scholarly journals Multi-Level-Phase Deep Learning Using Divide-and-Conquer for Scaffolding Safety

2020 ◽  
Vol 17 (7) ◽  
pp. 2391
Author(s):  
Sayan Sakhakarmi ◽  
Jee Woong Park
Keyword(s):  
Deep Learning ◽  
Failure Modes ◽  
Past Research ◽  
Divide And Conquer ◽  
Classification Problems ◽  
Multi Level ◽  
Improved Performance ◽  
Safety Cases ◽  
Global And Local ◽  
Local Levels

A traditional structural analysis of scaffolding structures requires loading conditions that are only possible during design, but not in operation. Thus, this study proposes a method that can be used during operation to make an automated safety prediction for scaffolds. It implements a divide-and-conquer technique with deep learning. As a test scaffolding, a four-bay, three-story scaffold model was used. Analysis of the model led to 1411 unique safety cases for the model. To apply deep learning, a test simulation generated 1,540,000 datasets for pre-training, and an additional 141,100 datasets for testing purposes. The cases were then sub-divided into 18 categories based on failure modes at both global and local levels, along with a combination of member failures. Accordingly, the divide-and-conquer technique was applied to the 18 categories, each of which were pre-trained by a neural network. For the test datasets, the overall accuracy was 99%. The prediction model showed that 82.78% of the 1411 safety cases showed 100% accuracy for the test datasets, which contributed to the high accuracy. In addition, the higher values of precision, recall, and F1 score for the majority of the safety cases indicate good performance of the model, and a significant improvement compared with past research conducted on simpler cases. Specifically, the method demonstrated improved performance with respect to accuracy and the number of classifications. Thus, the results suggest that the methodology could be reliably applied for the safety assessment of scaffolding systems that are more complex than systems tested in past studies. Furthermore, the implemented methodology can easily be replicated for other classification problems.

scholarly journals Real UAV-Bird Image Classification Using CNN with a Synthetic Dataset

2021 ◽  
Vol 11 (9) ◽  
pp. 3863
Author(s):  
Ali Emre Öztürk ◽  
Ergun Erçelebi
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Synthetic Data ◽  
Real Data ◽  
Corner Detection ◽  
Batch Size ◽  
Test Accuracy ◽  
Classification Problems ◽  
Auc Value ◽  
Classification Test

A large amount of training image data is required for solving image classification problems using deep learning (DL) networks. In this study, we aimed to train DL networks with synthetic images generated by using a game engine and determine the effects of the networks on performance when solving real-image classification problems. The study presents the results of using corner detection and nearest three-point selection (CDNTS) layers to classify bird and rotary-wing unmanned aerial vehicle (RW-UAV) images, provides a comprehensive comparison of two different experimental setups, and emphasizes the significant improvements in the performance in deep learning-based networks due to the inclusion of a CDNTS layer. Experiment 1 corresponds to training the commonly used deep learning-based networks with synthetic data and an image classification test on real data. Experiment 2 corresponds to training the CDNTS layer and commonly used deep learning-based networks with synthetic data and an image classification test on real data. In experiment 1, the best area under the curve (AUC) value for the image classification test accuracy was measured as 72%. In experiment 2, using the CDNTS layer, the AUC value for the image classification test accuracy was measured as 88.9%. A total of 432 different combinations of trainings were investigated in the experimental setups. The experiments were trained with various DL networks using four different optimizers by considering all combinations of batch size, learning rate, and dropout hyperparameters. The test accuracy AUC values for networks in experiment 1 ranged from 55% to 74%, whereas the test accuracy AUC values in experiment 2 networks with a CDNTS layer ranged from 76% to 89.9%. It was observed that the CDNTS layer has considerable effects on the image classification accuracy performance of deep learning-based networks. AUC, F-score, and test accuracy measures were used to validate the success of the networks.

scholarly journals Unsupervised Multi-Level Feature Extraction for Improvement of Hyperspectral Classification

2021 ◽  
Vol 13 (8) ◽  
pp. 1602
Author(s):  
Qiaoqiao Sun ◽  
Xuefeng Liu ◽  
Salah Bourennane
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Spatial Information ◽  
Hyperspectral Data ◽  
Great Promise ◽  
Learning Models ◽  
Single Level ◽  
Multiple Networks ◽  
Multi Level ◽  
Hyperspectral Classification

Deep learning models have strong abilities in learning features and they have been successfully applied in hyperspectral images (HSIs). However, the training of most deep learning models requires labeled samples and the collection of labeled samples are labor-consuming in HSI. In addition, single-level features from a single layer are usually considered, which may result in the loss of some important information. Using multiple networks to obtain multi-level features is a solution, but at the cost of longer training time and computational complexity. To solve these problems, a novel unsupervised multi-level feature extraction framework that is based on a three dimensional convolutional autoencoder (3D-CAE) is proposed in this paper. The designed 3D-CAE is stacked by fully 3D convolutional layers and 3D deconvolutional layers, which allows for the spectral-spatial information of targets to be mined simultaneously. Besides, the 3D-CAE can be trained in an unsupervised way without involving labeled samples. Moreover, the multi-level features are directly obtained from the encoded layers with different scales and resolutions, which is more efficient than using multiple networks to get them. The effectiveness of the proposed multi-level features is verified on two hyperspectral data sets. The results demonstrate that the proposed method has great promise in unsupervised feature learning and can help us to further improve the hyperspectral classification when compared with single-level features.

