A hybrid optimization-based deep belief neural network for the classification of vegetation area in multi-spectral satellite image

2021 ◽  
Vol 24 (4) ◽  
pp. 363-379
Author(s):  
Anil B. Gavade ◽  
Vijay S. Rajpurohit
Keyword(s):  
Neural Network ◽  
Land Use ◽  
Land Cover ◽  
False Positive Rate ◽  
Satellite Image ◽  
Harmony Search ◽  
Classification Problem ◽  
True Positive Rate ◽  
Positive Rate

Over the last few decades, multiple advances have been done for the classification of vegetation area through land cover, and land use. However, classification problem is one of the most complicated and contradicting problems that has received considerable attention. Therefore, to tackle this problem, this paper proposes a new Firefly-Harmony search based Deep Belief Neural Network method (FHS-DBN) for the classification of land cover, and land use. The segmentation process is done using Bayesian Fuzzy Clustering,and the feature matrix is developed. The feature matrix is given to the proposed FHS-DBN method that distinguishes the land coverfrom the land use in the multispectral satellite images, for analyzing the vegetation area. The proposed FHS-DBN method is designedby training the DBN using the FHS algorithm, which is developed by the combination of Firefly Algorithm (FA) and Harmony Search (HS) algorithm. The performance of the FHS-DBN model is evaluated using three metrics, such as Accuracy, True Positive Rate (TPR), and False Positive Rate (FPR). From the experimental analysis, it is concludedthat the proposed FHS-DBN model achieves ahigh classification accuracy of 0.9381, 0.9488, 0.9497, and 0.9477 usingIndian Pine, Salinas scene, Pavia Centre and university, and Pavia University scene dataset.

scholarly journals A Learning-based Neural Network Model for the Detection and Classification of SQL Injection Attacks

2017 ◽  
Vol 7 (2) ◽  
pp. 16-41 ◽  
Author(s):  
Naghmeh Moradpoor Sheykhkanloo
Keyword(s):  
Neural Network ◽  
Web Application ◽  
Query Language ◽  
False Positive Rate ◽  
True Positive Rate ◽  
Injection Technique ◽  
Injection Attacks ◽  
Proposed Model ◽  
Positive Rate ◽  
Sql Injection Attacks

Structured Query Language injection (SQLi) attack is a code injection technique where hackers inject SQL commands into a database via a vulnerable web application. Injected SQL commands can modify the back-end SQL database and thus compromise the security of a web application. In the previous publications, the author has proposed a Neural Network (NN)-based model for detections and classifications of the SQLi attacks. The proposed model was built from three elements: 1) a Uniform Resource Locator (URL) generator, 2) a URL classifier, and 3) a NN model. The proposed model was successful to: 1) detect each generated URL as either a benign URL or a malicious, and 2) identify the type of SQLi attack for each malicious URL. The published results proved the effectiveness of the proposal. In this paper, the author re-evaluates the performance of the proposal through two scenarios using controversial data sets. The results of the experiments are presented in order to demonstrate the effectiveness of the proposed model in terms of accuracy, true-positive rate as well as false-positive rate.

scholarly journals Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas

2020 ◽  
Vol 13 (1-2) ◽  
pp. 43-52
Author(s):  
Boudewijn van Leeuwen ◽  
Zalán Tobak ◽  
Ferenc Kovács
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Land Use ◽  
Land Cover ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Land Use Land Cover ◽  
Learning Techniques

AbstractClassification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus on temporary inundated land in a flat area in the south of Hungary. These inundations disrupt agricultural practices and can cause large financial loss. Sentinel 2 data with a high temporal and medium spatial resolution is classified using open source implementations of a random forest, support vector machine and an artificial neural network. Each classification model is applied to the same data set and the results are compared qualitatively and quantitatively. The accuracy of the results is high for all methods and does not show large overall differences. A quantitative spatial comparison demonstrates that the neural network gives the best results, but that all models are strongly influenced by atmospheric disturbances in the image.

WLI Fuzzy Clustering and Adaptive Lion Neural Network (ALNN) for Cloud Intrusion Detection

2019 ◽  
Vol 11 (1) ◽  
pp. 1-17
Author(s):  
Pinki Sharma ◽  
Jyotsna Sengupta ◽  
P. K. Suri
Keyword(s):  
Neural Network ◽  
Fuzzy Clustering ◽  
Clustered Data ◽  
False Positive Rate ◽  
Cloud Service ◽  
True Positive Rate ◽  
Aggregated Data ◽  
Marquardt Algorithm ◽  
Positive Rate ◽  
And Performance

Cloud computing is the internet-based technique where the users utilize the online resources for computing services. The attacks or intrusion into the cloud service is the major issue in the cloud environment since it degrades performance. In this article, we propose an adaptive lion-based neural network (ALNN) to detect the intrusion behaviour. Initially, the cloud network has generated the clusters using a WLI fuzzy clustering mechanism. This mechanism obtains the different numbers of clusters in which the data objects are grouped together. Then, the clustered data is fed into the newly designed adaptive lion-based neural network. The proposed method is developed by the combination of Levenberg-Marquardt algorithm of neural network and adaptive lion algorithm where female lions are used to update the weight adaptively using lion optimization algorithm. Then, the proposed method is used to detect the malicious activity through training process. Thus, the different clustered data is given to the proposed ALNN model. Once the data is trained, then it needs to be aggregated. Subsequently, the aggregated data is fed into the proposed ALNN method where the intrusion behaviour is detected. Finally, the simulation results of the proposed method and performance is analysed through accuracy, false positive rate, and true positive rate. Thus, the proposed ALNN algorithm attains 96.46% accuracy which ensures better detection performance.

