scholarly journals A Convolutional Neural Network Architecture for Auto-Detection of Landslide Photographs to Assess Citizen Science and Volunteered Geographic Information Data Quality

2019 ◽  
Vol 8 (7) ◽  
pp. 300 ◽  
Author(s):  
Recep Can ◽  
Sultan Kocaman ◽  
Candan Gokceoglu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Citizen Science ◽  
Network Architecture ◽  
High Performance ◽  
Training Data ◽  
Geographical Information ◽  
Training Dataset ◽  
Gis Environment ◽  
Automated Procedures

Several scientific processes benefit from Citizen Science (CitSci) and VGI (Volunteered Geographical Information) with the help of mobile and geospatial technologies. Studies on landslides can also take advantage of these approaches to a great extent. However, the quality of the collected data by both approaches is often questionable, and automated procedures to check the quality are needed for this purpose. In the present study, a convolutional neural network (CNN) architecture is proposed to validate landslide photos collected by citizens or nonexperts and integrated into a mobile- and web-based GIS environment designed specifically for a landslide CitSci project. The VGG16 has been used as the base model since it allows finetuning, and high performance could be achieved by selecting the best hyper-parameters. Although the training dataset was small, the proposed CNN architecture was found to be effective as it could identify the landslide photos with 94% precision. The accuracy of the results is sufficient for purpose and could even be improved further using a larger amount of training data, which is expected to be obtained with the help of volunteers.

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

scholarly journals BengaliNet: A Low-Cost Novel Convolutional Neural Network for Bengali Handwritten Characters Recognition

2021 ◽  
Vol 11 (15) ◽  
pp. 6845
Author(s):  
Abu Sayeed ◽  
Jungpil Shin ◽  
Md. Al Mehedi Hasan ◽  
Azmain Yakin Srizon ◽  
Md. Mehedi Hasan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Character Recognition ◽  
High Performance ◽  
Low Cost ◽  
Traditional Learning ◽  
Neural Network Architecture ◽  
Handwritten Character Recognition ◽  
Handwritten Character

As it is the seventh most-spoken language and fifth most-spoken native language in the world, the domain of Bengali handwritten character recognition has fascinated researchers for decades. Although other popular languages i.e., English, Chinese, Hindi, Spanish, etc. have received many contributions in the area of handwritten character recognition, Bengali has not received many noteworthy contributions in this domain because of the complex curvatures and similar writing fashions of Bengali characters. Previously, studies were conducted by using different approaches based on traditional learning, and deep learning. In this research, we proposed a low-cost novel convolutional neural network architecture for the recognition of Bengali characters with only 2.24 to 2.43 million parameters based on the number of output classes. We considered 8 different formations of CMATERdb datasets based on previous studies for the training phase. With experimental analysis, we showed that our proposed system outperformed previous works by a noteworthy margin for all 8 datasets. Moreover, we tested our trained models on other available Bengali characters datasets such as Ekush, BanglaLekha, and NumtaDB datasets. Our proposed architecture achieved 96–99% overall accuracies for these datasets as well. We believe our contributions will be beneficial for developing an automated high-performance recognition tool for Bengali handwritten characters.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

Segmentation Neural Network Incorporating Scale-Space in the Application of Cardiac MRI

2020 ◽  
Vol 10 (7) ◽  
pp. 1494-1505
Author(s):  
Hyo-Hun Kim ◽  
Byung-Woo Hong
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Cardiac Mri ◽  
Network Architecture ◽  
Data Augmentation ◽  
Scale Space ◽  
Segmentation Algorithm ◽  
Training Data ◽  
Training Procedure ◽  
Whole Heart

In this work, we present an image segmentation algorithm based on the convolutional neural network framework where the scale space theory is incorporated in the course of training procedure. The construction of data augmentation is designed to apply the scale space to the training data in order to effectively deal with the variability of regions of interest in geometry and appearance such as shape and contrast. The proposed data augmentation algorithm via scale space is aimed to improve invariant features with respect to both geometry and appearance by taking into consideration of their diffusion process. We develop a segmentation algorithm based on the convolutional neural network framework where the network architecture consists of encoding and decoding substructures in combination with the data augmentation scheme via the scale space induced by the heat equation. The quantitative analysis using the cardiac MRI dataset indicates that the proposed algorithm achieves better accuracy in the delineation of the left ventricles, which demonstrates the potential of the algorithm in the application of the whole heart segmentation as a compute-aided diagnosis system for the cardiac diseases.