Analysis of the Relationship Between Rail Seat Load Distribution and Rail Seat Deterioration in Concrete Crossties

2014 ◽  
Author(s):  
Matthew Greve ◽  
Marcus S. Dersch ◽  
J. Riley Edwards ◽  
Christopher P. L. Barkan ◽  
Jose Mediavilla ◽  
...  
Keyword(s):  
Load Distribution ◽  
Failure Modes ◽  
Failure Mechanisms ◽  
Past Research ◽  
Concrete Surface ◽  
Hydraulic Pressure ◽  
Valuable Insight ◽  
Increased Risk ◽  
Abrasive Erosion ◽  
Field Experimentation

One of the most common failure modes of concrete crossties in North America is the degradation of the concrete surface at the crosstie rail seat, also known as rail seat deterioration (RSD). Loss of material beneath the rail can lead to wide gauge, rail cant deficiency, and an increased risk of rail rollover. Previous research conducted at the University of Illinois at Urbana-Champaign (UIUC) has identified five primary failure mechanisms: abrasion, crushing, freeze-thaw damage, hydro-abrasive erosion, and hydraulic pressure cracking. The magnitude and distribution of load applied to the rail seat affects four of these five mechanisms; therefore, it is important to understand the characteristics of the rail seat load distribution to effectively address RSD. As part of a larger study funded by the Federal Railroad Administration (FRA) aimed at improving concrete crossties and fastening systems, researchers at UIUC are attempting to characterize the loading environment at the rail seat using matrix-based tactile surface sensors (MBTSS). This instrumentation technology has been implemented in both laboratory and field experimentation, and has provided valuable insight into the distribution of a single load over consecutive crossties. A review of past research into RSD characteristics and failure mechanisms has been conducted to integrate data from field experimentation with existing knowledge, to further explore the role of the rail seat load distribution on RSD. The knowledge gained from this experimentation will be integrated with associated research conducted at UIUC to form the framework for a mechanistic design approach for concrete crossties and fastening systems.

Demystifying Deep Learning: Developing and Evaluating a User-Centered Learning App for Beginners to Gain Practical Experience

i-com ◽  
2020 ◽  
Vol 19 (3) ◽  
pp. 201-213
Author(s):  
Sven Schultze ◽  
Uwe Gruenefeld ◽  
Susanne Boll
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Practical Experience ◽  
Learning Problems ◽  
User Evaluation ◽  
Classification Problems ◽  
Human Centered Design ◽  
Technical Evaluation ◽  
Programming Skills ◽  
Barrier To Entry

Abstract Deep Learning has revolutionized Machine Learning, enhancing our ability to solve complex computational problems. From image classification to speech recognition, the technology can be beneficial in a broad range of scenarios. However, the barrier to entry is quite high, especially when programming skills are missing. In this paper, we present the development of a learning application that is easy to use, yet powerful enough to solve practical Deep Learning problems. We followed the human-centered design approach and conducted a technical evaluation to identify solvable classification problems. Afterwards, we conducted an online user evaluation to gain insights on users’ experience with the app, and to understand positive as well as negative aspects of our implemented concept. Our results show that participants liked using the app and found it useful, especially for beginners. Nonetheless, future iterations of the learning app should step-wise include more features to support advancing users.

scholarly journals Hierarchical Recognition System for Target Recognition from Sparse Representations

2015 ◽  
Vol 2015 ◽  
pp. 1-6 ◽  
Author(s):  
Zongyong Cui ◽  
Zongjie Cao ◽  
Jianyu Yang ◽  
Hongliang Ren
Keyword(s):  
Deep Learning ◽  
Deep Structure ◽  
Target Recognition ◽  
Recognition System ◽  
Automatic Target Recognition ◽  
Feature Representation ◽  
Small Data ◽  
Learning Method ◽  
Classification Problems ◽  
Restricted Boltzmann Machines

