Deep learning-based endoscopic anatomy classification: an accelerated approach for data preparation and model validation

AbstractCho et al. report deep learning model accuracy for tilted myopic disc detection in a South Korean population. Here we explore the importance of generalisability of machine learning (ML) in healthcare, and we emphasise that recurrent underrepresentation of data-poor regions may inadvertently perpetuate global health inequity.Creating meaningful ML systems is contingent on understanding how, when, and why different ML models work in different settings. While we echo the need for the diversification of ML datasets, such a worthy effort would take time and does not obviate uses of presently available datasets if conclusions are validated and re-calibrated for different groups prior to implementation.The importance of external ML model validation on diverse populations should be highlighted where possible – especially for models built with single-centre data.

Download Full-text

Deep learning application for box-office evaluation of images

Computer Optics ◽

10.18287/2412-6179-co-515 ◽

2020 ◽

Vol 44 (1) ◽

pp. 127-132

Author(s):

V.G. Efremtsev ◽

N.G. Efremtsev ◽

E.P. Teterin ◽

P.E. Teterin ◽

V.V. Gantsovsky

Keyword(s):

Neural Network ◽

Deep Learning ◽

Sample Preparation ◽

Convolutional Neural Network ◽

Preliminary Data ◽

Classification Accuracy ◽

Training Sample ◽

Data Preparation ◽

Box Office ◽

The Neural Network

The possibility of application a convolutional neural network to assess the box-office effect of digital images is reviewed. We studied various conditions for sample preparation, optimizer algorithms, the number of pixels in the samples, the size of the training sample, color schemes, compression quality, and other photometric parameters in view of effect on training the neural network. Due to the proposed preliminary data preparation, the optimum of the architecture and hyperparameters of the neural network we achieved a classification accuracy of at least 98%.

Download Full-text

Stochastic Detection of Interior Design Styles Using a Deep-Learning Model for Reference Images

Applied Sciences ◽

10.3390/app10207299 ◽

2020 ◽

Vol 10 (20) ◽

pp. 7299 ◽

Cited By ~ 1

Author(s):

Jinsung Kim ◽

Jin-Kook Lee

Keyword(s):

Deep Learning ◽

Interior Design ◽

Learning Model ◽

Data Driven ◽

Data Preparation ◽

Reference Images ◽

Data Driven Approach ◽

Image Set ◽

Design Style ◽

Deep Learning Model

This paper describes an approach for identifying and appending interior design style information stochastically with reference images and a deep-learning model. In the field of interior design, design style is a useful concept and has played an important role in helping people understand and communicate interior design. Previous studies have focused on how the interior design style categories can be defined. On the other hand, this paper focuses on how stochastically recognizing the design style of given interior design reference images using a deep learning-based data-driven approach. The proposed method can be summarized as follows: (1) data preparation based on a general design style definition, (2) implementing an interior design style recognition model using a pre-trained VGG16 model, (3) training and evaluating the trained model, and (4) demonstration of stochastic detection of interior design styles for reference images. The result shows that the trained model automatically recognizes the design styles of given interior images with probability values. The recognition results, model, and trained image set contribute to facilitating the management and utilization of an interior design references database.

Download Full-text

How deep is your model? Network topology selection from a model validation perspective

Journal of Mathematics in Industry ◽

10.1186/s13362-021-00116-5 ◽

2022 ◽

Vol 12 (1) ◽

Author(s):

Nikolai Nowaczyk ◽

Jörg Kienitz ◽

Sarp Kaya Acar ◽

Qian Liang

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Model Selection ◽

Model Validation ◽

Network Topology ◽

Heston Model ◽

Financial Modeling ◽

Black Scholes ◽

Significant Obstacle ◽

Grid Based

AbstractDeep learning is a powerful tool, which is becoming increasingly popular in financial modeling. However, model validation requirements such as SR 11-7 pose a significant obstacle to the deployment of neural networks in a bank’s production system. Their typically high number of (hyper-)parameters poses a particular challenge to model selection, benchmarking and documentation. We present a simple grid based method together with an open source implementation and show how this pragmatically satisfies model validation requirements. We illustrate the method by learning the option pricing formula in the Black–Scholes and the Heston model.

Download Full-text

Segmentation of Multiple Tree Leaves Pictures with Natural Backgrounds using Deep Learning for Image-Based Agriculture Applications

Applied Sciences ◽

10.3390/app10010202 ◽

2019 ◽

Vol 10 (1) ◽

pp. 202 ◽

Cited By ~ 3

Author(s):

Jaime Giménez-Gallego ◽

Juan D. González-Teruel ◽

Manuel Jiménez-Buendía ◽

Ana B. Toledo-Moreo ◽

Fulgencio Soto-Valles ◽

...