scholarly journals Batik pattern recognition using convolutional neural network

2020 ◽  
Vol 9 (4) ◽  
pp. 1430-1437
Author(s):  
Mohammad Arif Rasyidi ◽  
Taufiqotul Bariyah
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Convolutional Neural Network ◽  
Test Data ◽  
Network Architecture ◽  
Experimental Results ◽  
Training Data ◽  
Excellent Performance ◽  
Artistic Value

Batik is one of Indonesia's cultures that is well-known worldwide. Batik is a fabric that is painted using canting and liquid wax so that it forms patterns of high artistic value. In this study, we applied the convolutional neural network (CNN) to identify six batik patterns, namely Banji, Ceplok, Kawung, Mega Mendung, Parang, and Sekar Jagad. 994 images from the 6 categories were collected and then divided into training and test data with a ratio of 8:2. Image augmentation was also done to provide variations in training data as well as to prevent overfitting. Experimental results on the test data showed that CNN produced an excellent performance as indicated by accuracy of 94% and top-2 accuracy of 99% which was obtained using the DenseNet network architecture.

scholarly journals DeephageTP: A Convolutional Neural Network  Framework for Identifying Phage-specific Proteins from metagenomic sequencing data

2020 ◽  
Author(s):  
Yunmeng Chu ◽  
Shun Guo ◽  
Dachao Cui ◽  
Haoran Zhang ◽  
xiongfei Fu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Performance ◽  
Protein Sequences ◽  
Training Dataset ◽  
Biological Entity ◽  
Metagenomic Sequencing ◽  
Subunit Protein ◽  
Terminase Subunit ◽  
Specific Proteins

Abstract Background: Bacteriophage (phage) is the most abundant and diverse biological entity on the Earth. This makes it a challenge to identify and annotate phage genomes efficiently on a large scale. Portal (portal protein), TerL (large terminase subunit protein) and TerS (small terminase subunit protein) are the three specific proteins of the tailed phage. Here, we develop a CNN (convolutional neural network)-based framework, DeephageTP, to identify these three proteins from metagenome data. The framework takes one-hot encoding data of the original protein sequences as the input and extracts the predictive features in the process of modeling. The cutoff loss value for each protein category was determined by exploiting the distributions of the loss values of the sequences within the same category. Finally, we tested the efficacy of the framework using three real metagenomic datasets. Result: The proposed multiclass classification CNN-based model was trained by the training datasets and shows relatively high prediction performance ( A ccuracy : Portal, 98.8%; TerL, 98.6%; TerS, 97.8%) for the three protein categories, respectively. The experiments using the independent mimic dataset demonstrate that the performance of the model could become worse along with the increase of the data size. To address this issue, we determined and set the cutoff loss values (i.e., TerL: -5.2, Portal: -4.2, TerS: -2.9) for each of the three categories, respectively. With these values, the model obtains high performance in terms of Precision in identifying the TerL and Portal sequences (i.e, ~ 94% and ~ 90%, respectively) from the mimic dataset that is 20 times larger than the training dataset. More interestingly, the framework identified from the three real metagenomic datasets many novel phage sequences that are not detectable by the two alignment-based methods (i.e., DIAMOND and HMMER). Conclusion: Compared to the conventional alignment-based methods, our proposed framework shows high performance in identifying phage-specific protein sequences with a particular advantage in identifying the novel protein sequences with remote homology to their known counterparts in public databases. Indeed, our method could also be applied for identifying the other protein sequences with the characteristic of high complexity and low conservation. The DeephageTP is available at https://github.com/chuym726/DeephageTP .

scholarly journals Land Cover Classification using Very High Spatial Resolution Remote Sensing Data and Deep Learning

2020 ◽  
Vol 57 (1-2) ◽  
pp. 71-77
Author(s):  
R. Ķēniņš
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Land Cover ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Human Error ◽  
Remote Sensing Data ◽  
Land Cover Classification ◽  
Training Data ◽  
Surface Model

