Fast Lane Detection Based on Deep Convolutional Neural Network and Automatic Training Data Labeling

Ground-penetrating radar allows the acquisition of many images for investigation of the pavement interior and shallow geological structures. Accordingly, an efficient methodology of detecting objects, such as pipes, reinforcing steel bars, and internal voids, in ground-penetrating radar images is an emerging technology. In this paper, we propose using a deep convolutional neural network to detect characteristic hyperbolic signatures from embedded objects. As a first step, we developed a migration-based method to collect many training data and created 53510 categorized images. We then examined the accuracy of the deep convolutional neural network in detecting the signatures. The accuracy of the classification was 0.945 (94.5%)–0.979 (97.9%) when using several thousands of training images and was much better than the accuracy of the conventional neural network approach. Our results demonstrate the effectiveness of the deep convolutional neural network in detecting characteristic events in ground-penetrating radar images.

Download Full-text

Multidimensional Face Representation in a Deep Convolutional Neural Network Reveals the Mechanism Underlying AI Racism

Frontiers in Computational Neuroscience ◽

10.3389/fncom.2021.620281 ◽

2021 ◽

Vol 15 ◽

Author(s):

Jinhua Tian ◽

Hailun Xie ◽

Siyuan Hu ◽

Jia Liu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Underlying Mechanism ◽

Deep Convolutional Neural Network ◽

The Other ◽

Training Data ◽

Identification Accuracy ◽

Social Bias ◽

Novel Approach ◽

Ai Ethics

The increasingly popular application of AI runs the risk of amplifying social bias, such as classifying non-white faces as animals. Recent research has largely attributed this bias to the training data implemented. However, the underlying mechanism is poorly understood; therefore, strategies to rectify the bias are unresolved. Here, we examined a typical deep convolutional neural network (DCNN), VGG-Face, which was trained with a face dataset consisting of more white faces than black and Asian faces. The transfer learning result showed significantly better performance in identifying white faces, similar to the well-known social bias in humans, the other-race effect (ORE). To test whether the effect resulted from the imbalance of face images, we retrained the VGG-Face with a dataset containing more Asian faces, and found a reverse ORE that the newly-trained VGG-Face preferred Asian faces over white faces in identification accuracy. Additionally, when the number of Asian faces and white faces were matched in the dataset, the DCNN did not show any bias. To further examine how imbalanced image input led to the ORE, we performed a representational similarity analysis on VGG-Face's activation. We found that when the dataset contained more white faces, the representation of white faces was more distinct, indexed by smaller in-group similarity and larger representational Euclidean distance. That is, white faces were scattered more sparsely in the representational face space of the VGG-Face than the other faces. Importantly, the distinctiveness of faces was positively correlated with identification accuracy, which explained the ORE observed in the VGG-Face. In summary, our study revealed the mechanism underlying the ORE in DCNNs, which provides a novel approach to studying AI ethics. In addition, the face multidimensional representation theory discovered in humans was also applicable to DCNNs, advocating for future studies to apply more cognitive theories to understand DCNNs' behavior.

Download Full-text

CT Image Segmentation of Liver Tumor with Deep Convolutional Neural Network

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3295 ◽

2021 ◽

Vol 11 (2) ◽

pp. 337-344

Author(s):

Yao Zeng ◽

Huanhuan Dai

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Automatic Segmentation ◽

Abdominal Cavity ◽

Mutual Exclusion ◽

Image Data ◽

Deep Convolutional Neural Network ◽

Training Data ◽

Segmentation Method ◽

Segmentation Boundary

The liver is the largest substantial organ in the abdominal cavity of the human body. Its structure is complex, the incidence of vascular abundance is high, and it has been seriously ribbed, human health and life. In this study, an automatic segmentation method based on deep convolutional neural network is proposed. Image data blocks of different sizes are extracted as training data and different network structures are designed, and features are automatically learned to obtain a segmentation structure of the tumor. Secondly, in order to further refine the segmentation boundary, we establish a multi-region segmentation model with region mutual exclusion constraints. The model combines the image grayscale, gradient and prior probability information, and overcomes the problem that the boundary point attribution area caused by boundary blur and regional adhesion is difficult to determine. Finally, the model is solved quickly using the time-invisible multi-phase level set. Compared with the traditional multi-organ segmentation method, this method does not require registration or model initialization. The experimental results show that the model can segment the liver, kidney and spleen quickly and effectively, and the segmentation accuracy reaches the advanced level of current methods.

Download Full-text

The Effect of Different Flaw Data to Machine Learning Powered Ultrasonic Inspection

Journal of Nondestructive Evaluation ◽

10.1007/s10921-021-00757-x ◽

2021 ◽

Vol 40 (1) ◽

Author(s):

Tuomas Koskinen ◽

Iikka Virkkunen ◽

Oskar Siljama ◽

Oskari Jessen-Juhler

Keyword(s):