A hierarchical recognition system (HRS) based on constrained Deep Belief Network (DBN) is proposed for SAR Automatic Target Recognition (SAR ATR). As a classical Deep Learning method, DBN has shown great performance on data reconstruction, big data mining, and classification. However, few works have been carried out to solve small data problems (like SAR ATR) by Deep Learning method. In HRS, the deep structure and pattern classifier are combined to solve small data classification problems. After building the DBN with multiple Restricted Boltzmann Machines (RBMs), hierarchical features can be obtained, and then they are fed to classifier directly. To obtain more natural sparse feature representation, the Constrained RBM (CRBM) is proposed with solving a generalized optimization problem. Three RBM variants,L1-RNM,L2-RBM, andL1/2-RBM, are presented and introduced to HRS in this paper. The experiments on MSTAR public dataset show that the performance of the proposed HRS with CRBM outperforms current pattern recognition methods in SAR ATR, like PCA + SVM, LDA + SVM, and NMF + SVM.

scholarly journals Channel state information–based multi-level fingerprinting for indoor localization with deep learning

2018 ◽  
Vol 14 (10) ◽  
pp. 155014771880671 ◽  
Author(s):  
Tao Li ◽  
Hai Wang ◽  
Yuan Shao ◽  
Qiang Niu
Keyword(s):  
Deep Learning ◽  
Channel State Information ◽  
Deep Neural Networks ◽  
Training Phase ◽  
Channel State ◽  
Positioning Accuracy ◽  
State Information ◽  
Filtering Method ◽  
Multi Level ◽  
Better Than

With the rapid growth of indoor positioning requirements without equipment and the convenience of channel state information acquisition, the research on indoor fingerprint positioning based on channel state information is increasingly valued. In this article, a multi-level fingerprinting approach is proposed, which is composed of two-level methods: the first layer is achieved by deep learning and the second layer is implemented by the optimal subcarriers filtering method. This method using channel state information is termed multi-level fingerprinting with deep learning. Deep neural networks are applied in the deep learning of the first layer of multi-level fingerprinting with deep learning, which includes two phases: an offline training phase and an online localization phase. In the offline training phase, deep neural networks are used to train the optimal weights. In the online localization phase, the top five closest positions to the location position are obtained through forward propagation. The second layer optimizes the results of the first layer through the optimal subcarriers filtering method. Under the accuracy of 0.6 m, the positioning accuracy of two common environments has reached, respectively, 96% and 93.9%. The evaluation results show that the positioning accuracy of this method is better than the method based on received signal strength, and it is better than the support vector machine method, which is also slightly improved compared with the deep learning method.

scholarly journals Inquality and the Future of Global History: A Round Table Discussion

2019 ◽  
Vol 3 (1) ◽  
pp. 53-81
Author(s):  
Julia McClure ◽  
Amitava Chowdhury ◽  
Sarah Easterby-Smith ◽  
Norberto Ferreras ◽  
Omar Gueye ◽  
...  
Keyword(s):  
Round Table ◽  
Round Table Discussion ◽  
Global History ◽  
New Directions ◽  
The University ◽  
Global And Local ◽  
North And South America ◽  
North And South ◽  
Local Levels

The following is an edited transcript of a roundtable that took place at the University of Glasgow in September 2018. The roundtable was organized by Dr. Julia McClure in conjunction with the Poverty Research Network’s conference - Beyond Development: The Local Visions of Global Poverty. That conference brought into focus the ways in which the global and local levels meet at the site of poverty and highlighted the different conceptions on the global are generated from the perspective of poverty. The roundtable brought together leading scholars from Europe, Africa, Asia and North and South America to take stock of global history as a field, to consider the role of existing centres of knowledge production, and to assess new directions for the field.

scholarly journals Deep Learning-Based Water Crystal Classification

2022 ◽  
Vol 12 (2) ◽  
pp. 825
Author(s):  
Hien Doan Thi ◽  
Frederic Andres ◽  
Long Tran Quoc ◽  
Hiro Emoto ◽  
Michiko Hayashi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Water Resources ◽  
Past Research ◽  
Fine Tuning ◽  
Quality Of Water ◽  
Snow Crystal ◽  
State Of Water ◽  
First World ◽  
Small Dataset

Much of the earth’s surface is covered by water. As was pointed out in the 2020 edition of the World Water Development Report, climate change challenges the sustainability of global water resources, so it is important to monitor the quality of water to preserve sustainable water resources. Quality of water can be related to the structure of water crystal, the solid-state of water, so methods to understand water crystals can help to improve water quality. As a first step, a water crystal exploratory analysis has been initiated with the cooperation with the Emoto Peace Project (EPP). The 5K EPP dataset has been created as the first world-wide small dataset of water crystals. Our research focused on reducing the inherent limitations when fitting machine learning models to the 5K EPP dataset. One major result is the classification of water crystals and how to split our small dataset into several related groups. Using the 5K EPP dataset of human observations and past research on snow crystal classification, we created a simple set of visual labels to identify water crystal shapes, in 13 categories. A deep learning-based method has been used to automatically do the classification task with a subset of the label dataset. The classification achieved high accuracy when using a fine-tuning technique.

Sign in / Sign up

Export Citation Format

Share Document