Search results for "deep learning"
showing 10 items of 337 documents
Individualizing deep dynamic models for psychological resilience data
2020
ABSTRACTDeep learning approaches can uncover complex patterns in data. In particular, variational autoencoders (VAEs) achieve this by a non-linear mapping of data into a low-dimensional latent space. Motivated by an application to psychological resilience in the Mainz Resilience Project (MARP), which features intermittent longitudinal measurements of stressors and mental health, we propose an approach for individualized, dynamic modeling in this latent space. Specifically, we utilize ordinary differential equations (ODEs) and develop a novel technique for obtaining person-specific ODE parameters even in settings with a rather small number of individuals and observations, incomplete data, an…
Motion Artifact Detection in Confocal Laser Endomicroscopy Images
2018
Confocal Laser Endomicroscopy (CLE), an optical imaging technique allowing non-invasive examination of the mucosa on a (sub)- cellular level, has proven to be a valuable diagnostic tool in gastroenterology and shows promising results in various anatomical regions including the oral cavity. Recently, the feasibility of automatic carcinoma detection for CLE images of sufficient quality was shown. However, in real world data sets a high amount of CLE images is corrupted by artifacts. Amongst the most prevalent artifact types are motion-induced image deteriorations. In the scope of this work, algorithmic approaches for the automatic detection of motion artifact-tainted image regions were develo…
Transferability of Deep Learning Algorithms for Malignancy Detection in Confocal Laser Endomicroscopy Images from Different Anatomical Locations of t…
2019
Squamous Cell Carcinoma (SCC) is the most common cancer type of the epithelium and is often detected at a late stage. Besides invasive diagnosis of SCC by means of biopsy and histo-pathologic assessment, Confocal Laser Endomicroscopy (CLE) has emerged as noninvasive method that was successfully used to diagnose SCC in vivo. For interpretation of CLE images, however, extensive training is required, which limits its applicability and use in clinical practice of the method. To aid diagnosis of SCC in a broader scope, automatic detection methods have been proposed. This work compares two methods with regard to their applicability in a transfer learning sense, i.e. training on one tissue type (f…
A system based on neural architectures for the reconstruction of 3-D shapes from images
1991
The connectionist approach to the recovery of 3-D shape information from 2-D images developed by the authors, is based on a system made up by two cascaded neural networks. The first network is an implementation of the BCS, an architecture which derives from a biological model of the low level visual processes developed by Grossberg and Mingolla: this architecture extracts a sort of brightness gradient map from the image. The second network is a backpropagation architecture that supplies an estimate of the geometric parameters of the objects in the scene under consideration, starting from the outputs of the BCS. A detailed description of the system and the experimental results obtained by si…
Optimization and sensitivity analysis of existing deep learning models for pavement surface monitoring using low-quality images
2022
Automated pavement distress detection systems have become increasingly sought after by road agencies to in crease the efficiency of field surveys and reduce the likelihood of insufficient road condition data. However, many modern approaches are developed without practical testing using real-world scenarios. This paper ad dresses this by practically analyzing Deep Learning models to detect pavement distresses using French Secondary road surface images, given the issues of limited available road condition data in those networks. The study specifically explores several experimental and sensitivity-testing strategies using augmentation and hyper- parameter case studies to bolster practical mode…
Implementing an embedded system to identify possible COVID-19 suspects using thermovision cameras
2020
The main goal of this paper is to prove that by combining thermal vision cameras and image processing with many deep learning classification algorithms we developed an effective embedded system with high applicability in this critical period caused by COVID-19 pandemic disease. Using fixed and mobile thermal cameras we envisioned and developed a real time temperature screening capable of sending alarm signals over network or by SMS to local authorities along with multiple detection metrics such as the age, the gender, the facial emotion, the GPS location where the alarm went off, the temperature reading from the human face and also if the subject is wearing or not a medical face mask.
Study and Evaluation of Pre-trained CNN Networks for Cultural Heritage Image Classification
2021
The classification of digital images is an essential task during the restoration and preservation of cultural heritage (CH). In computer vision, cultural heritage classification relies on the classification of asset images regarding a certain task such as type, artist, genre, style identification, etc. CH classification is challenging as various CH asset images have similar colors, textures, and shapes. In this chapter, the aim is to study and evaluate the use of pre-trained deep convolutional neural networks such as VGG16, VGG-19, ResNet50, and Inception-V3 for cultural heritage images classification using transfer learning techniques. The main idea is to start with CNN models previously t…
Deep Learning Architectures for DNA Sequence Classification
2016
DNA sequence classification is a key task in a generic computational framework for biomedical data analysis, and in recent years several machine learning technique have been adopted to successful accomplish with this task. Anyway, the main difficulty behind the problem remains the feature selection process. Sequences do not have explicit features, and the commonly used representations introduce the main drawback of the high dimensionality. For sure, machine learning method devoted to supervised classification tasks are strongly dependent on the feature extraction step, and in order to build a good representation it is necessary to recognize and measure meaningful details of the items to cla…
Towards Low-Cost Pavement Condition Health Monitoring and Analysis Using Deep Learning
2020
Governments are faced with countless challenges to maintain conditions of road networks. This is due to financial and physical resource deficiencies of road authorities. Therefore, low-cost automated systems are sought after to alleviate these issues and deliver adequate road conditions for citizens. There have been several attempts at creating such systems and integrating them within Pavement management systems. This paper utilizes replicable deep learning techniques to carry out hotspot analyses on urban road networks highlighting important pavement distress types and associated severities. Following this, analyses were performed illustrating how the hotspot analysis can be carried out to…
Streamlining distributed Deep Learning I/O with ad hoc file systems
2021
With evolving techniques to parallelize Deep Learning (DL) and the growing amount of training data and model complexity, High-Performance Computing (HPC) has become increasingly important for machine learning engineers. Although many compute clusters already use learning accelerators or GPUs, HPC storage systems are not suitable for the I/O requirements of DL workflows. Therefore, users typically copy the whole training data to the worker nodes or distribute partitions. Because DL depends on randomized input data, prior work stated that partitioning impacts DL accuracy. Their solutions focused mainly on training I/O performance on a high-speed network but did not cover the data stage-in pro…