Search results for "deep learning"
showing 10 items of 337 documents
Not a Target. A Deep Learning Approach for a Warning and Decision Support System to Improve Safety and Security of Humanitarian Aid Workers
2019
Humanitarian aid workers who try to provide aid to the most vulnerable populations in the Middle East or Africa are risking their own lives and safety to help others. The current lack of a collaborative real-time information system to predict threats prevents responders and local partners from developing a shared understanding of potentially threatening situations, causing increased response times and leading to inadequate protection. To solve this problem, this paper presents a threat detection and decision support system that combines knowledge and information from a network of responders with automated and modular threat detection. The system consists of three parts. It first collects te…
Deep Learning Techniques for Depression Assessment
2018
Depression is a typical mood disorder, which affects a significant number of individuals worldwide at an increasing rate. Objective measures for early detection of signs related to depression could be beneficial for clinicians with regards to a decision support system. In this paper, assessment of depression is done by applying three deep learning techniques of Convolutional Neural Network (CNN). These techniques are transfer learning using AlexNet, fine-tuning using AlexNet and building an end to end CNN. The inputs of the CNNs are a combination of Motion History Image, Landmark Motion History Image and Gabor Motion History Image, and have been generated on a depression dataset. Accuracy o…
A Simple and Efficient Deep Learning-Based Framework for Automatic Fruit Recognition
2022
Accurate detection and recognition of various kinds of fruits and vegetables by using the artificial intelligence (AI) approach always remain a challenging task due to similarity between various types of fruits and challenging environments such as lighting and background variations. Therefore, developing and exploring an expert system for automatic fruits’ recognition is getting more and more important after many successful approaches; however, this technology is still far from being mature. The deep learning-based models have emerged as state-of-the-art techniques for image segmentation and classification and have a lot of promise in challenging domains such as agriculture, where they can …
Semantic Analysis of the Driving Environment in Urban Scenarios
2021
Understanding urban scenes require recognizing the semantic constituents of a scene and the complex interactions between them. In this work, we explore and provide effective representations for understanding urban scenes based on in situ perception, which can be helpful for planning and decision-making in various complex urban environments and under a variety of environmental conditions. We first present a taxonomy of deep learning methods in the area of semantic segmentation, the most studied topic in the literature for understanding urban driving scenes. The methods are categorized based on their architectural structure and further elaborated with a discussion of their advantages, possibl…
Compréhension de scènes urbaines basées sur la polarisation
2021
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to mimic these capabilities by implementing intelligent algorithms to address complex understanding problems. In this regard, we are interested in understanding outdoor urban scenes in various weather conditions. This thesis specifically addresses the problems arising from the presence of specularity in the scenes. To this end, we aim to take advantage of polarization indices to define such surfaces in addition to traditional objects. In terms of understanding, we aim to introduce polarization to the fields of computer vision and deep learning.This thesis focuses on the following underlying challeng…
Compréhension de scènes urbaines basée sur la polarisation
2021
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to mimic these capabilities by implementing intelligent algorithms to address complex understanding problems. In this regard, we are interested in understanding outdoor urban scenes in various weather conditions. This thesis specifically addresses the problems arising from the presence of specularity in the scenes. To this end, we aim to take advantage of polarization indices to define such surfaces in addition to traditional objects. In terms of understanding, we aim to introduce polarization to the fields of computer vision and deep learning.This thesis focuses on the following underlying chall…
A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia
2023
Abstract Background The role of computed tomography (CT) in the diagnosis and characterization of coronavirus disease 2019 (COVID-19) pneumonia has been widely recognized. We evaluated the performance of a software for quantitative analysis of chest CT, the LungQuant system, by comparing its results with independent visual evaluations by a group of 14 clinical experts. The aim of this work is to evaluate the ability of the automated tool to extract quantitative information from lung CT, relevant for the design of a diagnosis support model. Methods LungQuant segments both the lungs and lesions associated with COVID-19 pneumonia (ground-glass opacities and consolidations) and computes derived…
Atrial fibrillation signatures on intracardiac electrograms identified by deep learning
2022
BACKGROUND: Automatic detection of atrial fibrillation (AF) by cardiac devices is increasingly common yet sub-optimally groups AF, flutter or tachycardia (AT) together as ‘high rate events’. This may delay or misdirect therapy. OBJECTIVE: We hypothesized that deep learning (DL) can accurately classify AF from AT by revealing electrogram (EGM) signatures. METHODS: We studied 86 patients in whom the diagnosis of AF or AT was established at electrophysiological study (25 female, 65 ± 11 years). Custom DL architectures were trained to identify AF using N = 29,340 unipolar and N = 23,760 bipolar EGM segments. We compared DL to traditional classifiers based on rate or regularity. We explained DL …
Metamodel specialization based DSL for DL lifecycle data management
2020
A new Domain Specific Language (DSL) based approach to Deep Learning (DL) lifecycle data management (LDM) is presented: a very simple but universal DL LDM tool, still usable in practice (called Core tool); and an advanced extension mechanism, that converts the Core tool into a DSL tool building framework for DL LDM tasks. The method used is based on the metamodel specialisation approach for DSL modeling tools introduced by authors.
Towards DSL for DL Lifecycle Data Management
2020
A new method based on Domain Specific Language (DSL) approach to Deep Learning (DL) lifecycle data management tool support is presented: a very simple DL lifecycle data management tool, which however is usable in practice (it will be called Core tool) and a very advanced extension mechanism which in fact converts the Core tool into domain specific tool (DSL tool) building framework for DL lifecycle data management tasks. The extension mechanism will be based on the metamodel specialization approach to DSL modeling tools introduced by authors. The main idea of metamodel specialization is that we, at first, define the Universal Metamodel (UMM) for a domain and then for each use case define a …