scholarly journals Random Projections and α-Shape to Support the Kernel Design (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13877-13878
Author(s):  
Daniel Moreira Cestari ◽  
Rodrigo Fernandes de Mello
Keyword(s):  
Neural Networks ◽  
Classification Performance ◽  
General Purpose ◽  
Considerable Improvement ◽  
Random Projections ◽  
Good Strategy ◽  
Data Points ◽  
Almost All ◽  
Kernel Design ◽  
Random Convex

We demonstrate that projecting data points into hyperplanes is good strategy for general-purpose kernel design. We used three different hyperplanes generation schemes, random, convex hull and α-shape, and evaluated the results on two synthetic and three well known image-based datasets. The results showed considerable improvement in the classification performance in almost all scenarios, corroborating the claim that such an approach can be used as a general-purpose kernel transformation. Also, we discuss some connection with Convolutional Neural Networks and how such an approach could be used to understand such networks better.

scholarly journals Group-Wise Dynamic Dropout Based on Latent Semantic Variations

2020 ◽  
Vol 34 (07) ◽  
pp. 11229-11236
Author(s):  
Zhiwei Ke ◽  
Zhiwei Wen ◽  
Weicheng Xie ◽  
Yi Wang ◽  
Linlin Shen
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Semantic Information ◽  
State Of The Art ◽  
Classification Performance ◽  
Network Robustness ◽  
Feature Detectors ◽  
Data Points ◽  
Adversarial Examples ◽  
Public Datasets

Dropout regularization has been widely used in various deep neural networks to combat overfitting. It works by training a network to be more robust on information-degraded data points for better generalization. Conventional dropout and variants are often applied to individual hidden units in a layer to break up co-adaptations of feature detectors. In this paper, we propose an adaptive dropout to reduce the co-adaptations in a group-wise manner by coarse semantic information to improve feature discriminability. In particular, we showed that adjusting the dropout probability based on local feature densities can not only improve the classification performance significantly but also enhance the network robustness against adversarial examples in some cases. The proposed approach was evaluated in comparison with the baseline and several state-of-the-art adaptive dropouts over four public datasets of Fashion-MNIST, CIFAR-10, CIFAR-100 and SVHN.

scholarly journals Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Hongbin Ma ◽  
Shuyuan Yang ◽  
Guangjun He ◽  
Ruowu Wu ◽  
Xiaojun Hao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Points ◽  
Few Data

scholarly journals Attention-based deep learning networks for identification of human gait using radar micro-Doppler spectrograms

2021 ◽  
pp. 1-6
Author(s):  
Hannah Garcia Doherty ◽  
Roberto Arnaiz Burgueño ◽  
Roeland P. Trommel ◽  
Vasileios Papanastasiou ◽  
Ronny I. A. Harmanny
Keyword(s):  
Neural Networks ◽  
Feature Vector ◽  
Classification Performance ◽  
Input Image ◽  
Human Gait ◽  
Learning Networks ◽  
Class Label ◽  
Deep Convolutional Neural Networks ◽  
Network Layers ◽  
Feature Dimension

Abstract Identification of human individuals within a group of 39 persons using micro-Doppler (μ-D) features has been investigated. Deep convolutional neural networks with two different training procedures have been used to perform classification. Visualization of the inner network layers revealed the sections of the input image most relevant when determining the class label of the target. A convolutional block attention module is added to provide a weighted feature vector in the channel and feature dimension, highlighting the relevant μ-D feature-filled areas in the image and improving classification performance.

