scholarly journals Flash-Flood Potential Mapping Using Deep Learning, Alternating Decision Trees and Data Provided by Remote Sensing Sensors

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 280
Author(s):  
Romulus Costache ◽  
Alireza Arabameri ◽  
Thomas Blaschke ◽  
Quoc Bao Pham ◽  
Binh Thai Pham ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
Decision Trees ◽  
Frequency Ratio ◽  
Flash Flood ◽  
Google Earth ◽  
Weights Of Evidence ◽  
Potential Index ◽  
Deep Learning Neural Network

There is an evident increase in the importance that remote sensing sensors play in the monitoring and evaluation of natural hazards susceptibility and risk. The present study aims to assess the flash-flood potential values, in a small catchment from Romania, using information provided remote sensing sensors and Geographic Informational Systems (GIS) databases which were involved as input data into a number of four ensemble models. In a first phase, with the help of high-resolution satellite images from the Google Earth application, 481 points affected by torrential processes were acquired, another 481 points being randomly positioned in areas without torrential processes. Seventy percent of the dataset was kept as training data, while the other 30% was assigned to validating sample. Further, in order to train the machine learning models, information regarding the 10 flash-flood predictors was extracted in the training sample locations. Finally, the following four ensembles were used to calculate the Flash-Flood Potential Index across the Bâsca Chiojdului river basin: Deep Learning Neural Network–Frequency Ratio (DLNN-FR), Deep Learning Neural Network–Weights of Evidence (DLNN-WOE), Alternating Decision Trees–Frequency Ratio (ADT-FR) and Alternating Decision Trees–Weights of Evidence (ADT-WOE). The model’s performances were assessed using several statistical metrics. Thus, in terms of Sensitivity, the highest value of 0.985 was achieved by the DLNN-FR model, meanwhile the lowest one (0.866) was assigned to ADT-FR ensemble. Moreover, the specificity analysis shows that the highest value (0.991) was attributed to DLNN-WOE algorithm, while the lowest value (0.892) was achieved by ADT-FR. During the training procedure, the models achieved overall accuracies between 0.878 (ADT-FR) and 0.985 (DLNN-WOE). K-index shows again that the most performant model was DLNN-WOE (0.97). The Flash-Flood Potential Index (FFPI) values revealed that the surfaces with high and very high flash-flood susceptibility cover between 46.57% (DLNN-FR) and 59.38% (ADT-FR) of the study zone. The use of the Receiver Operating Characteristic (ROC) curve for results validation highlights the fact that FFPIDLNN-WOE is characterized by the most precise results with an Area Under Curve of 0.96.

Heterogeneous Parallel Processing Enabled Deep Learning Pattern Recognition of Seismic Big Data in Syrna and Kandelioussa

2021 ◽  
Author(s):  
Antonios Konstantaras ◽  
Theofanis Frantzeskakis ◽  
Emmanouel Maravelakis ◽  
Alexandra Moshou ◽  
Panagiotis Argyrakis
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Pattern Recognition ◽  
Big Data ◽  
Deep Learning ◽  
Parallel Processing ◽  
Seismic Data ◽  
Seismic Activity ◽  
Point Cloud ◽  
Deep Learning Neural Network

