scholarly journals Pixel-Level Recognition of Pavement Distresses Based on U-Net

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Deru Li ◽  
Zhongdong Duan ◽  
Xiaoyang Hu ◽  
Dongchang Zhang
Keyword(s):  
Deep Neural Networks ◽  
Data Augmentation ◽  
Discriminative Learning ◽  
Road Maintenance ◽  
Transverse Cracks ◽  
Test Dataset ◽  
Learning Rates ◽  
Pavement Distresses ◽  
Validation Set ◽  
Longitudinal Cracks

This study develops and tests an automatic pixel-level image recognition model to reduce the amount of manual labor required to collect data for road maintenance. Firstly, images of six kinds of pavement distresses, namely, transverse cracks, longitudinal cracks, alligator cracks, block cracks, potholes, and patches, are collected from four asphalt highways in three provinces in China to build a labeled pixel-level dataset containing 10,097 images. Secondly, the U-net model, one of the most advanced deep neural networks for image segmentation, is combined with the ResNet neural network as the basic classification network to recognize distressed areas in the images. Data augmentation, batch normalization, momentum, transfer learning, and discriminative learning rates are used to train the model. Thirdly, the trained models are validated on the test dataset, and the results of experiments show the following: if the types of pavement distresses are not distinguished, the pixel accuracy (PA) values of the recognition models using ResNet-34 and ResNet-50 as basic classification networks are 97.336% and 95.772%, respectively, on the validation set. When the types of distresses are distinguished, the PA values of models using the two classification networks are 66.103% and 44.953%, respectively. For the model using ResNet-34, the category pixel accuracy (CPA) and intersection over union (IoU) of the identification of areas with no distress are 99.276% and 99.059%, respectively. For areas featuring distresses in the images, the CPA and IoU of the model are the highest for the identification of patches, at 82.774% and 73.778%, and are the lowest for alligator cracks, at 14.077% and 12.581%, respectively.

scholarly journals RALR: Random Amplify Learning Rates for Training Neural Networks

2021 ◽  
Vol 12 (1) ◽  
pp. 268
Author(s):  
Jiali Deng ◽  
Haigang Gong ◽  
Minghui Liu ◽  
Tianshu Xie ◽  
Xuan Cheng ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Saddle Points ◽  
Learning Rate ◽  
Global Learning ◽  
Fine Grained ◽  
Learning Rates ◽  
Overall Performance ◽  
Classification Tasks

It has been shown that the learning rate is one of the most critical hyper-parameters for the overall performance of deep neural networks. In this paper, we propose a new method for setting the global learning rate, named random amplify learning rates (RALR), to improve the performance of any optimizer in training deep neural networks. Instead of monotonically decreasing the learning rate, we expect to escape saddle points or local minima by amplifying the learning rate between reasonable boundary values based on a given probability. Training with RALR rather than conventionally decreasing the learning rate achieves further improvement on networks’ performance without extra consumption. Remarkably, the RALR is complementary with state-of-the-art data augmentation and regularization methods. Besides, we empirically study its performance on image classification tasks, fine-grained classification tasks, object detection tasks, and machine translation tasks. Experiments demonstrate that RALR can bring a notable improvement while preventing overfitting when training deep neural networks. For example, the classification accuracy of ResNet-110 trained on the CIFAR-100 dataset using RALR achieves a 1.34% gain compared with ResNet-110 trained traditionally.

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation

A Study on Laser Welding of Titanium and Stainless Steel

2018 ◽  
Author(s):  
Angshuman Chattopadhyay ◽  
Gopinath Muvvala ◽  
Vikranth Racherla ◽  
Ashish Kumar Nath
Keyword(s):  
Stainless Steel ◽  
Laser Welding ◽  
Weld Joint ◽  
Welding Speed ◽  
Fusion Process ◽  
Longitudinal Stress ◽  
Transverse Cracks ◽  
Cooling Rates ◽  
Melt Pool ◽  
Longitudinal Cracks

Joining of dissimilar metals and alloys has been envisioned since a long time with specific high end applications in various fields. One such combination is austenitic stainless steel grade SS304 and commercial grade titanium, which is very difficult to join under conventional fusion process due to extensive cracking and failure caused by mismatch in structural and thermal properties as well as formation of the extremely brittle and hard intermetallic compounds. One of the methods proposed in literature to control the formation of intermetallics is by fast cooling fusion process like laser beam welding. The present study has been done on laser welding of titanium and stainless steel AISI 304 to understand the interaction of these materials during laser welding at different laser power and welding speed which could yield different cooling rates. Two types of cracks were observed in the weld joint, namely longitudinal cracks and transverse cracks with respect to the weld direction. Longitudinal cracks could be completely eliminated at faster welding speeds, but transverse cracks were found little influenced by the welding speed. The thermal history, i.e. melt pool lifetime and cooling rate of the molten pool during laser welding was monitored and a relation between thermo-cycle with occurrence of cracks was established. It is inferred that the longitudinal cracks are mainly due to the formation of various brittle intermetallic phases of Fe and Ti, which could be minimized by providing relatively less melt pool lifetime at high welding speeds. The reason of the transverse cracks could be the generation of longitudinal stress in weld joint due to the large difference in the thermal expansion coefficient of steel and titanium. In order to mitigate the longitudinal stress laser welding was carried out with a novel experimental arrangement which ensured different cooling rates of these two metals during laser welding. With this the tendency of transverse cracks also could be minimized significantly.

