scholarly journals Hyperspectral Image Classification Using Parallel Autoencoding Diabolo Networks on Multi-Core and Many-Core Architectures

Electronics ◽  
2018 ◽  
Vol 7 (12) ◽  
pp. 411 ◽  
Author(s):  
Emanuele Torti ◽  
Alessandro Fontanella ◽  
Antonio Plaza ◽  
Javier Plaza ◽  
Francesco Leporati
Keyword(s):  
Deep Learning ◽  
Hyperspectral Imaging ◽  
Hyperspectral Image ◽  
Unsupervised Classification ◽  
Hyperspectral Data ◽  
Machine Learning Techniques ◽  
High Data ◽  
Learning Techniques ◽  
Speed Up ◽  
Many Core

One of the most important tasks in hyperspectral imaging is the classification of the pixels in the scene in order to produce thematic maps. This problem can be typically solved through machine learning techniques. In particular, deep learning algorithms have emerged in recent years as a suitable methodology to classify hyperspectral data. Moreover, the high dimensionality of hyperspectral data, together with the increasing availability of unlabeled samples, makes deep learning an appealing approach to process and interpret those data. However, the limited number of labeled samples often complicates the exploitation of supervised techniques. Indeed, in order to guarantee a suitable precision, a large number of labeled samples is normally required. This hurdle can be overcome by resorting to unsupervised classification algorithms. In particular, autoencoders can be used to analyze a hyperspectral image using only unlabeled data. However, the high data dimensionality leads to prohibitive training times. In this regard, it is important to realize that the operations involved in autoencoders training are intrinsically parallel. Therefore, in this paper we present an approach that exploits multi-core and many-core devices in order to achieve efficient autoencoders training in hyperspectral imaging applications. Specifically, in this paper, we present new OpenMP and CUDA frameworks for autoencoder training. The obtained results show that the CUDA framework provides a speed-up of about two orders of magnitudes as compared to an optimized serial processing chain.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Multimodal Deep Learning and Visible-Light and Hyperspectral Imaging for Fruit Maturity Estimation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1288
Author(s):  
Cinmayii A. Garillos-Manliguez ◽  
John Y. Chiang
Keyword(s):  
Deep Learning ◽  
Visible Light ◽  
Hyperspectral Imaging ◽  
Morphological Changes ◽  
Consumer Preference ◽  
Hyperspectral Data ◽  
Sensitivity Analyses ◽  
Deep Convolutional Neural Networks ◽  
Fruit Maturity ◽  
Learning Architectures

Fruit maturity is a critical factor in the supply chain, consumer preference, and agriculture industry. Most classification methods on fruit maturity identify only two classes: ripe and unripe, but this paper estimates six maturity stages of papaya fruit. Deep learning architectures have gained respect and brought breakthroughs in unimodal processing. This paper suggests a novel non-destructive and multimodal classification using deep convolutional neural networks that estimate fruit maturity by feature concatenation of data acquired from two imaging modes: visible-light and hyperspectral imaging systems. Morphological changes in the sample fruits can be easily measured with RGB images, while spectral signatures that provide high sensitivity and high correlation with the internal properties of fruits can be extracted from hyperspectral images with wavelength range in between 400 nm and 900 nm—factors that must be considered when building a model. This study further modified the architectures: AlexNet, VGG16, VGG19, ResNet50, ResNeXt50, MobileNet, and MobileNetV2 to utilize multimodal data cubes composed of RGB and hyperspectral data for sensitivity analyses. These multimodal variants can achieve up to 0.90 F1 scores and 1.45% top-2 error rate for the classification of six stages. Overall, taking advantage of multimodal input coupled with powerful deep convolutional neural network models can classify fruit maturity even at refined levels of six stages. This indicates that multimodal deep learning architectures and multimodal imaging have great potential for real-time in-field fruit maturity estimation that can help estimate optimal harvest time and other in-field industrial applications.

scholarly journals Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Vibration ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 341-356
Author(s):  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Rolling Stock ◽  
Raw Data ◽  
Learning Techniques ◽  
Combined Defects

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

Assessing the Accuracy of Fault Interpretation using Machine Learning Techniques when Risking Faults for CO2 Storage Site Assessment

2021 ◽  
pp. 1-55
Author(s):  
Emma A. H. Michie ◽  
Behzad Alaei ◽  
Alvar Braathen
Keyword(s):  
Deep Learning ◽  
New Technologies ◽  
Co2 Storage ◽  
Fault Reactivation ◽  
Machine Learning Techniques ◽  
Close Similarity ◽  
Storage Site ◽  
Site Assessment ◽  
Learning Techniques ◽  
Fault Interpretation

Generating an accurate model of the subsurface for the purpose of assessing the feasibility of a CO2 storage site is crucial. In particular, how faults are interpreted is likely to influence the predicted capacity and integrity of the reservoir; whether this is through identifying high risk areas along the fault, where fluid is likely to flow across the fault, or by assessing the reactivation potential of the fault with increased pressure, causing fluid to flow up the fault. New technologies allow users to interpret faults effortlessly, and in much quicker time, utilizing methods such as Deep Learning. These Deep Learning techniques use knowledge from Neural Networks to allow end-users to compute areas where faults are likely to occur. Although these new technologies may be attractive due to reduced interpretation time, it is important to understand the inherent uncertainties in their ability to predict accurate fault geometries. Here, we compare Deep Learning fault interpretation versus manual fault interpretation, and can see distinct differences to those faults where significant ambiguity exists due to poor seismic resolution at the fault; we observe an increased irregularity when Deep Learning methods are used over conventional manual interpretation. This can result in significant differences between the resulting analyses, such as fault reactivation potential. Conversely, we observe that well-imaged faults show a close similarity between the resulting fault surfaces when both Deep Learning and manual fault interpretation methods are employed, and hence we also observe a close similarity between any attributes and fault analyses made.