<p>This research aims to depict ontological findings related to topical seismic phenomena within the Hellenic-Seismic-Arc via deep-data-mining of the existing big-seismological-dataset, encompassing a deep-learning neural network model for pattern recognition along with heterogeneous parallel processing-enabled interactive big data visualization. Using software that utilizes the R language, seismic data were 3D plotted on a 3D Cartesian plane point cloud viewer for further investigation of the formed three-dimensional morphology. As a means of mining information from seismic big data, a deep neural network was trained and refined for pattern recognition and occurrence manifestation attributes of seismic data of magnitudes greater than Ms 4.0. The deep learning neural network comprises of an input layer with six input neurons for the insertion of year, month, day, latitude, longitude and depth, followed by six hidden layers with a hundred neurons each, and one output layer of the estimated magnitude level. This approach was conceptualised to investigate for topical patterns in time yielding minor, interim and strong seismic activity, such as the one depicted by the deep learning neural network, observed in the past ten years on the region between Syrna and Kandelioussa. This area’s coordinates are around 36,4 degrees in latitude and 26,7 degrees in longitude, with the deep learning neural network achieving low error rates, possibly depicting a pattern in seismic activity.</p><p>References</p><p>Axaridou A., I. Chrysakis, C. Georgis, M. Theodoridou, M. Doerr, A. Konstantaras, and E. Maravelakis. 3D-SYSTEK: Recording and exploiting the production workflow of 3D-models in cultural heritage. IISA 2014 - 5th International Conference on Information, Intelligence, Systems and Applications, 51-56, 2014.</p><p>Konstantaras A. Deep Learning and Parallel Processing Spatio-Temporal Clustering Unveil New Ionian Distinct Seismic Zone. Informatics, 7 (4), 39, 2020.</p><p>Konstantaras A.J. Expert knowledge-based algorithm for the dynamic discrimination of interactive natural clusters. Earth Science Informatics. 9 (1), 95-100, 2016.</p><p>Konstantaras A.J. Classification of distinct seismic regions and regional temporal modelling of seismicity in the vicinity of the Hellenic seismic arc. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 6 (4), 1857-1863, 2012.</p><p>Konstantaras A., F. Vallianatos, M.R. Varley, J.P. Makris. Soft-Computing modelling of seismicity in the southern Hellenic Arc. IEEE Geoscience and Remote Sensing Letters, 5 (3), 323-327, 2008.</p><p>Konstantaras A., M.R. Varley, F. Vallianatos, G. Collins and P. Holifield. Recognition of electric earthquake precursors using neuro-fuzzy methods: methodology and simulation results. Proc. IASTED Int. Conf. Signal Processing, Pattern Recognition and Applications (SPPRA 2002), Crete, Greece, 303-308, 2002.</p><p>Maravelakis E., Konstantaras A., Kilty J., Karapidakis E. and Katsifarakis E. Automatic building identification and features extraction from aerial images: Application on the historic 1866 square of Chania Greece. 2014 International Symposium on Fundamentals of Electrical Engineering (ISFEE), Bucharest, 1-6, 2014. doi: 10.1109/ISFEE.2014.7050594.</p><p>Maravelakis E., A. Konstantaras, K. Kabassi, I. Chrysakis, C. Georgis and A. Axaridou. 3DSYSTEK web-based point cloud viewer. IISA 2014 - 5th International Conference on Information, Intelligence, Systems and Applications, 262-266, 2014.</p><p>Maravelakis E., Bilalis N., Mantzorou I., Konstantaras A. and Antoniadis A. 3D modelling of the oldest olive tree of the world. International Journal Of Computational Engineering Research. 2 (2), 340-347, 2012.</p>

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

scholarly journals Convolutional Neural Network for the Semantic Segmentation of Remote Sensing Images

2021 ◽  
Vol 26 (1) ◽  
pp. 200-215
Author(s):  
Muhammad Alam ◽  
Jian-Feng Wang ◽  
Cong Guangpei ◽  
LV Yunrong ◽  
Yuanfang Chen
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Image Processing ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Natural Scene ◽  
Remote Sensing Images ◽  
Advantages And Disadvantages ◽  
Target Segmentation

AbstractIn recent years, the success of deep learning in natural scene image processing boosted its application in the analysis of remote sensing images. In this paper, we applied Convolutional Neural Networks (CNN) on the semantic segmentation of remote sensing images. We improve the Encoder- Decoder CNN structure SegNet with index pooling and U-net to make them suitable for multi-targets semantic segmentation of remote sensing images. The results show that these two models have their own advantages and disadvantages on the segmentation of different objects. In addition, we propose an integrated algorithm that integrates these two models. Experimental results show that the presented integrated algorithm can exploite the advantages of both the models for multi-target segmentation and achieve a better segmentation compared to these two models.

Sign in / Sign up

Export Citation Format

Share Document