scholarly journals A comparison and classification of land use land cover to estimate their effect on environment: case study in Baghdad city

2021 ◽  
Vol 2114 (1) ◽  
pp. 012017
Author(s):  
Bushra A. Ahmed ◽  
Ghaida S. Hadi
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Satellite Image ◽  
Major Change ◽  
Land Cover Changes ◽  
Land Use Land Cover ◽  
Two Cities ◽  
Landsat Satellite

Abstract This study compared and classified of land use and land cover changes by using Remote Sensing (RS) and Geographic Information Systems (GIS) on two cities (Al-Saydiya city and Al-Hurriya) in Baghdad province, capital of Iraq. In this study, Landsat satellite image for 2020 were used for (Land Use/Land Cover) classification. The change in the size of the surface area of each class in the Al-Saydiya city and Al-Hurriya cities was also calculated to estimate their effect on environment. The major change identified, in the study, was in agricultural area in Al-Saydiya city compare with Al-Hurriya city in Baghdad province. The results of the research showed that the percentage of the green area from the total area in Al-Saydiya city is 34.95%, while in Al-Hurriya is 27.53%. Therefore, available results of land use and land cover changes can provide critical input to decision-making of environmental management and planning the future.

scholarly journals A Learning-based Neural Network Model for the Detection and Classification of SQL Injection Attacks

2020 ◽  
pp. 450-475
Author(s):  
Naghmeh Moradpoor Sheykhkanloo
Keyword(s):  
Neural Network ◽  
Web Application ◽  
Query Language ◽  
False Positive Rate ◽  
True Positive Rate ◽  
Injection Technique ◽  
Data Sets ◽  
Injection Attacks ◽  
Proposed Model ◽  
Positive Rate

Structured Query Language injection (SQLi) attack is a code injection technique where hackers inject SQL commands into a database via a vulnerable web application. Injected SQL commands can modify the back-end SQL database and thus compromise the security of a web application. In the previous publications, the author has proposed a Neural Network (NN)-based model for detections and classifications of the SQLi attacks. The proposed model was built from three elements: 1) a Uniform Resource Locator (URL) generator, 2) a URL classifier, and 3) a NN model. The proposed model was successful to: 1) detect each generated URL as either a benign URL or a malicious, and 2) identify the type of SQLi attack for each malicious URL. The published results proved the effectiveness of the proposal. In this paper, the author re-evaluates the performance of the proposal through two scenarios using controversial data sets. The results of the experiments are presented in order to demonstrate the effectiveness of the proposed model in terms of accuracy, true-positive rate as well as false-positive rate.

Satellite Image Classes Categorization Schemes for United Nations Framework Convention on Climatic Change (UNFCCC)

2018 ◽  
pp. 101-113
Author(s):  
Joyce Gosata Maphanyane ◽  
Gofetamang Phunyuka
Keyword(s):  
Climate Change ◽  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Electromagnetic Waves ◽  
Satellite Image ◽  
National Representation ◽  
Thematic Resolution ◽  
The One

This chapter looks at the disparities between the UNFCCC – GHG – Land-Use and Land-Cover Change (LULCC) remote sensing images classification scheme with that of Botswana for the GHG inventory for the National Representation. This chapter has points out that the Botswana Scheme maximizes the LANDSAT System electromagnetic waves capabilities and maps produced give more classes and better thematic resolution for the classification of land cover classes. Suggestions are made for these two schemes to be reconciled and use the one which gives the best GHG calculated results for inventories for Inter-Governmental Panel on Climate Change (IPCC) Reporting

Neural Network Detection and Segmentation of Mental Foramen in Panoramic Imaging

2020 ◽  
Vol 44 (3) ◽  
pp. 168-173
Author(s):  
Lazar Kats ◽  
Marilena Vered ◽  
Sigalit Blumer ◽  
Eytan Kats
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Biomedical Application ◽  
False Positive Rate ◽  
True Positive Rate ◽  
Mental Foramen ◽  
Dice Similarity Coefficient ◽  
Tel Aviv ◽  
Positive Rate ◽  
Panoramic Images

Objective: To apply the technique of deep learning on a small dataset of panoramic images for the detection and segmentation of the mental foramen (MF). Study design: In this study we used in-house dataset created within the School of Dental Medicine, Tel Aviv University. The dataset contained randomly chosen and anonymized 112 digital panoramic X-ray images and corresponding segmentations of MF. In order to solve the task of segmentation of the MF we used a single fully convolution neural network, that was based on U-net as well as a cascade architecture. 70% of the data were randomly chosen for training, 15% for validation and accuracy was tested on 15%. The model was trained using NVIDIA GeForce GTX 1080 GPU. The SPSS software, version 17.0 (Chicago, IL, USA) was used for the statistical analysis. The study was approved by the ethical committee of Tel Aviv University. Results: The best results of the dice similarity coefficient ( DSC), precision, recall, MF-wise true positive rate (MFTPR) and MF-wise false positive rate (MFFPR) in single networks were 49.51%, 71.13%, 68.24%, 87.81% and 14.08%, respectively. The cascade of networks has shown better results than simple networks in recall and MFTPR, which were 88.83%, 93.75%, respectively, while DSC and precision achieved the lowest values, 31.77% and 23.92%, respectively. Conclusions: Currently, the U-net, one of the most used neural network architectures for biomedical application, was effectively used in this study. Methods based on deep learning are extremely important for automatic detection and segmentation in radiology and require further development.

Sign in / Sign up

Export Citation Format

Share Document