather conditions. This thesis studies the problem of deep semantic segmentation with multimodal image inputs. Multimodal images captured from various sensory modalities provide complementary information for complete scene understanding. We provided effective solutions for fully-supervised multimodal image segmentation and few-shot semantic segmentation of the outdoor road scene. Regarding the former case, we proposed a multi-level fusion network to integrate RGB and polarimetric images. A central fusion framework was also introduced to adaptiv…