Application of Deep Learning in Dynamic Link-Level Virtualization of Cloud Networks Through the Learning Process

2021 ◽  
Author(s):  
Nader F. Mir ◽  
Aysha S. H. Basha ◽  
Anirudhha A. K. Tiwari
Keyword(s):  
Deep Learning ◽  
Learning Process ◽  
Cloud Networks ◽  
Dynamic Link

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

scholarly journals Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

2020 ◽  
Vol 10 (21) ◽  
pp. 7751
Author(s):  
Seong-Jae Hong ◽  
Won-Kyung Baek ◽  
Hyung-Sup Jung
Keyword(s):  
Deep Learning ◽  
Learning Process ◽  
Intensity Difference ◽  
Sar Images ◽  
Ship Detection ◽  
Detection Model ◽  
Learning Techniques ◽  
Vessel Detection ◽  
Intensity Images ◽  
Deep Learning Model

Synthetic aperture radar (SAR) images have been used in many studies for ship detection because they can be captured without being affected by time and weather. In recent years, the development of deep learning techniques has facilitated studies on ship detection in SAR images using deep learning techniques. However, because the noise from SAR images can negatively affect the learning of the deep learning model, it is necessary to reduce the noise through preprocessing. In this study, deep learning vessel detection was performed using preprocessed SAR images, and the effects of the preprocessing of the images on deep learning vessel detection were compared and analyzed. Through the preprocessing of SAR images, (1) intensity images, (2) decibel images, and (3) intensity difference and texture images were generated. The M2Det object detection model was used for the deep learning process and preprocessed SAR images. After the object detection model was trained, ship detection was performed using test images. The test results are presented in terms of precision, recall, and average precision (AP), which were 93.18%, 91.11%, and 89.78% for the intensity images, respectively, 94.16%, 94.16%, and 92.34% for the decibel images, respectively, and 97.40%, 94.94%, and 95.55% for the intensity difference and texture images, respectively. From the results, it can be found that the preprocessing of the SAR images can facilitate the deep learning process and improve the ship detection performance. The results of this study are expected to contribute to the development of deep learning-based ship detection techniques in SAR images in the future.

Mixed Approaches to Learning in the Flipped Classroom: How Students Approach the Learning Environment

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Margrét Sigrún Sigurðardóttir ◽  
Thamar Melanie Heijstra
Keyword(s):  
Deep Learning ◽  
Active Learning ◽  
Learning Environment ◽  
Learning Process ◽  
Flipped Classroom ◽  
Approaches To Learning ◽  
Male Students ◽  
Learning Approach ◽  
Learning Approaches ◽  
Surface Approach

Flipped teaching is a trend within higher education. Through flipped teaching the learning environment can be altered by moving the lecture out of the classroom through online recordings, while in-classroom sessions focus on active learning and engaging students in their own learning process. In this paper, we used focus groups comprised of male students in a qualitative research course with the aim of understanding the ways in which we might improve active student engagement and motivation within the flipped classroom. The findings indicated that, within the flipped classroom, students mix surface and deep-learning approaches. The online recordings, which students interact with through a surface approach, can function as a stepping stone toward a deep-learning approach to in-class activities, but only if students come to class prepared. The findings therefore suggest that students must be made aware of the importance of preparation prior to flipped classroom in-class activities to ensure the active learning process is successful. By not listening to the recordings (e.g., due to technological failure, as was the case in this study), students can result in only employing a surface approach.

scholarly journals Predicting Groundnut Disease using CNN Models

2021 ◽  
Vol 23 (06) ◽  
pp. 756-766
Author(s):  
Neha Suresh ◽  
◽  
Dr.AnandiGiridharan Dr.AnandiGiridharan ◽  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Arachis Hypogaea ◽  
Efficient Method ◽  
Learning Process ◽  
Plant Disease ◽  
Disease Classification ◽  
Agricultural Field ◽  
Arachis Hypogaea L ◽  
Overall Performance

Groundnut is one of the most important and popular oilseed foods in the agricultural field, and its botanical name is Arachis hypogaea L. Approximately, the pod of mature groundnut contains 1–5 seeds with 57% of oil and 25% of protein content. Groundnut cultivation is affected by different kinds of diseases such as fungi, viruses, and bacteria. Hence, these diseases affect the leaf, root, and stem of the groundnut plant and it leads to heavy loss in yield. Moreover, the enlarger number of diseases affects the leaf and root-like Alternaria, Pestalotiopsis, Bud necrosis, tikka, Phyllosticta, Rust, Pepper spot, Choanephora, early and late leaf spot. To overcome these issues, we introduce an efficient method of convolutional neural network (CNN) because it automatically detects the important features without any human supervision. The proposed methodology can deeply detect plant disease by using a deep learning process. Ultimately, the groundnut disease classification with its overall performance of the proposed methodology provides 96% accuracy.

scholarly journals Effective End-to-End Deep Learning Process in Medical Imaging Using Independent Task Learning: Application for Diagnosis of Maxillary Sinusitis