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Canopy Temperature ◽

Stress Index ◽

Support Vector ◽

Data Preparation ◽

Crop Water Stress Index ◽

Weight Decay ◽

Water Stress Index ◽

Svm Model

The crop water stress index (CWSI) is one of the parameters measured in deficit irrigation and it is obtained from crop canopy temperature. However, image segmentation is required for non-leaf region exclusion in temperature measurement, as it is critical to obtain the temperature values for the calculation of the CWSI. To this end, two image-segmentation models based on support vector machine (SVM) and deep learning have been studied in this article. The models have been trained with different parameters (encoder depth, optimizer, learning rate, weight decay, validation frequency and validation patience), and several indicators (accuracy, precision, recall and F1 score/dice coefficient), as well as prediction, training and data preparation times are discussed. The results of the F1 score indicator are 83.11% for SVM and 86.27% for deep-learning models. More accurate results are expected for the deep-learning model by increasing the dataset, whereas the SVM model is worthwhile in terms of reduced data preparation times.

Download Full-text

A Review of Deep Learning Based Methods for Acoustic Scene Classification

Applied Sciences ◽

10.3390/app10062020 ◽

2020 ◽

Vol 10 (6) ◽

pp. 2020 ◽

Cited By ~ 6

Author(s):

Jakob Abeßer

Keyword(s):

Deep Learning ◽

Data Augmentation ◽

Real Life ◽

Network Architectures ◽

Data Preparation ◽

Scene Classification ◽

Feature Representations ◽

Audio Recordings ◽

Number Of Publications

The number of publications on acoustic scene classification (ASC) in environmental audio recordings has constantly increased over the last few years. This was mainly stimulated by the annual Detection and Classification of Acoustic Scenes and Events (DCASE) competition with its first edition in 2013. All competitions so far involved one or multiple ASC tasks. With a focus on deep learning based ASC algorithms, this article summarizes and groups existing approaches for data preparation, i.e., feature representations, feature pre-processing, and data augmentation, and for data modeling, i.e., neural network architectures and learning paradigms. Finally, the paper discusses current algorithmic limitations and open challenges in order to preview possible future developments towards the real-life application of ASC systems.

Download Full-text

Data Preparation for Deep Learning

10.1007/978-981-16-2233-5_14 ◽

2021 ◽

pp. 329-362

Author(s):

Chen Lei

Keyword(s):

Deep Learning ◽

Data Preparation

Download Full-text

Towards Urban Scene Semantic Segmentation with Deep Learning from LiDAR Point Clouds: A Case Study in Baden-Württemberg, Germany

Remote Sensing ◽

10.3390/rs13163220 ◽

2021 ◽

Vol 13 (16) ◽

pp. 3220

Author(s):

Yanling Zou ◽

Holger Weinacker ◽

Barbara Koch

Keyword(s):

Deep Learning ◽

Smart Cities ◽

Real Life ◽

Semantic Segmentation ◽

Point Clouds ◽

Accuracy Score ◽

City Management ◽

Data Preparation ◽

3D Point Clouds ◽

Urban Scene

An accurate understanding of urban objects is critical for urban modeling, intelligent infrastructure planning and city management. The semantic segmentation of light detection and ranging (LiDAR) point clouds is a fundamental approach for urban scene analysis. Over the last years, several methods have been developed to segment urban furniture with point clouds. However, the traditional processing of large amounts of spatial data has become increasingly costly, both time-wise and financially. Recently, deep learning (DL) techniques have been increasingly used for 3D segmentation tasks. Yet, most of these deep neural networks (DNNs) were conducted on benchmarks. It is, therefore, arguable whether DL approaches can achieve the state-of-the-art performance of 3D point clouds segmentation in real-life scenarios. In this research, we apply an adapted DNN (ARandLA-Net) to directly process large-scale point clouds. In particular, we develop a new paradigm for training and validation, which presents a typical urban scene in central Europe (Munzingen, Freiburg, Baden-Württemberg, Germany). Our dataset consists of nearly 390 million dense points acquired by Mobile Laser Scanning (MLS), which has a rather larger quantity of sample points in comparison to existing datasets and includes meaningful object categories that are particular to applications for smart cities and urban planning. We further assess the DNN on our dataset and investigate a number of key challenges from varying aspects, such as data preparation strategies, the advantage of color information and the unbalanced class distribution in the real world. The final segmentation model achieved a mean Intersection-over-Union (mIoU) score of 54.4% and an overall accuracy score of 83.9%. Our experiments indicated that different data preparation strategies influenced the model performance. Additional RGB information yielded an approximately 4% higher mIoU score. Our results also demonstrate that the use of weighted cross-entropy with inverse square root frequency loss led to better segmentation performance than when other losses were considered.

Download Full-text

Deep Learning

10.1017/cbo9780511780295 ◽

2009 ◽

Cited By ~ 94

Author(s):

Stellan Ohlsson

Keyword(s):

Deep Learning

Download Full-text

Intelligence artificielle : le futur de l’Orthodontie ?

Revue d Orthopédie Dento-Faciale ◽

10.1051/odf/2019026 ◽

2019 ◽

Vol 53 (3) ◽

pp. 281-294

Author(s):

Jean-Michel Foucart ◽

Augustin Chavanne ◽

Jérôme Bourriau

Keyword(s):

Big Data ◽

Deep Learning ◽

Intelligence Artificielle ◽

Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Download Full-text