A Guide to Convolutional Neural Networks for Computer Vision

Khan, Salman; Rahmani, Hossein; Shah, Syed Afaq Ali; Bennamoun, Mohammed

doi:10.2200/s00822ed1v01y201712cov015

Cited by 374 publications

(231 citation statements)

References 90 publications

Supporting

Mentioning

208

Contrasting

Unclassified

Order By: Relevance

“…19 Every node in the input layer is fully connected to all the nodes of the hidden layer. 19 Every node in the input layer is fully connected to all the nodes of the hidden layer.…”

Section: Model Descriptionmentioning

confidence: 99%

“…19.1 for developing all other prediction models including the logistic regression. The MLP-based approach was implemented using the Keras Library v2.1.5 with Tensor Flow backend v1.8.0.…”

Section: Software Packagesmentioning

confidence: 99%

“…Multi-layer perceptron In short, a multi-layer perceptron (MLP) is a feedforward artificial neural network with an input layer, at least one hidden layer, and an output layer. 19 Every node in the input layer is fully connected to all the nodes of the hidden layer. Similarly, all the nodes of the hidden layer are fully connected to the nodes of the output layer as shown in Figure 2.…”

Section: Model Descriptionmentioning

confidence: 99%

“…We used the scikit-learn library v0. 19.1 for developing all other prediction models including the logistic regression. To create the models, we set the corresponding parameter, namely, class_weights in the scikit library implementation.…”

Section: Software Packagesmentioning

confidence: 99%

See 3 more Smart Citations

Machine learning‐based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

et al. 2019

Self Cite

View full text Add to dashboard Cite

Aims Machine learning (ML) is widely believed to be able to learn complex hidden interactions from the data and has the potential in predicting events such as heart failure (HF) readmission and death. Recent studies have revealed conflicting results likely due to failure to take into account the class imbalance problem commonly seen with medical data. We developed a new ML approach to predict 30 day HF readmission or death and compared the performance of this model with other commonly used prediction models. Methods and results We identified all Western Australian patients aged above 65 years admitted for HF between 2003 and 2008 in the linked Hospital Morbidity Data Collection. Taking into consideration the class imbalance problem, we developed a multi‐layer perceptron (MLP)‐based approach to predict 30 day HF readmission or death and compared the predictive performances using the performance metrics, that is, area under the receiver operating characteristic curve (AUC), area under the precision–recall curve (AUPRC), sensitivity and specificity with other ML and regression models. Out of the 10 757 patients with HF, 23.6% were readmitted or died within 30 days of hospital discharge. We observed an AUC of 0.55, 0.53, 0.58, and 0.54 while an AUPRC of 0.39, 0.38, 0.46, and 0.38 for weighted random forest, weighted decision trees, logistic regression, and weighted support vector machines models, respectively. The MLP‐based approach produced the highest AUC (0.62) and AUPRC (0.46) with 48% sensitivity and 70% specificity. Conclusions We show that for the medical data with class imbalance, the proposed MLP‐based approach is superior to other ML and regression techniques for the prediction of 30 day HF readmission or death.

show abstract

“…19 Every node in the input layer is fully connected to all the nodes of the hidden layer. 19 Every node in the input layer is fully connected to all the nodes of the hidden layer.…”

Section: Model Descriptionmentioning

confidence: 99%

“…19.1 for developing all other prediction models including the logistic regression. The MLP-based approach was implemented using the Keras Library v2.1.5 with Tensor Flow backend v1.8.0.…”

Section: Software Packagesmentioning

confidence: 99%

Section: Model Descriptionmentioning

confidence: 99%

Section: Software Packagesmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning‐based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Typically loss functions are hand-crafted, though weightings between terms can be learned [37]. Naturally, numerous loss functions have been devised to train networks to accomplish various tasks [38].…”

Section: Loss Functionsmentioning

confidence: 99%

RGB-D Image-Based Object Detection: From Traditional Methods to Deep Learning Techniques

Ward¹,

Laga

Bennamoun

2019

Advances in Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Object detection from RGB images is a long-standing problem in image processing and computer vision. It has applications in various domains including robotics, surveillance, human-computer interaction, and medical diagnosis. With the availability of low cost 3D scanners, a large number of RGB-D object detection approaches have been proposed in the past years. This chapter provides a comprehensive survey of the recent developments in this field. We structure the chapter into two parts; the focus of the first part is on techniques that are based on hand-crafted features combined with machine learning algorithms. The focus of the second part is on the more recent work, which is based on deep learning. Deep learning techniques, coupled with the availability of large training datasets, have now revolutionized the field of computer vision, including RGB-D object detection, achieving an unprecedented level of performance. We survey the key contributions, summarize the most commonly used pipelines, discuss their benefits and limitations, and highlight some important directions for future research.

show abstract

References

2018

3D Shape Analysis

View full text Add to dashboard Cite

A Guide to Convolutional Neural Networks for Computer Vision

Cited by 374 publications

References 90 publications

Machine learning‐based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

Machine learning‐based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

RGB-D Image-Based Object Detection: From Traditional Methods to Deep Learning Techniques

References

Contact Info

Product

Resources

About