scholarly journals Detection of activity and position of speakers by using deep neural networks and acoustic data augmentation

2019 ◽  
Vol 134 ◽  
pp. 53-65 ◽  
Author(s):  
Paolo Vecchiotti ◽  
Giovanni Pepe ◽  
Emanuele Principi ◽  
Stefano Squartini
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Acoustic Data

scholarly journals The Use of Synthetic Data to Facilitate Eye Segmentation Using Deeplabv3+

2021 ◽  
Vol 5 (3) ◽  
pp. 1-10
Author(s):  
Melih Öz ◽  
Taner Danışman ◽  
Melih Günay ◽  
Esra Zekiye Şanal ◽  
Özgür Duman ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Real Life ◽  
Synthetic Data ◽  
Limited Data ◽  
Test Set ◽  
Human Eye ◽  
Context Data ◽  
Head Positions

The human eye contains valuable information about an individual’s identity and health. Therefore, segmenting the eye into distinct regions is an essential step towards gathering this useful information precisely. The main challenges in segmenting the human eye include low light conditions, reflections on the eye, variations in the eyelid, and head positions that make an eye image hard to segment. For this reason, there is a need for deep neural networks, which are preferred due to their success in segmentation problems. However, deep neural networks need a large amount of manually annotated data to be trained. Manual annotation is a labor-intensive task, and to tackle this problem, we used data augmentation methods to improve synthetic data. In this paper, we detail the exploration of the scenario, which, with limited data, whether performance can be enhanced using similar context data with image augmentation methods. Our training and test set consists of 3D synthetic eye images generated from the UnityEyes application and manually annotated real-life eye images, respectively. We examined the effect of using synthetic eye images with the Deeplabv3+ network in different conditions using image augmentation methods on the synthetic data. According to our experiments, the network trained with processed synthetic images beside real-life images produced better mIoU results than the network, which only trained with real-life images in the Base dataset. We also observed mIoU increase in the test set we created from MICHE II competition images.

scholarly journals Text Mining Drug-Protein Interactions using an Ensemble of BERT, Sentence BERT and T5 models

2021 ◽  
Author(s):  
Xin Sui ◽  
Wanjing Wang ◽  
Jinfeng Zhang
Keyword(s):  
Protein Interactions ◽  
Clustering Algorithm ◽  
Data Augmentation ◽  
Majority Vote ◽  
Classification Model ◽  
Ensemble Model ◽  
K Nearest Neighbors ◽  
Test Dataset ◽  
Improved Performance ◽  
Using Data

In this work, we trained an ensemble model for predicting drug-protein interactions within a sentence based on only its semantics. Our ensembled model was built using three separate models: 1) a classification model using a fine-tuned BERT model; 2) a fine-tuned sentence BERT model that embeds every sentence into a vector; and 3) another classification model using a fine-tuned T5 model. In all models, we further improved performance using data augmentation. For model 2, we predicted the label of a sentence using k-nearest neighbors with its embedded vector. We also explored ways to ensemble these 3 models: a) we used the majority vote method to ensemble these 3 models; and b) based on the HDBSCAN clustering algorithm, we trained another ensemble model using features from all the models to make decisions. Our best model achieved an F-1 score of 0.753 on the BioCreative VII Track 1 test dataset.

scholarly journals Ship-Iceberg Classification in SAR and Multispectral Satellite Images with Neural Networks

2020 ◽  
Vol 12 (15) ◽  
pp. 2353
Author(s):  
Henning Heiselberg
Keyword(s):  
Neural Networks ◽  
Satellite Images ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Neural Nets ◽  
The Arctic ◽  
Support Vector ◽  
Sar Images ◽  
Multispectral Satellite Images ◽  
The Cost

Classification of ships and icebergs in the Arctic in satellite images is an important problem. We study how to train deep neural networks for improving the discrimination of ships and icebergs in multispectral satellite images. We also analyze synthetic-aperture radar (SAR) images for comparison. The annotated datasets of ships and icebergs are collected from multispectral Sentinel-2 data and taken from the C-CORE dataset of Sentinel-1 SAR images. Convolutional Neural Networks with a range of hyperparameters are tested and optimized. Classification accuracies are considerably better for deep neural networks than for support vector machines. Deeper neural nets improve the accuracy per epoch but at the cost of longer processing time. Extending the datasets with semi-supervised data from Greenland improves the accuracy considerably whereas data augmentation by rotating and flipping the images has little effect. The resulting classification accuracies for ships and icebergs are 86% for the SAR data and 96% for the MSI data due to the better resolution and more multispectral bands. The size and quality of the datasets are essential for training the deep neural networks, and methods to improve them are discussed. The reduced false alarm rates and exploitation of multisensory data are important for Arctic search and rescue services.

scholarly journals Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Felipe Oviedo ◽  
Zekun Ren ◽  
Shijing Sun ◽  
Charles Settens ◽  
Zhe Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
X Ray Diffraction ◽  
X Ray ◽  
Small X ◽  
Using Data ◽  
Interpretable Classification
Sign in / Sign up

Export Citation Format

Share Document