Search results for " Deep Learning"
showing 10 items of 30 documents
Development of a Novel Object Detection System Based on Synthetic Data Generated from Unreal Game Engine
2022
This paper presents a novel approach to training a real-world object detection system based on synthetic data utilizing state-of-the-art technologies. Training an object detection system can be challenging and time-consuming as machine learning requires substantial volumes of training data with associated metadata. Synthetic data can solve this by providing unlimited desired training data with automatic generation. However, the main challenge is creating a balanced dataset that closes the reality gap and generalizes well when deployed in the real world. A state-of-the-art game engine, Unreal Engine 4, was used to approach the challenge of generating a photorealistic dataset for deep learnin…
Robustness, Stability, and Fidelity of Explanations for a Deep Skin Cancer Classification Model
2022
Skin cancer is one of the most prevalent of all cancers. Because of its being widespread and externally observable, there is a potential that machine learning models integrated into artificial intelligence systems will allow self-screening and automatic analysis in the future. Especially, the recent success of various deep machine learning models shows promise that, in the future, patients could self-analyse their external signs of skin cancer by uploading pictures of these signs to an artificial intelligence system, which runs such a deep learning model and returns the classification results. However, both patients and dermatologists, who might use such a system to aid their work, need to …
Detection of Hate Speech Spreaders using Convolutional Neural Networks
2021
In this paper we describe a deep learning model based on a Convolutional Neural Network (CNN). The model was developed for the Profiling Hate Speech Spreaders (HSSs) task proposed by PAN 2021 organizers and hosted at the 2021 CLEF Conference. Our approach to the task of classifying an author as HSS or not (nHSS) takes advantage of a CNN based on a single convolutional layer. In this binary classification task, on the tests performed using a 5-fold cross validation, the proposed model reaches a maximum accuracy of 0.80 on the multilingual (i.e., English and Spanish) training set, and a minimum loss value of 0.51 on the same set. As announced by the task organizers, the trained model presente…
Deep learning for knowledge tracing in learning analytics: An overview
2021
Learning Analytics (LA) is a recent research branch that refers to methods for measuring, collecting, analyzing, and reporting learners’ data, in order to better understand and optimize the processes and the environments. Knowledge Tracing (KT) deals with the modeling of the evolution, during the time, of the students’ learning process. Particularly its aim is to predict students’ outcomes in order to avoid failures and to support both students and teachers. Recently, KT has been tackled by exploiting Deep Learning (DL) models and generating a new, ongoing, research line that is known as Deep Knowledge Tracing (DKT). This was made possible by the digitalization process that has simplified t…
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 maChine and deep Learning Approach to predict pulmoNary hyperteNsIon in newbornS with congenital diaphragmatic Hernia (CLANNISH): Protocol for a re…
2021
Introduction Outcome predictions of patients with congenital diaphragmatic hernia (CDH) still have some limitations in the prenatal estimate of postnatal pulmonary hypertension (PH). We propose applying Machine Learning (ML), and Deep Learning (DL) approaches to fetuses and newborns with CDH to develop forecasting models in prenatal epoch, based on the integrated analysis of clinical data, to provide neonatal PH as the first outcome and, possibly: favorable response to fetal endoscopic tracheal occlusion (FETO), need for Extracorporeal Membrane Oxygenation (ECMO), survival to ECMO, and death. Moreover, we plan to produce a (semi)automatic fetus lung segmentation system in Magnetic Resonanc…
Fingerprint classification based on deep learning approaches: Experimental findings and comparisons
2021
Biometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs…
Automatic Quality Assessment of Cardiac MR Images with Motion Artefacts using Multi-task Learning and K-Space Motion Artefact Augmentation
2022
The movement of patients and respiratory motion during MRI acquisition produce image artefacts that reduce the image quality and its diagnostic value. Quality assessment of the images is essential to minimize segmentation errors and avoid wrong clinical decisions in the downstream tasks. In this paper, we propose automatic multi-task learning (MTL) based classification model to detect cardiac MR images with different levels of motion artefact. We also develop an automatic segmentation model that leverages k-space based motion artefact augmentation (MAA) and a novel compound loss that utilizes Dice loss with a polynomial version of cross-entropy loss (PolyLoss) to robustly segment cardiac st…
De novo liquid biopsy and radio genomic diagnostic approach with combined deep learning artificial neural networks for NSCLC
2022
Each year, the mortality rate and incidence of non-small cell lung cancer (NSCLC) are dramatically increasing. The introduction of liquid biopsy in the clinical practice of NSCLC has completely revolutionized the approach to such neoplasm since is generally detected through complex and invasive procedures and unfortunately at advanced stages. The importance and innovation of liquid biopsy are linked with the possibility of cancer detection at every stage, adjuvant treatment, resistance genotyping, systematic initiation of treatment, minimal residual disease, early detection of relapse, and screening of NSCLC. Circulating tumor DNA (ctDNA) is now emerging as a non-invasive biomarker that wil…
Automatic Segmentation Using a Hybrid Dense Network Integrated With an 3D-Atrous Spatial Pyramid Pooling Module for Computed Tomography (CT) Imaging
2020
Computed tomography (CT) with a contrast-enhanced imaging technique is extensively proposed for the assessment and segmentation of multiple organs, especially organs at risk. It is an important factor involved in the decision making in clinical applications. Automatic segmentation and extraction of abdominal organs, such as thoracic organs at risk, from CT images are challenging tasks due to the low contrast of pixel values surrounding other organs. Various deep learning models based on 2D and 3D convolutional neural networks have been proposed for the segmentation of medical images because of their automatic feature extraction capability based on large labeled datasets. In this paper, we p…