Analyses on Influence of Training Data Set to Neural Network Supervised Learning Performance

Zhou, Yu; Wu, Yali

doi:10.1007/978-3-642-23753-9_4

Cited by 19 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training process of machine or deep learning algorithms, embedded in CAD, is strongly influenced by the quality and quantity of the dataset [ 5 , 6 ]. Hence, the first step in the CAD system is dataset preparation.…”

Section: Introductionmentioning

confidence: 99%

Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Magnuska

Theek

Darguzyte

et al. 2022

Cancers

View full text Add to dashboard Cite

Automation of medical data analysis is an important topic in modern cancer diagnostics, aiming at robust and reproducible workflows. Therefore, we used a dataset of breast US images (252 malignant and 253 benign cases) to realize and compare different strategies for CAD support in lesion detection and classification. Eight different datasets (including pre-processed and spatially augmented images) were prepared, and machine learning algorithms (i.e., Viola–Jones; YOLOv3) were trained for lesion detection. The radiomics signature (RS) was derived from detection boxes and compared with RS derived from manually obtained segments. Finally, the classification model was established and evaluated concerning accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve. After training on a dataset including logarithmic derivatives of US images, we found that YOLOv3 obtains better results in breast lesion detection (IoU: 0.544 ± 0.081; LE: 0.171 ± 0.009) than the Viola–Jones framework (IoU: 0.399 ± 0.054; LE: 0.096 ± 0.016). Interestingly, our findings show that the classification model trained with RS derived from detection boxes and the model based on the RS derived from a gold standard manual segmentation are comparable (p-value = 0.071). Thus, deriving radiomics signatures from the detection box is a promising technique for building a breast lesion classification model, and may reduce the need for the lesion segmentation step in the future design of CAD systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Magnuska

Theek

Darguzyte

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…These options have their own cost. The number of training samples used to train the NN to predict the scattered wavefield is a delicate matter [33]. It directly affects the cost of the training and yet it is necessary that we have enough samples to accurately train the network to predict the wavefield.…”

Section: Discussionmentioning

confidence: 99%

Wavefield solutions from machine learned functions

Alkhalifah,

Song,

Waheed

et al. 2021

Preprint

View full text Add to dashboard Cite

Solving the wave equation is one of the most (if not the most) fundamental problems we face as we try to illuminate the Earth using recorded seismic data. The Helmholtz equation provides wavefield solutions that are dimensionally reduced, per frequency, compared to the time domain, which is useful for many applications, like full waveform inversion (FWI). However, our ability to attain such wavefield solutions depends often on the size of the model and the complexity of the wave equation. Thus, we use here a recently introduced framework based on neural networks to predict functional solutions through setting the underlying physical equation as a loss function to optimize the neural network parameters. For an input given by a location in the model space, the network learns to predict the wavefield value at that location, and its partial derivatives using a concept referred to as automatic differentiation, to fit, in our case, a form of the Helmholtz equation. We specifically seek the solution of the scattered wavefield considering a simple homogeneous background model that allows for analytical solutions of the background wavefield. Providing the neural network (NN) a reasonable number of random points from the model space will ultimately train a fully connected deep NN to predict the scattered wavefield function. The size of the network depends mainly on the complexity of the desired wavefield, with such complexity increasing with increasing frequency and increasing model complexity. However, smaller networks can provide smoother wavefields that might be useful for inversion applications.

show abstract

“…In this sense, Zhu and Wu [30] list several methods from the literature which improve the results obtained by random selection. In addition, Hao and Jiang [31] propose a clustering method based on the nearest neighbour rule in order to reduce redundancy information included in the original dataset.…”

Section: Selection Of the Training Datasetmentioning

confidence: 98%

CPV module electric characterisation by artificial neural networks

et al. 2015

View full text Add to dashboard Cite

a b s t r a c tConcentrating photovoltaic (CPV) is a relatively new technology with promising future expectations. However, it is at an early stage of development and it has much room for improvement. In order to gain knowledge about CPV technology, outdoor measurements are necessary to adjust models and to study the influence of the atmospheric conditions on the modules performance. In this work, multilayer perceptron models are applied to generate IeV characteristic curves of one of the most extended commercial module of concentrating photovoltaic technology, using the influential atmospheric variables as inputs to the networks. To train these networks an experiment with real measurements was carried out in Ja en, Spain, from July 2011 to June 2012. In addition to a model based on IeV curves expressed as a list of points in Cartesian coordinates, we present an alternative model trained with curves represented in polar coordinates. A previous selection of the most representative samples from the initial dataset was performed using a Kohonen self-organising map. This procedure allows the simulation of the curves even under non-frequent atmospheric conditions. Using the proposed models, it is possible to obtain the characteristic curve of other CPV modules under different meteorological conditions, with high accuracy and fidelity.

show abstract

Analyses on Influence of Training Data Set to Neural Network Supervised Learning Performance

Cited by 19 publications

References 5 publications

Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Wavefield solutions from machine learned functions

CPV module electric characterisation by artificial neural networks

Contact Info

Product

Resources

About