DCNN-based Ship Classification using Enhanced Edge Information and Inception Module

2021 ◽  
Author(s):  
Bo Wang ◽  
Xiaoting Yu ◽  
Chengeng Huang ◽  
Qinghong Sheng ◽  
Yuanyuan Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Classification Performance ◽  
Image Features ◽  
Deep Convolutional Neural Networks ◽  
Edge Information ◽  
Average Accuracy ◽  
Ship Classification ◽  
Edge Features ◽  
High Level ◽  
Better Than

The excellent feature extraction ability of deep convolutional neural networks (DCNNs) has been demonstrated in many image processing tasks, by which image classification can achieve high accuracy with only raw input images. However, the specific image features that influence the classification results are not readily determinable and what lies behind the predictions is unclear. This study proposes a method combining the Sobel and Canny operators and an Inception module for ship classification. The Sobel and Canny operators obtain enhanced edge features from the input images. A convolutional layer is replaced with the Inception module, which can automatically select the proper convolution kernel for ship objects in different image regions. The principle is that the high-level features abstracted by the DCNN, and the features obtained by multi-convolution concatenation of the Inception module must ultimately derive from the edge information of the preprocessing input images. This indicates that the classification results are based on the input edge features, which indirectly interpret the classification results to some extent. Experimental results show that the combination of the edge features and the Inception module improves DCNN ship classification performance. The original model with the raw dataset has an average accuracy of 88.72%, while when using enhanced edge features as input, it achieves the best performance of 90.54% among all models. The model that replaces the fifth convolutional layer with the Inception module has the best performance of 89.50%. It performs close to VGG-16 on the raw dataset and is significantly better than other deep neural networks. The results validate the functionality and feasibility of the idea posited.

Fake News Detection Using Recurrent Neural Networks and Distributed Representations for the Portuguese Language

2021 ◽  
Author(s):  
Guilherme Zanini Moreira ◽  
Marcelo Romero ◽  
Manassés Ribeiro
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Classification Performance ◽  
Fake News ◽  
Distributed Representations ◽  
Memory Network ◽  
Long Short Term Memory ◽  
Media Channels ◽  
Damage Rule

After the advent of Web, the number of people who abandoned traditional media channels and started receiving news only through social media has increased. However, this caused an increase of the spread of fake news due to the ease of sharing information. The consequences are various, with one of the main ones being the possible attempts to manipulate public opinion for elections or promotion of movements that can damage rule of law or the institutions that represent it. The objective of this work is to perform fake news detection using Distributed Representations and Recurrent Neural Networks (RNNs). Although fake news detection using RNNs has been already explored in the literature, there is little research on the processing of texts in Portuguese language, which is the focus of this work. For this purpose, distributed representations from texts are generated with three different algorithms (fastText, GloVe and word2vec) and used as input features for a Long Short-term Memory Network (LSTM). The approach is evaluated using a publicly available labelled news dataset. The proposed approach shows promising results for all the three distributed representation methods for feature extraction, with the combination word2vec+LSTM providing the best results. The results of the proposed approach shows a better classification performance when compared to simple architectures, while similar results are obtained when the approach is compared to deeper architectures or more complex methods.

scholarly journals Integrating Audio Signal Processing and Deep Learning Algorithms for Gait Pattern Classification in Brazilian Gaited Horses

2021 ◽  
Vol 2 ◽  
Author(s):  
Anderson Antonio Carvalho Alves ◽  
Lucas Tassoni Andrietta ◽  
Rafael Zinni Lopes ◽  
Fernando Oliveira Bussiman ◽  
Fabyano Fonseca e Silva ◽  
...  
Keyword(s):  
Neural Networks ◽  
Signal Processing ◽  
Deep Learning ◽  
Audio Signal ◽  
Gait Pattern ◽  
Classification Performance ◽  
Audio Signal Processing ◽  
Gait Patterns ◽  
Audio Features ◽  
Gaited Horses