Neural Network ◽

Machine Learning ◽

Convolutional Neural Network ◽

Image Recognition ◽

Phased Array ◽

Ultrasonic Inspection ◽

Deep Convolutional Neural Network ◽

Flaw Size ◽

Training Data ◽

Link Type

AbstractPrevious research (Li et al., Understanding the disharmony between dropout and batch normalization by variance shift. CoRR abs/1801.05134 (2018). http://arxiv.org/abs/1801.05134arXiv:1801.05134) has shown the plausibility of using a modern deep convolutional neural network to detect flaws from phased-array ultrasonic data. This brings the repeatability and effectiveness of automated systems to complex ultrasonic signal evaluation, previously done exclusively by human inspectors. The major breakthrough was to use virtual flaws to generate ample flaw data for the teaching of the algorithm. This enabled the use of raw ultrasonic scan data for detection and to leverage some of the approaches used in machine learning for image recognition. Unlike traditional image recognition, training data for ultrasonic inspection is scarce. While virtual flaws allow us to broaden the data considerably, original flaws with proper flaw-size distribution are still required. This is of course the same for training human inspectors. The training of human inspectors is usually done with easily manufacturable flaws such as side-drilled holes and EDM notches. While the difference between these easily manufactured artificial flaws and real flaws is obvious, human inspectors still manage to train with them and perform well in real inspection scenarios. In the present work, we use a modern, deep convolutional neural network to detect flaws from phased-array ultrasonic data and compare the results achieved from different training data obtained from various artificial flaws. The model demonstrated good generalization capability toward flaw sizes larger than the original training data, and the effect of the minimum flaw size in the data set affects the $$a_{90/95}$$ a 90 / 95 value. This work also demonstrates how different artificial flaws, solidification cracks, EDM notch and simple simulated flaws generalize differently.

Download Full-text

Deep convolutional neural network structural design for synthetic aperture radar image target recognition based on incomplete training data and displacement insensitivity

Journal of Electronic Imaging ◽

10.1117/1.jei.28.5.053002 ◽

2019 ◽

Vol 28 (05) ◽

pp. 1 ◽

Cited By ~ 1

Author(s):

Yuchao Hou ◽

Yanping Bai ◽

Ting Xu ◽

Huichao Yan ◽

Yan Hao ◽

...

Keyword(s):

Neural Network ◽

Synthetic Aperture Radar ◽

Convolutional Neural Network ◽

Structural Design ◽

Target Recognition ◽

Synthetic Aperture Radar Image ◽

Deep Convolutional Neural Network ◽

Training Data ◽

Radar Image ◽

Synthetic Aperture

Download Full-text

Learning a deep convolutional neural network via tensor decomposition

Information and Inference A Journal of the IMA ◽

10.1093/imaiai/iaaa042 ◽

2021 ◽

Author(s):

Samet Oymak ◽

Mahdi Soltanolkotabi

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Sample Size ◽

Gaussian Distribution ◽

Tensor Decomposition ◽

Deep Convolutional Neural Network ◽

Training Data ◽

Low Rank ◽

Rank Tensor

Abstract In this paper, we study the problem of learning the weights of a deep convolutional neural network. We consider a network where convolutions are carried out over non-overlapping patches. We develop an algorithm for simultaneously learning all the kernels from the training data. Our approach dubbed deep tensor decomposition (DeepTD) is based on a low-rank tensor decomposition. We theoretically investigate DeepTD under a realizable model for the training data where the inputs are chosen i.i.d. from a Gaussian distribution and the labels are generated according to planted convolutional kernels. We show that DeepTD is sample efficient and provably works as soon as the sample size exceeds the total number of convolutional weights in the network.

Download Full-text

A deep convolutional neural network approach with information fusion for bearing fault diagnosis under different working conditions

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science ◽

10.1177/0954406220902181 ◽

2020 ◽

pp. 095440622090218

Author(s):

Tang Tang ◽

Tianhao Hu ◽

Ming Chen ◽

Ronglai Lin ◽

Guorui Chen

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Convolutional Neural Network ◽

Information Fusion ◽

Vibration Signal ◽

Deep Convolutional Neural Network ◽

Feature Representation ◽

Training Data ◽

Data Sets ◽

Neural Network Approach

In recent years, deep learning-based fault diagnosis methods have drawn lots of attention. However, for most cases, the success of machine learning-based models relies on the circumstance that training data and testing data are under the same working condition, which is too strict for real implementation cases. Combined with the features of robustness of deep convolutional neural network and vibration signal characteristics, information fusion technology is introduced in this study to enhance the feature representation capability as well as the transferability of diagnosis models. With the basis of multi-sensors and narrow-band decomposition techniques, a convolutional architecture named fusion unit is proposed to extract multi-scale features from different sensors. The proposed method is tested on two data sets and has achieved relatively higher generalization ability when compared with several existing works, which demonstrates the effectiveness of our proposed fusion unit for feature extraction on both source task and target task.

Download Full-text

Comparing performance of deep convolutional neural network with orthopaedic surgeons on identification of total hip prosthesis design from plain radiographs

10.1101/2020.03.31.20048934 ◽

2020 ◽

Author(s):

Alireza Borjali ◽

Antonia F. Chen ◽

Hany S. Bedair ◽

Christopher M. Melnic ◽

Orhun K. Muratoglu ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Deep Convolutional Neural Network ◽

Training Data ◽

Identification Accuracy ◽

Automated System ◽

Implant Design ◽

Plain Radiographs ◽

Orthopaedic Surgeons ◽

Total Hip

ABSTRACTA crucial step in preoperative planning for a revision total hip replacement (THR) surgery is accurate identification of failed implant design, especially if one or more well-fixed/functioning components are to be retained. Manual identification of the implant design from preoperative radiographic images can be time-consuming and inaccurate, which can ultimately lead to increased operating room time, more complex surgery, and increased healthcare costs. No automated system has been developed to accurately and efficiently identify THR implant designs. In this study, we present a novel, fully automatic and interpretable approach to identify the design of nine different THR femoral implants from plain radiographs using deep convolutional neural network (CNN). We also compared the CNN’s performance with three board-certified and fellowship trained orthopaedic surgeons. The CNN achieved on-par accuracy with the orthopaedic surgeons while being significantly faster. The need for additional training data for less distinct designs was also highlighted. Such CNN can be used to automatically identify the design of a failed THR femoral implant preoperatively in just a fraction of a second, saving time and improving identification accuracy.

Download Full-text