scholarly journals Flight Considerations and Hyperspectral Image Classifications for Dryland Vegetation Management from a Fixed-wing UAS

2016 ◽  
Vol 5 (2) ◽  
pp. 41 ◽  
Author(s):  
Jessica Mitchell ◽  
Nancy Glenn ◽  
Matthew Anderson ◽  
Ryan Hruska
Keyword(s):  
Hyperspectral Image ◽  
Distribution Patterns ◽  
Unsupervised Classification ◽  
Vegetation Management ◽  
Geometric Error ◽  
Hyperspectral Data ◽  
Unmanned Aerial Systems ◽  
Native Grasses ◽  
Management Objectives ◽  
Aerial Systems

<p class="emsd"><span lang="EN-GB">Unmanned Aerial Systems (UAS)-based hyperspectral remote sensing capabilities developed by the Idaho National Lab and Boise Center Aerospace Lab were tested via demonstration flights that explored the influence of altitude on geometric error, image mosaicking, and dryland vegetation classification. The motivation for this study was to better understand the challenges associated with UAS-based hyperspectral data for distinguishing native grasses such as Sandberg bluegrass (<em>Poa secunda</em>) from invasives such as burr buttercup (<em>Ranunculus testiculatus)</em> in a shrubland environment. The test flights successfully acquired usable flightline data capable of supporting classifiable composite images. Unsupervised classification results support vegetation management objectives that rely on mapping shrub cover and distribution patterns. However, supervised classifications performed poorly despite spectral separability in the image-derived endmember pixels. In many cases, the supervised classifications accentuated noise or features in the mosaic that were artifacts of color balancing and feathering in areas of flightline overlap. Future UAS flight missions that optimize flight planning; minimize illumination differences between flightlines; and leverage ground reference data and time series analysis should be able to effectively distinguish native grasses such as Sandberg bluegrass from burr buttercup. </span></p>

scholarly journals Sentiment Analysis using various Machine Learning and Deep Learning Techniques

2021 ◽  
pp. 385-394
Author(s):  
V Umarani ◽  
A Julian ◽  
J Deepa
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Analysis Process ◽  
Learning Techniques

Sentiment analysis has gained a lot of attention from researchers in the last year because it has been widely applied to a variety of application domains such as business, government, education, sports, tourism, biomedicine, and telecommunication services. Sentiment analysis is an automated computational method for studying or evaluating sentiments, feelings, and emotions expressed as comments, feedbacks, or critiques. The sentiment analysis process can be automated using machine learning techniques, which analyses text patterns faster. The supervised machine learning technique is the most used mechanism for sentiment analysis. The proposed work discusses the flow of sentiment analysis process and investigates the common supervised machine learning techniques such as multinomial naive bayes, Bernoulli naive bayes, logistic regression, support vector machine, random forest, K-nearest neighbor, decision tree, and deep learning techniques such as Long Short-Term Memory and Convolution Neural Network. The work examines such learning methods using standard data set and the experimental results of sentiment analysis demonstrate the performance of various classifiers taken in terms of the precision, recall, F1-score, RoC-Curve, accuracy, running time and k fold cross validation and helps in appreciating the novelty of the several deep learning techniques and also giving the user an overview of choosing the right technique for their application.

scholarly journals Cognitive Radio Transceivers: RF, Spectrum Sensing, and Learning Algorithms Review

2014 ◽  
Vol 2014 ◽  
pp. 1-21 ◽  
Author(s):  
Lise Safatly ◽  
Mario Bkassiny ◽  
Mohammed Al-Husseini ◽  
Ali El-Hajj
Keyword(s):  
Spectrum Sensing ◽  
Model Uncertainty ◽  
Unsupervised Classification ◽  
Machine Learning Techniques ◽  
Classification Algorithms ◽  
Cognitive Engine ◽  
Uwb Antennas ◽  
Hardware Impairments ◽  
Learning Techniques ◽  
Reconfigurable Radio

A cognitive transceiver is required to opportunistically use vacant spectrum resources licensed to primary users. Thus, it relies on a complete adaptive behavior composed of: reconfigurable radio frequency (RF) parts, enhanced spectrum sensing algorithms, and sophisticated machine learning techniques. In this paper, we present a review of the recent advances in CR transceivers hardware design and algorithms. For the RF part, three types of antennas are presented: UWB antennas, frequency-reconfigurable/tunable antennas, and UWB antennas with reconfigurable band notches. The main challenges faced by the design of the other RF blocks are also discussed. Sophisticated spectrum sensing algorithms that overcome main sensing challenges such as model uncertainty, hardware impairments, and wideband sensing are highlighted. The cognitive engine features are discussed. Moreover, we study unsupervised classification algorithms and a reinforcement learning (RL) algorithm that has been proposed to perform decision-making in CR networks.

Sign in / Sign up

Export Citation Format

Share Document