2021 ◽  
Vol 62 (12) ◽  
pp. 1125
Author(s):  
Jang-Hoon Oh ◽  
Hyug-Gi Kim ◽  
Kyung Mi Lee ◽  
Chang-Woo Ryu ◽  
Soonchan Park ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Imaging ◽  
Learning Process ◽  
Maxillary Sinusitis ◽  
Independent Task ◽  
Task Learning ◽  
End To End

scholarly journals AN APPLICATION OF SEGNET FOR DETECTING LANDSLIDE AREAS BY USING FULLY POLARIMETRIC SAR DATA

2019 ◽  
Vol 13 (2) ◽  
pp. 215
Author(s):  
I Made Oka Guna Antara ◽  
Norikazu Shimizu ◽  
Takahiro Osawa ◽  
I Wayan Nuarsa
Keyword(s):  
Deep Learning ◽  
Learning Process ◽  
Training Data ◽  
Memory Usage ◽  
Polarimetric Sar ◽  
Training Images ◽  
Sar Data ◽  
Color Composite

The study location of landslide is in Hokkaido, Japan which occurred due to the Iburi Earthquake 2018. In this study the landslide has been estimated by the fully Polarimetric SAR (Pol-SAR) technique based on ALOS-2 PALSAR-2 data using the Yamaguchi’s decomposition. The Yamaguchi's decomposition is proposed by Yoshio Yamaguchi et.al. The data has been analyzed using the deep learning process with SegNet architecture with color composite. In this research, the performance of SegNet is fast and efficient in memory usage. However, the result is not good, based on the Intersection over Union (IoU) evaluation obtained the lowest value is 0.0515 and the highest value is 0.1483. That is because of difficulty to make training datasets and of a small number of datasets. The greater difference between accuracy and loss graph along with higher epochs represents overfitting. The overfitting can be caused by the limited amount of training data and failure of the network to generalize the feature set over the training images.

Survey of Deep-learning Techniques in Big-Data analytics

2021 ◽  
Author(s):  
Shubhashish Goswami ◽  
Abhimanyu Kumar
Keyword(s):  
Decision Making ◽  
Big Data ◽  
Deep Learning ◽  
Learning Process ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Operational Parameters ◽  
Learning Techniques ◽  
The Impact ◽  
Business Sectors

Abstract The present elaboration of Big-data research studies relying upon Deep-learning methods had revitalized the decision-making mechanism in the business sectors and the enterprise domains. The firms' operational parameters also have the dependency of the Big-data analytics phase, their way of managing the data, and to evolve the outcomes of Big-data implementation by using the Deep-learning algorithms. The present enhancements in the Deep-learning approaches in Big-data applications facilitate the decision-making process such as the information-processing to the employees, analytical potentials augmentation, and in the transition to having more innovative work. In this DL-approach, the robust-patterns of the data-predictions resulted from the unstructured information by conceptualizing the Decision-making methods. Hence this paper elaborates the above statements stating the impact of the Deep-learning process utilizing the Big-data to operate in the enterprise and Business sectors. Also this study provides a comprehensive survey of all the Deep-learning techniques illustrating the efficiency of Big-Data processing on having the impacts of operational parameters, concentrating the data-dimensionality factors and the Big-data complications rectifying by utilizing the DL-algorithms, usage of Machine-learning or deep-learning process for the decision-making mechanism in the Enterprise sectors and business sectors, the predictions of the Big-data analytics resulting to the decision parameters within the organisations, and in the management of larger scale of datasets in Big-data analytics processing by utilizing the Deep-learning implementations. The comparative analysis of the reviewed studies has also been described by comparing existing approaches of Deep-learning methodologies in employing Big-data analytics.

AUTOMATIC DETECTION OF CARDIOVASCULAR DISEASE USING DEEP KERNEL EXTREME LEARNING MACHINE

2018 ◽  
Vol 30 (06) ◽  
pp. 1850038
Author(s):  
Dongping Li
Keyword(s):  
Neural Network ◽  
Cardiovascular Disease ◽  
Feature Extraction ◽  
Deep Learning ◽  
Extreme Learning Machine ◽  
Learning Process ◽  
Support Vector ◽  
Learning Models ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

The electrocardiogram (ECG) is a principal signal employed to automatically diagnose cardiovascular disease in shallow and deep learning models. However, ECG feature extraction is required and this may reduce diagnosis accuracy in traditional shallow learning models, while backward propagation (BP) algorithm used by the traditional deep learning models has the disadvantages of local minimization and slow convergence rate. To solve these problems, a new deep learning algorithm called deep kernel extreme learning machine (DKELM) is proposed by combining the extreme learning machine auto-encoder (ELM-AE) and kernel ELM (KELM). In the new DKELM architecture with [Formula: see text] hidden layers, ELM-AEs are employed by the front [Formula: see text] hidden layers for feature extraction in the unsupervised learning process, which can effectively extract abstract features from the original ECG signal. To overcome the “dimension disaster” problem, the kernel function is introduced into ELM to act as classifier by the [Formula: see text]th hidden layer in the supervised learning process. The experiments demonstrate that DKELM outperforms the BP neural network, support vector machine (SVM), extreme learning machine (ELM), deep auto-encoder (DAE), deep belief network (DBN) in classification accuracy. Though the accuracy of convolutional neural network (CNN) is almost the same as DKELM, the computing time of CNN is much longer than DKELM.

Sign in / Sign up

Export Citation Format

Share Document