AbstractThe paper describes the process of training a convolutional neural network to segment land into its labelled land cover types such as grass, water, forest and buildings. This segmentation can promote automated updating of topographical maps since doing this manually is a time-consuming process, which is prone to human error. The aim of the study is to evaluate the application of U-net convolutional neural network for land cover classification using countrywide aerial data. U-net neural network architecture has initially been developed for use in biomedical image segmentation and it is one of the most widely used CNN architectures for image segmentation. Training data have been prepared using colour infrared images of Ventspils town and its digital surface model (DSM). Forest, buildings, water, roads and other land plots have been selected as classes, into which the image has been segmented. As a result, images have been segmented with an overall accuracy of 82.9 % with especially high average accuracy for the forest and water classes.

scholarly journals Multi-attribute self-attention guided vehicle local region detection based on convolutional neural network architecture

2020 ◽  
Vol 17 (4) ◽  
pp. 172988142094434
Author(s):  
Jingbo Chen ◽  
Shengyong Chen ◽  
Linjie Bian
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Quantitative Evaluation ◽  
Network Architecture ◽  
Local Region ◽  
Training Data ◽  
Detection Methods ◽  
Data Set ◽  
Region Detection ◽  
Bounding Boxes

Many pieces of information are included in the front region of a vehicle, especially in windshield and bumper regions. Thus, windshield or bumper region detection is making sense to extract useful information. But the existing windshield and bumper detection methods based on traditional artificial features are not robust enough. Those features may become invalid in many real situations (e.g. occlude, illumination change, viewpoint change.). In this article, we propose a multi-attribute-guided vehicle discriminately region detection method based on convolutional neural network and not rely on bounding box regression. We separate the net into two branches, respectively, for identification (ID) and Model attributes training. Therefore, the feature spaces of different attributes become more independent. Additionally, we embed a self-attention block into our framework to improve the performance of local region detection. We train our model on PKU_VD data set which has a huge number of images inside. Furthermore, we labeled the handcrafted bounding boxes on 5000 randomly picked testing images, and 1020 of them are used for evaluation and 3980 as the training data for YOLOv3. We use Intersection over Union for quantitative evaluation. Experiments were conducted in three different latest convolutional neural network trunks to illustrate the detection performance of the proposed method. Simultaneously, in terms of quantitative evaluation, the performance of our method is close to YOLOv3 even without handcrafted bounding boxes.

scholarly journals Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 450
Author(s):  
Xudong Li ◽  
Jianhua Zheng ◽  
Mingtao Li ◽  
Wenzhen Ma ◽  
Yang Hu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Transfer Learning ◽  
Network Architecture ◽  
Domain Adaptation ◽  
Training Dataset ◽  
Testing Dataset ◽  
Feature Extractor

In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing dataset in transfer learning. Moreover, Convolutional Neural Network (CNN) is the most widely used network among existing domain adaptation approaches due to its powerful feature extraction capability. However, network designing is too empirical, and there is no network designing principle from the frequency domain. In this paper, we propose a unified convolutional neural network architecture from a frequency domain perspective for a domain adaptation named Frequency-domain Fusing Convolutional Neural Network (FFCNN). The method of FFCNN contains two parts, frequency-domain fusing layer and feature extractor. The frequency-domain fusing layer uses convolution operations to filter signals at different frequency bands and combines them into new input signals. These signals are input to the feature extractor to extract features and make domain adaptation. We apply FFCNN for three domain adaptation methods, and the diagnosis accuracy is improved compared to the typical CNN.

scholarly journals Automatic vectorization of point symbols on archive maps using deep convolutional neural network

2021 ◽  
Vol 4 ◽  
pp. 1-5
Author(s):  
Gergely Vassányi ◽  
Mátyás Gede
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Geographical Information ◽  
Test Sheet ◽  
Complete Test ◽  
Automatic Methods ◽  
Feature Pyramid ◽  
Topographical Maps ◽  
Point Symbol

Abstract. Archive topographical maps are a key source of geographical information from past ages, which can be valuable for several science fields. Since manual digitization is usually slow and takes much human resource, automatic methods are preferred, such as deep learning algorithms. Although automatic vectorization is a common problem, there have been few approaches regarding point symbols. In this paper, a point symbol vectorization method is proposed, which was tested on Third Military Survey map sheets using a Mask Regional Convolutional Neural Network (MRCNN). The MRCNN implementation uses the ResNet101 network improved with the Feature Pyramid Network architecture and is developed in a Google Colab environment. The pretrained network was trained on four point symbol categories simultaneously. Results show 90% accuracy, while 94% of symbols detected for some categories on the complete test sheet.

Sign in / Sign up

Export Citation Format

Share Document