This study focused on assessing the usefulness of using audio signal processing in the gaited horse industry. A total of 196 short-time audio files (4 s) were collected from video recordings of Brazilian gaited horses. These files were converted into waveform signals (196 samples by 80,000 columns) and divided into training (N = 164) and validation (N = 32) datasets. Twelve single-valued audio features were initially extracted to summarize the training data according to the gait patterns (Marcha Batida—MB and Marcha Picada—MP). After preliminary analyses, high-dimensional arrays of the Mel Frequency Cepstral Coefficients (MFCC), Onset Strength (OS), and Tempogram (TEMP) were extracted and used as input information in the classification algorithms. A principal component analysis (PCA) was performed using the 12 single-valued features set and each audio-feature dataset—AFD (MFCC, OS, and TEMP) for prior data visualization. Machine learning (random forest, RF; support vector machine, SVM) and deep learning (multilayer perceptron neural networks, MLP; convolution neural networks, CNN) algorithms were used to classify the gait types. A five-fold cross-validation scheme with 10 repetitions was employed for assessing the models' predictive performance. The classification performance across models and AFD was also validated with independent observations. The models and AFD were compared based on the classification accuracy (ACC), specificity (SPEC), sensitivity (SEN), and area under the curve (AUC). In the logistic regression analysis, five out of the 12 audio features extracted were significant (p < 0.05) between the gait types. ACC averages ranged from 0.806 to 0.932 for MFCC, from 0.758 to 0.948 for OS and, from 0.936 to 0.968 for TEMP. Overall, the TEMP dataset provided the best classification accuracies for all models. The most suitable method for audio-based horse gait pattern classification was CNN. Both cross and independent validation schemes confirmed that high values of ACC, SPEC, SEN, and AUC are expected for yet-to-be-observed labels, except for MFCC-based models, in which clear overfitting was observed. Using audio-generated data for describing gait phenotypes in Brazilian horses is a promising approach, as the two gait patterns were correctly distinguished. The highest classification performance was achieved by combining CNN and the rhythmic-descriptive AFD.

Prediction of Bubble Point Pressure Using Artificial Neural Networks in the Niger Delta

2020 ◽  
Vol 11 (01) ◽  
pp. 1445-1454
Author(s):  
Uduma U. Idika
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Niger Delta ◽  
Reservoir Temperature ◽  
Bubble Point ◽  
Bubble Point Pressure ◽  
Point Pressure ◽  
Data Points ◽  
Artificial Neural ◽  
Propagation Network

A model was developed to predict the bubble point pressure of saturated reservoirs. The model was based on artificial neural networks and was developed using 700 generic data sets which are representative of the Niger Delta region of Nigeria. The data set was first cleaned to remove erroneous and repeated data points. After cleaning, 618 data points were remaining. Of the 618 data points, 463 were used to train the ANN model, 93 were used to cross-validate the relationships established during the training process and the remaining 62 were used to test the model to evaluate its accuracy. A backward propagation network utilizing the LM algorithm was used in developing the model. The first layer consisted of four neurons representing the input values of reservoir temperature, API oil gravity, gas specific gravity, and solution GOR. The second (hidden) layer consisted of 26 neurons, and the third layer contained one neuron representing the output value of the bubble point pressure. The results showed that the developed model provides better predictions and higher accuracy than the existing empirical correlations considered when exposed to an additional 13 data points which were unseen by the model during its development. The model provided predictions of the bubble point pressure with an absolute average percent error of 3.98%, RMSE of 177.6479 and correlation coefficient of 0.9851. Trend analysis was performed to check the behavior of the predicted values of P_b for any change in reservoir temperature, oil API gravity, gas gravity and solution GOR. The model was found to be physically correct. Its stability indicated that it did not overfit the data, implying that it was successfully trained.

Towards Stroke Biomarkers on Fundus Retinal Imaging: A Comparison Between Vasculature Embeddings and General Purpose Convolutional Neural Networks

2021 ◽  
Author(s):  
Ivan Coronado ◽  
Rania Abdelkhaleq ◽  
Juntao Yan ◽  
Sergio Salazar Marioni ◽  
Amanda Jagolino-Cole ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Retinal Imaging ◽  
General Purpose
Sign in / Sign up

Export Citation Format

Share Document